Module `avx512f`

Functions

_cvtmask16_u32 Convert 16-bit mask a into an integer value, and store the result in dst.
_cvtu32_mask16 Convert 32-bit integer value a to an 16-bit mask and store the result in dst.
_kand_mask16 Compute the bitwise AND of 16-bit masks a and b, and store the result in k.
_kandn_mask16 Compute the bitwise NOT of 16-bit masks a and then AND with b, and store the result in k.
_knot_mask16 Compute the bitwise NOT of 16-bit mask a, and store the result in k.
_kor_mask16 Compute the bitwise OR of 16-bit masks a and b, and store the result in k.
_kortest_mask16_u8 Compute the bitwise OR of 16-bit masks a and b. If the result is all zeros, store 1 in dst, otherwise store 0 in dst. If the result is all ones, store 1 in all_ones, otherwise store 0 in all_ones.
_kortestc_mask16_u8 Compute the bitwise OR of 16-bit masks a and b. If the result is all ones, store 1 in dst, otherwise store 0 in dst.
_kortestz_mask16_u8 Compute the bitwise OR of 16-bit masks a and b. If the result is all zeros, store 1 in dst, otherwise store 0 in dst.
_kshiftli_mask16 Shift 16-bit mask a left by count bits while shifting in zeros, and store the result in dst.
_kshiftri_mask16 Shift 16-bit mask a right by count bits while shifting in zeros, and store the result in dst.
_kxnor_mask16 Compute the bitwise XNOR of 16-bit masks a and b, and store the result in k.
_kxor_mask16 Compute the bitwise XOR of 16-bit masks a and b, and store the result in k.
_load_mask16 Load 16-bit mask from memory
_mm256_abs_epi64 Compute the absolute value of packed signed 64-bit integers in a, and store the unsigned results in dst.
_mm256_alignr_epi32 Concatenate a and b into a 64-byte immediate result, shift the result right by imm8 32-bit elements, and store the low 32 bytes (8 elements) in dst.
_mm256_alignr_epi64 Concatenate a and b into a 64-byte immediate result, shift the result right by imm8 64-bit elements, and store the low 32 bytes (4 elements) in dst.
_mm256_broadcast_f32x4 Broadcast the 4 packed single-precision (32-bit) floating-point elements from a to all elements of dst.
_mm256_broadcast_i32x4 Broadcast the 4 packed 32-bit integers from a to all elements of dst.
_mm256_cmp_epi32_mask Compare packed signed 32-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
_mm256_cmp_epi64_mask Compare packed signed 64-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
_mm256_cmp_epu32_mask Compare packed unsigned 32-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
_mm256_cmp_epu64_mask Compare packed unsigned 64-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
_mm256_cmp_pd_mask Compare packed double-precision (64-bit) floating-point elements in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
_mm256_cmp_ps_mask Compare packed single-precision (32-bit) floating-point elements in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
_mm256_cmpeq_epi32_mask Compare packed 32-bit integers in a and b for equality, and store the results in mask vector k.
_mm256_cmpeq_epi64_mask Compare packed 64-bit integers in a and b for equality, and store the results in mask vector k.
_mm256_cmpeq_epu32_mask Compare packed unsigned 32-bit integers in a and b for equality, and store the results in mask vector k.
_mm256_cmpeq_epu64_mask Compare packed unsigned 64-bit integers in a and b for equality, and store the results in mask vector k.
_mm256_cmpge_epi32_mask Compare packed signed 32-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k.
_mm256_cmpge_epi64_mask Compare packed signed 64-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k.
_mm256_cmpge_epu32_mask Compare packed unsigned 32-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k.
_mm256_cmpge_epu64_mask Compare packed unsigned 64-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k.
_mm256_cmpgt_epi32_mask Compare packed signed 32-bit integers in a and b for greater-than, and store the results in mask vector k.
_mm256_cmpgt_epi64_mask Compare packed signed 64-bit integers in a and b for greater-than, and store the results in mask vector k.
_mm256_cmpgt_epu32_mask Compare packed unsigned 32-bit integers in a and b for greater-than, and store the results in mask vector k.
_mm256_cmpgt_epu64_mask Compare packed unsigned 64-bit integers in a and b for greater-than, and store the results in mask vector k.
_mm256_cmple_epi32_mask Compare packed signed 32-bit integers in a and b for less-than-or-equal, and store the results in mask vector k.
_mm256_cmple_epi64_mask Compare packed signed 64-bit integers in a and b for less-than-or-equal, and store the results in mask vector k.
_mm256_cmple_epu32_mask Compare packed unsigned 32-bit integers in a and b for less-than-or-equal, and store the results in mask vector k.
_mm256_cmple_epu64_mask Compare packed unsigned 64-bit integers in a and b for less-than-or-equal, and store the results in mask vector k.
_mm256_cmplt_epi32_mask Compare packed signed 32-bit integers in a and b for less-than, and store the results in mask vector k.
_mm256_cmplt_epi64_mask Compare packed signed 64-bit integers in a and b for less-than, and store the results in mask vector k.
_mm256_cmplt_epu32_mask Compare packed unsigned 32-bit integers in a and b for less-than, and store the results in mask vector k.
_mm256_cmplt_epu64_mask Compare packed unsigned 64-bit integers in a and b for less-than, and store the results in mask vector k.
_mm256_cmpneq_epi32_mask Compare packed 32-bit integers in a and b for not-equal, and store the results in mask vector k.
_mm256_cmpneq_epi64_mask Compare packed signed 64-bit integers in a and b for not-equal, and store the results in mask vector k.
_mm256_cmpneq_epu32_mask Compare packed unsigned 32-bit integers in a and b for not-equal, and store the results in mask vector k.
_mm256_cmpneq_epu64_mask Compare packed unsigned 64-bit integers in a and b for not-equal, and store the results in mask vector k.
_mm256_cvtepi32_epi16 Convert packed 32-bit integers in a to packed 16-bit integers with truncation, and store the results in dst.
_mm256_cvtepi32_epi8 Convert packed 32-bit integers in a to packed 8-bit integers with truncation, and store the results in dst.
_mm256_cvtepi64_epi16 Convert packed 64-bit integers in a to packed 16-bit integers with truncation, and store the results in dst.
_mm256_cvtepi64_epi32 Convert packed 64-bit integers in a to packed 32-bit integers with truncation, and store the results in dst.
_mm256_cvtepi64_epi8 Convert packed 64-bit integers in a to packed 8-bit integers with truncation, and store the results in dst.
_mm256_cvtepu32_pd Convert packed unsigned 32-bit integers in a to packed double-precision (64-bit) floating-point elements, and store the results in dst.
_mm256_cvtpd_epu32 Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-bit integers, and store the results in dst.
_mm256_cvtps_epu32 Convert packed single-precision (32-bit) floating-point elements in a to packed unsigned 32-bit integers, and store the results in dst.
_mm256_cvtsepi32_epi16 Convert packed signed 32-bit integers in a to packed 16-bit integers with signed saturation, and store the results in dst.
_mm256_cvtsepi32_epi8 Convert packed signed 32-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst.
_mm256_cvtsepi64_epi16 Convert packed signed 64-bit integers in a to packed 16-bit integers with signed saturation, and store the results in dst.
_mm256_cvtsepi64_epi32 Convert packed signed 64-bit integers in a to packed 32-bit integers with signed saturation, and store the results in dst.
_mm256_cvtsepi64_epi8 Convert packed signed 64-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst.
_mm256_cvttpd_epu32 Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-bit integers with truncation, and store the results in dst.
_mm256_cvttps_epu32 Convert packed single-precision (32-bit) floating-point elements in a to packed unsigned 32-bit integers with truncation, and store the results in dst.
_mm256_cvtusepi32_epi16 Convert packed unsigned 32-bit integers in a to packed unsigned 16-bit integers with unsigned saturation, and store the results in dst.
_mm256_cvtusepi32_epi8 Convert packed unsigned 32-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst.
_mm256_cvtusepi64_epi16 Convert packed unsigned 64-bit integers in a to packed unsigned 16-bit integers with unsigned saturation, and store the results in dst.
_mm256_cvtusepi64_epi32 Convert packed unsigned 64-bit integers in a to packed unsigned 32-bit integers with unsigned saturation, and store the results in dst.
_mm256_cvtusepi64_epi8 Convert packed unsigned 64-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst.
_mm256_extractf32x4_ps Extract 128 bits (composed of 4 packed single-precision (32-bit) floating-point elements) from a, selected with imm8, and store the result in dst.
_mm256_extracti32x4_epi32 Extract 128 bits (composed of 4 packed 32-bit integers) from a, selected with IMM1, and store the result in dst.
_mm256_fixupimm_pd Fix up packed double-precision (64-bit) floating-point elements in a and b using packed 64-bit integers in c, and store the results in dst. imm8 is used to set the required flags reporting.
_mm256_fixupimm_ps Fix up packed single-precision (32-bit) floating-point elements in a and b using packed 32-bit integers in c, and store the results in dst. imm8 is used to set the required flags reporting.
_mm256_getexp_pd Convert the exponent of each packed double-precision (64-bit) floating-point element in a to a double-precision (64-bit) floating-point number representing the integer exponent, and store the results in dst. This intrinsic essentially calculates floor(log2(x)) for each element.
_mm256_getexp_ps Convert the exponent of each packed single-precision (32-bit) floating-point element in a to a single-precision (32-bit) floating-point number representing the integer exponent, and store the results in dst. This intrinsic essentially calculates floor(log2(x)) for each element.
_mm256_getmant_pd Normalize the mantissas of packed double-precision (64-bit) floating-point elements in a, and store the results in dst. This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
_mm256_getmant_ps Normalize the mantissas of packed single-precision (32-bit) floating-point elements in a, and store the results in dst. This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign. The mantissa is normalized to the interval specified by interv, which can take the following values: _MM_MANT_NORM_1_2 // interval [1, 2) _MM_MANT_NORM_p5_2 // interval [0.5, 2) _MM_MANT_NORM_p5_1 // interval [0.5, 1) _MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5) The sign is determined by sc which can take the following values: _MM_MANT_SIGN_src // sign = sign(src) _MM_MANT_SIGN_zero // sign = 0 _MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
_mm256_i32scatter_epi32 Stores 8 32-bit integer elements from a to memory starting at location base_addr at packed 32-bit integer indices stored in vindex scaled by scale
_mm256_i32scatter_epi64 Scatter 64-bit integers from a into memory using 32-bit indices. 64-bit elements are stored at addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale). scale should be 1, 2, 4 or 8.
_mm256_i32scatter_pd Stores 4 double-precision (64-bit) floating-point elements from a to memory starting at location base_addr at packed 32-bit integer indices stored in vindex scaled by scale
_mm256_i32scatter_ps Stores 8 single-precision (32-bit) floating-point elements from a to memory starting at location base_addr at packed 32-bit integer indices stored in vindex scaled by scale
_mm256_i64scatter_epi32 Stores 4 32-bit integer elements from a to memory starting at location base_addr at packed 64-bit integer indices stored in vindex scaled by scale
_mm256_i64scatter_epi64 Stores 4 64-bit integer elements from a to memory starting at location base_addr at packed 64-bit integer indices stored in vindex scaled by scale
_mm256_i64scatter_pd Stores 4 double-precision (64-bit) floating-point elements from a to memory starting at location base_addr at packed 64-bit integer indices stored in vindex scaled by scale
_mm256_i64scatter_ps Stores 4 single-precision (32-bit) floating-point elements from a to memory starting at location base_addr at packed 64-bit integer indices stored in vindex scaled by scale
_mm256_insertf32x4 Copy a to dst, then insert 128 bits (composed of 4 packed single-precision (32-bit) floating-point elements) from b into dst at the location specified by imm8.
_mm256_inserti32x4 Copy a to dst, then insert 128 bits (composed of 4 packed 32-bit integers) from b into dst at the location specified by imm8.
_mm256_load_epi32 Load 256-bits (composed of 8 packed 32-bit integers) from memory into dst. mem_addr must be aligned on a 32-byte boundary or a general-protection exception may be generated.
_mm256_load_epi64 Load 256-bits (composed of 4 packed 64-bit integers) from memory into dst. mem_addr must be aligned on a 32-byte boundary or a general-protection exception may be generated.
_mm256_loadu_epi32 Load 256-bits (composed of 8 packed 32-bit integers) from memory into dst. mem_addr does not need to be aligned on any particular boundary.
_mm256_loadu_epi64 Load 256-bits (composed of 4 packed 64-bit integers) from memory into dst. mem_addr does not need to be aligned on any particular boundary.
_mm256_mask2_permutex2var_epi32 Shuffle 32-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from idx when the corresponding mask bit is not set).
_mm256_mask2_permutex2var_epi64 Shuffle 64-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from idx when the corresponding mask bit is not set).
_mm256_mask2_permutex2var_pd Shuffle double-precision (64-bit) floating-point elements in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from idx when the corresponding mask bit is not set)
_mm256_mask2_permutex2var_ps Shuffle single-precision (32-bit) floating-point elements in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from idx when the corresponding mask bit is not set).
_mm256_mask3_fmadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm256_mask3_fmadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm256_mask3_fmaddsub_pd Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm256_mask3_fmaddsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm256_mask3_fmsub_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm256_mask3_fmsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm256_mask3_fmsubadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm256_mask3_fmsubadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm256_mask3_fnmadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm256_mask3_fnmadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm256_mask3_fnmsub_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm256_mask3_fnmsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm256_mask_abs_epi32 Compute the absolute value of packed signed 32-bit integers in a, and store the unsigned results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_abs_epi64 Compute the absolute value of packed signed 64-bit integers in a, and store the unsigned results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_add_epi32 Add packed 32-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_add_epi64 Add packed 64-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_add_pd Add packed double-precision (64-bit) floating-point elements in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_add_ps Add packed single-precision (32-bit) floating-point elements in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_alignr_epi32 Concatenate a and b into a 64-byte immediate result, shift the result right by imm8 32-bit elements, and store the low 32 bytes (8 elements) in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_alignr_epi64 Concatenate a and b into a 64-byte immediate result, shift the result right by imm8 64-bit elements, and store the low 32 bytes (4 elements) in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_and_epi32 Performs element-by-element bitwise AND between packed 32-bit integer elements of a and b, storing the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_and_epi64 Compute the bitwise AND of packed 64-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_andnot_epi32 Compute the bitwise NOT of packed 32-bit integers in a and then AND with b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_andnot_epi64 Compute the bitwise NOT of packed 64-bit integers in a and then AND with b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_blend_epi32 Blend packed 32-bit integers from a and b using control mask k, and store the results in dst.
_mm256_mask_blend_epi64 Blend packed 64-bit integers from a and b using control mask k, and store the results in dst.
_mm256_mask_blend_pd Blend packed double-precision (64-bit) floating-point elements from a and b using control mask k, and store the results in dst.
_mm256_mask_blend_ps Blend packed single-precision (32-bit) floating-point elements from a and b using control mask k, and store the results in dst.
_mm256_mask_broadcast_f32x4 Broadcast the 4 packed single-precision (32-bit) floating-point elements from a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_broadcast_i32x4 Broadcast the 4 packed 32-bit integers from a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_broadcastd_epi32 Broadcast the low packed 32-bit integer from a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_broadcastq_epi64 Broadcast the low packed 64-bit integer from a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_broadcastsd_pd Broadcast the low double-precision (64-bit) floating-point element from a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_broadcastss_ps Broadcast the low single-precision (32-bit) floating-point element from a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cmp_epi32_mask Compare packed signed 32-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmp_epi64_mask Compare packed signed 64-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmp_epu32_mask Compare packed unsigned 32-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmp_epu64_mask Compare packed unsigned 64-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmp_pd_mask Compare packed double-precision (64-bit) floating-point elements in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmp_ps_mask Compare packed single-precision (32-bit) floating-point elements in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmpeq_epi32_mask Compare packed 32-bit integers in a and b for equality, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmpeq_epi64_mask Compare packed 64-bit integers in a and b for equality, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmpeq_epu32_mask Compare packed unsigned 32-bit integers in a and b for equality, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmpeq_epu64_mask Compare packed unsigned 64-bit integers in a and b for equality, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmpge_epi32_mask Compare packed signed 32-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmpge_epi64_mask Compare packed signed 64-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmpge_epu32_mask Compare packed unsigned 32-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmpge_epu64_mask Compare packed unsigned 64-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmpgt_epi32_mask Compare packed signed 32-bit integers in a and b for greater-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmpgt_epi64_mask Compare packed signed 64-bit integers in a and b for greater-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmpgt_epu32_mask Compare packed unsigned 32-bit integers in a and b for greater-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmpgt_epu64_mask Compare packed unsigned 64-bit integers in a and b for greater-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmple_epi32_mask Compare packed signed 32-bit integers in a and b for less-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmple_epi64_mask Compare packed signed 64-bit integers in a and b for less-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmple_epu32_mask Compare packed unsigned 32-bit integers in a and b for less-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmple_epu64_mask Compare packed unsigned 64-bit integers in a and b for less-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmplt_epi32_mask Compare packed signed 32-bit integers in a and b for less-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmplt_epi64_mask Compare packed signed 64-bit integers in a and b for less-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmplt_epu32_mask Compare packed unsigned 32-bit integers in a and b for less-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmplt_epu64_mask Compare packed unsigned 64-bit integers in a and b for less-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmpneq_epi32_mask Compare packed 32-bit integers in a and b for not-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmpneq_epi64_mask Compare packed signed 64-bit integers in a and b for not-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmpneq_epu32_mask Compare packed unsigned 32-bit integers in a and b for not-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_cmpneq_epu64_mask Compare packed unsigned 64-bit integers in a and b for not-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm256_mask_compress_epi32 Contiguously store the active 32-bit integers in a (those with their respective bit set in writemask k) to dst, and pass through the remaining elements from src.
_mm256_mask_compress_epi64 Contiguously store the active 64-bit integers in a (those with their respective bit set in writemask k) to dst, and pass through the remaining elements from src.
_mm256_mask_compress_pd Contiguously store the active double-precision (64-bit) floating-point elements in a (those with their respective bit set in writemask k) to dst, and pass through the remaining elements from src.
_mm256_mask_compress_ps Contiguously store the active single-precision (32-bit) floating-point elements in a (those with their respective bit set in writemask k) to dst, and pass through the remaining elements from src.
_mm256_mask_compressstoreu_epi32 Contiguously store the active 32-bit integers in a (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm256_mask_compressstoreu_epi64 Contiguously store the active 64-bit integers in a (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm256_mask_compressstoreu_pd Contiguously store the active double-precision (64-bit) floating-point elements in a (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm256_mask_compressstoreu_ps Contiguously store the active single-precision (32-bit) floating-point elements in a (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm256_mask_cvt_roundps_ph Convert packed single-precision (32-bit) floating-point elements in a to packed half-precision (16-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
Rounding is done according to the imm8[2:0] parameter, which can be one of:
_mm256_mask_cvtepi16_epi32 Sign extend packed 16-bit integers in a to packed 32-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtepi16_epi64 Sign extend packed 16-bit integers in a to packed 64-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtepi32_epi16 Convert packed 32-bit integers in a to packed 16-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtepi32_epi64 Sign extend packed 32-bit integers in a to packed 64-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtepi32_epi8 Convert packed 32-bit integers in a to packed 8-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtepi32_pd Convert packed signed 32-bit integers in a to packed double-precision (64-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtepi32_ps Convert packed signed 32-bit integers in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtepi32_storeu_epi16 Convert packed 32-bit integers in a to packed 16-bit integers with truncation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm256_mask_cvtepi32_storeu_epi8 Convert packed 32-bit integers in a to packed 8-bit integers with truncation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm256_mask_cvtepi64_epi16 Convert packed 64-bit integers in a to packed 16-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtepi64_epi32 Convert packed 64-bit integers in a to packed 32-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtepi64_epi8 Convert packed 64-bit integers in a to packed 8-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtepi64_storeu_epi16 Convert packed 64-bit integers in a to packed 16-bit integers with truncation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm256_mask_cvtepi64_storeu_epi32 Convert packed 64-bit integers in a to packed 32-bit integers with truncation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm256_mask_cvtepi64_storeu_epi8 Convert packed 64-bit integers in a to packed 8-bit integers with truncation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm256_mask_cvtepi8_epi32 Sign extend packed 8-bit integers in a to packed 32-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtepi8_epi64 Sign extend packed 8-bit integers in the low 4 bytes of a to packed 64-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtepu16_epi32 Zero extend packed unsigned 16-bit integers in a to packed 32-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtepu16_epi64 Zero extend packed unsigned 16-bit integers in the low 8 bytes of a to packed 64-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtepu32_epi64 Zero extend packed unsigned 32-bit integers in a to packed 64-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtepu32_pd Convert packed unsigned 32-bit integers in a to packed double-precision (64-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtepu8_epi32 Zero extend packed unsigned 8-bit integers in the low 8 bytes of a to packed 32-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtepu8_epi64 Zero extend packed unsigned 8-bit integers in the low 4 bytes of a to packed 64-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtpd_epi32 Convert packed double-precision (64-bit) floating-point elements in a to packed 32-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtpd_epu32 Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtpd_ps Convert packed double-precision (64-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtph_ps Convert packed half-precision (16-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtps_epi32 Convert packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtps_epu32 Convert packed single-precision (32-bit) floating-point elements in a to packed unsigned 32-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtps_ph Convert packed single-precision (32-bit) floating-point elements in a to packed half-precision (16-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm256_mask_cvtsepi32_epi16 Convert packed signed 32-bit integers in a to packed 16-bit integers with signed saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtsepi32_epi8 Convert packed signed 32-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtsepi32_storeu_epi16 Convert packed signed 32-bit integers in a to packed 16-bit integers with signed saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm256_mask_cvtsepi32_storeu_epi8 Convert packed signed 32-bit integers in a to packed 8-bit integers with signed saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm256_mask_cvtsepi64_epi16 Convert packed signed 64-bit integers in a to packed 16-bit integers with signed saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtsepi64_epi32 Convert packed signed 64-bit integers in a to packed 32-bit integers with signed saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtsepi64_epi8 Convert packed signed 64-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtsepi64_storeu_epi16 Convert packed signed 64-bit integers in a to packed 16-bit integers with signed saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm256_mask_cvtsepi64_storeu_epi32 Convert packed signed 64-bit integers in a to packed 32-bit integers with signed saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm256_mask_cvtsepi64_storeu_epi8 Convert packed signed 64-bit integers in a to packed 8-bit integers with signed saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm256_mask_cvttpd_epi32 Convert packed double-precision (64-bit) floating-point elements in a to packed 32-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvttpd_epu32 Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvttps_epi32 Convert packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvttps_epu32 Convert packed double-precision (32-bit) floating-point elements in a to packed unsigned 32-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtusepi32_epi16 Convert packed unsigned 32-bit integers in a to packed unsigned 16-bit integers with unsigned saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtusepi32_epi8 Convert packed unsigned 32-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtusepi32_storeu_epi16 Convert packed unsigned 32-bit integers in a to packed unsigned 16-bit integers with unsigned saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm256_mask_cvtusepi32_storeu_epi8 Convert packed unsigned 32-bit integers in a to packed 8-bit integers with unsigned saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm256_mask_cvtusepi64_epi16 Convert packed unsigned 64-bit integers in a to packed unsigned 16-bit integers with unsigned saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtusepi64_epi32 Convert packed unsigned 64-bit integers in a to packed unsigned 32-bit integers with unsigned saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtusepi64_epi8 Convert packed unsigned 64-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_cvtusepi64_storeu_epi16 Convert packed unsigned 64-bit integers in a to packed 16-bit integers with unsigned saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm256_mask_cvtusepi64_storeu_epi32 Convert packed unsigned 64-bit integers in a to packed 32-bit integers with unsigned saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm256_mask_cvtusepi64_storeu_epi8 Convert packed unsigned 64-bit integers in a to packed 8-bit integers with unsigned saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm256_mask_div_pd Divide packed double-precision (64-bit) floating-point elements in a by packed elements in b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_div_ps Divide packed single-precision (32-bit) floating-point elements in a by packed elements in b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_expand_epi32 Load contiguous active 32-bit integers from a (those with their respective bit set in mask k), and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_expand_epi64 Load contiguous active 64-bit integers from a (those with their respective bit set in mask k), and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_expand_pd Load contiguous active double-precision (64-bit) floating-point elements from a (those with their respective bit set in mask k), and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_expand_ps Load contiguous active single-precision (32-bit) floating-point elements from a (those with their respective bit set in mask k), and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_expandloadu_epi32 Load contiguous active 32-bit integers from unaligned memory at mem_addr (those with their respective bit set in mask k), and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_expandloadu_epi64 Load contiguous active 64-bit integers from unaligned memory at mem_addr (those with their respective bit set in mask k), and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_expandloadu_pd Load contiguous active double-precision (64-bit) floating-point elements from unaligned memory at mem_addr (those with their respective bit set in mask k), and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_expandloadu_ps Load contiguous active single-precision (32-bit) floating-point elements from unaligned memory at mem_addr (those with their respective bit set in mask k), and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_extractf32x4_ps Extract 128 bits (composed of 4 packed single-precision (32-bit) floating-point elements) from a, selected with imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_extracti32x4_epi32 Extract 128 bits (composed of 4 packed 32-bit integers) from a, selected with IMM1, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_fixupimm_pd Fix up packed double-precision (64-bit) floating-point elements in a and b using packed 64-bit integers in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). imm8 is used to set the required flags reporting.
_mm256_mask_fixupimm_ps Fix up packed single-precision (32-bit) floating-point elements in a and b using packed 32-bit integers in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). imm8 is used to set the required flags reporting.
_mm256_mask_fmadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm256_mask_fmadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm256_mask_fmaddsub_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm256_mask_fmaddsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm256_mask_fmsub_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm256_mask_fmsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm256_mask_fmsubadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm256_mask_fmsubadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm256_mask_fnmadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm256_mask_fnmadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm256_mask_fnmsub_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm256_mask_fnmsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm256_mask_getexp_pd Convert the exponent of each packed double-precision (64-bit) floating-point element in a to a double-precision (64-bit) floating-point number representing the integer exponent, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). This intrinsic essentially calculates floor(log2(x)) for each element.
_mm256_mask_getexp_ps Convert the exponent of each packed single-precision (32-bit) floating-point element in a to a single-precision (32-bit) floating-point number representing the integer exponent, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). This intrinsic essentially calculates floor(log2(x)) for each element.
_mm256_mask_getmant_pd Normalize the mantissas of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
_mm256_mask_getmant_ps Normalize the mantissas of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
_mm256_mask_i32scatter_epi32 Stores 8 32-bit integer elements from a to memory starting at location base_addr at packed 32-bit integer indices stored in vindex scaled by scale using writemask k (elements whose corresponding mask bit is not set are not written to memory).
_mm256_mask_i32scatter_epi64 Stores 4 64-bit integer elements from a to memory starting at location base_addr at packed 32-bit integer indices stored in vindex scaled by scale using writemask k (elements whose corresponding mask bit is not set are not written to memory).
_mm256_mask_i32scatter_pd Stores 4 double-precision (64-bit) floating-point elements from a to memory starting at location base_addr at packed 32-bit integer indices stored in vindex scaled by scale using writemask k (elements whose corresponding mask bit is not set are not written to memory).
_mm256_mask_i32scatter_ps Stores 8 single-precision (32-bit) floating-point elements from a to memory starting at location base_addr at packed 32-bit integer indices stored in vindex scaled by scale using writemask k (elements whose corresponding mask bit is not set are not written to memory).
_mm256_mask_i64scatter_epi32 Stores 4 32-bit integer elements from a to memory starting at location base_addr at packed 64-bit integer indices stored in vindex scaled by scale using writemask k (elements whose corresponding mask bit is not set are not written to memory).
_mm256_mask_i64scatter_epi64 Stores 4 64-bit integer elements from a to memory starting at location base_addr at packed 64-bit integer indices stored in vindex scaled by scale using writemask k (elements whose corresponding mask bit is not set are not written to memory).
_mm256_mask_i64scatter_pd Stores 4 double-precision (64-bit) floating-point elements from a to memory starting at location base_addr at packed 64-bit integer indices stored in vindex scaled by scale using writemask k (elements whose corresponding mask bit is not set are not written to memory).
_mm256_mask_i64scatter_ps Stores 4 single-precision (32-bit) floating-point elements from a to memory starting at location base_addr at packed 64-bit integer indices stored in vindex scaled by scale using writemask k (elements whose corresponding mask bit is not set are not written to memory).
_mm256_mask_insertf32x4 Copy a to tmp, then insert 128 bits (composed of 4 packed single-precision (32-bit) floating-point elements) from b into tmp at the location specified by imm8. Store tmp to dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_inserti32x4 Copy a to tmp, then insert 128 bits (composed of 4 packed 32-bit integers) from b into tmp at the location specified by imm8. Store tmp to dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_load_epi32 Load packed 32-bit integers from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr must be aligned on a 32-byte boundary or a general-protection exception may be generated.
_mm256_mask_load_epi64 Load packed 64-bit integers from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr must be aligned on a 32-byte boundary or a general-protection exception may be generated.
_mm256_mask_load_pd Load packed double-precision (64-bit) floating-point elements from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr must be aligned on a 32-byte boundary or a general-protection exception may be generated.
_mm256_mask_load_ps Load packed single-precision (32-bit) floating-point elements from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr must be aligned on a 32-byte boundary or a general-protection exception may be generated.
_mm256_mask_loadu_epi32 Load packed 32-bit integers from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
_mm256_mask_loadu_epi64 Load packed 64-bit integers from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
_mm256_mask_loadu_pd Load packed double-precision (64-bit) floating-point elements from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
_mm256_mask_loadu_ps Load packed single-precision (32-bit) floating-point elements from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
_mm256_mask_max_epi32 Compare packed signed 32-bit integers in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_max_epi64 Compare packed signed 64-bit integers in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_max_epu32 Compare packed unsigned 32-bit integers in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_max_epu64 Compare packed unsigned 64-bit integers in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_max_pd Compare packed double-precision (64-bit) floating-point elements in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_max_ps Compare packed single-precision (32-bit) floating-point elements in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_min_epi32 Compare packed signed 32-bit integers in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_min_epi64 Compare packed signed 64-bit integers in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_min_epu32 Compare packed unsigned 32-bit integers in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_min_epu64 Compare packed unsigned 64-bit integers in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_min_pd Compare packed double-precision (64-bit) floating-point elements in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_min_ps Compare packed single-precision (32-bit) floating-point elements in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_mov_epi32 Move packed 32-bit integers from a to dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_mov_epi64 Move packed 64-bit integers from a to dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_mov_pd Move packed double-precision (64-bit) floating-point elements from a to dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_mov_ps Move packed single-precision (32-bit) floating-point elements from a to dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_movedup_pd Duplicate even-indexed double-precision (64-bit) floating-point elements from a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_movehdup_ps Duplicate odd-indexed single-precision (32-bit) floating-point elements from a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_moveldup_ps Duplicate even-indexed single-precision (32-bit) floating-point elements from a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_mul_epi32 Multiply the low signed 32-bit integers from each packed 64-bit element in a and b, and store the signed 64-bit results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_mul_epu32 Multiply the low unsigned 32-bit integers from each packed 64-bit element in a and b, and store the unsigned 64-bit results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_mul_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_mul_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_mullo_epi32 Multiply the packed 32-bit integers in a and b, producing intermediate 64-bit integers, and store the low 32 bits of the intermediate integers in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_or_epi32 Compute the bitwise OR of packed 32-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_or_epi64 Compute the bitwise OR of packed 64-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_permute_pd Shuffle double-precision (64-bit) floating-point elements in a within 128-bit lanes using the control in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_permute_ps Shuffle single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_permutevar_pd Shuffle double-precision (64-bit) floating-point elements in a within 128-bit lanes using the control in b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_permutevar_ps Shuffle single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_permutex2var_epi32 Shuffle 32-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm256_mask_permutex2var_epi64 Shuffle 64-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm256_mask_permutex2var_pd Shuffle double-precision (64-bit) floating-point elements in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm256_mask_permutex2var_ps Shuffle single-precision (32-bit) floating-point elements in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm256_mask_permutex_epi64 Shuffle 64-bit integers in a within 256-bit lanes using the control in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_permutex_pd Shuffle double-precision (64-bit) floating-point elements in a within 256-bit lanes using the control in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_permutexvar_epi32 Shuffle 32-bit integers in a across lanes using the corresponding index in idx, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_permutexvar_epi64 Shuffle 64-bit integers in a across lanes using the corresponding index in idx, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_permutexvar_pd Shuffle double-precision (64-bit) floating-point elements in a across lanes using the corresponding index in idx, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_permutexvar_ps Shuffle single-precision (32-bit) floating-point elements in a across lanes using the corresponding index in idx, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_rcp14_pd Compute the approximate reciprocal of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14.
_mm256_mask_rcp14_ps Compute the approximate reciprocal of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14.
_mm256_mask_rol_epi32 Rotate the bits in each packed 32-bit integer in a to the left by the number of bits specified in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_rol_epi64 Rotate the bits in each packed 64-bit integer in a to the left by the number of bits specified in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_rolv_epi32 Rotate the bits in each packed 32-bit integer in a to the left by the number of bits specified in the corresponding element of b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_rolv_epi64 Rotate the bits in each packed 64-bit integer in a to the left by the number of bits specified in the corresponding element of b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_ror_epi32 Rotate the bits in each packed 32-bit integer in a to the right by the number of bits specified in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_ror_epi64 Rotate the bits in each packed 64-bit integer in a to the right by the number of bits specified in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_rorv_epi32 Rotate the bits in each packed 32-bit integer in a to the right by the number of bits specified in the corresponding element of b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_rorv_epi64 Rotate the bits in each packed 64-bit integer in a to the right by the number of bits specified in the corresponding element of b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_roundscale_pd Round packed double-precision (64-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm256_mask_roundscale_ps Round packed single-precision (32-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm256_mask_rsqrt14_pd Compute the approximate reciprocal square root of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14.
_mm256_mask_rsqrt14_ps Compute the approximate reciprocal square root of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14.
_mm256_mask_scalef_pd Scale the packed double-precision (64-bit) floating-point elements in a using values from b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_scalef_ps Scale the packed single-precision (32-bit) floating-point elements in a using values from b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_set1_epi32 Broadcast 32-bit integer a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_set1_epi64 Broadcast 64-bit integer a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_shuffle_epi32 Shuffle 32-bit integers in a within 128-bit lanes using the control in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_shuffle_f32x4 Shuffle 128-bits (composed of 4 single-precision (32-bit) floating-point elements) selected by imm8 from a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_shuffle_f64x2 Shuffle 128-bits (composed of 2 double-precision (64-bit) floating-point elements) selected by imm8 from a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_shuffle_i32x4 Shuffle 128-bits (composed of 4 32-bit integers) selected by imm8 from a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_shuffle_i64x2 Shuffle 128-bits (composed of 2 64-bit integers) selected by imm8 from a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_shuffle_pd Shuffle double-precision (64-bit) floating-point elements within 128-bit lanes using the control in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_shuffle_ps Shuffle single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_sll_epi32 Shift packed 32-bit integers in a left by count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_sll_epi64 Shift packed 64-bit integers in a left by count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_slli_epi32 Shift packed 32-bit integers in a left by imm8 while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_slli_epi64 Shift packed 64-bit integers in a left by imm8 while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_sllv_epi32 Shift packed 32-bit integers in a left by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_sllv_epi64 Shift packed 64-bit integers in a left by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_sqrt_pd Compute the square root of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_sqrt_ps Compute the square root of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_sra_epi32 Shift packed 32-bit integers in a right by count while shifting in sign bits, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_sra_epi64 Shift packed 64-bit integers in a right by count while shifting in sign bits, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_srai_epi32 Shift packed 32-bit integers in a right by imm8 while shifting in sign bits, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_srai_epi64 Shift packed 64-bit integers in a right by imm8 while shifting in sign bits, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_srav_epi32 Shift packed 32-bit integers in a right by the amount specified by the corresponding element in count while shifting in sign bits, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_srav_epi64 Shift packed 64-bit integers in a right by the amount specified by the corresponding element in count while shifting in sign bits, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_srl_epi32 Shift packed 32-bit integers in a right by count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_srl_epi64 Shift packed 64-bit integers in a right by count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_srli_epi32 Shift packed 32-bit integers in a right by imm8 while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_srli_epi64 Shift packed 64-bit integers in a right by imm8 while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_srlv_epi32 Shift packed 32-bit integers in a right by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_srlv_epi64 Shift packed 64-bit integers in a right by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_store_epi32 Store packed 32-bit integers from a into memory using writemask k. mem_addr must be aligned on a 32-byte boundary or a general-protection exception may be generated.
_mm256_mask_store_epi64 Store packed 64-bit integers from a into memory using writemask k. mem_addr must be aligned on a 32-byte boundary or a general-protection exception may be generated.
_mm256_mask_store_pd Store packed double-precision (64-bit) floating-point elements from a into memory using writemask k. mem_addr must be aligned on a 32-byte boundary or a general-protection exception may be generated.
_mm256_mask_store_ps Store packed single-precision (32-bit) floating-point elements from a into memory using writemask k. mem_addr must be aligned on a 32-byte boundary or a general-protection exception may be generated.
_mm256_mask_storeu_epi32 Store packed 32-bit integers from a into memory using writemask k. mem_addr does not need to be aligned on any particular boundary.
_mm256_mask_storeu_epi64 Store packed 64-bit integers from a into memory using writemask k. mem_addr does not need to be aligned on any particular boundary.
_mm256_mask_storeu_pd Store packed double-precision (64-bit) floating-point elements from a into memory using writemask k. mem_addr does not need to be aligned on any particular boundary.
_mm256_mask_storeu_ps Store packed single-precision (32-bit) floating-point elements from a into memory using writemask k. mem_addr does not need to be aligned on any particular boundary.
_mm256_mask_sub_epi32 Subtract packed 32-bit integers in b from packed 32-bit integers in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_sub_epi64 Subtract packed 64-bit integers in b from packed 64-bit integers in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_sub_pd Subtract packed double-precision (64-bit) floating-point elements in b from packed double-precision (64-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_sub_ps Subtract packed single-precision (32-bit) floating-point elements in b from packed single-precision (32-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_ternarylogic_epi32 Bitwise ternary logic that provides the capability to implement any three-operand binary function; the specific binary function is specified by value in imm8. For each bit in each packed 32-bit integer, the corresponding bit from src, a, and b are used to form a 3 bit index into imm8, and the value at that bit in imm8 is written to the corresponding bit in dst using writemask k at 32-bit granularity (32-bit elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_ternarylogic_epi64 Bitwise ternary logic that provides the capability to implement any three-operand binary function; the specific binary function is specified by value in imm8. For each bit in each packed 64-bit integer, the corresponding bit from src, a, and b are used to form a 3 bit index into imm8, and the value at that bit in imm8 is written to the corresponding bit in dst using writemask k at 64-bit granularity (64-bit elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_test_epi32_mask Compute the bitwise AND of packed 32-bit integers in a and b, producing intermediate 32-bit values, and set the corresponding bit in result mask k (subject to writemask k) if the intermediate value is non-zero.
_mm256_mask_test_epi64_mask Compute the bitwise AND of packed 64-bit integers in a and b, producing intermediate 64-bit values, and set the corresponding bit in result mask k (subject to writemask k) if the intermediate value is non-zero.
_mm256_mask_testn_epi32_mask Compute the bitwise NAND of packed 32-bit integers in a and b, producing intermediate 32-bit values, and set the corresponding bit in result mask k (subject to writemask k) if the intermediate value is zero.
_mm256_mask_testn_epi64_mask Compute the bitwise NAND of packed 64-bit integers in a and b, producing intermediate 64-bit values, and set the corresponding bit in result mask k (subject to writemask k) if the intermediate value is zero.
_mm256_mask_unpackhi_epi32 Unpack and interleave 32-bit integers from the high half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_unpackhi_epi64 Unpack and interleave 64-bit integers from the high half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_unpackhi_pd Unpack and interleave double-precision (64-bit) floating-point elements from the high half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_unpackhi_ps Unpack and interleave single-precision (32-bit) floating-point elements from the high half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_unpacklo_epi32 Unpack and interleave 32-bit integers from the low half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_unpacklo_epi64 Unpack and interleave 64-bit integers from the low half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_unpacklo_pd Unpack and interleave double-precision (64-bit) floating-point elements from the low half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_unpacklo_ps Unpack and interleave single-precision (32-bit) floating-point elements from the low half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_xor_epi32 Compute the bitwise XOR of packed 32-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mask_xor_epi64 Compute the bitwise XOR of packed 64-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_maskz_abs_epi32 Compute the absolute value of packed signed 32-bit integers in a, and store the unsigned results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_abs_epi64 Compute the absolute value of packed signed 64-bit integers in a, and store the unsigned results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_add_epi32 Add packed 32-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_add_epi64 Add packed 64-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_add_pd Add packed double-precision (64-bit) floating-point elements in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_add_ps Add packed single-precision (32-bit) floating-point elements in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_alignr_epi32 Concatenate a and b into a 64-byte immediate result, shift the result right by imm8 32-bit elements, and store the low 32 bytes (8 elements) in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_alignr_epi64 Concatenate a and b into a 64-byte immediate result, shift the result right by imm8 64-bit elements, and store the low 32 bytes (4 elements) in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_and_epi32 Compute the bitwise AND of packed 32-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_and_epi64 Compute the bitwise AND of packed 64-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_andnot_epi32 Compute the bitwise NOT of packed 32-bit integers in a and then AND with b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_andnot_epi64 Compute the bitwise NOT of packed 64-bit integers in a and then AND with b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_broadcast_f32x4 Broadcast the 4 packed single-precision (32-bit) floating-point elements from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_broadcast_i32x4 Broadcast the 4 packed 32-bit integers from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_broadcastd_epi32 Broadcast the low packed 32-bit integer from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_broadcastq_epi64 Broadcast the low packed 64-bit integer from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_broadcastsd_pd Broadcast the low double-precision (64-bit) floating-point element from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_broadcastss_ps Broadcast the low single-precision (32-bit) floating-point element from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_compress_epi32 Contiguously store the active 32-bit integers in a (those with their respective bit set in zeromask k) to dst, and set the remaining elements to zero.
_mm256_maskz_compress_epi64 Contiguously store the active 64-bit integers in a (those with their respective bit set in zeromask k) to dst, and set the remaining elements to zero.
_mm256_maskz_compress_pd Contiguously store the active double-precision (64-bit) floating-point elements in a (those with their respective bit set in zeromask k) to dst, and set the remaining elements to zero.
_mm256_maskz_compress_ps Contiguously store the active single-precision (32-bit) floating-point elements in a (those with their respective bit set in zeromask k) to dst, and set the remaining elements to zero.
_mm256_maskz_cvt_roundps_ph Convert packed single-precision (32-bit) floating-point elements in a to packed half-precision (16-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm256_maskz_cvtepi16_epi32 Sign extend packed 16-bit integers in a to packed 32-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtepi16_epi64 Sign extend packed 16-bit integers in a to packed 64-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtepi32_epi16 Convert packed 32-bit integers in a to packed 16-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtepi32_epi64 Sign extend packed 32-bit integers in a to packed 64-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtepi32_epi8 Convert packed 32-bit integers in a to packed 8-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtepi32_pd Convert packed signed 32-bit integers in a to packed double-precision (64-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtepi32_ps Convert packed signed 32-bit integers in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtepi64_epi16 Convert packed 64-bit integers in a to packed 16-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtepi64_epi32 Convert packed 64-bit integers in a to packed 32-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtepi64_epi8 Convert packed 64-bit integers in a to packed 8-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtepi8_epi32 Sign extend packed 8-bit integers in a to packed 32-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtepi8_epi64 Sign extend packed 8-bit integers in the low 4 bytes of a to packed 64-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtepu16_epi32 Zero extend packed unsigned 16-bit integers in a to packed 32-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtepu16_epi64 Zero extend packed unsigned 16-bit integers in the low 8 bytes of a to packed 64-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtepu32_epi64 Zero extend packed unsigned 32-bit integers in a to packed 64-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtepu32_pd Convert packed unsigned 32-bit integers in a to packed double-precision (64-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtepu8_epi32 Zero extend packed unsigned 8-bit integers in the low 8 bytes of a to packed 32-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtepu8_epi64 Zero extend packed unsigned 8-bit integers in the low 4 bytes of a to packed 64-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtpd_epi32 Convert packed double-precision (64-bit) floating-point elements in a to packed 32-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtpd_epu32 Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtpd_ps Convert packed double-precision (64-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtph_ps Convert packed half-precision (16-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtps_epi32 Convert packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtps_epu32 Convert packed single-precision (32-bit) floating-point elements in a to packed unsigned 32-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtps_ph Convert packed single-precision (32-bit) floating-point elements in a to packed half-precision (16-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm256_maskz_cvtsepi32_epi16 Convert packed signed 32-bit integers in a to packed 16-bit integers with signed saturation, and store the results in dst.
_mm256_maskz_cvtsepi32_epi8 Convert packed signed 32-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtsepi64_epi16 Convert packed signed 64-bit integers in a to packed 16-bit integers with signed saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtsepi64_epi32 Convert packed signed 64-bit integers in a to packed 32-bit integers with signed saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtsepi64_epi8 Convert packed signed 64-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvttpd_epi32 Convert packed double-precision (64-bit) floating-point elements in a to packed 32-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvttpd_epu32 Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvttps_epi32 Convert packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvttps_epu32 Convert packed double-precision (32-bit) floating-point elements in a to packed unsigned 32-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtusepi32_epi16 Convert packed unsigned 32-bit integers in a to packed unsigned 16-bit integers with unsigned saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtusepi32_epi8 Convert packed unsigned 32-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtusepi64_epi16 Convert packed unsigned 64-bit integers in a to packed unsigned 16-bit integers with unsigned saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtusepi64_epi32 Convert packed unsigned 64-bit integers in a to packed unsigned 32-bit integers with unsigned saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_cvtusepi64_epi8 Convert packed unsigned 64-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_div_pd Divide packed double-precision (64-bit) floating-point elements in a by packed elements in b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_div_ps Divide packed single-precision (32-bit) floating-point elements in a by packed elements in b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_expand_epi32 Load contiguous active 32-bit integers from a (those with their respective bit set in mask k), and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_expand_epi64 Load contiguous active 64-bit integers from a (those with their respective bit set in mask k), and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_expand_pd Load contiguous active double-precision (64-bit) floating-point elements from a (those with their respective bit set in mask k), and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_expand_ps Load contiguous active single-precision (32-bit) floating-point elements from a (those with their respective bit set in mask k), and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_expandloadu_epi32 Load contiguous active 32-bit integers from unaligned memory at mem_addr (those with their respective bit set in mask k), and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_expandloadu_epi64 Load contiguous active 64-bit integers from unaligned memory at mem_addr (those with their respective bit set in mask k), and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_expandloadu_pd Load contiguous active double-precision (64-bit) floating-point elements from unaligned memory at mem_addr (those with their respective bit set in mask k), and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_expandloadu_ps Load contiguous active single-precision (32-bit) floating-point elements from unaligned memory at mem_addr (those with their respective bit set in mask k), and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_extractf32x4_ps Extract 128 bits (composed of 4 packed single-precision (32-bit) floating-point elements) from a, selected with imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_extracti32x4_epi32 Extract 128 bits (composed of 4 packed 32-bit integers) from a, selected with IMM1, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_fixupimm_pd Fix up packed double-precision (64-bit) floating-point elements in a and b using packed 64-bit integers in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). imm8 is used to set the required flags reporting.
_mm256_maskz_fixupimm_ps Fix up packed single-precision (32-bit) floating-point elements in a and b using packed 32-bit integers in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). imm8 is used to set the required flags reporting.
_mm256_maskz_fmadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_fmadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_fmaddsub_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_fmaddsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_fmsub_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_fmsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_fmsubadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_fmsubadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_fnmadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_fnmadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_fnmsub_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_fnmsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_getexp_pd Convert the exponent of each packed double-precision (64-bit) floating-point element in a to a double-precision (64-bit) floating-point number representing the integer exponent, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). This intrinsic essentially calculates floor(log2(x)) for each element.
_mm256_maskz_getexp_ps Convert the exponent of each packed single-precision (32-bit) floating-point element in a to a single-precision (32-bit) floating-point number representing the integer exponent, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). This intrinsic essentially calculates floor(log2(x)) for each element.
_mm256_maskz_getmant_pd Normalize the mantissas of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
_mm256_maskz_getmant_ps Normalize the mantissas of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
_mm256_maskz_insertf32x4 Copy a to tmp, then insert 128 bits (composed of 4 packed single-precision (32-bit) floating-point elements) from b into tmp at the location specified by imm8. Store tmp to dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_inserti32x4 Copy a to tmp, then insert 128 bits (composed of 4 packed 32-bit integers) from b into tmp at the location specified by imm8. Store tmp to dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_load_epi32 Load packed 32-bit integers from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr must be aligned on a 32-byte boundary or a general-protection exception may be generated.
_mm256_maskz_load_epi64 Load packed 64-bit integers from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr must be aligned on a 32-byte boundary or a general-protection exception may be generated.
_mm256_maskz_load_pd Load packed double-precision (64-bit) floating-point elements from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr must be aligned on a 32-byte boundary or a general-protection exception may be generated.
_mm256_maskz_load_ps Load packed single-precision (32-bit) floating-point elements from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr must be aligned on a 32-byte boundary or a general-protection exception may be generated.
_mm256_maskz_loadu_epi32 Load packed 32-bit integers from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
_mm256_maskz_loadu_epi64 Load packed 64-bit integers from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
_mm256_maskz_loadu_pd Load packed double-precision (64-bit) floating-point elements from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
_mm256_maskz_loadu_ps Load packed single-precision (32-bit) floating-point elements from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
_mm256_maskz_max_epi32 Compare packed signed 32-bit integers in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_max_epi64 Compare packed signed 64-bit integers in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_max_epu32 Compare packed unsigned 32-bit integers in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_max_epu64 Compare packed unsigned 64-bit integers in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_max_pd Compare packed double-precision (64-bit) floating-point elements in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_max_ps Compare packed single-precision (32-bit) floating-point elements in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_min_epi32 Compare packed signed 32-bit integers in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_min_epi64 Compare packed signed 64-bit integers in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_min_epu32 Compare packed unsigned 32-bit integers in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_min_epu64 Compare packed unsigned 64-bit integers in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_min_pd Compare packed double-precision (64-bit) floating-point elements in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_min_ps Compare packed single-precision (32-bit) floating-point elements in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_mov_epi32 Move packed 32-bit integers from a into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_mov_epi64 Move packed 64-bit integers from a into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_mov_pd Move packed double-precision (64-bit) floating-point elements from a into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_mov_ps Move packed single-precision (32-bit) floating-point elements from a into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_movedup_pd Duplicate even-indexed double-precision (64-bit) floating-point elements from a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_movehdup_ps Duplicate odd-indexed single-precision (32-bit) floating-point elements from a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_moveldup_ps Duplicate even-indexed single-precision (32-bit) floating-point elements from a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_mul_epi32 Multiply the low signed 32-bit integers from each packed 64-bit element in a and b, and store the signed 64-bit results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_mul_epu32 Multiply the low unsigned 32-bit integers from each packed 64-bit element in a and b, and store the unsigned 64-bit results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_mul_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_mul_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_mullo_epi32 Multiply the packed 32-bit integers in a and b, producing intermediate 64-bit integers, and store the low 32 bits of the intermediate integers in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_or_epi32 Compute the bitwise OR of packed 32-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_or_epi64 Compute the bitwise OR of packed 64-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_permute_pd Shuffle double-precision (64-bit) floating-point elements in a within 128-bit lanes using the control in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_permute_ps Shuffle single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_permutevar_pd Shuffle double-precision (64-bit) floating-point elements in a within 128-bit lanes using the control in b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_permutevar_ps Shuffle single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_permutex2var_epi32 Shuffle 32-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_permutex2var_epi64 Shuffle 64-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_permutex2var_pd Shuffle double-precision (64-bit) floating-point elements in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_permutex2var_ps Shuffle single-precision (32-bit) floating-point elements in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_permutex_epi64 Shuffle 64-bit integers in a within 256-bit lanes using the control in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_permutex_pd Shuffle double-precision (64-bit) floating-point elements in a within 256-bit lanes using the control in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_permutexvar_epi32 Shuffle 32-bit integers in a across lanes using the corresponding index in idx, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_permutexvar_epi64 Shuffle 64-bit integers in a across lanes using the corresponding index in idx, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_permutexvar_pd Shuffle double-precision (64-bit) floating-point elements in a across lanes using the corresponding index in idx, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_permutexvar_ps Shuffle single-precision (32-bit) floating-point elements in a across lanes using the corresponding index in idx, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_rcp14_pd Compute the approximate reciprocal of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14.
_mm256_maskz_rcp14_ps Compute the approximate reciprocal of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14.
_mm256_maskz_rol_epi32 Rotate the bits in each packed 32-bit integer in a to the left by the number of bits specified in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_rol_epi64 Rotate the bits in each packed 64-bit integer in a to the left by the number of bits specified in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_rolv_epi32 Rotate the bits in each packed 32-bit integer in a to the left by the number of bits specified in the corresponding element of b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_rolv_epi64 Rotate the bits in each packed 64-bit integer in a to the left by the number of bits specified in the corresponding element of b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_ror_epi32 Rotate the bits in each packed 32-bit integer in a to the right by the number of bits specified in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_ror_epi64 Rotate the bits in each packed 64-bit integer in a to the right by the number of bits specified in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_rorv_epi32 Rotate the bits in each packed 32-bit integer in a to the right by the number of bits specified in the corresponding element of b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_rorv_epi64 Rotate the bits in each packed 64-bit integer in a to the right by the number of bits specified in the corresponding element of b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_roundscale_pd Round packed double-precision (64-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm256_maskz_roundscale_ps Round packed single-precision (32-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm256_maskz_rsqrt14_pd Compute the approximate reciprocal square root of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14.
_mm256_maskz_rsqrt14_ps Compute the approximate reciprocal square root of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14.
_mm256_maskz_scalef_pd Scale the packed double-precision (64-bit) floating-point elements in a using values from b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_scalef_ps Scale the packed single-precision (32-bit) floating-point elements in a using values from b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_set1_epi32 Broadcast 32-bit integer a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_set1_epi64 Broadcast 64-bit integer a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_shuffle_epi32 Shuffle 32-bit integers in a within 128-bit lanes using the control in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_shuffle_f32x4 Shuffle 128-bits (composed of 4 single-precision (32-bit) floating-point elements) selected by imm8 from a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_shuffle_f64x2 Shuffle 128-bits (composed of 2 double-precision (64-bit) floating-point elements) selected by imm8 from a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_shuffle_i32x4 Shuffle 128-bits (composed of 4 32-bit integers) selected by imm8 from a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_shuffle_i64x2 Shuffle 128-bits (composed of 2 64-bit integers) selected by imm8 from a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_shuffle_pd Shuffle double-precision (64-bit) floating-point elements within 128-bit lanes using the control in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_shuffle_ps Shuffle single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_sll_epi32 Shift packed 32-bit integers in a left by count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_sll_epi64 Shift packed 64-bit integers in a left by count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_slli_epi32 Shift packed 32-bit integers in a left by imm8 while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_slli_epi64 Shift packed 64-bit integers in a left by imm8 while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_sllv_epi32 Shift packed 32-bit integers in a left by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_sllv_epi64 Shift packed 64-bit integers in a left by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_sqrt_pd Compute the square root of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_sqrt_ps Compute the square root of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_sra_epi32 Shift packed 32-bit integers in a right by count while shifting in sign bits, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_sra_epi64 Shift packed 64-bit integers in a right by count while shifting in sign bits, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_srai_epi32 Shift packed 32-bit integers in a right by imm8 while shifting in sign bits, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_srai_epi64 Shift packed 64-bit integers in a right by imm8 while shifting in sign bits, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_srav_epi32 Shift packed 32-bit integers in a right by the amount specified by the corresponding element in count while shifting in sign bits, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_srav_epi64 Shift packed 64-bit integers in a right by the amount specified by the corresponding element in count while shifting in sign bits, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_srl_epi32 Shift packed 32-bit integers in a right by count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_srl_epi64 Shift packed 64-bit integers in a right by count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_srli_epi32 Shift packed 32-bit integers in a right by imm8 while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_srli_epi64 Shift packed 64-bit integers in a right by imm8 while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_srlv_epi32 Shift packed 32-bit integers in a right by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_srlv_epi64 Shift packed 64-bit integers in a right by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_sub_epi32 Subtract packed 32-bit integers in b from packed 32-bit integers in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_sub_epi64 Subtract packed 64-bit integers in b from packed 64-bit integers in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_sub_pd Subtract packed double-precision (64-bit) floating-point elements in b from packed double-precision (64-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_sub_ps Subtract packed single-precision (32-bit) floating-point elements in b from packed single-precision (32-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_ternarylogic_epi32 Bitwise ternary logic that provides the capability to implement any three-operand binary function; the specific binary function is specified by value in imm8. For each bit in each packed 32-bit integer, the corresponding bit from a, b, and c are used to form a 3 bit index into imm8, and the value at that bit in imm8 is written to the corresponding bit in dst using zeromask k at 32-bit granularity (32-bit elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_ternarylogic_epi64 Bitwise ternary logic that provides the capability to implement any three-operand binary function; the specific binary function is specified by value in imm8. For each bit in each packed 64-bit integer, the corresponding bit from a, b, and c are used to form a 3 bit index into imm8, and the value at that bit in imm8 is written to the corresponding bit in dst using zeromask k at 64-bit granularity (64-bit elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_unpackhi_epi32 Unpack and interleave 32-bit integers from the high half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_unpackhi_epi64 Unpack and interleave 64-bit integers from the high half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_unpackhi_pd Unpack and interleave double-precision (64-bit) floating-point elements from the high half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_unpackhi_ps Unpack and interleave single-precision (32-bit) floating-point elements from the high half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_unpacklo_epi32 Unpack and interleave 32-bit integers from the low half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_unpacklo_epi64 Unpack and interleave 64-bit integers from the low half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_unpacklo_pd Unpack and interleave double-precision (64-bit) floating-point elements from the low half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_unpacklo_ps Unpack and interleave single-precision (32-bit) floating-point elements from the low half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_xor_epi32 Compute the bitwise XOR of packed 32-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_maskz_xor_epi64 Compute the bitwise XOR of packed 64-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm256_max_epi64 Compare packed signed 64-bit integers in a and b, and store packed maximum values in dst.
_mm256_max_epu64 Compare packed unsigned 64-bit integers in a and b, and store packed maximum values in dst.
_mm256_min_epi64 Compare packed signed 64-bit integers in a and b, and store packed minimum values in dst.
_mm256_min_epu64 Compare packed unsigned 64-bit integers in a and b, and store packed minimum values in dst.
_mm256_mmask_i32gather_epi32 Loads 8 32-bit integer elements from memory starting at location base_addr at packed 32-bit integer indices stored in vindex scaled by scale using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mmask_i32gather_epi64 Loads 4 64-bit integer elements from memory starting at location base_addr at packed 32-bit integer indices stored in vindex scaled by scale using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mmask_i32gather_pd Loads 4 double-precision (64-bit) floating-point elements from memory starting at location base_addr at packed 32-bit integer indices stored in vindex scaled by scale using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mmask_i32gather_ps Loads 8 single-precision (32-bit) floating-point elements from memory starting at location base_addr at packed 32-bit integer indices stored in vindex scaled by scale using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mmask_i64gather_epi32 Loads 4 32-bit integer elements from memory starting at location base_addr at packed 64-bit integer indices stored in vindex scaled by scale using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mmask_i64gather_epi64 Loads 4 64-bit integer elements from memory starting at location base_addr at packed 32-bit integer indices stored in vindex scaled by scale using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mmask_i64gather_pd Loads 4 double-precision (64-bit) floating-point elements from memory starting at location base_addr at packed 32-bit integer indices stored in vindex scaled by scale using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_mmask_i64gather_ps Loads 4 single-precision (32-bit) floating-point elements from memory starting at location base_addr at packed 32-bit integer indices stored in vindex scaled by scale using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm256_or_epi32 Compute the bitwise OR of packed 32-bit integers in a and b, and store the results in dst.
_mm256_or_epi64 Compute the bitwise OR of packed 64-bit integers in a and b, and store the resut in dst.
_mm256_permutex2var_epi32 Shuffle 32-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst.
_mm256_permutex2var_epi64 Shuffle 64-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst.
_mm256_permutex2var_pd Shuffle double-precision (64-bit) floating-point elements in a and b across lanes using the corresponding selector and index in idx, and store the results in dst.
_mm256_permutex2var_ps Shuffle single-precision (32-bit) floating-point elements in a and b across lanes using the corresponding selector and index in idx, and store the results in dst.
_mm256_permutex_epi64 Shuffle 64-bit integers in a within 256-bit lanes using the control in imm8, and store the results in dst.
_mm256_permutex_pd Shuffle double-precision (64-bit) floating-point elements in a within 256-bit lanes using the control in imm8, and store the results in dst.
_mm256_permutexvar_epi32 Shuffle 32-bit integers in a across lanes using the corresponding index in idx, and store the results in dst.
_mm256_permutexvar_epi64 Shuffle 64-bit integers in a across lanes using the corresponding index in idx, and store the results in dst.
_mm256_permutexvar_pd Shuffle double-precision (64-bit) floating-point elements in a across lanes using the corresponding index in idx, and store the results in dst.
_mm256_permutexvar_ps Shuffle single-precision (32-bit) floating-point elements in a across lanes using the corresponding index in idx.
_mm256_rcp14_pd Compute the approximate reciprocal of packed double-precision (64-bit) floating-point elements in a, and store the results in dst. The maximum relative error for this approximation is less than 2^-14.
_mm256_rcp14_ps Compute the approximate reciprocal of packed single-precision (32-bit) floating-point elements in a, and store the results in dst. The maximum relative error for this approximation is less than 2^-14.
_mm256_rol_epi32 Rotate the bits in each packed 32-bit integer in a to the left by the number of bits specified in imm8, and store the results in dst.
_mm256_rol_epi64 Rotate the bits in each packed 64-bit integer in a to the left by the number of bits specified in imm8, and store the results in dst.
_mm256_rolv_epi32 Rotate the bits in each packed 32-bit integer in a to the left by the number of bits specified in the corresponding element of b, and store the results in dst.
_mm256_rolv_epi64 Rotate the bits in each packed 64-bit integer in a to the left by the number of bits specified in the corresponding element of b, and store the results in dst.
_mm256_ror_epi32 Rotate the bits in each packed 32-bit integer in a to the right by the number of bits specified in imm8, and store the results in dst.
_mm256_ror_epi64 Rotate the bits in each packed 64-bit integer in a to the right by the number of bits specified in imm8, and store the results in dst.
_mm256_rorv_epi32 Rotate the bits in each packed 32-bit integer in a to the right by the number of bits specified in the corresponding element of b, and store the results in dst.
_mm256_rorv_epi64 Rotate the bits in each packed 64-bit integer in a to the right by the number of bits specified in the corresponding element of b, and store the results in dst.
_mm256_roundscale_pd Round packed double-precision (64-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst.
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm256_roundscale_ps Round packed single-precision (32-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst.
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm256_rsqrt14_pd Compute the approximate reciprocal square root of packed double-precision (64-bit) floating-point elements in a, and store the results in dst. The maximum relative error for this approximation is less than 2^-14.
_mm256_rsqrt14_ps Compute the approximate reciprocal square root of packed single-precision (32-bit) floating-point elements in a, and store the results in dst. The maximum relative error for this approximation is less than 2^-14.
_mm256_scalef_pd Scale the packed double-precision (64-bit) floating-point elements in a using values from b, and store the results in dst.
_mm256_scalef_ps Scale the packed single-precision (32-bit) floating-point elements in a using values from b, and store the results in dst.
_mm256_shuffle_f32x4 Shuffle 128-bits (composed of 4 single-precision (32-bit) floating-point elements) selected by imm8 from a and b, and store the results in dst.
_mm256_shuffle_f64x2 Shuffle 128-bits (composed of 2 double-precision (64-bit) floating-point elements) selected by imm8 from a and b, and store the results in dst.
_mm256_shuffle_i32x4 Shuffle 128-bits (composed of 4 32-bit integers) selected by imm8 from a and b, and store the results in dst.
_mm256_shuffle_i64x2 Shuffle 128-bits (composed of 2 64-bit integers) selected by imm8 from a and b, and store the results in dst.
_mm256_sra_epi64 Shift packed 64-bit integers in a right by count while shifting in sign bits, and store the results in dst.
_mm256_srai_epi64 Shift packed 64-bit integers in a right by imm8 while shifting in sign bits, and store the results in dst.
_mm256_srav_epi64 Shift packed 64-bit integers in a right by the amount specified by the corresponding element in count while shifting in sign bits, and store the results in dst.
_mm256_store_epi32 Store 256-bits (composed of 8 packed 32-bit integers) from a into memory. mem_addr must be aligned on a 32-byte boundary or a general-protection exception may be generated.
_mm256_store_epi64 Store 256-bits (composed of 4 packed 64-bit integers) from a into memory. mem_addr must be aligned on a 32-byte boundary or a general-protection exception may be generated.
_mm256_storeu_epi32 Store 256-bits (composed of 8 packed 32-bit integers) from a into memory. mem_addr does not need to be aligned on any particular boundary.
_mm256_storeu_epi64 Store 256-bits (composed of 4 packed 64-bit integers) from a into memory. mem_addr does not need to be aligned on any particular boundary.
_mm256_ternarylogic_epi32 Bitwise ternary logic that provides the capability to implement any three-operand binary function; the specific binary function is specified by value in imm8. For each bit in each packed 32-bit integer, the corresponding bit from a, b, and c are used to form a 3 bit index into imm8, and the value at that bit in imm8 is written to the corresponding bit in dst.
_mm256_ternarylogic_epi64 Bitwise ternary logic that provides the capability to implement any three-operand binary function; the specific binary function is specified by value in imm8. For each bit in each packed 64-bit integer, the corresponding bit from a, b, and c are used to form a 3 bit index into imm8, and the value at that bit in imm8 is written to the corresponding bit in dst.
_mm256_test_epi32_mask Compute the bitwise AND of packed 32-bit integers in a and b, producing intermediate 32-bit values, and set the corresponding bit in result mask k if the intermediate value is non-zero.
_mm256_test_epi64_mask Compute the bitwise AND of packed 64-bit integers in a and b, producing intermediate 64-bit values, and set the corresponding bit in result mask k if the intermediate value is non-zero.
_mm256_testn_epi32_mask Compute the bitwise NAND of packed 32-bit integers in a and b, producing intermediate 32-bit values, and set the corresponding bit in result mask k if the intermediate value is zero.
_mm256_testn_epi64_mask Compute the bitwise NAND of packed 64-bit integers in a and b, producing intermediate 64-bit values, and set the corresponding bit in result mask k if the intermediate value is zero.
_mm256_xor_epi32 Compute the bitwise XOR of packed 32-bit integers in a and b, and store the results in dst.
_mm256_xor_epi64 Compute the bitwise XOR of packed 64-bit integers in a and b, and store the results in dst.
_mm512_abs_epi32 Computes the absolute values of packed 32-bit integers in a.
_mm512_abs_epi64 Compute the absolute value of packed signed 64-bit integers in a, and store the unsigned results in dst.
_mm512_abs_pd Finds the absolute value of each packed double-precision (64-bit) floating-point element in v2, storing the results in dst.
_mm512_abs_ps Finds the absolute value of each packed single-precision (32-bit) floating-point element in v2, storing the results in dst.
_mm512_add_epi32 Add packed 32-bit integers in a and b, and store the results in dst.
_mm512_add_epi64 Add packed 64-bit integers in a and b, and store the results in dst.
_mm512_add_pd Add packed double-precision (64-bit) floating-point elements in a and b, and store the results in dst.
_mm512_add_ps Add packed single-precision (32-bit) floating-point elements in a and b, and store the results in dst.
_mm512_add_round_pd Add packed double-precision (64-bit) floating-point elements in a and b, and store the results in dst.\
_mm512_add_round_ps Add packed single-precision (32-bit) floating-point elements in a and b, and store the results in dst.\
_mm512_alignr_epi32 Concatenate a and b into a 128-byte immediate result, shift the result right by imm8 32-bit elements, and store the low 64 bytes (16 elements) in dst.
_mm512_alignr_epi64 Concatenate a and b into a 128-byte immediate result, shift the result right by imm8 64-bit elements, and store the low 64 bytes (8 elements) in dst.
_mm512_and_epi32 Compute the bitwise AND of packed 32-bit integers in a and b, and store the results in dst.
_mm512_and_epi64 Compute the bitwise AND of 512 bits (composed of packed 64-bit integers) in a and b, and store the results in dst.
_mm512_and_si512 Compute the bitwise AND of 512 bits (representing integer data) in a and b, and store the result in dst.
_mm512_andnot_epi32 Compute the bitwise NOT of packed 32-bit integers in a and then AND with b, and store the results in dst.
_mm512_andnot_epi64 Compute the bitwise NOT of 512 bits (composed of packed 64-bit integers) in a and then AND with b, and store the results in dst.
_mm512_andnot_si512 Compute the bitwise NOT of 512 bits (representing integer data) in a and then AND with b, and store the result in dst.
_mm512_broadcast_f32x4 Broadcast the 4 packed single-precision (32-bit) floating-point elements from a to all elements of dst.
_mm512_broadcast_f64x4 Broadcast the 4 packed double-precision (64-bit) floating-point elements from a to all elements of dst.
_mm512_broadcast_i32x4 Broadcast the 4 packed 32-bit integers from a to all elements of dst.
_mm512_broadcast_i64x4 Broadcast the 4 packed 64-bit integers from a to all elements of dst.
_mm512_broadcastd_epi32 Broadcast the low packed 32-bit integer from a to all elements of dst.
_mm512_broadcastq_epi64 Broadcast the low packed 64-bit integer from a to all elements of dst.
_mm512_broadcastsd_pd Broadcast the low double-precision (64-bit) floating-point element from a to all elements of dst.
_mm512_broadcastss_ps Broadcast the low single-precision (32-bit) floating-point element from a to all elements of dst.
_mm512_castpd128_pd512 Cast vector of type __m128d to type __m512d; the upper 384 bits of the result are indeterminate.
_mm512_castpd256_pd512 Cast vector of type __m256d to type __m512d; the upper 256 bits of the result are indeterminate.
_mm512_castpd512_pd128 Cast vector of type __m512d to type __m128d. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency.
_mm512_castpd512_pd256 Cast vector of type __m512d to type __m256d. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency.
_mm512_castpd_ps Cast vector of type __m512d to type __m512. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency.
_mm512_castpd_si512 Cast vector of type __m512d to type __m512i. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency.
_mm512_castps128_ps512 Cast vector of type __m128 to type __m512; the upper 384 bits of the result are indeterminate.
_mm512_castps256_ps512 Cast vector of type __m256 to type __m512; the upper 256 bits of the result are indeterminate.
_mm512_castps512_ps128 Cast vector of type __m512 to type __m128. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency.
_mm512_castps512_ps256 Cast vector of type __m512 to type __m256. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency.
_mm512_castps_pd Cast vector of type __m512 to type __m512d. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency.
_mm512_castps_si512 Cast vector of type __m512 to type __m512i. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency.
_mm512_castsi128_si512 Cast vector of type __m128i to type __m512i; the upper 384 bits of the result are indeterminate.
_mm512_castsi256_si512 Cast vector of type __m256i to type __m512i; the upper 256 bits of the result are indeterminate.
_mm512_castsi512_pd Cast vector of type __m512i to type __m512d. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency.
_mm512_castsi512_ps Cast vector of type __m512i to type __m512. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency.
_mm512_castsi512_si128 Cast vector of type __m512i to type __m128i. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency.
_mm512_castsi512_si256 Cast vector of type __m512i to type __m256i. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency.
_mm512_cmp_epi32_mask Compare packed signed 32-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
_mm512_cmp_epi64_mask Compare packed signed 64-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
_mm512_cmp_epu32_mask Compare packed unsigned 32-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
_mm512_cmp_epu64_mask Compare packed unsigned 64-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
_mm512_cmp_pd_mask Compare packed double-precision (64-bit) floating-point elements in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
_mm512_cmp_ps_mask Compare packed single-precision (32-bit) floating-point elements in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
_mm512_cmp_round_pd_mask Compare packed double-precision (64-bit) floating-point elements in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_cmp_round_ps_mask Compare packed single-precision (32-bit) floating-point elements in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_cmpeq_epi32_mask Compare packed 32-bit integers in a and b for equality, and store the results in mask vector k.
_mm512_cmpeq_epi64_mask Compare packed 64-bit integers in a and b for equality, and store the results in mask vector k.
_mm512_cmpeq_epu32_mask Compare packed unsigned 32-bit integers in a and b for equality, and store the results in mask vector k.
_mm512_cmpeq_epu64_mask Compare packed unsigned 64-bit integers in a and b for equality, and store the results in mask vector k.
_mm512_cmpeq_pd_mask Compare packed double-precision (64-bit) floating-point elements in a and b for equality, and store the results in mask vector k.
_mm512_cmpeq_ps_mask Compare packed single-precision (32-bit) floating-point elements in a and b for equality, and store the results in mask vector k.
_mm512_cmpge_epi32_mask Compare packed signed 32-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k.
_mm512_cmpge_epi64_mask Compare packed signed 64-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k.
_mm512_cmpge_epu32_mask Compare packed unsigned 32-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k.
_mm512_cmpge_epu64_mask Compare packed unsigned 64-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k.
_mm512_cmpgt_epi32_mask Compare packed signed 32-bit integers in a and b for greater-than, and store the results in mask vector k.
_mm512_cmpgt_epi64_mask Compare packed signed 64-bit integers in a and b for greater-than, and store the results in mask vector k.
_mm512_cmpgt_epu32_mask Compare packed unsigned 32-bit integers in a and b for greater-than, and store the results in mask vector k.
_mm512_cmpgt_epu64_mask Compare packed unsigned 64-bit integers in a and b for greater-than, and store the results in mask vector k.
_mm512_cmple_epi32_mask Compare packed signed 32-bit integers in a and b for less-than-or-equal, and store the results in mask vector k.
_mm512_cmple_epi64_mask Compare packed signed 64-bit integers in a and b for less-than-or-equal, and store the results in mask vector k.
_mm512_cmple_epu32_mask Compare packed unsigned 32-bit integers in a and b for less-than-or-equal, and store the results in mask vector k.
_mm512_cmple_epu64_mask Compare packed unsigned 64-bit integers in a and b for less-than-or-equal, and store the results in mask vector k.
_mm512_cmple_pd_mask Compare packed double-precision (64-bit) floating-point elements in a and b for less-than-or-equal, and store the results in mask vector k.
_mm512_cmple_ps_mask Compare packed single-precision (32-bit) floating-point elements in a and b for less-than-or-equal, and store the results in mask vector k.
_mm512_cmplt_epi32_mask Compare packed signed 32-bit integers in a and b for less-than, and store the results in mask vector k.
_mm512_cmplt_epi64_mask Compare packed signed 64-bit integers in a and b for less-than, and store the results in mask vector k.
_mm512_cmplt_epu32_mask Compare packed unsigned 32-bit integers in a and b for less-than, and store the results in mask vector k.
_mm512_cmplt_epu64_mask Compare packed unsigned 64-bit integers in a and b for less-than, and store the results in mask vector k.
_mm512_cmplt_pd_mask Compare packed double-precision (64-bit) floating-point elements in a and b for less-than, and store the results in mask vector k.
_mm512_cmplt_ps_mask Compare packed single-precision (32-bit) floating-point elements in a and b for less-than, and store the results in mask vector k.
_mm512_cmpneq_epi32_mask Compare packed 32-bit integers in a and b for not-equal, and store the results in mask vector k.
_mm512_cmpneq_epi64_mask Compare packed signed 64-bit integers in a and b for not-equal, and store the results in mask vector k.
_mm512_cmpneq_epu32_mask Compare packed unsigned 32-bit integers in a and b for not-equal, and store the results in mask vector k.
_mm512_cmpneq_epu64_mask Compare packed unsigned 64-bit integers in a and b for not-equal, and store the results in mask vector k.
_mm512_cmpneq_pd_mask Compare packed double-precision (64-bit) floating-point elements in a and b for not-equal, and store the results in mask vector k.
_mm512_cmpneq_ps_mask Compare packed single-precision (32-bit) floating-point elements in a and b for not-equal, and store the results in mask vector k.
_mm512_cmpnle_pd_mask Compare packed double-precision (64-bit) floating-point elements in a and b for not-less-than-or-equal, and store the results in mask vector k.
_mm512_cmpnle_ps_mask Compare packed single-precision (32-bit) floating-point elements in a and b for not-less-than-or-equal, and store the results in mask vector k.
_mm512_cmpnlt_pd_mask Compare packed double-precision (64-bit) floating-point elements in a and b for not-less-than, and store the results in mask vector k.
_mm512_cmpnlt_ps_mask Compare packed single-precision (32-bit) floating-point elements in a and b for not-less-than, and store the results in mask vector k.
_mm512_cmpord_pd_mask Compare packed double-precision (64-bit) floating-point elements in a and b to see if neither is NaN, and store the results in mask vector k.
_mm512_cmpord_ps_mask Compare packed single-precision (32-bit) floating-point elements in a and b to see if neither is NaN, and store the results in mask vector k.
_mm512_cmpunord_pd_mask Compare packed double-precision (64-bit) floating-point elements in a and b to see if either is NaN, and store the results in mask vector k.
_mm512_cmpunord_ps_mask Compare packed single-precision (32-bit) floating-point elements in a and b to see if either is NaN, and store the results in mask vector k.
_mm512_cvt_roundepi32_ps Convert packed signed 32-bit integers in a to packed single-precision (32-bit) floating-point elements, and store the results in dst.\
_mm512_cvt_roundepu32_ps Convert packed unsigned 32-bit integers in a to packed single-precision (32-bit) floating-point elements, and store the results in dst.\
_mm512_cvt_roundpd_epi32 Convert packed double-precision (64-bit) floating-point elements in a to packed 32-bit integers, and store the results in dst.\
_mm512_cvt_roundpd_epu32 Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-bit integers, and store the results in dst.\
_mm512_cvt_roundpd_ps Convert packed double-precision (64-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst.\
_mm512_cvt_roundph_ps Convert packed half-precision (16-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_cvt_roundps_epi32 Convert packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers, and store the results in dst.
_mm512_cvt_roundps_epu32 Convert packed single-precision (32-bit) floating-point elements in a to packed unsigned 32-bit integers, and store the results in dst.\
_mm512_cvt_roundps_pd Convert packed single-precision (32-bit) floating-point elements in a to packed double-precision (64-bit) floating-point elements, and store the results in dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_cvt_roundps_ph Convert packed single-precision (32-bit) floating-point elements in a to packed half-precision (16-bit) floating-point elements, and store the results in dst.
Rounding is done according to the rounding[3:0] parameter, which can be one of:
_mm512_cvtepi16_epi32 Sign extend packed 16-bit integers in a to packed 32-bit integers, and store the results in dst.
_mm512_cvtepi16_epi64 Sign extend packed 16-bit integers in a to packed 64-bit integers, and store the results in dst.
_mm512_cvtepi32_epi16 Convert packed 32-bit integers in a to packed 16-bit integers with truncation, and store the results in dst.
_mm512_cvtepi32_epi64 Sign extend packed 32-bit integers in a to packed 64-bit integers, and store the results in dst.
_mm512_cvtepi32_epi8 Convert packed 32-bit integers in a to packed 8-bit integers with truncation, and store the results in dst.
_mm512_cvtepi32_pd Convert packed signed 32-bit integers in a to packed double-precision (64-bit) floating-point elements, and store the results in dst.
_mm512_cvtepi32_ps Convert packed signed 32-bit integers in a to packed single-precision (32-bit) floating-point elements, and store the results in dst.
_mm512_cvtepi32lo_pd Performs element-by-element conversion of the lower half of packed 32-bit integer elements in v2 to packed double-precision (64-bit) floating-point elements, storing the results in dst.
_mm512_cvtepi64_epi16 Convert packed 64-bit integers in a to packed 16-bit integers with truncation, and store the results in dst.
_mm512_cvtepi64_epi32 Convert packed 64-bit integers in a to packed 32-bit integers with truncation, and store the results in dst.
_mm512_cvtepi64_epi8 Convert packed 64-bit integers in a to packed 8-bit integers with truncation, and store the results in dst.
_mm512_cvtepi8_epi32 Sign extend packed 8-bit integers in a to packed 32-bit integers, and store the results in dst.
_mm512_cvtepi8_epi64 Sign extend packed 8-bit integers in the low 8 bytes of a to packed 64-bit integers, and store the results in dst.
_mm512_cvtepu16_epi32 Zero extend packed unsigned 16-bit integers in a to packed 32-bit integers, and store the results in dst.
_mm512_cvtepu16_epi64 Zero extend packed unsigned 16-bit integers in a to packed 64-bit integers, and store the results in dst.
_mm512_cvtepu32_epi64 Zero extend packed unsigned 32-bit integers in a to packed 64-bit integers, and store the results in dst.
_mm512_cvtepu32_pd Convert packed unsigned 32-bit integers in a to packed double-precision (64-bit) floating-point elements, and store the results in dst.
_mm512_cvtepu32_ps Convert packed unsigned 32-bit integers in a to packed single-precision (32-bit) floating-point elements, and store the results in dst.
_mm512_cvtepu32lo_pd Performs element-by-element conversion of the lower half of packed 32-bit unsigned integer elements in v2 to packed double-precision (64-bit) floating-point elements, storing the results in dst.
_mm512_cvtepu8_epi32 Zero extend packed unsigned 8-bit integers in a to packed 32-bit integers, and store the results in dst.
_mm512_cvtepu8_epi64 Zero extend packed unsigned 8-bit integers in the low 8 byte sof a to packed 64-bit integers, and store the results in dst.
_mm512_cvtpd_epi32 Convert packed double-precision (64-bit) floating-point elements in a to packed 32-bit integers, and store the results in dst.
_mm512_cvtpd_epu32 Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-bit integers, and store the results in dst.
_mm512_cvtpd_ps Convert packed double-precision (64-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst.
_mm512_cvtpd_pslo Performs an element-by-element conversion of packed double-precision (64-bit) floating-point elements in v2 to single-precision (32-bit) floating-point elements and stores them in dst. The elements are stored in the lower half of the results vector, while the remaining upper half locations are set to 0.
_mm512_cvtph_ps Convert packed half-precision (16-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst.
_mm512_cvtps_epi32 Convert packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers, and store the results in dst.
_mm512_cvtps_epu32 Convert packed single-precision (32-bit) floating-point elements in a to packed unsigned 32-bit integers, and store the results in dst.
_mm512_cvtps_pd Convert packed single-precision (32-bit) floating-point elements in a to packed double-precision (64-bit) floating-point elements, and store the results in dst.
_mm512_cvtps_ph Convert packed single-precision (32-bit) floating-point elements in a to packed half-precision (16-bit) floating-point elements, and store the results in dst.
Rounding is done according to the rounding[3:0] parameter, which can be one of:
_mm512_cvtpslo_pd Performs element-by-element conversion of the lower half of packed single-precision (32-bit) floating-point elements in v2 to packed double-precision (64-bit) floating-point elements, storing the results in dst.
_mm512_cvtsd_f64 Copy the lower double-precision (64-bit) floating-point element of a to dst.
_mm512_cvtsepi32_epi16 Convert packed signed 32-bit integers in a to packed 16-bit integers with signed saturation, and store the results in dst.
_mm512_cvtsepi32_epi8 Convert packed signed 32-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst.
_mm512_cvtsepi64_epi16 Convert packed signed 64-bit integers in a to packed 16-bit integers with signed saturation, and store the results in dst.
_mm512_cvtsepi64_epi32 Convert packed signed 64-bit integers in a to packed 32-bit integers with signed saturation, and store the results in dst.
_mm512_cvtsepi64_epi8 Convert packed signed 64-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst.
_mm512_cvtsi512_si32 Copy the lower 32-bit integer in a to dst.
_mm512_cvtss_f32 Copy the lower single-precision (32-bit) floating-point element of a to dst.
_mm512_cvtt_roundpd_epi32 Convert packed double-precision (64-bit) floating-point elements in a to packed 32-bit integers with truncation, and store the results in dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_cvtt_roundpd_epu32 Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-bit integers with truncation, and store the results in dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_cvtt_roundps_epi32 Convert packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers with truncation, and store the results in dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_cvtt_roundps_epu32 Convert packed single-precision (32-bit) floating-point elements in a to packed unsigned 32-bit integers with truncation, and store the results in dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_cvttpd_epi32 Convert packed double-precision (64-bit) floating-point elements in a to packed 32-bit integers with truncation, and store the results in dst.
_mm512_cvttpd_epu32 Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-bit integers with truncation, and store the results in dst.
_mm512_cvttps_epi32 Convert packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers with truncation, and store the results in dst.
_mm512_cvttps_epu32 Convert packed single-precision (32-bit) floating-point elements in a to packed unsigned 32-bit integers with truncation, and store the results in dst.
_mm512_cvtusepi32_epi16 Convert packed unsigned 32-bit integers in a to packed unsigned 16-bit integers with unsigned saturation, and store the results in dst.
_mm512_cvtusepi32_epi8 Convert packed unsigned 32-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst.
_mm512_cvtusepi64_epi16 Convert packed unsigned 64-bit integers in a to packed unsigned 16-bit integers with unsigned saturation, and store the results in dst.
_mm512_cvtusepi64_epi32 Convert packed unsigned 64-bit integers in a to packed unsigned 32-bit integers with unsigned saturation, and store the results in dst.
_mm512_cvtusepi64_epi8 Convert packed unsigned 64-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst.
_mm512_div_pd Divide packed double-precision (64-bit) floating-point elements in a by packed elements in b, and store the results in dst.
_mm512_div_ps Divide packed single-precision (32-bit) floating-point elements in a by packed elements in b, and store the results in dst.
_mm512_div_round_pd Divide packed double-precision (64-bit) floating-point elements in a by packed elements in b, =and store the results in dst.\
_mm512_div_round_ps Divide packed single-precision (32-bit) floating-point elements in a by packed elements in b, and store the results in dst.\
_mm512_extractf32x4_ps Extract 128 bits (composed of 4 packed single-precision (32-bit) floating-point elements) from a, selected with imm8, and store the result in dst.
_mm512_extractf64x4_pd Extract 256 bits (composed of 4 packed double-precision (64-bit) floating-point elements) from a, selected with imm8, and store the result in dst.
_mm512_extracti32x4_epi32 Extract 128 bits (composed of 4 packed 32-bit integers) from a, selected with IMM2, and store the result in dst.
_mm512_extracti64x4_epi64 Extract 256 bits (composed of 4 packed 64-bit integers) from a, selected with IMM1, and store the result in dst.
_mm512_fixupimm_pd Fix up packed double-precision (64-bit) floating-point elements in a and b using packed 64-bit integers in c, and store the results in dst. imm8 is used to set the required flags reporting.
_mm512_fixupimm_ps Fix up packed single-precision (32-bit) floating-point elements in a and b using packed 32-bit integers in c, and store the results in dst. imm8 is used to set the required flags reporting.
_mm512_fixupimm_round_pd Fix up packed double-precision (64-bit) floating-point elements in a and b using packed 64-bit integers in c, and store the results in dst. imm8 is used to set the required flags reporting.\
_mm512_fixupimm_round_ps Fix up packed single-precision (32-bit) floating-point elements in a and b using packed 32-bit integers in c, and store the results in dst. imm8 is used to set the required flags reporting.\
_mm512_fmadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst.
_mm512_fmadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst.
_mm512_fmadd_round_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst.\
_mm512_fmadd_round_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst.\
_mm512_fmaddsub_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst.
_mm512_fmaddsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst.
_mm512_fmaddsub_round_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst.\
_mm512_fmaddsub_round_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst.\
_mm512_fmsub_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst.
_mm512_fmsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst.
_mm512_fmsub_round_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst.\
_mm512_fmsub_round_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst.\
_mm512_fmsubadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst.
_mm512_fmsubadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst.
_mm512_fmsubadd_round_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst.\
_mm512_fmsubadd_round_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst.\
_mm512_fnmadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst.
_mm512_fnmadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst.
_mm512_fnmadd_round_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst.\
_mm512_fnmadd_round_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst.\
_mm512_fnmsub_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst.
_mm512_fnmsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst.
_mm512_fnmsub_round_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst.\
_mm512_fnmsub_round_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst.\
_mm512_getexp_pd Convert the exponent of each packed double-precision (64-bit) floating-point element in a to a double-precision (64-bit) floating-point number representing the integer exponent, and store the results in dst. This intrinsic essentially calculates floor(log2(x)) for each element.
_mm512_getexp_ps Convert the exponent of each packed single-precision (32-bit) floating-point element in a to a single-precision (32-bit) floating-point number representing the integer exponent, and store the results in dst. This intrinsic essentially calculates floor(log2(x)) for each element.
_mm512_getexp_round_pd Convert the exponent of each packed double-precision (64-bit) floating-point element in a to a double-precision (64-bit) floating-point number representing the integer exponent, and store the results in dst. This intrinsic essentially calculates floor(log2(x)) for each element.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_getexp_round_ps Convert the exponent of each packed single-precision (32-bit) floating-point element in a to a single-precision (32-bit) floating-point number representing the integer exponent, and store the results in dst. This intrinsic essentially calculates floor(log2(x)) for each element.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_getmant_pd Normalize the mantissas of packed double-precision (64-bit) floating-point elements in a, and store the results in dst. This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
_mm512_getmant_ps Normalize the mantissas of packed single-precision (32-bit) floating-point elements in a, and store the results in dst. This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign. The mantissa is normalized to the interval specified by interv, which can take the following values: _MM_MANT_NORM_1_2 // interval [1, 2) _MM_MANT_NORM_p5_2 // interval [0.5, 2) _MM_MANT_NORM_p5_1 // interval [0.5, 1) _MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5) The sign is determined by sc which can take the following values: _MM_MANT_SIGN_src // sign = sign(src) _MM_MANT_SIGN_zero // sign = 0 _MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
_mm512_getmant_round_pd Normalize the mantissas of packed double-precision (64-bit) floating-point elements in a, and store the results in dst. This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_getmant_round_ps Normalize the mantissas of packed single-precision (32-bit) floating-point elements in a, and store the results in dst. This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_i32gather_epi32 Gather 32-bit integers from memory using 32-bit indices. 32-bit elements are loaded from addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst. scale should be 1, 2, 4 or 8.
_mm512_i32gather_epi64 Gather 64-bit integers from memory using 32-bit indices. 64-bit elements are loaded from addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst. scale should be 1, 2, 4 or 8.
_mm512_i32gather_pd Gather double-precision (64-bit) floating-point elements from memory using 32-bit indices. 64-bit elements are loaded from addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst. scale should be 1, 2, 4 or 8.
_mm512_i32gather_ps Gather single-precision (32-bit) floating-point elements from memory using 32-bit indices. 32-bit elements are loaded from addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst. scale should be 1, 2, 4 or 8.
_mm512_i32logather_epi64 Loads 8 64-bit integer elements from memory starting at location base_addr at packed 32-bit integer indices stored in the lower half of vindex scaled by scale and stores them in dst.
_mm512_i32logather_pd Loads 8 double-precision (64-bit) floating-point elements from memory starting at location base_addr at packed 32-bit integer indices stored in the lower half of vindex scaled by scale and stores them in dst.
_mm512_i32loscatter_epi64 Stores 8 64-bit integer elements from a to memory starting at location base_addr at packed 32-bit integer indices stored in the lower half of vindex scaled by scale.
_mm512_i32loscatter_pd Stores 8 double-precision (64-bit) floating-point elements from a to memory starting at location base_addr at packed 32-bit integer indices stored in the lower half of vindex scaled by scale.
_mm512_i32scatter_epi32 Scatter 32-bit integers from a into memory using 32-bit indices. 32-bit elements are stored at addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale). scale should be 1, 2, 4 or 8.
_mm512_i32scatter_epi64 Scatter 64-bit integers from a into memory using 32-bit indices. 64-bit elements are stored at addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale). scale should be 1, 2, 4 or 8.
_mm512_i32scatter_pd Scatter double-precision (64-bit) floating-point elements from a into memory using 32-bit indices. 64-bit elements are stored at addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale). scale should be 1, 2, 4 or 8.
_mm512_i32scatter_ps Scatter single-precision (32-bit) floating-point elements from a into memory using 32-bit indices. 32-bit elements are stored at addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale). scale should be 1, 2, 4 or 8.
_mm512_i64gather_epi32 Gather 32-bit integers from memory using 64-bit indices. 32-bit elements are loaded from addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst. scale should be 1, 2, 4 or 8.
_mm512_i64gather_epi64 Gather 64-bit integers from memory using 64-bit indices. 64-bit elements are loaded from addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst. scale should be 1, 2, 4 or 8.
_mm512_i64gather_pd Gather double-precision (64-bit) floating-point elements from memory using 64-bit indices. 64-bit elements are loaded from addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst. scale should be 1, 2, 4 or 8.
_mm512_i64gather_ps Gather single-precision (32-bit) floating-point elements from memory using 64-bit indices. 32-bit elements are loaded from addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst. scale should be 1, 2, 4 or 8.
_mm512_i64scatter_epi32 Scatter 32-bit integers from a into memory using 64-bit indices. 32-bit elements are stored at addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale). scale should be 1, 2, 4 or 8.
_mm512_i64scatter_epi64 Scatter 64-bit integers from a into memory using 64-bit indices. 64-bit elements are stored at addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale). scale should be 1, 2, 4 or 8.
_mm512_i64scatter_pd Scatter double-precision (64-bit) floating-point elements from a into memory using 64-bit indices. 64-bit elements are stored at addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale). scale should be 1, 2, 4 or 8.
_mm512_i64scatter_ps Scatter single-precision (32-bit) floating-point elements from a into memory using 64-bit indices. 32-bit elements are stored at addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale) subject to mask k (elements are not stored when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8.
_mm512_insertf32x4 Copy a to dst, then insert 128 bits (composed of 4 packed single-precision (32-bit) floating-point elements) from b into dst at the location specified by imm8.
_mm512_insertf64x4 Copy a to dst, then insert 256 bits (composed of 4 packed double-precision (64-bit) floating-point elements) from b into dst at the location specified by imm8.
_mm512_inserti32x4 Copy a to dst, then insert 128 bits (composed of 4 packed 32-bit integers) from b into dst at the location specified by imm8.
_mm512_inserti64x4 Copy a to dst, then insert 256 bits (composed of 4 packed 64-bit integers) from b into dst at the location specified by imm8.
_mm512_int2mask Converts integer mask into bitmask, storing the result in dst.
_mm512_kand Compute the bitwise AND of 16-bit masks a and b, and store the result in k.
_mm512_kandn Compute the bitwise NOT of 16-bit masks a and then AND with b, and store the result in k.
_mm512_kmov Copy 16-bit mask a to k.
_mm512_knot Compute the bitwise NOT of 16-bit mask a, and store the result in k.
_mm512_kor Compute the bitwise OR of 16-bit masks a and b, and store the result in k.
_mm512_kortestc Performs bitwise OR between k1 and k2, storing the result in dst. CF flag is set if dst consists of all 1's.
_mm512_kortestz Performs bitwise OR between k1 and k2, storing the result in dst. ZF flag is set if dst is 0.
_mm512_kunpackb Unpack and interleave 8 bits from masks a and b, and store the 16-bit result in k.
_mm512_kxnor Compute the bitwise XNOR of 16-bit masks a and b, and store the result in k.
_mm512_kxor Compute the bitwise XOR of 16-bit masks a and b, and store the result in k.
_mm512_load_epi32 Load 512-bits (composed of 16 packed 32-bit integers) from memory into dst. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_load_epi64 Load 512-bits (composed of 8 packed 64-bit integers) from memory into dst. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_load_pd Load 512-bits (composed of 8 packed double-precision (64-bit) floating-point elements) from memory into dst. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_load_ps Load 512-bits (composed of 16 packed single-precision (32-bit) floating-point elements) from memory into dst. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_load_si512 Load 512-bits of integer data from memory into dst. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_loadu_epi32 Load 512-bits (composed of 16 packed 32-bit integers) from memory into dst. mem_addr does not need to be aligned on any particular boundary.
_mm512_loadu_epi64 Load 512-bits (composed of 8 packed 64-bit integers) from memory into dst. mem_addr does not need to be aligned on any particular boundary.
_mm512_loadu_pd Loads 512-bits (composed of 8 packed double-precision (64-bit) floating-point elements) from memory into result. mem_addr does not need to be aligned on any particular boundary.
_mm512_loadu_ps Loads 512-bits (composed of 16 packed single-precision (32-bit) floating-point elements) from memory into result. mem_addr does not need to be aligned on any particular boundary.
_mm512_loadu_si512 Load 512-bits of integer data from memory into dst. mem_addr does not need to be aligned on any particular boundary.
_mm512_mask2_permutex2var_epi32 Shuffle 32-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from idx when the corresponding mask bit is not set).
_mm512_mask2_permutex2var_epi64 Shuffle 64-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from idx when the corresponding mask bit is not set).
_mm512_mask2_permutex2var_pd Shuffle double-precision (64-bit) floating-point elements in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from idx when the corresponding mask bit is not set)
_mm512_mask2_permutex2var_ps Shuffle single-precision (32-bit) floating-point elements in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from idx when the corresponding mask bit is not set).
_mm512_mask2int Converts bit mask k1 into an integer value, storing the results in dst.
_mm512_mask3_fmadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm512_mask3_fmadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm512_mask3_fmadd_round_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).\
_mm512_mask3_fmadd_round_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).\
_mm512_mask3_fmaddsub_pd Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm512_mask3_fmaddsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm512_mask3_fmaddsub_round_pd Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).\
_mm512_mask3_fmaddsub_round_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).\
_mm512_mask3_fmsub_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm512_mask3_fmsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm512_mask3_fmsub_round_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).\
_mm512_mask3_fmsub_round_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).\
_mm512_mask3_fmsubadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm512_mask3_fmsubadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm512_mask3_fmsubadd_round_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).\
_mm512_mask3_fmsubadd_round_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).\
_mm512_mask3_fnmadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm512_mask3_fnmadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm512_mask3_fnmadd_round_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).\
_mm512_mask3_fnmadd_round_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).\
_mm512_mask3_fnmsub_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm512_mask3_fnmsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm512_mask3_fnmsub_round_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).\
_mm512_mask3_fnmsub_round_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).\
_mm512_mask_abs_epi32 Computes the absolute value of packed 32-bit integers in a, and store the unsigned results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_abs_epi64 Compute the absolute value of packed signed 64-bit integers in a, and store the unsigned results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_abs_pd Finds the absolute value of each packed double-precision (64-bit) floating-point element in v2, storing the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_abs_ps Finds the absolute value of each packed single-precision (32-bit) floating-point element in v2, storing the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_add_epi32 Add packed 32-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_add_epi64 Add packed 64-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_add_pd Add packed double-precision (64-bit) floating-point elements in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_add_ps Add packed single-precision (32-bit) floating-point elements in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_add_round_pd Add packed double-precision (64-bit) floating-point elements in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).\
_mm512_mask_add_round_ps Add packed single-precision (32-bit) floating-point elements in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).\
_mm512_mask_alignr_epi32 Concatenate a and b into a 128-byte immediate result, shift the result right by imm8 32-bit elements, and store the low 64 bytes (16 elements) in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_alignr_epi64 Concatenate a and b into a 128-byte immediate result, shift the result right by imm8 64-bit elements, and store the low 64 bytes (8 elements) in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_and_epi32 Performs element-by-element bitwise AND between packed 32-bit integer elements of a and b, storing the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_and_epi64 Compute the bitwise AND of packed 64-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_andnot_epi32 Compute the bitwise NOT of packed 32-bit integers in a and then AND with b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_andnot_epi64 Compute the bitwise NOT of packed 64-bit integers in a and then AND with b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_blend_epi32 Blend packed 32-bit integers from a and b using control mask k, and store the results in dst.
_mm512_mask_blend_epi64 Blend packed 64-bit integers from a and b using control mask k, and store the results in dst.
_mm512_mask_blend_pd Blend packed double-precision (64-bit) floating-point elements from a and b using control mask k, and store the results in dst.
_mm512_mask_blend_ps Blend packed single-precision (32-bit) floating-point elements from a and b using control mask k, and store the results in dst.
_mm512_mask_broadcast_f32x4 Broadcast the 4 packed single-precision (32-bit) floating-point elements from a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_broadcast_f64x4 Broadcast the 4 packed double-precision (64-bit) floating-point elements from a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_broadcast_i32x4 Broadcast the 4 packed 32-bit integers from a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_broadcast_i64x4 Broadcast the 4 packed 64-bit integers from a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_broadcastd_epi32 Broadcast the low packed 32-bit integer from a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_broadcastq_epi64 Broadcast the low packed 64-bit integer from a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_broadcastsd_pd Broadcast the low double-precision (64-bit) floating-point element from a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_broadcastss_ps Broadcast the low single-precision (32-bit) floating-point element from a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cmp_epi32_mask Compare packed signed 32-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmp_epi64_mask Compare packed signed 64-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmp_epu32_mask Compare packed unsigned 32-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmp_epu64_mask Compare packed unsigned 64-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmp_pd_mask Compare packed double-precision (64-bit) floating-point elements in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmp_ps_mask Compare packed single-precision (32-bit) floating-point elements in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmp_round_pd_mask Compare packed double-precision (64-bit) floating-point elements in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_mask_cmp_round_ps_mask Compare packed single-precision (32-bit) floating-point elements in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_mask_cmpeq_epi32_mask Compare packed 32-bit integers in a and b for equality, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpeq_epi64_mask Compare packed 64-bit integers in a and b for equality, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpeq_epu32_mask Compare packed unsigned 32-bit integers in a and b for equality, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpeq_epu64_mask Compare packed unsigned 64-bit integers in a and b for equality, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpeq_pd_mask Compare packed double-precision (64-bit) floating-point elements in a and b for equality, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpeq_ps_mask Compare packed single-precision (32-bit) floating-point elements in a and b for equality, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpge_epi32_mask Compare packed signed 32-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpge_epi64_mask Compare packed signed 64-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpge_epu32_mask Compare packed unsigned 32-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpge_epu64_mask Compare packed unsigned 64-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpgt_epi32_mask Compare packed signed 32-bit integers in a and b for greater-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpgt_epi64_mask Compare packed signed 64-bit integers in a and b for greater-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpgt_epu32_mask Compare packed unsigned 32-bit integers in a and b for greater-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpgt_epu64_mask Compare packed unsigned 64-bit integers in a and b for greater-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmple_epi32_mask Compare packed signed 32-bit integers in a and b for less-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmple_epi64_mask Compare packed signed 64-bit integers in a and b for less-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmple_epu32_mask Compare packed unsigned 32-bit integers in a and b for less-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmple_epu64_mask Compare packed unsigned 64-bit integers in a and b for less-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmple_pd_mask Compare packed double-precision (64-bit) floating-point elements in a and b for less-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmple_ps_mask Compare packed single-precision (32-bit) floating-point elements in a and b for less-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmplt_epi32_mask Compare packed signed 32-bit integers in a and b for less-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmplt_epi64_mask Compare packed signed 64-bit integers in a and b for less-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmplt_epu32_mask Compare packed unsigned 32-bit integers in a and b for less-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmplt_epu64_mask Compare packed unsigned 64-bit integers in a and b for less-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmplt_pd_mask Compare packed double-precision (64-bit) floating-point elements in a and b for less-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmplt_ps_mask Compare packed single-precision (32-bit) floating-point elements in a and b for less-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpneq_epi32_mask Compare packed 32-bit integers in a and b for not-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpneq_epi64_mask Compare packed signed 64-bit integers in a and b for not-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpneq_epu32_mask Compare packed unsigned 32-bit integers in a and b for not-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpneq_epu64_mask Compare packed unsigned 64-bit integers in a and b for not-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpneq_pd_mask Compare packed double-precision (64-bit) floating-point elements in a and b for not-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpneq_ps_mask Compare packed single-precision (32-bit) floating-point elements in a and b for not-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpnle_pd_mask Compare packed double-precision (64-bit) floating-point elements in a and b for not-less-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpnle_ps_mask Compare packed single-precision (32-bit) floating-point elements in a and b for not-less-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpnlt_pd_mask Compare packed double-precision (64-bit) floating-point elements in a and b for not-less-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpnlt_ps_mask Compare packed single-precision (32-bit) floating-point elements in a and b for not-less-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpord_pd_mask Compare packed double-precision (64-bit) floating-point elements in a and b to see if neither is NaN, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpord_ps_mask Compare packed single-precision (32-bit) floating-point elements in a and b to see if neither is NaN, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpunord_pd_mask Compare packed double-precision (64-bit) floating-point elements in a and b to see if either is NaN, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpunord_ps_mask Compare packed single-precision (32-bit) floating-point elements in a and b to see if either is NaN, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_compress_epi32 Contiguously store the active 32-bit integers in a (those with their respective bit set in writemask k) to dst, and pass through the remaining elements from src.
_mm512_mask_compress_epi64 Contiguously store the active 64-bit integers in a (those with their respective bit set in writemask k) to dst, and pass through the remaining elements from src.
_mm512_mask_compress_pd Contiguously store the active double-precision (64-bit) floating-point elements in a (those with their respective bit set in writemask k) to dst, and pass through the remaining elements from src.
_mm512_mask_compress_ps Contiguously store the active single-precision (32-bit) floating-point elements in a (those with their respective bit set in writemask k) to dst, and pass through the remaining elements from src.
_mm512_mask_compressstoreu_epi32 Contiguously store the active 32-bit integers in a (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm512_mask_compressstoreu_epi64 Contiguously store the active 64-bit integers in a (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm512_mask_compressstoreu_pd Contiguously store the active double-precision (64-bit) floating-point elements in a (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm512_mask_compressstoreu_ps Contiguously store the active single-precision (32-bit) floating-point elements in a (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm512_mask_cvt_roundepi32_ps Convert packed signed 32-bit integers in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).\
_mm512_mask_cvt_roundepu32_ps Convert packed unsigned 32-bit integers in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).\
_mm512_mask_cvt_roundpd_epi32 Convert packed double-precision (64-bit) floating-point elements in a to packed 32-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).\
_mm512_mask_cvt_roundpd_epu32 Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).\
_mm512_mask_cvt_roundpd_ps Convert packed double-precision (64-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).\
_mm512_mask_cvt_roundph_ps Convert packed half-precision (16-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_mask_cvt_roundps_epi32 Convert packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).\
_mm512_mask_cvt_roundps_epu32 Convert packed single-precision (32-bit) floating-point elements in a to packed unsigned 32-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).\
_mm512_mask_cvt_roundps_pd Convert packed single-precision (32-bit) floating-point elements in a to packed double-precision (64-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_mask_cvt_roundps_ph Convert packed single-precision (32-bit) floating-point elements in a to packed half-precision (16-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
Rounding is done according to the rounding[3:0] parameter, which can be one of:
_mm512_mask_cvtepi16_epi32 Sign extend packed 16-bit integers in a to packed 32-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtepi16_epi64 Sign extend packed 16-bit integers in a to packed 64-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtepi32_epi16 Convert packed 32-bit integers in a to packed 16-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtepi32_epi64 Sign extend packed 32-bit integers in a to packed 64-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtepi32_epi8 Convert packed 32-bit integers in a to packed 8-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtepi32_pd Convert packed signed 32-bit integers in a to packed double-precision (64-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtepi32_ps Convert packed signed 32-bit integers in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtepi32_storeu_epi16 Convert packed 32-bit integers in a to packed 16-bit integers with truncation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm512_mask_cvtepi32_storeu_epi8 Convert packed 32-bit integers in a to packed 8-bit integers with truncation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm512_mask_cvtepi32lo_pd Performs element-by-element conversion of the lower half of packed 32-bit integer elements in v2 to packed double-precision (64-bit) floating-point elements, storing the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtepi64_epi16 Convert packed 64-bit integers in a to packed 16-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtepi64_epi32 Convert packed 64-bit integers in a to packed 32-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtepi64_epi8 Convert packed 64-bit integers in a to packed 8-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtepi64_storeu_epi16 Convert packed 64-bit integers in a to packed 16-bit integers with truncation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm512_mask_cvtepi64_storeu_epi32 Convert packed 64-bit integers in a to packed 32-bit integers with truncation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm512_mask_cvtepi64_storeu_epi8 Convert packed 64-bit integers in a to packed 8-bit integers with truncation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm512_mask_cvtepi8_epi32 Sign extend packed 8-bit integers in a to packed 32-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtepi8_epi64 Sign extend packed 8-bit integers in the low 8 bytes of a to packed 64-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtepu16_epi32 Zero extend packed unsigned 16-bit integers in a to packed 32-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtepu16_epi64 Zero extend packed unsigned 16-bit integers in a to packed 64-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtepu32_epi64 Zero extend packed unsigned 32-bit integers in a to packed 64-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtepu32_pd Convert packed unsigned 32-bit integers in a to packed double-precision (64-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtepu32_ps Convert packed unsigned 32-bit integers in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtepu32lo_pd Performs element-by-element conversion of the lower half of 32-bit unsigned integer elements in v2 to packed double-precision (64-bit) floating-point elements, storing the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtepu8_epi32 Zero extend packed unsigned 8-bit integers in a to packed 32-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtepu8_epi64 Zero extend packed unsigned 8-bit integers in the low 8 bytes of a to packed 64-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtpd_epi32 Convert packed double-precision (64-bit) floating-point elements in a to packed 32-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtpd_epu32 Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtpd_ps Convert packed double-precision (64-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtpd_pslo Performs an element-by-element conversion of packed double-precision (64-bit) floating-point elements in v2 to single-precision (32-bit) floating-point elements and stores them in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). The elements are stored in the lower half of the results vector, while the remaining upper half locations are set to 0.
_mm512_mask_cvtph_ps Convert packed half-precision (16-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtps_epi32 Convert packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtps_epu32 Convert packed single-precision (32-bit) floating-point elements in a to packed unsigned 32-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtps_pd Convert packed single-precision (32-bit) floating-point elements in a to packed double-precision (64-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtps_ph Convert packed single-precision (32-bit) floating-point elements in a to packed half-precision (16-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
Rounding is done according to the rounding[3:0] parameter, which can be one of:
_mm512_mask_cvtpslo_pd Performs element-by-element conversion of the lower half of packed single-precision (32-bit) floating-point elements in v2 to packed double-precision (64-bit) floating-point elements, storing the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtsepi32_epi16 Convert packed signed 32-bit integers in a to packed 16-bit integers with signed saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtsepi32_epi8 Convert packed signed 32-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtsepi32_storeu_epi16 Convert packed signed 32-bit integers in a to packed 16-bit integers with signed saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm512_mask_cvtsepi32_storeu_epi8 Convert packed signed 32-bit integers in a to packed 8-bit integers with signed saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm512_mask_cvtsepi64_epi16 Convert packed signed 64-bit integers in a to packed 16-bit integers with signed saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtsepi64_epi32 Convert packed signed 64-bit integers in a to packed 32-bit integers with signed saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtsepi64_epi8 Convert packed signed 64-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtsepi64_storeu_epi16 Convert packed signed 64-bit integers in a to packed 16-bit integers with signed saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm512_mask_cvtsepi64_storeu_epi32 Convert packed signed 64-bit integers in a to packed 32-bit integers with signed saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm512_mask_cvtsepi64_storeu_epi8 Convert packed signed 64-bit integers in a to packed 8-bit integers with signed saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm512_mask_cvtt_roundpd_epi32 Convert packed double-precision (64-bit) floating-point elements in a to packed 32-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_mask_cvtt_roundpd_epu32 Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_mask_cvtt_roundps_epi32 Convert packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_mask_cvtt_roundps_epu32 Convert packed single-precision (32-bit) floating-point elements in a to packed unsigned 32-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_mask_cvttpd_epi32 Convert packed double-precision (64-bit) floating-point elements in a to packed 32-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvttpd_epu32 Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvttps_epi32 Convert packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvttps_epu32 Convert packed double-precision (32-bit) floating-point elements in a to packed unsigned 32-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtusepi32_epi16 Convert packed unsigned 32-bit integers in a to packed unsigned 16-bit integers with unsigned saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtusepi32_epi8 Convert packed unsigned 32-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtusepi32_storeu_epi16 Convert packed unsigned 32-bit integers in a to packed 16-bit integers with unsigned saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm512_mask_cvtusepi32_storeu_epi8 Convert packed unsigned 32-bit integers in a to packed 8-bit integers with unsigned saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm512_mask_cvtusepi64_epi16 Convert packed unsigned 64-bit integers in a to packed unsigned 16-bit integers with unsigned saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtusepi64_epi32 Convert packed unsigned 64-bit integers in a to packed unsigned 32-bit integers with unsigned saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtusepi64_epi8 Convert packed unsigned 64-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_cvtusepi64_storeu_epi16 Convert packed unsigned 64-bit integers in a to packed 16-bit integers with unsigned saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm512_mask_cvtusepi64_storeu_epi32 Convert packed unsigned 64-bit integers in a to packed 32-bit integers with unsigned saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm512_mask_cvtusepi64_storeu_epi8 Convert packed unsigned 64-bit integers in a to packed 8-bit integers with unsigned saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm512_mask_div_pd Divide packed double-precision (64-bit) floating-point elements in a by packed elements in b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_div_ps Divide packed single-precision (32-bit) floating-point elements in a by packed elements in b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_div_round_pd Divide packed double-precision (64-bit) floating-point elements in a by packed elements in b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).\
_mm512_mask_div_round_ps Divide packed single-precision (32-bit) floating-point elements in a by packed elements in b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).\
_mm512_mask_expand_epi32 Load contiguous active 32-bit integers from a (those with their respective bit set in mask k), and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_expand_epi64 Load contiguous active 64-bit integers from a (those with their respective bit set in mask k), and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_expand_pd Load contiguous active double-precision (64-bit) floating-point elements from a (those with their respective bit set in mask k), and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_expand_ps Load contiguous active single-precision (32-bit) floating-point elements from a (those with their respective bit set in mask k), and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_expandloadu_epi32 Load contiguous active 32-bit integers from unaligned memory at mem_addr (those with their respective bit set in mask k), and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_expandloadu_epi64 Load contiguous active 64-bit integers from unaligned memory at mem_addr (those with their respective bit set in mask k), and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_expandloadu_pd Load contiguous active double-precision (64-bit) floating-point elements from unaligned memory at mem_addr (those with their respective bit set in mask k), and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_expandloadu_ps Load contiguous active single-precision (32-bit) floating-point elements from unaligned memory at mem_addr (those with their respective bit set in mask k), and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_extractf32x4_ps Extract 128 bits (composed of 4 packed single-precision (32-bit) floating-point elements) from a, selected with imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_extractf64x4_pd Extract 256 bits (composed of 4 packed double-precision (64-bit) floating-point elements) from a, selected with imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_extracti32x4_epi32 Extract 128 bits (composed of 4 packed 32-bit integers) from a, selected with IMM2, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_extracti64x4_epi64 Extract 256 bits (composed of 4 packed 64-bit integers) from a, selected with IMM1, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_fixupimm_pd Fix up packed double-precision (64-bit) floating-point elements in a and b using packed 64-bit integers in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). imm8 is used to set the required flags reporting.
_mm512_mask_fixupimm_ps Fix up packed single-precision (32-bit) floating-point elements in a and b using packed 32-bit integers in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). imm8 is used to set the required flags reporting.
_mm512_mask_fixupimm_round_pd Fix up packed double-precision (64-bit) floating-point elements in a and b using packed 64-bit integers in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). imm8 is used to set the required flags reporting.\
_mm512_mask_fixupimm_round_ps Fix up packed single-precision (32-bit) floating-point elements in a and b using packed 32-bit integers in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). imm8 is used to set the required flags reporting.\
_mm512_mask_fmadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm512_mask_fmadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm512_mask_fmadd_round_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).\
_mm512_mask_fmadd_round_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).\
_mm512_mask_fmaddsub_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm512_mask_fmaddsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm512_mask_fmaddsub_round_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).\
_mm512_mask_fmaddsub_round_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).\
_mm512_mask_fmsub_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm512_mask_fmsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm512_mask_fmsub_round_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).\
_mm512_mask_fmsub_round_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).\
_mm512_mask_fmsubadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm512_mask_fmsubadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm512_mask_fmsubadd_round_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).\
_mm512_mask_fmsubadd_round_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).\
_mm512_mask_fnmadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm512_mask_fnmadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm512_mask_fnmadd_round_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).\
_mm512_mask_fnmadd_round_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).\
_mm512_mask_fnmsub_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm512_mask_fnmsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm512_mask_fnmsub_round_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).\
_mm512_mask_fnmsub_round_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).\
_mm512_mask_getexp_pd Convert the exponent of each packed double-precision (64-bit) floating-point element in a to a double-precision (64-bit) floating-point number representing the integer exponent, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). This intrinsic essentially calculates floor(log2(x)) for each element.
_mm512_mask_getexp_ps Convert the exponent of each packed single-precision (32-bit) floating-point element in a to a single-precision (32-bit) floating-point number representing the integer exponent, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). This intrinsic essentially calculates floor(log2(x)) for each element.
_mm512_mask_getexp_round_pd Convert the exponent of each packed double-precision (64-bit) floating-point element in a to a double-precision (64-bit) floating-point number representing the integer exponent, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). This intrinsic essentially calculates floor(log2(x)) for each element.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_mask_getexp_round_ps Convert the exponent of each packed single-precision (32-bit) floating-point element in a to a single-precision (32-bit) floating-point number representing the integer exponent, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). This intrinsic essentially calculates floor(log2(x)) for each element.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_mask_getmant_pd Normalize the mantissas of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
_mm512_mask_getmant_ps Normalize the mantissas of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
_mm512_mask_getmant_round_pd Normalize the mantissas of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_mask_getmant_round_ps Normalize the mantissas of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_mask_i32gather_epi32 Gather 32-bit integers from memory using 32-bit indices. 32-bit elements are loaded from addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8.
_mm512_mask_i32gather_epi64 Gather 64-bit integers from memory using 32-bit indices. 64-bit elements are loaded from addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8.
_mm512_mask_i32gather_pd Gather double-precision (64-bit) floating-point elements from memory using 32-bit indices. 64-bit elements are loaded from addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8.
_mm512_mask_i32gather_ps Gather single-precision (32-bit) floating-point elements from memory using 32-bit indices. 32-bit elements are loaded from addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8.
_mm512_mask_i32logather_epi64 Loads 8 64-bit integer elements from memory starting at location base_addr at packed 32-bit integer indices stored in the lower half of vindex scaled by scale and stores them in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_i32logather_pd Loads 8 double-precision (64-bit) floating-point elements from memory starting at location base_addr at packed 32-bit integer indices stored in the lower half of vindex scaled by scale and stores them in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_i32loscatter_epi64 Stores 8 64-bit integer elements from a to memory starting at location base_addr at packed 32-bit integer indices stored in the lower half of vindex scaled by scale using writemask k (elements whose corresponding mask bit is not set are not written to memory).
_mm512_mask_i32loscatter_pd Stores 8 double-precision (64-bit) floating-point elements from a to memory starting at location base_addr at packed 32-bit integer indices stored in the lower half of vindex scaled by scale using writemask k (elements whose corresponding mask bit is not set are not written to memory).
_mm512_mask_i32scatter_epi32 Scatter 32-bit integers from a into memory using 32-bit indices. 32-bit elements are stored at addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale) subject to mask k (elements are not stored when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8.
_mm512_mask_i32scatter_epi64 Scatter 64-bit integers from a into memory using 32-bit indices. 64-bit elements are stored at addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale) subject to mask k (elements are not stored when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8.
_mm512_mask_i32scatter_pd Scatter double-precision (64-bit) floating-point elements from a into memory using 32-bit indices. 64-bit elements are stored at addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale) subject to mask k (elements are not stored when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8.
_mm512_mask_i32scatter_ps Scatter single-precision (32-bit) floating-point elements from a into memory using 32-bit indices. 32-bit elements are stored at addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale) subject to mask k (elements are not stored when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8.
_mm512_mask_i64gather_epi32 Gather 32-bit integers from memory using 64-bit indices. 32-bit elements are loaded from addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8.
_mm512_mask_i64gather_epi64 Gather 64-bit integers from memory using 64-bit indices. 64-bit elements are loaded from addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8.
_mm512_mask_i64gather_pd Gather double-precision (64-bit) floating-point elements from memory using 64-bit indices. 64-bit elements are loaded from addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8.
_mm512_mask_i64gather_ps Gather single-precision (32-bit) floating-point elements from memory using 64-bit indices. 32-bit elements are loaded from addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8.
_mm512_mask_i64scatter_epi32 Scatter 32-bit integers from a into memory using 64-bit indices. 32-bit elements are stored at addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale) subject to mask k (elements are not stored when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8.
_mm512_mask_i64scatter_epi64 Scatter 64-bit integers from a into memory using 64-bit indices. 64-bit elements are stored at addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale) subject to mask k (elements are not stored when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8.
_mm512_mask_i64scatter_pd Scatter double-precision (64-bit) floating-point elements from a into memory using 64-bit indices. 64-bit elements are stored at addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale) subject to mask k (elements are not stored when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8.
_mm512_mask_i64scatter_ps Scatter single-precision (32-bit) floating-point elements from a into memory using 64-bit indices. 32-bit elements are stored at addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale) subject to mask k (elements are not stored when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8.
_mm512_mask_insertf32x4 Copy a to tmp, then insert 128 bits (composed of 4 packed single-precision (32-bit) floating-point elements) from b into tmp at the location specified by imm8. Store tmp to dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_insertf64x4 Copy a to tmp, then insert 256 bits (composed of 4 packed double-precision (64-bit) floating-point elements) from b into tmp at the location specified by imm8. Store tmp to dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_inserti32x4 Copy a to tmp, then insert 128 bits (composed of 4 packed 32-bit integers) from b into tmp at the location specified by imm8. Store tmp to dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_inserti64x4 Copy a to tmp, then insert 256 bits (composed of 4 packed 64-bit integers) from b into tmp at the location specified by imm8. Store tmp to dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_load_epi32 Load packed 32-bit integers from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_mask_load_epi64 Load packed 64-bit integers from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_mask_load_pd Load packed double-precision (64-bit) floating-point elements from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_mask_load_ps Load packed single-precision (32-bit) floating-point elements from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_mask_loadu_epi32 Load packed 32-bit integers from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
_mm512_mask_loadu_epi64 Load packed 64-bit integers from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
_mm512_mask_loadu_pd Load packed double-precision (64-bit) floating-point elements from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
_mm512_mask_loadu_ps Load packed single-precision (32-bit) floating-point elements from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
_mm512_mask_max_epi32 Compare packed signed 32-bit integers in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_max_epi64 Compare packed signed 64-bit integers in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_max_epu32 Compare packed unsigned 32-bit integers in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_max_epu64 Compare packed unsigned 64-bit integers in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_max_pd Compare packed double-precision (64-bit) floating-point elements in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_max_ps Compare packed single-precision (32-bit) floating-point elements in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_max_round_pd Compare packed double-precision (64-bit) floating-point elements in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_mask_max_round_ps Compare packed single-precision (32-bit) floating-point elements in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_mask_min_epi32 Compare packed signed 32-bit integers in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_min_epi64 Compare packed signed 64-bit integers in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_min_epu32 Compare packed unsigned 32-bit integers in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_min_epu64 Compare packed unsigned 64-bit integers in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_min_pd Compare packed double-precision (64-bit) floating-point elements in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_min_ps Compare packed single-precision (32-bit) floating-point elements in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_min_round_pd Compare packed double-precision (64-bit) floating-point elements in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_mask_min_round_ps Compare packed single-precision (32-bit) floating-point elements in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_mask_mov_epi32 Move packed 32-bit integers from a to dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_mov_epi64 Move packed 64-bit integers from a to dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_mov_pd Move packed double-precision (64-bit) floating-point elements from a to dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_mov_ps Move packed single-precision (32-bit) floating-point elements from a to dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_movedup_pd Duplicate even-indexed double-precision (64-bit) floating-point elements from a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_movehdup_ps Duplicate odd-indexed single-precision (32-bit) floating-point elements from a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_moveldup_ps Duplicate even-indexed single-precision (32-bit) floating-point elements from a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_mul_epi32 Multiply the low signed 32-bit integers from each packed 64-bit element in a and b, and store the signed 64-bit results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_mul_epu32 Multiply the low unsigned 32-bit integers from each packed 64-bit element in a and b, and store the unsigned 64-bit results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_mul_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_mul_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_mul_round_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).\
_mm512_mask_mul_round_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).\
_mm512_mask_mullo_epi32 Multiply the packed 32-bit integers in a and b, producing intermediate 64-bit integers, and store the low 32 bits of the intermediate integers in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_mullox_epi64 Multiplies elements in packed 64-bit integer vectors a and b together, storing the lower 64 bits of the result in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_or_epi32 Compute the bitwise OR of packed 32-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_or_epi64 Compute the bitwise OR of packed 64-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_permute_pd Shuffle double-precision (64-bit) floating-point elements in a within 128-bit lanes using the control in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_permute_ps Shuffle single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_permutevar_epi32 Shuffle 32-bit integers in a across lanes using the corresponding index in idx, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). Note that this intrinsic shuffles across 128-bit lanes, unlike past intrinsics that use the permutevar name. This intrinsic is identical to _mm512_mask_permutexvar_epi32, and it is recommended that you use that intrinsic name.
_mm512_mask_permutevar_pd Shuffle double-precision (64-bit) floating-point elements in a within 128-bit lanes using the control in b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_permutevar_ps Shuffle single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_permutex2var_epi32 Shuffle 32-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm512_mask_permutex2var_epi64 Shuffle 64-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm512_mask_permutex2var_pd Shuffle double-precision (64-bit) floating-point elements in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm512_mask_permutex2var_ps Shuffle single-precision (32-bit) floating-point elements in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm512_mask_permutex_epi64 Shuffle 64-bit integers in a within 256-bit lanes using the control in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_permutex_pd Shuffle double-precision (64-bit) floating-point elements in a within 256-bit lanes using the control in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_permutexvar_epi32 Shuffle 32-bit integers in a across lanes using the corresponding index in idx, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_permutexvar_epi64 Shuffle 64-bit integers in a across lanes using the corresponding index in idx, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_permutexvar_pd Shuffle double-precision (64-bit) floating-point elements in a across lanes using the corresponding index in idx, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_permutexvar_ps Shuffle single-precision (32-bit) floating-point elements in a across lanes using the corresponding index in idx, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_rcp14_pd Compute the approximate reciprocal of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14.
_mm512_mask_rcp14_ps Compute the approximate reciprocal of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14.
_mm512_mask_reduce_add_epi32 Reduce the packed 32-bit integers in a by addition using mask k. Returns the sum of all active elements in a.
_mm512_mask_reduce_add_epi64 Reduce the packed 64-bit integers in a by addition using mask k. Returns the sum of all active elements in a.
_mm512_mask_reduce_add_pd Reduce the packed double-precision (64-bit) floating-point elements in a by addition using mask k. Returns the sum of all active elements in a.
_mm512_mask_reduce_add_ps Reduce the packed single-precision (32-bit) floating-point elements in a by addition using mask k. Returns the sum of all active elements in a.
_mm512_mask_reduce_and_epi32 Reduce the packed 32-bit integers in a by bitwise AND using mask k. Returns the bitwise AND of all active elements in a.
_mm512_mask_reduce_and_epi64 Reduce the packed 64-bit integers in a by addition using mask k. Returns the sum of all active elements in a.
_mm512_mask_reduce_max_epi32 Reduce the packed signed 32-bit integers in a by maximum using mask k. Returns the maximum of all active elements in a.
_mm512_mask_reduce_max_epi64 Reduce the packed signed 64-bit integers in a by maximum using mask k. Returns the maximum of all active elements in a.
_mm512_mask_reduce_max_epu32 Reduce the packed unsigned 32-bit integers in a by maximum using mask k. Returns the maximum of all active elements in a.
_mm512_mask_reduce_max_epu64 Reduce the packed unsigned 64-bit integers in a by maximum using mask k. Returns the maximum of all active elements in a.
_mm512_mask_reduce_max_pd Reduce the packed double-precision (64-bit) floating-point elements in a by maximum using mask k. Returns the maximum of all active elements in a.
_mm512_mask_reduce_max_ps Reduce the packed single-precision (32-bit) floating-point elements in a by maximum using mask k. Returns the maximum of all active elements in a.
_mm512_mask_reduce_min_epi32 Reduce the packed signed 32-bit integers in a by maximum using mask k. Returns the minimum of all active elements in a.
_mm512_mask_reduce_min_epi64 Reduce the packed signed 64-bit integers in a by maximum using mask k. Returns the minimum of all active elements in a.
_mm512_mask_reduce_min_epu32 Reduce the packed unsigned 32-bit integers in a by maximum using mask k. Returns the minimum of all active elements in a.
_mm512_mask_reduce_min_epu64 Reduce the packed signed 64-bit integers in a by maximum using mask k. Returns the minimum of all active elements in a.
_mm512_mask_reduce_min_pd Reduce the packed double-precision (64-bit) floating-point elements in a by maximum using mask k. Returns the minimum of all active elements in a.
_mm512_mask_reduce_min_ps Reduce the packed single-precision (32-bit) floating-point elements in a by maximum using mask k. Returns the minimum of all active elements in a.
_mm512_mask_reduce_mul_epi32 Reduce the packed 32-bit integers in a by multiplication using mask k. Returns the product of all active elements in a.
_mm512_mask_reduce_mul_epi64 Reduce the packed 64-bit integers in a by multiplication using mask k. Returns the product of all active elements in a.
_mm512_mask_reduce_mul_pd Reduce the packed double-precision (64-bit) floating-point elements in a by multiplication using mask k. Returns the product of all active elements in a.
_mm512_mask_reduce_mul_ps Reduce the packed single-precision (32-bit) floating-point elements in a by multiplication using mask k. Returns the product of all active elements in a.
_mm512_mask_reduce_or_epi32 Reduce the packed 32-bit integers in a by bitwise OR using mask k. Returns the bitwise OR of all active elements in a.
_mm512_mask_reduce_or_epi64 Reduce the packed 64-bit integers in a by bitwise OR using mask k. Returns the bitwise OR of all active elements in a.
_mm512_mask_rol_epi32 Rotate the bits in each packed 32-bit integer in a to the left by the number of bits specified in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_rol_epi64 Rotate the bits in each packed 64-bit integer in a to the left by the number of bits specified in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_rolv_epi32 Rotate the bits in each packed 32-bit integer in a to the left by the number of bits specified in the corresponding element of b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_rolv_epi64 Rotate the bits in each packed 64-bit integer in a to the left by the number of bits specified in the corresponding element of b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_ror_epi32 Rotate the bits in each packed 32-bit integer in a to the right by the number of bits specified in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_ror_epi64 Rotate the bits in each packed 64-bit integer in a to the right by the number of bits specified in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_rorv_epi32 Rotate the bits in each packed 32-bit integer in a to the right by the number of bits specified in the corresponding element of b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_rorv_epi64 Rotate the bits in each packed 64-bit integer in a to the right by the number of bits specified in the corresponding element of b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_roundscale_pd Round packed double-precision (64-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm512_mask_roundscale_ps Round packed single-precision (32-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm512_mask_roundscale_round_pd Round packed double-precision (64-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm512_mask_roundscale_round_ps Round packed single-precision (32-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm512_mask_rsqrt14_pd Compute the approximate reciprocal square root of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14.
_mm512_mask_rsqrt14_ps Compute the approximate reciprocal square root of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14.
_mm512_mask_scalef_pd Scale the packed double-precision (64-bit) floating-point elements in a using values from b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_scalef_ps Scale the packed single-precision (32-bit) floating-point elements in a using values from b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_scalef_round_pd Scale the packed double-precision (64-bit) floating-point elements in a using values from b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).\
_mm512_mask_scalef_round_ps Scale the packed single-precision (32-bit) floating-point elements in a using values from b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).\
_mm512_mask_set1_epi32 Broadcast 32-bit integer a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_set1_epi64 Broadcast 64-bit integer a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_shuffle_epi32 Shuffle 32-bit integers in a within 128-bit lanes using the control in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_shuffle_f32x4 Shuffle 128-bits (composed of 4 single-precision (32-bit) floating-point elements) selected by imm8 from a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_shuffle_f64x2 Shuffle 128-bits (composed of 2 double-precision (64-bit) floating-point elements) selected by imm8 from a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_shuffle_i32x4 Shuffle 128-bits (composed of 4 32-bit integers) selected by imm8 from a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_shuffle_i64x2 Shuffle 128-bits (composed of 2 64-bit integers) selected by imm8 from a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_shuffle_pd Shuffle double-precision (64-bit) floating-point elements within 128-bit lanes using the control in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_shuffle_ps Shuffle single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_sll_epi32 Shift packed 32-bit integers in a left by count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_sll_epi64 Shift packed 64-bit integers in a left by count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_slli_epi32 Shift packed 32-bit integers in a left by imm8 while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_slli_epi64 Shift packed 64-bit integers in a left by imm8 while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_sllv_epi32 Shift packed 32-bit integers in a left by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_sllv_epi64 Shift packed 64-bit integers in a left by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_sqrt_pd Compute the square root of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_sqrt_ps Compute the square root of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_sqrt_round_pd Compute the square root of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).\
_mm512_mask_sqrt_round_ps Compute the square root of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).\
_mm512_mask_sra_epi32 Shift packed 32-bit integers in a right by count while shifting in sign bits, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_sra_epi64 Shift packed 64-bit integers in a right by count while shifting in sign bits, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_srai_epi32 Shift packed 32-bit integers in a right by imm8 while shifting in sign bits, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_srai_epi64 Shift packed 64-bit integers in a right by imm8 while shifting in sign bits, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_srav_epi32 Shift packed 32-bit integers in a right by the amount specified by the corresponding element in count while shifting in sign bits, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_srav_epi64 Shift packed 64-bit integers in a right by the amount specified by the corresponding element in count while shifting in sign bits, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_srl_epi32 Shift packed 32-bit integers in a right by count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_srl_epi64 Shift packed 64-bit integers in a right by count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_srli_epi32 Shift packed 32-bit integers in a right by imm8 while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_srli_epi64 Shift packed 64-bit integers in a right by imm8 while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_srlv_epi32 Shift packed 32-bit integers in a right by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_srlv_epi64 Shift packed 64-bit integers in a right by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_store_epi32 Store packed 32-bit integers from a into memory using writemask k. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_mask_store_epi64 Store packed 64-bit integers from a into memory using writemask k. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_mask_store_pd Store packed double-precision (64-bit) floating-point elements from a into memory using writemask k. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_mask_store_ps Store packed single-precision (32-bit) floating-point elements from a into memory using writemask k. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_mask_storeu_epi32 Store packed 32-bit integers from a into memory using writemask k. mem_addr does not need to be aligned on any particular boundary.
_mm512_mask_storeu_epi64 Store packed 64-bit integers from a into memory using writemask k. mem_addr does not need to be aligned on any particular boundary.
_mm512_mask_storeu_pd Store packed double-precision (64-bit) floating-point elements from a into memory using writemask k. mem_addr does not need to be aligned on any particular boundary.
_mm512_mask_storeu_ps Store packed single-precision (32-bit) floating-point elements from a into memory using writemask k. mem_addr does not need to be aligned on any particular boundary.
_mm512_mask_sub_epi32 Subtract packed 32-bit integers in b from packed 32-bit integers in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_sub_epi64 Subtract packed 64-bit integers in b from packed 64-bit integers in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_sub_pd Subtract packed double-precision (64-bit) floating-point elements in b from packed double-precision (64-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_sub_ps Subtract packed single-precision (32-bit) floating-point elements in b from packed single-precision (32-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_sub_round_pd Subtract packed double-precision (64-bit) floating-point elements in b from packed double-precision (64-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).\
_mm512_mask_sub_round_ps Subtract packed single-precision (32-bit) floating-point elements in b from packed single-precision (32-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).\
_mm512_mask_ternarylogic_epi32 Bitwise ternary logic that provides the capability to implement any three-operand binary function; the specific binary function is specified by value in imm8. For each bit in each packed 32-bit integer, the corresponding bit from src, a, and b are used to form a 3 bit index into imm8, and the value at that bit in imm8 is written to the corresponding bit in dst using writemask k at 32-bit granularity (32-bit elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_ternarylogic_epi64 Bitwise ternary logic that provides the capability to implement any three-operand binary function; the specific binary function is specified by value in imm8. For each bit in each packed 64-bit integer, the corresponding bit from src, a, and b are used to form a 3 bit index into imm8, and the value at that bit in imm8 is written to the corresponding bit in dst using writemask k at 64-bit granularity (64-bit elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_test_epi32_mask Compute the bitwise AND of packed 32-bit integers in a and b, producing intermediate 32-bit values, and set the corresponding bit in result mask k (subject to writemask k) if the intermediate value is non-zero.
_mm512_mask_test_epi64_mask Compute the bitwise AND of packed 64-bit integers in a and b, producing intermediate 64-bit values, and set the corresponding bit in result mask k (subject to writemask k) if the intermediate value is non-zero.
_mm512_mask_testn_epi32_mask Compute the bitwise NAND of packed 32-bit integers in a and b, producing intermediate 32-bit values, and set the corresponding bit in result mask k (subject to writemask k) if the intermediate value is zero.
_mm512_mask_testn_epi64_mask Compute the bitwise NAND of packed 64-bit integers in a and b, producing intermediate 64-bit values, and set the corresponding bit in result mask k (subject to writemask k) if the intermediate value is zero.
_mm512_mask_unpackhi_epi32 Unpack and interleave 32-bit integers from the high half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_unpackhi_epi64 Unpack and interleave 64-bit integers from the high half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_unpackhi_pd Unpack and interleave double-precision (64-bit) floating-point elements from the high half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_unpackhi_ps Unpack and interleave single-precision (32-bit) floating-point elements from the high half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_unpacklo_epi32 Unpack and interleave 32-bit integers from the low half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_unpacklo_epi64 Unpack and interleave 64-bit integers from the low half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_unpacklo_pd Unpack and interleave double-precision (64-bit) floating-point elements from the low half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_unpacklo_ps Unpack and interleave single-precision (32-bit) floating-point elements from the low half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_xor_epi32 Compute the bitwise XOR of packed 32-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_mask_xor_epi64 Compute the bitwise XOR of packed 64-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm512_maskz_abs_epi32 Computes the absolute value of packed 32-bit integers in a, and store the unsigned results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_abs_epi64 Compute the absolute value of packed signed 64-bit integers in a, and store the unsigned results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_add_epi32 Add packed 32-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_add_epi64 Add packed 64-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_add_pd Add packed double-precision (64-bit) floating-point elements in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_add_ps Add packed single-precision (32-bit) floating-point elements in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_add_round_pd Add packed double-precision (64-bit) floating-point elements in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_add_round_ps Add packed single-precision (32-bit) floating-point elements in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_alignr_epi32 Concatenate a and b into a 128-byte immediate result, shift the result right by imm8 32-bit elements, and stores the low 64 bytes (16 elements) in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_alignr_epi64 Concatenate a and b into a 128-byte immediate result, shift the result right by imm8 64-bit elements, and stores the low 64 bytes (8 elements) in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_and_epi32 Compute the bitwise AND of packed 32-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_and_epi64 Compute the bitwise AND of packed 64-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_andnot_epi32 Compute the bitwise NOT of packed 32-bit integers in a and then AND with b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_andnot_epi64 Compute the bitwise NOT of packed 64-bit integers in a and then AND with b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_broadcast_f32x4 Broadcast the 4 packed single-precision (32-bit) floating-point elements from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_broadcast_f64x4 Broadcast the 4 packed double-precision (64-bit) floating-point elements from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_broadcast_i32x4 Broadcast the 4 packed 32-bit integers from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_broadcast_i64x4 Broadcast the 4 packed 64-bit integers from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_broadcastd_epi32 Broadcast the low packed 32-bit integer from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_broadcastq_epi64 Broadcast the low packed 64-bit integer from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_broadcastsd_pd Broadcast the low double-precision (64-bit) floating-point element from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_broadcastss_ps Broadcast the low single-precision (32-bit) floating-point element from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_compress_epi32 Contiguously store the active 32-bit integers in a (those with their respective bit set in zeromask k) to dst, and set the remaining elements to zero.
_mm512_maskz_compress_epi64 Contiguously store the active 64-bit integers in a (those with their respective bit set in zeromask k) to dst, and set the remaining elements to zero.
_mm512_maskz_compress_pd Contiguously store the active double-precision (64-bit) floating-point elements in a (those with their respective bit set in zeromask k) to dst, and set the remaining elements to zero.
_mm512_maskz_compress_ps Contiguously store the active single-precision (32-bit) floating-point elements in a (those with their respective bit set in zeromask k) to dst, and set the remaining elements to zero.
_mm512_maskz_cvt_roundepi32_ps Convert packed signed 32-bit integers in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_cvt_roundepu32_ps Convert packed unsigned 32-bit integers in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_cvt_roundpd_epi32 Convert packed double-precision (64-bit) floating-point elements in a to packed 32-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_cvt_roundpd_epu32 Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_cvt_roundpd_ps Convert packed double-precision (64-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_cvt_roundph_ps Convert packed half-precision (16-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_maskz_cvt_roundps_epi32 Convert packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_cvt_roundps_epu32 Convert packed single-precision (32-bit) floating-point elements in a to packed unsigned 32-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_cvt_roundps_pd Convert packed single-precision (32-bit) floating-point elements in a to packed double-precision (64-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_maskz_cvt_roundps_ph Convert packed single-precision (32-bit) floating-point elements in a to packed half-precision (16-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
Rounding is done according to the rounding[3:0] parameter, which can be one of:
_mm512_maskz_cvtepi16_epi32 Sign extend packed 16-bit integers in a to packed 32-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtepi16_epi64 Sign extend packed 16-bit integers in a to packed 64-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtepi32_epi16 Convert packed 32-bit integers in a to packed 16-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtepi32_epi64 Sign extend packed 32-bit integers in a to packed 64-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtepi32_epi8 Convert packed 32-bit integers in a to packed 8-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtepi32_pd Convert packed signed 32-bit integers in a to packed double-precision (64-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtepi32_ps Convert packed signed 32-bit integers in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtepi64_epi16 Convert packed 64-bit integers in a to packed 16-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtepi64_epi32 Convert packed 64-bit integers in a to packed 32-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtepi64_epi8 Convert packed 64-bit integers in a to packed 8-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtepi8_epi32 Sign extend packed 8-bit integers in a to packed 32-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtepi8_epi64 Sign extend packed 8-bit integers in the low 8 bytes of a to packed 64-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtepu16_epi32 Zero extend packed unsigned 16-bit integers in a to packed 32-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtepu16_epi64 Zero extend packed unsigned 16-bit integers in a to packed 64-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtepu32_epi64 Zero extend packed unsigned 32-bit integers in a to packed 64-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtepu32_pd Convert packed unsigned 32-bit integers in a to packed double-precision (64-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtepu32_ps Convert packed unsigned 32-bit integers in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtepu8_epi32 Zero extend packed unsigned 8-bit integers in a to packed 32-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtepu8_epi64 Zero extend packed unsigned 8-bit integers in the low 8 bytes of a to packed 64-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtpd_epi32 Convert packed double-precision (64-bit) floating-point elements in a to packed 32-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtpd_epu32 Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtpd_ps Convert packed double-precision (64-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtph_ps Convert packed half-precision (16-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtps_epi32 Convert packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtps_epu32 Convert packed single-precision (32-bit) floating-point elements in a to packed unsigned 32-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtps_pd Convert packed single-precision (32-bit) floating-point elements in a to packed double-precision (64-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtps_ph Convert packed single-precision (32-bit) floating-point elements in a to packed half-precision (16-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
Rounding is done according to the rounding[3:0] parameter, which can be one of:
_mm512_maskz_cvtsepi32_epi16 Convert packed signed 32-bit integers in a to packed 16-bit integers with signed saturation, and store the results in dst.
_mm512_maskz_cvtsepi32_epi8 Convert packed signed 32-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtsepi64_epi16 Convert packed signed 64-bit integers in a to packed 16-bit integers with signed saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtsepi64_epi32 Convert packed signed 64-bit integers in a to packed 32-bit integers with signed saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtsepi64_epi8 Convert packed signed 64-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtt_roundpd_epi32 Convert packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_maskz_cvtt_roundpd_epu32 Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_maskz_cvtt_roundps_epi32 Convert packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_maskz_cvtt_roundps_epu32 Convert packed single-precision (32-bit) floating-point elements in a to packed unsigned 32-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_maskz_cvttpd_epi32 Convert packed double-precision (64-bit) floating-point elements in a to packed 32-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvttpd_epu32 Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvttps_epi32 Convert packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvttps_epu32 Convert packed double-precision (32-bit) floating-point elements in a to packed unsigned 32-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtusepi32_epi16 Convert packed unsigned 32-bit integers in a to packed unsigned 16-bit integers with unsigned saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtusepi32_epi8 Convert packed unsigned 32-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtusepi64_epi16 Convert packed unsigned 64-bit integers in a to packed unsigned 16-bit integers with unsigned saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtusepi64_epi32 Convert packed unsigned 64-bit integers in a to packed unsigned 32-bit integers with unsigned saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_cvtusepi64_epi8 Convert packed unsigned 64-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_div_pd Divide packed double-precision (64-bit) floating-point elements in a by packed elements in b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_div_ps Divide packed single-precision (32-bit) floating-point elements in a by packed elements in b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_div_round_pd Divide packed double-precision (64-bit) floating-point elements in a by packed elements in b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_div_round_ps Divide packed single-precision (32-bit) floating-point elements in a by packed elements in b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_expand_epi32 Load contiguous active 32-bit integers from a (those with their respective bit set in mask k), and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_expand_epi64 Load contiguous active 64-bit integers from a (those with their respective bit set in mask k), and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_expand_pd Load contiguous active double-precision (64-bit) floating-point elements from a (those with their respective bit set in mask k), and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_expand_ps Load contiguous active single-precision (32-bit) floating-point elements from a (those with their respective bit set in mask k), and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_expandloadu_epi32 Load contiguous active 32-bit integers from unaligned memory at mem_addr (those with their respective bit set in mask k), and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_expandloadu_epi64 Load contiguous active 64-bit integers from unaligned memory at mem_addr (those with their respective bit set in mask k), and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_expandloadu_pd Load contiguous active double-precision (64-bit) floating-point elements from unaligned memory at mem_addr (those with their respective bit set in mask k), and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_expandloadu_ps Load contiguous active single-precision (32-bit) floating-point elements from unaligned memory at mem_addr (those with their respective bit set in mask k), and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_extractf32x4_ps Extract 128 bits (composed of 4 packed single-precision (32-bit) floating-point elements) from a, selected with imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_extractf64x4_pd Extract 256 bits (composed of 4 packed double-precision (64-bit) floating-point elements) from a, selected with imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_extracti32x4_epi32 Extract 128 bits (composed of 4 packed 32-bit integers) from a, selected with IMM2, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_extracti64x4_epi64 Extract 256 bits (composed of 4 packed 64-bit integers) from a, selected with IMM1, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_fixupimm_pd Fix up packed double-precision (64-bit) floating-point elements in a and b using packed 64-bit integers in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). imm8 is used to set the required flags reporting.
_mm512_maskz_fixupimm_ps Fix up packed single-precision (32-bit) floating-point elements in a and b using packed 32-bit integers in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). imm8 is used to set the required flags reporting.
_mm512_maskz_fixupimm_round_pd Fix up packed double-precision (64-bit) floating-point elements in a and b using packed 64-bit integers in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). imm8 is used to set the required flags reporting.\
_mm512_maskz_fixupimm_round_ps Fix up packed single-precision (32-bit) floating-point elements in a and b using packed 32-bit integers in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). imm8 is used to set the required flags reporting.\
_mm512_maskz_fmadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_fmadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_fmadd_round_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_fmadd_round_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in a using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_fmaddsub_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_fmaddsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_fmaddsub_round_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_fmaddsub_round_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_fmsub_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_fmsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_fmsub_round_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_fmsub_round_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_fmsubadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_fmsubadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_fmsubadd_round_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_fmsubadd_round_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_fnmadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_fnmadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_fnmadd_round_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_fnmadd_round_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_fnmsub_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_fnmsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_fnmsub_round_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_fnmsub_round_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_getexp_pd Convert the exponent of each packed double-precision (64-bit) floating-point element in a to a double-precision (64-bit) floating-point number representing the integer exponent, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). This intrinsic essentially calculates floor(log2(x)) for each element.
_mm512_maskz_getexp_ps Convert the exponent of each packed single-precision (32-bit) floating-point element in a to a single-precision (32-bit) floating-point number representing the integer exponent, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). This intrinsic essentially calculates floor(log2(x)) for each element.
_mm512_maskz_getexp_round_pd Convert the exponent of each packed double-precision (64-bit) floating-point element in a to a double-precision (64-bit) floating-point number representing the integer exponent, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). This intrinsic essentially calculates floor(log2(x)) for each element.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_maskz_getexp_round_ps Convert the exponent of each packed single-precision (32-bit) floating-point element in a to a single-precision (32-bit) floating-point number representing the integer exponent, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). This intrinsic essentially calculates floor(log2(x)) for each element.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_maskz_getmant_pd Normalize the mantissas of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
_mm512_maskz_getmant_ps Normalize the mantissas of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
_mm512_maskz_getmant_round_pd Normalize the mantissas of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_maskz_getmant_round_ps Normalize the mantissas of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_maskz_insertf32x4 Copy a to tmp, then insert 128 bits (composed of 4 packed single-precision (32-bit) floating-point elements) from b into tmp at the location specified by imm8. Store tmp to dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_insertf64x4 Copy a to tmp, then insert 256 bits (composed of 4 packed double-precision (64-bit) floating-point elements) from b into tmp at the location specified by imm8. Store tmp to dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_inserti32x4 Copy a to tmp, then insert 128 bits (composed of 4 packed 32-bit integers) from b into tmp at the location specified by imm8. Store tmp to dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_inserti64x4 Copy a to tmp, then insert 256 bits (composed of 4 packed 64-bit integers) from b into tmp at the location specified by imm8. Store tmp to dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_load_epi32 Load packed 32-bit integers from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_maskz_load_epi64 Load packed 64-bit integers from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_maskz_load_pd Load packed double-precision (64-bit) floating-point elements from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_maskz_load_ps Load packed single-precision (32-bit) floating-point elements from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_maskz_loadu_epi32 Load packed 32-bit integers from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
_mm512_maskz_loadu_epi64 Load packed 64-bit integers from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
_mm512_maskz_loadu_pd Load packed double-precision (64-bit) floating-point elements from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
_mm512_maskz_loadu_ps Load packed single-precision (32-bit) floating-point elements from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
_mm512_maskz_max_epi32 Compare packed signed 32-bit integers in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_max_epi64 Compare packed signed 64-bit integers in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_max_epu32 Compare packed unsigned 32-bit integers in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_max_epu64 Compare packed unsigned 64-bit integers in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_max_pd Compare packed double-precision (64-bit) floating-point elements in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_max_ps Compare packed single-precision (32-bit) floating-point elements in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_max_round_pd Compare packed double-precision (64-bit) floating-point elements in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_maskz_max_round_ps Compare packed single-precision (32-bit) floating-point elements in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_maskz_min_epi32 Compare packed signed 32-bit integers in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_min_epi64 Compare packed signed 64-bit integers in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_min_epu32 Compare packed unsigned 32-bit integers in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_min_epu64 Compare packed unsigned 64-bit integers in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_min_pd Compare packed double-precision (64-bit) floating-point elements in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_min_ps Compare packed single-precision (32-bit) floating-point elements in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_min_round_pd Compare packed double-precision (64-bit) floating-point elements in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_maskz_min_round_ps Compare packed single-precision (32-bit) floating-point elements in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_maskz_mov_epi32 Move packed 32-bit integers from a into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_mov_epi64 Move packed 64-bit integers from a into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_mov_pd Move packed double-precision (64-bit) floating-point elements from a into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_mov_ps Move packed single-precision (32-bit) floating-point elements from a into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_movedup_pd Duplicate even-indexed double-precision (64-bit) floating-point elements from a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_movehdup_ps Duplicate odd-indexed single-precision (32-bit) floating-point elements from a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_moveldup_ps Duplicate even-indexed single-precision (32-bit) floating-point elements from a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_mul_epi32 Multiply the low signed 32-bit integers from each packed 64-bit element in a and b, and store the signed 64-bit results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_mul_epu32 Multiply the low unsigned 32-bit integers from each packed 64-bit element in a and b, and store the unsigned 64-bit results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_mul_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_mul_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_mul_round_pd Multiply packed single-precision (32-bit) floating-point elements in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_mul_round_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_mullo_epi32 Multiply the packed 32-bit integers in a and b, producing intermediate 64-bit integers, and store the low 32 bits of the intermediate integers in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_or_epi32 Compute the bitwise OR of packed 32-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_or_epi64 Compute the bitwise OR of packed 64-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_permute_pd Shuffle double-precision (64-bit) floating-point elements in a within 128-bit lanes using the control in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_permute_ps Shuffle single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_permutevar_pd Shuffle double-precision (64-bit) floating-point elements in a within 128-bit lanes using the control in b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_permutevar_ps Shuffle single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_permutex2var_epi32 Shuffle 32-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_permutex2var_epi64 Shuffle 64-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_permutex2var_pd Shuffle double-precision (64-bit) floating-point elements in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_permutex2var_ps Shuffle single-precision (32-bit) floating-point elements in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_permutex_epi64 Shuffle 64-bit integers in a within 256-bit lanes using the control in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_permutex_pd Shuffle double-precision (64-bit) floating-point elements in a within 256-bit lanes using the control in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_permutexvar_epi32 Shuffle 32-bit integers in a across lanes using the corresponding index in idx, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_permutexvar_epi64 Shuffle 64-bit integers in a across lanes using the corresponding index in idx, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_permutexvar_pd Shuffle double-precision (64-bit) floating-point elements in a across lanes using the corresponding index in idx, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_permutexvar_ps Shuffle single-precision (32-bit) floating-point elements in a across lanes using the corresponding index in idx, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_rcp14_pd Compute the approximate reciprocal of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14.
_mm512_maskz_rcp14_ps Compute the approximate reciprocal of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14.
_mm512_maskz_rol_epi32 Rotate the bits in each packed 32-bit integer in a to the left by the number of bits specified in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_rol_epi64 Rotate the bits in each packed 64-bit integer in a to the left by the number of bits specified in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_rolv_epi32 Rotate the bits in each packed 32-bit integer in a to the left by the number of bits specified in the corresponding element of b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_rolv_epi64 Rotate the bits in each packed 64-bit integer in a to the left by the number of bits specified in the corresponding element of b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_ror_epi32 Rotate the bits in each packed 32-bit integer in a to the right by the number of bits specified in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_ror_epi64 Rotate the bits in each packed 64-bit integer in a to the right by the number of bits specified in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_rorv_epi32 Rotate the bits in each packed 32-bit integer in a to the right by the number of bits specified in the corresponding element of b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_rorv_epi64 Rotate the bits in each packed 64-bit integer in a to the right by the number of bits specified in the corresponding element of b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_roundscale_pd Round packed double-precision (64-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm512_maskz_roundscale_ps Round packed single-precision (32-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm512_maskz_roundscale_round_pd Round packed double-precision (64-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm512_maskz_roundscale_round_ps Round packed single-precision (32-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm512_maskz_rsqrt14_pd Compute the approximate reciprocal square root of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14.
_mm512_maskz_rsqrt14_ps Compute the approximate reciprocal square root of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14.
_mm512_maskz_scalef_pd Scale the packed double-precision (64-bit) floating-point elements in a using values from b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_scalef_ps Scale the packed single-precision (32-bit) floating-point elements in a using values from b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_scalef_round_pd Scale the packed double-precision (64-bit) floating-point elements in a using values from b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_scalef_round_ps Scale the packed single-precision (32-bit) floating-point elements in a using values from b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_set1_epi32 Broadcast 32-bit integer a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_set1_epi64 Broadcast 64-bit integer a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_shuffle_epi32 Shuffle 32-bit integers in a within 128-bit lanes using the control in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_shuffle_f32x4 Shuffle 128-bits (composed of 4 single-precision (32-bit) floating-point elements) selected by imm8 from a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_shuffle_f64x2 Shuffle 128-bits (composed of 2 double-precision (64-bit) floating-point elements) selected by imm8 from a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_shuffle_i32x4 Shuffle 128-bits (composed of 4 32-bit integers) selected by imm8 from a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_shuffle_i64x2 Shuffle 128-bits (composed of 2 64-bit integers) selected by imm8 from a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_shuffle_pd Shuffle double-precision (64-bit) floating-point elements within 128-bit lanes using the control in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_shuffle_ps Shuffle single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_sll_epi32 Shift packed 32-bit integers in a left by count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_sll_epi64 Shift packed 64-bit integers in a left by count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_slli_epi32 Shift packed 32-bit integers in a left by imm8 while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_slli_epi64 Shift packed 64-bit integers in a left by imm8 while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_sllv_epi32 Shift packed 32-bit integers in a left by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_sllv_epi64 Shift packed 64-bit integers in a left by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_sqrt_pd Compute the square root of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_sqrt_ps Compute the square root of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_sqrt_round_pd Compute the square root of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_sqrt_round_ps Compute the square root of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_sra_epi32 Shift packed 32-bit integers in a right by count while shifting in sign bits, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_sra_epi64 Shift packed 64-bit integers in a right by count while shifting in sign bits, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_srai_epi32 Shift packed 32-bit integers in a right by imm8 while shifting in sign bits, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_srai_epi64 Shift packed 64-bit integers in a right by imm8 while shifting in sign bits, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_srav_epi32 Shift packed 32-bit integers in a right by the amount specified by the corresponding element in count while shifting in sign bits, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_srav_epi64 Shift packed 64-bit integers in a right by the amount specified by the corresponding element in count while shifting in sign bits, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_srl_epi32 Shift packed 32-bit integers in a right by count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_srl_epi64 Shift packed 64-bit integers in a right by count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_srli_epi32 Shift packed 32-bit integers in a right by imm8 while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_srli_epi64 Shift packed 64-bit integers in a right by imm8 while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_srlv_epi32 Shift packed 32-bit integers in a right by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_srlv_epi64 Shift packed 64-bit integers in a right by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_sub_epi32 Subtract packed 32-bit integers in b from packed 32-bit integers in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_sub_epi64 Subtract packed 64-bit integers in b from packed 64-bit integers in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_sub_pd Subtract packed double-precision (64-bit) floating-point elements in b from packed double-precision (64-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_sub_ps Subtract packed single-precision (32-bit) floating-point elements in b from packed single-precision (32-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_sub_round_pd Subtract packed double-precision (64-bit) floating-point elements in b from packed double-precision (64-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_sub_round_ps Subtract packed single-precision (32-bit) floating-point elements in b from packed single-precision (32-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).\
_mm512_maskz_ternarylogic_epi32 Bitwise ternary logic that provides the capability to implement any three-operand binary function; the specific binary function is specified by value in imm8. For each bit in each packed 32-bit integer, the corresponding bit from a, b, and c are used to form a 3 bit index into imm8, and the value at that bit in imm8 is written to the corresponding bit in dst using zeromask k at 32-bit granularity (32-bit elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_ternarylogic_epi64 Bitwise ternary logic that provides the capability to implement any three-operand binary function; the specific binary function is specified by value in imm8. For each bit in each packed 64-bit integer, the corresponding bit from a, b, and c are used to form a 3 bit index into imm8, and the value at that bit in imm8 is written to the corresponding bit in dst using zeromask k at 64-bit granularity (64-bit elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_unpackhi_epi32 Unpack and interleave 32-bit integers from the high half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_unpackhi_epi64 Unpack and interleave 64-bit integers from the high half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_unpackhi_pd Unpack and interleave double-precision (64-bit) floating-point elements from the high half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_unpackhi_ps Unpack and interleave single-precision (32-bit) floating-point elements from the high half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_unpacklo_epi32 Unpack and interleave 32-bit integers from the low half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_unpacklo_epi64 Unpack and interleave 64-bit integers from the low half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_unpacklo_pd Unpack and interleave double-precision (64-bit) floating-point elements from the low half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_unpacklo_ps Unpack and interleave single-precision (32-bit) floating-point elements from the low half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_xor_epi32 Compute the bitwise XOR of packed 32-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_maskz_xor_epi64 Compute the bitwise XOR of packed 64-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm512_max_epi32 Compare packed signed 32-bit integers in a and b, and store packed maximum values in dst.
_mm512_max_epi64 Compare packed signed 64-bit integers in a and b, and store packed maximum values in dst.
_mm512_max_epu32 Compare packed unsigned 32-bit integers in a and b, and store packed maximum values in dst.
_mm512_max_epu64 Compare packed unsigned 64-bit integers in a and b, and store packed maximum values in dst.
_mm512_max_pd Compare packed double-precision (64-bit) floating-point elements in a and b, and store packed maximum values in dst.
_mm512_max_ps Compare packed single-precision (32-bit) floating-point elements in a and b, and store packed maximum values in dst.
_mm512_max_round_pd Compare packed double-precision (64-bit) floating-point elements in a and b, and store packed maximum values in dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_max_round_ps Compare packed single-precision (32-bit) floating-point elements in a and b, and store packed maximum values in dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_min_epi32 Compare packed signed 32-bit integers in a and b, and store packed minimum values in dst.
_mm512_min_epi64 Compare packed signed 64-bit integers in a and b, and store packed minimum values in dst.
_mm512_min_epu32 Compare packed unsigned 32-bit integers in a and b, and store packed minimum values in dst.
_mm512_min_epu64 Compare packed unsigned 64-bit integers in a and b, and store packed minimum values in dst.
_mm512_min_pd Compare packed double-precision (64-bit) floating-point elements in a and b, and store packed minimum values in dst.
_mm512_min_ps Compare packed single-precision (32-bit) floating-point elements in a and b, and store packed minimum values in dst.
_mm512_min_round_pd Compare packed double-precision (64-bit) floating-point elements in a and b, and store packed minimum values in dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_min_round_ps Compare packed single-precision (32-bit) floating-point elements in a and b, and store packed minimum values in dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm512_movedup_pd Duplicate even-indexed double-precision (64-bit) floating-point elements from a, and store the results in dst.
_mm512_movehdup_ps Duplicate odd-indexed single-precision (32-bit) floating-point elements from a, and store the results in dst.
_mm512_moveldup_ps Duplicate even-indexed single-precision (32-bit) floating-point elements from a, and store the results in dst.
_mm512_mul_epi32 Multiply the low signed 32-bit integers from each packed 64-bit element in a and b, and store the signed 64-bit results in dst.
_mm512_mul_epu32 Multiply the low unsigned 32-bit integers from each packed 64-bit element in a and b, and store the unsigned 64-bit results in dst.
_mm512_mul_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, and store the results in dst.
_mm512_mul_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, and store the results in dst.
_mm512_mul_round_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, and store the results in dst.\
_mm512_mul_round_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, and store the results in dst.\
_mm512_mullo_epi32 Multiply the packed 32-bit integers in a and b, producing intermediate 64-bit integers, and store the low 32 bits of the intermediate integers in dst.
_mm512_mullox_epi64 Multiplies elements in packed 64-bit integer vectors a and b together, storing the lower 64 bits of the result in dst.
_mm512_or_epi32 Compute the bitwise OR of packed 32-bit integers in a and b, and store the results in dst.
_mm512_or_epi64 Compute the bitwise OR of packed 64-bit integers in a and b, and store the resut in dst.
_mm512_or_si512 Compute the bitwise OR of 512 bits (representing integer data) in a and b, and store the result in dst.
_mm512_permute_pd Shuffle double-precision (64-bit) floating-point elements in a within 128-bit lanes using the control in imm8, and store the results in dst.
_mm512_permute_ps Shuffle single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in imm8, and store the results in dst.
_mm512_permutevar_epi32 Shuffle 32-bit integers in a across lanes using the corresponding index in idx, and store the results in dst. Note that this intrinsic shuffles across 128-bit lanes, unlike past intrinsics that use the permutevar name. This intrinsic is identical to _mm512_permutexvar_epi32, and it is recommended that you use that intrinsic name.
_mm512_permutevar_pd Shuffle double-precision (64-bit) floating-point elements in a within 128-bit lanes using the control in b, and store the results in dst.
_mm512_permutevar_ps Shuffle single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in b, and store the results in dst.
_mm512_permutex2var_epi32 Shuffle 32-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst.
_mm512_permutex2var_epi64 Shuffle 64-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst.
_mm512_permutex2var_pd Shuffle double-precision (64-bit) floating-point elements in a and b across lanes using the corresponding selector and index in idx, and store the results in dst.
_mm512_permutex2var_ps Shuffle single-precision (32-bit) floating-point elements in a and b across lanes using the corresponding selector and index in idx, and store the results in dst.
_mm512_permutex_epi64 Shuffle 64-bit integers in a within 256-bit lanes using the control in imm8, and store the results in dst.
_mm512_permutex_pd Shuffle double-precision (64-bit) floating-point elements in a within 256-bit lanes using the control in imm8, and store the results in dst.
_mm512_permutexvar_epi32 Shuffle 32-bit integers in a across lanes using the corresponding index in idx, and store the results in dst.
_mm512_permutexvar_epi64 Shuffle 64-bit integers in a across lanes using the corresponding index in idx, and store the results in dst.
_mm512_permutexvar_pd Shuffle double-precision (64-bit) floating-point elements in a across lanes using the corresponding index in idx, and store the results in dst.
_mm512_permutexvar_ps Shuffle single-precision (32-bit) floating-point elements in a across lanes using the corresponding index in idx.
_mm512_rcp14_pd Compute the approximate reciprocal of packed double-precision (64-bit) floating-point elements in a, and store the results in dst. The maximum relative error for this approximation is less than 2^-14.
_mm512_rcp14_ps Compute the approximate reciprocal of packed single-precision (32-bit) floating-point elements in a, and store the results in dst. The maximum relative error for this approximation is less than 2^-14.
_mm512_reduce_add_epi32 Reduce the packed 32-bit integers in a by addition. Returns the sum of all elements in a.
_mm512_reduce_add_epi64 Reduce the packed 64-bit integers in a by addition. Returns the sum of all elements in a.
_mm512_reduce_add_pd Reduce the packed double-precision (64-bit) floating-point elements in a by addition. Returns the sum of all elements in a.
_mm512_reduce_add_ps Reduce the packed single-precision (32-bit) floating-point elements in a by addition. Returns the sum of all elements in a.
_mm512_reduce_and_epi32 Reduce the packed 32-bit integers in a by bitwise AND. Returns the bitwise AND of all elements in a.
_mm512_reduce_and_epi64 Reduce the packed 64-bit integers in a by bitwise AND. Returns the bitwise AND of all elements in a.
_mm512_reduce_max_epi32 Reduce the packed signed 32-bit integers in a by maximum. Returns the maximum of all elements in a.
_mm512_reduce_max_epi64 Reduce the packed signed 64-bit integers in a by maximum. Returns the maximum of all elements in a.
_mm512_reduce_max_epu32 Reduce the packed unsigned 32-bit integers in a by maximum. Returns the maximum of all elements in a.
_mm512_reduce_max_epu64 Reduce the packed unsigned 64-bit integers in a by maximum. Returns the maximum of all elements in a.
_mm512_reduce_max_pd Reduce the packed double-precision (64-bit) floating-point elements in a by maximum. Returns the maximum of all elements in a.
_mm512_reduce_max_ps Reduce the packed single-precision (32-bit) floating-point elements in a by maximum. Returns the maximum of all elements in a.
_mm512_reduce_min_epi32 Reduce the packed signed 32-bit integers in a by minimum. Returns the minimum of all elements in a.
_mm512_reduce_min_epi64 Reduce the packed signed 64-bit integers in a by minimum. Returns the minimum of all elements in a.
_mm512_reduce_min_epu32 Reduce the packed unsigned 32-bit integers in a by minimum. Returns the minimum of all elements in a.
_mm512_reduce_min_epu64 Reduce the packed unsigned 64-bit integers in a by minimum. Returns the minimum of all elements in a.
_mm512_reduce_min_pd Reduce the packed double-precision (64-bit) floating-point elements in a by minimum. Returns the minimum of all elements in a.
_mm512_reduce_min_ps Reduce the packed single-precision (32-bit) floating-point elements in a by minimum. Returns the minimum of all elements in a.
_mm512_reduce_mul_epi32 Reduce the packed 32-bit integers in a by multiplication. Returns the product of all elements in a.
_mm512_reduce_mul_epi64 Reduce the packed 64-bit integers in a by multiplication. Returns the product of all elements in a.
_mm512_reduce_mul_pd Reduce the packed double-precision (64-bit) floating-point elements in a by multiplication. Returns the product of all elements in a.
_mm512_reduce_mul_ps Reduce the packed single-precision (32-bit) floating-point elements in a by multiplication. Returns the product of all elements in a.
_mm512_reduce_or_epi32 Reduce the packed 32-bit integers in a by bitwise OR. Returns the bitwise OR of all elements in a.
_mm512_reduce_or_epi64 Reduce the packed 64-bit integers in a by bitwise OR. Returns the bitwise OR of all elements in a.
_mm512_rol_epi32 Rotate the bits in each packed 32-bit integer in a to the left by the number of bits specified in imm8, and store the results in dst.
_mm512_rol_epi64 Rotate the bits in each packed 64-bit integer in a to the left by the number of bits specified in imm8, and store the results in dst.
_mm512_rolv_epi32 Rotate the bits in each packed 32-bit integer in a to the left by the number of bits specified in the corresponding element of b, and store the results in dst.
_mm512_rolv_epi64 Rotate the bits in each packed 64-bit integer in a to the left by the number of bits specified in the corresponding element of b, and store the results in dst.
_mm512_ror_epi32 Rotate the bits in each packed 32-bit integer in a to the right by the number of bits specified in imm8, and store the results in dst.
_mm512_ror_epi64 Rotate the bits in each packed 64-bit integer in a to the right by the number of bits specified in imm8, and store the results in dst.
_mm512_rorv_epi32 Rotate the bits in each packed 32-bit integer in a to the right by the number of bits specified in the corresponding element of b, and store the results in dst.
_mm512_rorv_epi64 Rotate the bits in each packed 64-bit integer in a to the right by the number of bits specified in the corresponding element of b, and store the results in dst.
_mm512_roundscale_pd Round packed double-precision (64-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst.
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm512_roundscale_ps Round packed single-precision (32-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst.
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm512_roundscale_round_pd Round packed double-precision (64-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst.
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm512_roundscale_round_ps Round packed single-precision (32-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst.
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm512_rsqrt14_pd Compute the approximate reciprocal square root of packed double-precision (64-bit) floating-point elements in a, and store the results in dst. The maximum relative error for this approximation is less than 2^-14.
_mm512_rsqrt14_ps Compute the approximate reciprocal square root of packed single-precision (32-bit) floating-point elements in a, and store the results in dst. The maximum relative error for this approximation is less than 2^-14.
_mm512_scalef_pd Scale the packed double-precision (64-bit) floating-point elements in a using values from b, and store the results in dst.
_mm512_scalef_ps Scale the packed single-precision (32-bit) floating-point elements in a using values from b, and store the results in dst.
_mm512_scalef_round_pd Scale the packed double-precision (64-bit) floating-point elements in a using values from b, and store the results in dst.\
_mm512_scalef_round_ps Scale the packed single-precision (32-bit) floating-point elements in a using values from b, and store the results in dst.\
_mm512_set1_epi16 Broadcast the low packed 16-bit integer from a to all elements of dst.
_mm512_set1_epi32 Broadcast 32-bit integer a to all elements of dst.
_mm512_set1_epi64 Broadcast 64-bit integer a to all elements of dst.
_mm512_set1_epi8 Broadcast 8-bit integer a to all elements of dst.
_mm512_set1_pd Broadcast 64-bit float a to all elements of dst.
_mm512_set1_ps Broadcast 32-bit float a to all elements of dst.
_mm512_set4_epi32 Set packed 32-bit integers in dst with the repeated 4 element sequence.
_mm512_set4_epi64 Set packed 64-bit integers in dst with the repeated 4 element sequence.
_mm512_set4_pd Set packed double-precision (64-bit) floating-point elements in dst with the repeated 4 element sequence.
_mm512_set4_ps Set packed single-precision (32-bit) floating-point elements in dst with the repeated 4 element sequence.
_mm512_set_epi16 Set packed 16-bit integers in dst with the supplied values.
_mm512_set_epi32 Sets packed 32-bit integers in dst with the supplied values.
_mm512_set_epi64 Set packed 64-bit integers in dst with the supplied values.
_mm512_set_epi8 Set packed 8-bit integers in dst with the supplied values.
_mm512_set_pd Set packed double-precision (64-bit) floating-point elements in dst with the supplied values.
_mm512_set_ps Sets packed 32-bit integers in dst with the supplied values.
_mm512_setr4_epi32 Set packed 32-bit integers in dst with the repeated 4 element sequence in reverse order.
_mm512_setr4_epi64 Set packed 64-bit integers in dst with the repeated 4 element sequence in reverse order.
_mm512_setr4_pd Set packed double-precision (64-bit) floating-point elements in dst with the repeated 4 element sequence in reverse order.
_mm512_setr4_ps Set packed single-precision (32-bit) floating-point elements in dst with the repeated 4 element sequence in reverse order.
_mm512_setr_epi32 Sets packed 32-bit integers in dst with the supplied values in reverse order.
_mm512_setr_epi64 Set packed 64-bit integers in dst with the supplied values in reverse order.
_mm512_setr_pd Set packed double-precision (64-bit) floating-point elements in dst with the supplied values in reverse order.
_mm512_setr_ps Sets packed 32-bit integers in dst with the supplied values in reverse order.
_mm512_setzero Return vector of type __m512 with all elements set to zero.
_mm512_setzero_epi32 Return vector of type __m512i with all elements set to zero.
_mm512_setzero_pd Returns vector of type __m512d with all elements set to zero.
_mm512_setzero_ps Returns vector of type __m512 with all elements set to zero.
_mm512_setzero_si512 Returns vector of type __m512i with all elements set to zero.
_mm512_shuffle_epi32 Shuffle single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in imm8, and store the results in dst.
_mm512_shuffle_f32x4 Shuffle 128-bits (composed of 4 single-precision (32-bit) floating-point elements) selected by imm8 from a and b, and store the results in dst.
_mm512_shuffle_f64x2 Shuffle 128-bits (composed of 2 double-precision (64-bit) floating-point elements) selected by imm8 from a and b, and store the results in dst.
_mm512_shuffle_i32x4 Shuffle 128-bits (composed of 4 32-bit integers) selected by imm8 from a and b, and store the results in dst.
_mm512_shuffle_i64x2 Shuffle 128-bits (composed of 2 64-bit integers) selected by imm8 from a and b, and store the results in dst.
_mm512_shuffle_pd Shuffle double-precision (64-bit) floating-point elements within 128-bit lanes using the control in imm8, and store the results in dst.
_mm512_shuffle_ps Shuffle single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in imm8, and store the results in dst.
_mm512_sll_epi32 Shift packed 32-bit integers in a left by count while shifting in zeros, and store the results in dst.
_mm512_sll_epi64 Shift packed 64-bit integers in a left by count while shifting in zeros, and store the results in dst.
_mm512_slli_epi32 Shift packed 32-bit integers in a left by imm8 while shifting in zeros, and store the results in dst.
_mm512_slli_epi64 Shift packed 64-bit integers in a left by imm8 while shifting in zeros, and store the results in dst.
_mm512_sllv_epi32 Shift packed 32-bit integers in a left by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst.
_mm512_sllv_epi64 Shift packed 64-bit integers in a left by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst.
_mm512_sqrt_pd Compute the square root of packed double-precision (64-bit) floating-point elements in a, and store the results in dst.
_mm512_sqrt_ps Compute the square root of packed single-precision (32-bit) floating-point elements in a, and store the results in dst.
_mm512_sqrt_round_pd Compute the square root of packed double-precision (64-bit) floating-point elements in a, and store the results in dst.\
_mm512_sqrt_round_ps Compute the square root of packed single-precision (32-bit) floating-point elements in a, and store the results in dst.\
_mm512_sra_epi32 Shift packed 32-bit integers in a right by count while shifting in sign bits, and store the results in dst.
_mm512_sra_epi64 Shift packed 64-bit integers in a right by count while shifting in sign bits, and store the results in dst.
_mm512_srai_epi32 Shift packed 32-bit integers in a right by imm8 while shifting in sign bits, and store the results in dst.
_mm512_srai_epi64 Shift packed 64-bit integers in a right by imm8 while shifting in sign bits, and store the results in dst.
_mm512_srav_epi32 Shift packed 32-bit integers in a right by the amount specified by the corresponding element in count while shifting in sign bits, and store the results in dst.
_mm512_srav_epi64 Shift packed 64-bit integers in a right by the amount specified by the corresponding element in count while shifting in sign bits, and store the results in dst.
_mm512_srl_epi32 Shift packed 32-bit integers in a right by count while shifting in zeros, and store the results in dst.
_mm512_srl_epi64 Shift packed 64-bit integers in a right by count while shifting in zeros, and store the results in dst.
_mm512_srli_epi32 Shift packed 32-bit integers in a right by imm8 while shifting in zeros, and store the results in dst.
_mm512_srli_epi64 Shift packed 64-bit integers in a right by imm8 while shifting in zeros, and store the results in dst.
_mm512_srlv_epi32 Shift packed 32-bit integers in a right by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst.
_mm512_srlv_epi64 Shift packed 64-bit integers in a right by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst.
_mm512_store_epi32 Store 512-bits (composed of 16 packed 32-bit integers) from a into memory. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_store_epi64 Store 512-bits (composed of 8 packed 64-bit integers) from a into memory. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_store_pd Store 512-bits (composed of 8 packed double-precision (64-bit) floating-point elements) from a into memory. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_store_ps Store 512-bits of integer data from a into memory. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_store_si512 Store 512-bits of integer data from a into memory. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_storeu_epi32 Store 512-bits (composed of 16 packed 32-bit integers) from a into memory. mem_addr does not need to be aligned on any particular boundary.
_mm512_storeu_epi64 Store 512-bits (composed of 8 packed 64-bit integers) from a into memory. mem_addr does not need to be aligned on any particular boundary.
_mm512_storeu_pd Stores 512-bits (composed of 8 packed double-precision (64-bit) floating-point elements) from a into memory. mem_addr does not need to be aligned on any particular boundary.
_mm512_storeu_ps Stores 512-bits (composed of 16 packed single-precision (32-bit) floating-point elements) from a into memory. mem_addr does not need to be aligned on any particular boundary.
_mm512_storeu_si512 Store 512-bits of integer data from a into memory. mem_addr does not need to be aligned on any particular boundary.
_mm512_stream_load_si512 Load 512-bits of integer data from memory into dst using a non-temporal memory hint. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated. To minimize caching, the data is flagged as non-temporal (unlikely to be used again soon)
_mm512_stream_pd Store 512-bits (composed of 8 packed double-precision (64-bit) floating-point elements) from a into memory using a non-temporal memory hint. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_stream_ps Store 512-bits (composed of 16 packed single-precision (32-bit) floating-point elements) from a into memory using a non-temporal memory hint. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_stream_si512 Store 512-bits of integer data from a into memory using a non-temporal memory hint. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_sub_epi32 Subtract packed 32-bit integers in b from packed 32-bit integers in a, and store the results in dst.
_mm512_sub_epi64 Subtract packed 64-bit integers in b from packed 64-bit integers in a, and store the results in dst.
_mm512_sub_pd Subtract packed double-precision (64-bit) floating-point elements in b from packed double-precision (64-bit) floating-point elements in a, and store the results in dst.
_mm512_sub_ps Subtract packed single-precision (32-bit) floating-point elements in b from packed single-precision (32-bit) floating-point elements in a, and store the results in dst.
_mm512_sub_round_pd Subtract packed double-precision (64-bit) floating-point elements in b from packed double-precision (64-bit) floating-point elements in a, and store the results in dst.\
_mm512_sub_round_ps Subtract packed single-precision (32-bit) floating-point elements in b from packed single-precision (32-bit) floating-point elements in a, and store the results in dst.\
_mm512_ternarylogic_epi32 Bitwise ternary logic that provides the capability to implement any three-operand binary function; the specific binary function is specified by value in imm8. For each bit in each packed 32-bit integer, the corresponding bit from a, b, and c are used to form a 3 bit index into imm8, and the value at that bit in imm8 is written to the corresponding bit in dst.
_mm512_ternarylogic_epi64 Bitwise ternary logic that provides the capability to implement any three-operand binary function; the specific binary function is specified by value in imm8. For each bit in each packed 64-bit integer, the corresponding bit from a, b, and c are used to form a 3 bit index into imm8, and the value at that bit in imm8 is written to the corresponding bit in dst.
_mm512_test_epi32_mask Compute the bitwise AND of packed 32-bit integers in a and b, producing intermediate 32-bit values, and set the corresponding bit in result mask k if the intermediate value is non-zero.
_mm512_test_epi64_mask Compute the bitwise AND of packed 64-bit integers in a and b, producing intermediate 64-bit values, and set the corresponding bit in result mask k if the intermediate value is non-zero.
_mm512_testn_epi32_mask Compute the bitwise NAND of packed 32-bit integers in a and b, producing intermediate 32-bit values, and set the corresponding bit in result mask k if the intermediate value is zero.
_mm512_testn_epi64_mask Compute the bitwise NAND of packed 64-bit integers in a and b, producing intermediate 64-bit values, and set the corresponding bit in result mask k if the intermediate value is zero.
_mm512_undefined Return vector of type __m512 with indeterminate elements. Despite using the word "undefined" (following Intel's naming scheme), this non-deterministically picks some valid value and is not equivalent to mem::MaybeUninit. In practice, this is typically equivalent to mem::zeroed.
_mm512_undefined_epi32 Return vector of type __m512i with indeterminate elements. Despite using the word "undefined" (following Intel's naming scheme), this non-deterministically picks some valid value and is not equivalent to mem::MaybeUninit. In practice, this is typically equivalent to mem::zeroed.
_mm512_undefined_pd Returns vector of type __m512d with indeterminate elements. Despite using the word "undefined" (following Intel's naming scheme), this non-deterministically picks some valid value and is not equivalent to mem::MaybeUninit. In practice, this is typically equivalent to mem::zeroed.
_mm512_undefined_ps Returns vector of type __m512 with indeterminate elements. Despite using the word "undefined" (following Intel's naming scheme), this non-deterministically picks some valid value and is not equivalent to mem::MaybeUninit. In practice, this is typically equivalent to mem::zeroed.
_mm512_unpackhi_epi32 Unpack and interleave 32-bit integers from the high half of each 128-bit lane in a and b, and store the results in dst.
_mm512_unpackhi_epi64 Unpack and interleave 64-bit integers from the high half of each 128-bit lane in a and b, and store the results in dst.
_mm512_unpackhi_pd Unpack and interleave double-precision (64-bit) floating-point elements from the high half of each 128-bit lane in a and b, and store the results in dst.
_mm512_unpackhi_ps Unpack and interleave single-precision (32-bit) floating-point elements from the high half of each 128-bit lane in a and b, and store the results in dst.
_mm512_unpacklo_epi32 Unpack and interleave 32-bit integers from the low half of each 128-bit lane in a and b, and store the results in dst.
_mm512_unpacklo_epi64 Unpack and interleave 64-bit integers from the low half of each 128-bit lane in a and b, and store the results in dst.
_mm512_unpacklo_pd Unpack and interleave double-precision (64-bit) floating-point elements from the low half of each 128-bit lane in a and b, and store the results in dst.
_mm512_unpacklo_ps Unpack and interleave single-precision (32-bit) floating-point elements from the low half of each 128-bit lane in a and b, and store the results in dst.
_mm512_xor_epi32 Compute the bitwise XOR of packed 32-bit integers in a and b, and store the results in dst.
_mm512_xor_epi64 Compute the bitwise XOR of packed 64-bit integers in a and b, and store the results in dst.
_mm512_xor_si512 Compute the bitwise XOR of 512 bits (representing integer data) in a and b, and store the result in dst.
_mm512_zextpd128_pd512 Cast vector of type __m128d to type __m512d; the upper 384 bits of the result are zeroed. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency.
_mm512_zextpd256_pd512 Cast vector of type __m256d to type __m512d; the upper 256 bits of the result are zeroed. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency.
_mm512_zextps128_ps512 Cast vector of type __m128 to type __m512; the upper 384 bits of the result are zeroed. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency.
_mm512_zextps256_ps512 Cast vector of type __m256 to type __m512; the upper 256 bits of the result are zeroed. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency.
_mm512_zextsi128_si512 Cast vector of type __m128i to type __m512i; the upper 384 bits of the result are zeroed. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency.
_mm512_zextsi256_si512 Cast vector of type __m256i to type __m512i; the upper 256 bits of the result are zeroed. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency.
_mm_abs_epi64 Compute the absolute value of packed signed 64-bit integers in a, and store the unsigned results in dst.
_mm_add_round_sd Add the lower double-precision (64-bit) floating-point element in a and b, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.\
_mm_add_round_ss Add the lower single-precision (32-bit) floating-point element in a and b, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_alignr_epi32 Concatenate a and b into a 32-byte immediate result, shift the result right by imm8 32-bit elements, and store the low 16 bytes (4 elements) in dst.
_mm_alignr_epi64 Concatenate a and b into a 32-byte immediate result, shift the result right by imm8 64-bit elements, and store the low 16 bytes (2 elements) in dst.
_mm_cmp_epi32_mask Compare packed signed 32-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
_mm_cmp_epi64_mask Compare packed signed 64-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
_mm_cmp_epu32_mask Compare packed unsigned 32-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
_mm_cmp_epu64_mask Compare packed unsigned 64-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
_mm_cmp_pd_mask Compare packed double-precision (64-bit) floating-point elements in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
_mm_cmp_ps_mask Compare packed single-precision (32-bit) floating-point elements in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
_mm_cmp_round_sd_mask Compare the lower double-precision (64-bit) floating-point element in a and b based on the comparison operand specified by imm8, and store the result in mask vector k.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_cmp_round_ss_mask Compare the lower single-precision (32-bit) floating-point element in a and b based on the comparison operand specified by imm8, and store the result in mask vector k.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_cmp_sd_mask Compare the lower double-precision (64-bit) floating-point element in a and b based on the comparison operand specified by imm8, and store the result in mask vector k.
_mm_cmp_ss_mask Compare the lower single-precision (32-bit) floating-point element in a and b based on the comparison operand specified by imm8, and store the result in mask vector k.
_mm_cmpeq_epi32_mask Compare packed 32-bit integers in a and b for equality, and store the results in mask vector k.
_mm_cmpeq_epi64_mask Compare packed 64-bit integers in a and b for equality, and store the results in mask vector k.
_mm_cmpeq_epu32_mask Compare packed unsigned 32-bit integers in a and b for equality, and store the results in mask vector k.
_mm_cmpeq_epu64_mask Compare packed unsigned 64-bit integers in a and b for equality, and store the results in mask vector k.
_mm_cmpge_epi32_mask Compare packed signed 32-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k.
_mm_cmpge_epi64_mask Compare packed signed 64-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k.
_mm_cmpge_epu32_mask Compare packed unsigned 32-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k.
_mm_cmpge_epu64_mask Compare packed unsigned 64-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k.
_mm_cmpgt_epi32_mask Compare packed signed 32-bit integers in a and b for greater-than, and store the results in mask vector k.
_mm_cmpgt_epi64_mask Compare packed signed 64-bit integers in a and b for greater-than, and store the results in mask vector k.
_mm_cmpgt_epu32_mask Compare packed unsigned 32-bit integers in a and b for greater-than, and store the results in mask vector k.
_mm_cmpgt_epu64_mask Compare packed unsigned 64-bit integers in a and b for greater-than, and store the results in mask vector k.
_mm_cmple_epi32_mask Compare packed signed 32-bit integers in a and b for less-than-or-equal, and store the results in mask vector k.
_mm_cmple_epi64_mask Compare packed signed 64-bit integers in a and b for less-than-or-equal, and store the results in mask vector k.
_mm_cmple_epu32_mask Compare packed unsigned 32-bit integers in a and b for less-than-or-equal, and store the results in mask vector k.
_mm_cmple_epu64_mask Compare packed unsigned 64-bit integers in a and b for less-than-or-equal, and store the results in mask vector k.
_mm_cmplt_epi32_mask Compare packed signed 32-bit integers in a and b for less-than, and store the results in mask vector k.
_mm_cmplt_epi64_mask Compare packed signed 64-bit integers in a and b for less-than, and store the results in mask vector k.
_mm_cmplt_epu32_mask Compare packed unsigned 32-bit integers in a and b for less-than, and store the results in mask vector k.
_mm_cmplt_epu64_mask Compare packed unsigned 64-bit integers in a and b for less-than, and store the results in mask vector k.
_mm_cmpneq_epi32_mask Compare packed 32-bit integers in a and b for not-equal, and store the results in mask vector k.
_mm_cmpneq_epi64_mask Compare packed signed 64-bit integers in a and b for not-equal, and store the results in mask vector k.
_mm_cmpneq_epu32_mask Compare packed unsigned 32-bit integers in a and b for not-equal, and store the results in mask vector k.
_mm_cmpneq_epu64_mask Compare packed unsigned 64-bit integers in a and b for not-equal, and store the results in mask vector k.
_mm_comi_round_sd Compare the lower double-precision (64-bit) floating-point element in a and b based on the comparison operand specified by imm8, and return the boolean result (0 or 1).
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_comi_round_ss Compare the lower single-precision (32-bit) floating-point element in a and b based on the comparison operand specified by imm8, and return the boolean result (0 or 1).
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_cvt_roundi32_ss Convert the signed 32-bit integer b to a single-precision (32-bit) floating-point element, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_cvt_roundsd_i32 Convert the lower single-precision (32-bit) floating-point element in a to a 32-bit integer, and store the result in dst.
Rounding is done according to the rounding[3:0] parameter, which can be one of:\
_mm_cvt_roundsd_si32 Convert the lower double-precision (64-bit) floating-point element in a to a 32-bit integer, and store the result in dst.
Rounding is done according to the rounding[3:0] parameter, which can be one of:\
_mm_cvt_roundsd_ss Convert the lower double-precision (64-bit) floating-point element in b to a single-precision (32-bit) floating-point element, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
Rounding is done according to the rounding[3:0] parameter, which can be one of:\
_mm_cvt_roundsd_u32 Convert the lower double-precision (64-bit) floating-point element in a to an unsigned 32-bit integer, and store the result in dst.
Rounding is done according to the rounding[3:0] parameter, which can be one of:\
_mm_cvt_roundsi32_ss Convert the signed 32-bit integer b to a single-precision (32-bit) floating-point element, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_cvt_roundss_i32 Convert the lower single-precision (32-bit) floating-point element in a to a 32-bit integer, and store the result in dst.
Rounding is done according to the rounding[3:0] parameter, which can be one of:\
_mm_cvt_roundss_sd Convert the lower single-precision (32-bit) floating-point element in b to a double-precision (64-bit) floating-point element, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_cvt_roundss_si32 Convert the lower single-precision (32-bit) floating-point element in a to a 32-bit integer, and store the result in dst.
Rounding is done according to the rounding[3:0] parameter, which can be one of:\
_mm_cvt_roundss_u32 Convert the lower single-precision (32-bit) floating-point element in a to an unsigned 32-bit integer, and store the result in dst.
Rounding is done according to the rounding[3:0] parameter, which can be one of:\
_mm_cvt_roundu32_ss Convert the unsigned 32-bit integer b to a single-precision (32-bit) floating-point element, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
Rounding is done according to the rounding[3:0] parameter, which can be one of:\
_mm_cvtepi32_epi16 Convert packed 32-bit integers in a to packed 16-bit integers with truncation, and store the results in dst.
_mm_cvtepi32_epi8 Convert packed 32-bit integers in a to packed 8-bit integers with truncation, and store the results in dst.
_mm_cvtepi64_epi16 Convert packed 64-bit integers in a to packed 16-bit integers with truncation, and store the results in dst.
_mm_cvtepi64_epi32 Convert packed 64-bit integers in a to packed 32-bit integers with truncation, and store the results in dst.
_mm_cvtepi64_epi8 Convert packed 64-bit integers in a to packed 8-bit integers with truncation, and store the results in dst.
_mm_cvtepu32_pd Convert packed unsigned 32-bit integers in a to packed double-precision (64-bit) floating-point elements, and store the results in dst.
_mm_cvti32_sd Convert the signed 32-bit integer b to a double-precision (64-bit) floating-point element, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.
_mm_cvti32_ss Convert the signed 32-bit integer b to a single-precision (32-bit) floating-point element, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_cvtpd_epu32 Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-bit integers, and store the results in dst.
_mm_cvtps_epu32 Convert packed single-precision (32-bit) floating-point elements in a to packed unsigned 32-bit integers, and store the results in dst.
_mm_cvtsd_i32 Convert the lower double-precision (64-bit) floating-point element in a to a 32-bit integer, and store the result in dst.
_mm_cvtsd_u32 Convert the lower double-precision (64-bit) floating-point element in a to an unsigned 32-bit integer, and store the result in dst.
_mm_cvtsepi32_epi16 Convert packed signed 32-bit integers in a to packed 16-bit integers with signed saturation, and store the results in dst.
_mm_cvtsepi32_epi8 Convert packed signed 32-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst.
_mm_cvtsepi64_epi16 Convert packed signed 64-bit integers in a to packed 16-bit integers with signed saturation, and store the results in dst.
_mm_cvtsepi64_epi32 Convert packed signed 64-bit integers in a to packed 32-bit integers with signed saturation, and store the results in dst.
_mm_cvtsepi64_epi8 Convert packed signed 64-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst.
_mm_cvtss_i32 Convert the lower single-precision (32-bit) floating-point element in a to a 32-bit integer, and store the result in dst.
_mm_cvtss_u32 Convert the lower single-precision (32-bit) floating-point element in a to an unsigned 32-bit integer, and store the result in dst.
_mm_cvtt_roundsd_i32 Convert the lower double-precision (64-bit) floating-point element in a to a 32-bit integer with truncation, and store the result in dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_cvtt_roundsd_si32 Convert the lower double-precision (64-bit) floating-point element in a to a 32-bit integer with truncation, and store the result in dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_cvtt_roundsd_u32 Convert the lower double-precision (64-bit) floating-point element in a to an unsigned 32-bit integer with truncation, and store the result in dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_cvtt_roundss_i32 Convert the lower single-precision (32-bit) floating-point element in a to a 32-bit integer with truncation, and store the result in dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_cvtt_roundss_si32 Convert the lower single-precision (32-bit) floating-point element in a to a 32-bit integer with truncation, and store the result in dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_cvtt_roundss_u32 Convert the lower single-precision (32-bit) floating-point element in a to an unsigned 32-bit integer with truncation, and store the result in dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_cvttpd_epu32 Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-bit integers with truncation, and store the results in dst.
_mm_cvttps_epu32 Convert packed single-precision (32-bit) floating-point elements in a to packed unsigned 32-bit integers with truncation, and store the results in dst.
_mm_cvttsd_i32 Convert the lower double-precision (64-bit) floating-point element in a to a 32-bit integer with truncation, and store the result in dst.
_mm_cvttsd_u32 Convert the lower double-precision (64-bit) floating-point element in a to an unsigned 32-bit integer with truncation, and store the result in dst.
_mm_cvttss_i32 Convert the lower single-precision (32-bit) floating-point element in a to a 32-bit integer with truncation, and store the result in dst.
_mm_cvttss_u32 Convert the lower single-precision (32-bit) floating-point element in a to an unsigned 32-bit integer with truncation, and store the result in dst.
_mm_cvtu32_sd Convert the unsigned 32-bit integer b to a double-precision (64-bit) floating-point element, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.
_mm_cvtu32_ss Convert the unsigned 32-bit integer b to a single-precision (32-bit) floating-point element, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_cvtusepi32_epi16 Convert packed unsigned 32-bit integers in a to packed unsigned 16-bit integers with unsigned saturation, and store the results in dst.
_mm_cvtusepi32_epi8 Convert packed unsigned 32-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst.
_mm_cvtusepi64_epi16 Convert packed unsigned 64-bit integers in a to packed unsigned 16-bit integers with unsigned saturation, and store the results in dst.
_mm_cvtusepi64_epi32 Convert packed unsigned 64-bit integers in a to packed unsigned 32-bit integers with unsigned saturation, and store the results in dst.
_mm_cvtusepi64_epi8 Convert packed unsigned 64-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst.
_mm_div_round_sd Divide the lower double-precision (64-bit) floating-point element in a by the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.\
_mm_div_round_ss Divide the lower single-precision (32-bit) floating-point element in a by the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_fixupimm_pd Fix up packed double-precision (64-bit) floating-point elements in a and b using packed 64-bit integers in c, and store the results in dst. imm8 is used to set the required flags reporting.
_mm_fixupimm_ps Fix up packed single-precision (32-bit) floating-point elements in a and b using packed 32-bit integers in c, and store the results in dst. imm8 is used to set the required flags reporting.
_mm_fixupimm_round_sd Fix up the lower double-precision (64-bit) floating-point elements in a and b using the lower 64-bit integer in c, store the result in the lower element of dst, and copy the upper element from b to the upper element of dst. imm8 is used to set the required flags reporting.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_fixupimm_round_ss Fix up the lower single-precision (32-bit) floating-point elements in a and b using the lower 32-bit integer in c, store the result in the lower element of dst, and copy the upper 3 packed elements from b to the upper elements of dst. imm8 is used to set the required flags reporting.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_fixupimm_sd Fix up the lower double-precision (64-bit) floating-point elements in a and b using the lower 64-bit integer in c, store the result in the lower element of dst, and copy the upper element from b to the upper element of dst. imm8 is used to set the required flags reporting.
_mm_fixupimm_ss Fix up the lower single-precision (32-bit) floating-point elements in a and b using the lower 32-bit integer in c, store the result in the lower element of dst, and copy the upper 3 packed elements from b to the upper elements of dst. imm8 is used to set the required flags reporting.
_mm_fmadd_round_sd Multiply the lower double-precision (64-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.\
_mm_fmadd_round_ss Multiply the lower single-precision (32-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_fmsub_round_sd Multiply the lower double-precision (64-bit) floating-point elements in a and b, and subtract the lower element in c from the intermediate result. Store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.\
_mm_fmsub_round_ss Multiply the lower single-precision (32-bit) floating-point elements in a and b, and subtract the lower element in c from the intermediate result. Store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_fnmadd_round_sd Multiply the lower double-precision (64-bit) floating-point elements in a and b, and add the negated intermediate result to the lower element in c. Store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.\
_mm_fnmadd_round_ss Multiply the lower single-precision (32-bit) floating-point elements in a and b, and add the negated intermediate result to the lower element in c. Store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_fnmsub_round_sd Multiply the lower double-precision (64-bit) floating-point elements in a and b, and subtract the lower element in c from the negated intermediate result. Store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.\
_mm_fnmsub_round_ss Multiply the lower single-precision (32-bit) floating-point elements in a and b, subtract the lower element in c from the negated intermediate result, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_getexp_pd Convert the exponent of each packed double-precision (64-bit) floating-point element in a to a double-precision (64-bit) floating-point number representing the integer exponent, and store the results in dst. This intrinsic essentially calculates floor(log2(x)) for each element.
_mm_getexp_ps Convert the exponent of each packed single-precision (32-bit) floating-point element in a to a single-precision (32-bit) floating-point number representing the integer exponent, and store the results in dst. This intrinsic essentially calculates floor(log2(x)) for each element.
_mm_getexp_round_sd Convert the exponent of the lower double-precision (64-bit) floating-point element in b to a double-precision (64-bit) floating-point number representing the integer exponent, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst. This intrinsic essentially calculates floor(log2(x)) for the lower element.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_getexp_round_ss Convert the exponent of the lower single-precision (32-bit) floating-point element in b to a single-precision (32-bit) floating-point number representing the integer exponent, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst. This intrinsic essentially calculates floor(log2(x)) for the lower element.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_getexp_sd Convert the exponent of the lower double-precision (64-bit) floating-point element in b to a double-precision (64-bit) floating-point number representing the integer exponent, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst. This intrinsic essentially calculates floor(log2(x)) for the lower element.
_mm_getexp_ss Convert the exponent of the lower single-precision (32-bit) floating-point element in b to a single-precision (32-bit) floating-point number representing the integer exponent, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst. This intrinsic essentially calculates floor(log2(x)) for the lower element.
_mm_getmant_pd Normalize the mantissas of packed double-precision (64-bit) floating-point elements in a, and store the results in dst. This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
_mm_getmant_ps Normalize the mantissas of packed single-precision (32-bit) floating-point elements in a, and store the results in dst. This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign. The mantissa is normalized to the interval specified by interv, which can take the following values: _MM_MANT_NORM_1_2 // interval [1, 2) _MM_MANT_NORM_p5_2 // interval [0.5, 2) _MM_MANT_NORM_p5_1 // interval [0.5, 1) _MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5) The sign is determined by sc which can take the following values: _MM_MANT_SIGN_src // sign = sign(src) _MM_MANT_SIGN_zero // sign = 0 _MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
_mm_getmant_round_sd Normalize the mantissas of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst. This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_getmant_round_ss Normalize the mantissas of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst. This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_getmant_sd Normalize the mantissas of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst. This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_getmant_ss Normalize the mantissas of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst. This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_i32scatter_epi32 Stores 4 32-bit integer elements from a to memory starting at location base_addr at packed 32-bit integer indices stored in vindex scaled by scale
_mm_i32scatter_epi64 Stores 2 64-bit integer elements from a to memory starting at location base_addr at packed 32-bit integer indices stored in vindex scaled by scale
_mm_i32scatter_pd Stores 2 double-precision (64-bit) floating-point elements from a to memory starting at location base_addr at packed 32-bit integer indices stored in vindex scaled by scale
_mm_i32scatter_ps Stores 4 single-precision (32-bit) floating-point elements from a to memory starting at location base_addr at packed 32-bit integer indices stored in vindex scaled by scale
_mm_i64scatter_epi32 Stores 2 32-bit integer elements from a to memory starting at location base_addr at packed 64-bit integer indices stored in vindex scaled by scale
_mm_i64scatter_epi64 Stores 2 64-bit integer elements from a to memory starting at location base_addr at packed 64-bit integer indices stored in vindex scaled by scale
_mm_i64scatter_pd Stores 2 double-precision (64-bit) floating-point elements from a to memory starting at location base_addr at packed 64-bit integer indices stored in vindex scaled by scale
_mm_i64scatter_ps Stores 2 single-precision (32-bit) floating-point elements from a to memory starting at location base_addr at packed 64-bit integer indices stored in vindex scaled by scale
_mm_load_epi32 Load 128-bits (composed of 4 packed 32-bit integers) from memory into dst. mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated.
_mm_load_epi64 Load 128-bits (composed of 2 packed 64-bit integers) from memory into dst. mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated.
_mm_loadu_epi32 Load 128-bits (composed of 4 packed 32-bit integers) from memory into dst. mem_addr does not need to be aligned on any particular boundary.
_mm_loadu_epi64 Load 128-bits (composed of 2 packed 64-bit integers) from memory into dst. mem_addr does not need to be aligned on any particular boundary.
_mm_mask2_permutex2var_epi32 Shuffle 32-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from idx when the corresponding mask bit is not set).
_mm_mask2_permutex2var_epi64 Shuffle 64-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from idx when the corresponding mask bit is not set).
_mm_mask2_permutex2var_pd Shuffle double-precision (64-bit) floating-point elements in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from idx when the corresponding mask bit is not set)
_mm_mask2_permutex2var_ps Shuffle single-precision (32-bit) floating-point elements in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from idx when the corresponding mask bit is not set).
_mm_mask3_fmadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm_mask3_fmadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm_mask3_fmadd_round_sd Multiply the lower double-precision (64-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper element from c to the upper element of dst.\
_mm_mask3_fmadd_round_ss Multiply the lower single-precision (32-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper 3 packed elements from c to the upper elements of dst.\
_mm_mask3_fmadd_sd Multiply the lower double-precision (64-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper element from c to the upper element of dst.
_mm_mask3_fmadd_ss Multiply the lower single-precision (32-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper 3 packed elements from c to the upper elements of dst.
_mm_mask3_fmaddsub_pd Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm_mask3_fmaddsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm_mask3_fmsub_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm_mask3_fmsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm_mask3_fmsub_round_sd Multiply the lower double-precision (64-bit) floating-point elements in a and b, and subtract the lower element in c from the intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper element from c to the upper element of dst.\
_mm_mask3_fmsub_round_ss Multiply the lower single-precision (32-bit) floating-point elements in a and b, and subtract the lower element in c from the intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper 3 packed elements from c to the upper elements of dst.\
_mm_mask3_fmsub_sd Multiply the lower double-precision (64-bit) floating-point elements in a and b, and subtract the lower element in c from the intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper element from c to the upper element of dst.
_mm_mask3_fmsub_ss Multiply the lower single-precision (32-bit) floating-point elements in a and b, and subtract the lower element in c from the intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper 3 packed elements from c to the upper elements of dst.
_mm_mask3_fmsubadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm_mask3_fmsubadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm_mask3_fnmadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm_mask3_fnmadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm_mask3_fnmadd_round_sd Multiply the lower double-precision (64-bit) floating-point elements in a and b, and add the negated intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper element from c to the upper element of dst.\
_mm_mask3_fnmadd_round_ss Multiply the lower single-precision (32-bit) floating-point elements in a and b, and add the negated intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper 3 packed elements from c to the upper elements of dst.\
_mm_mask3_fnmadd_sd Multiply the lower double-precision (64-bit) floating-point elements in a and b, and add the negated intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper element from c to the upper element of dst.
_mm_mask3_fnmadd_ss Multiply the lower single-precision (32-bit) floating-point elements in a and b, and add the negated intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper 3 packed elements from c to the upper elements of dst.
_mm_mask3_fnmsub_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm_mask3_fnmsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set).
_mm_mask3_fnmsub_round_sd Multiply the lower double-precision (64-bit) floating-point elements in a and b, and subtract the lower element in c from the negated intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper element from c to the upper element of dst.\
_mm_mask3_fnmsub_round_ss Multiply the lower single-precision (32-bit) floating-point elements in a and b, subtract the lower element in c from the negated intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper 3 packed elements from c to the upper elements of dst.\
_mm_mask3_fnmsub_sd Multiply the lower double-precision (64-bit) floating-point elements in a and b, and subtract the lower element in c from the negated intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper element from c to the upper element of dst.
_mm_mask3_fnmsub_ss Multiply the lower single-precision (32-bit) floating-point elements in a and b, and subtract the lower element in c from the negated intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper 3 packed elements from c to the upper elements of dst.
_mm_mask_abs_epi32 Compute the absolute value of packed signed 32-bit integers in a, and store the unsigned results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_abs_epi64 Compute the absolute value of packed signed 64-bit integers in a, and store the unsigned results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_add_epi32 Add packed 32-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_add_epi64 Add packed 64-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_add_pd Add packed double-precision (64-bit) floating-point elements in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_add_ps Add packed single-precision (32-bit) floating-point elements in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_add_round_sd Add the lower double-precision (64-bit) floating-point element in a and b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.\
_mm_mask_add_round_ss Add the lower single-precision (32-bit) floating-point element in a and b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_mask_add_sd Add the lower double-precision (64-bit) floating-point element in a and b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_add_ss Add the lower single-precision (32-bit) floating-point element in a and b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_alignr_epi32 Concatenate a and b into a 32-byte immediate result, shift the result right by imm8 32-bit elements, and store the low 16 bytes (4 elements) in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_alignr_epi64 Concatenate a and b into a 32-byte immediate result, shift the result right by imm8 64-bit elements, and store the low 16 bytes (2 elements) in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_and_epi32 Performs element-by-element bitwise AND between packed 32-bit integer elements of a and b, storing the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_and_epi64 Compute the bitwise AND of packed 64-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_andnot_epi32 Compute the bitwise NOT of packed 32-bit integers in a and then AND with b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_andnot_epi64 Compute the bitwise NOT of packed 64-bit integers in a and then AND with b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_blend_epi32 Blend packed 32-bit integers from a and b using control mask k, and store the results in dst.
_mm_mask_blend_epi64 Blend packed 64-bit integers from a and b using control mask k, and store the results in dst.
_mm_mask_blend_pd Blend packed double-precision (64-bit) floating-point elements from a and b using control mask k, and store the results in dst.
_mm_mask_blend_ps Blend packed single-precision (32-bit) floating-point elements from a and b using control mask k, and store the results in dst.
_mm_mask_broadcastd_epi32 Broadcast the low packed 32-bit integer from a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_broadcastq_epi64 Broadcast the low packed 64-bit integer from a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_broadcastss_ps Broadcast the low single-precision (32-bit) floating-point element from a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cmp_epi32_mask Compare packed signed 32-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmp_epi64_mask Compare packed signed 64-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmp_epu32_mask Compare packed unsigned 32-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmp_epu64_mask Compare packed unsigned 64-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmp_pd_mask Compare packed double-precision (64-bit) floating-point elements in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmp_ps_mask Compare packed single-precision (32-bit) floating-point elements in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmp_round_sd_mask Compare the lower double-precision (64-bit) floating-point element in a and b based on the comparison operand specified by imm8, and store the result in mask vector k using zeromask k1 (the element is zeroed out when mask bit 0 is not set).
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mask_cmp_round_ss_mask Compare the lower single-precision (32-bit) floating-point element in a and b based on the comparison operand specified by imm8, and store the result in mask vector k using zeromask k1 (the element is zeroed out when mask bit 0 is not seti).
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mask_cmp_sd_mask Compare the lower double-precision (64-bit) floating-point element in a and b based on the comparison operand specified by imm8, and store the result in mask vector k using zeromask k1 (the element is zeroed out when mask bit 0 is not set).
_mm_mask_cmp_ss_mask Compare the lower single-precision (32-bit) floating-point element in a and b based on the comparison operand specified by imm8, and store the result in mask vector k using zeromask k1 (the element is zeroed out when mask bit 0 is not set).
_mm_mask_cmpeq_epi32_mask Compare packed 32-bit integers in a and b for equality, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmpeq_epi64_mask Compare packed 64-bit integers in a and b for equality, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmpeq_epu32_mask Compare packed unsigned 32-bit integers in a and b for equality, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmpeq_epu64_mask Compare packed unsigned 64-bit integers in a and b for equality, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmpge_epi32_mask Compare packed signed 32-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmpge_epi64_mask Compare packed signed 64-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmpge_epu32_mask Compare packed unsigned 32-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmpge_epu64_mask Compare packed unsigned 64-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmpgt_epi32_mask Compare packed signed 32-bit integers in a and b for greater-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmpgt_epi64_mask Compare packed signed 64-bit integers in a and b for greater-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmpgt_epu32_mask Compare packed unsigned 32-bit integers in a and b for greater-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmpgt_epu64_mask Compare packed unsigned 64-bit integers in a and b for greater-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmple_epi32_mask Compare packed signed 32-bit integers in a and b for less-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmple_epi64_mask Compare packed signed 64-bit integers in a and b for less-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmple_epu32_mask Compare packed unsigned 32-bit integers in a and b for less-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmple_epu64_mask Compare packed unsigned 64-bit integers in a and b for less-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmplt_epi32_mask Compare packed signed 32-bit integers in a and b for less-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmplt_epi64_mask Compare packed signed 64-bit integers in a and b for less-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmplt_epu32_mask Compare packed unsigned 32-bit integers in a and b for less-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmplt_epu64_mask Compare packed unsigned 64-bit integers in a and b for less-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmpneq_epi32_mask Compare packed 32-bit integers in a and b for not-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmpneq_epi64_mask Compare packed signed 64-bit integers in a and b for not-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmpneq_epu32_mask Compare packed unsigned 32-bit integers in a and b for not-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_cmpneq_epu64_mask Compare packed unsigned 64-bit integers in a and b for not-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
_mm_mask_compress_epi32 Contiguously store the active 32-bit integers in a (those with their respective bit set in writemask k) to dst, and pass through the remaining elements from src.
_mm_mask_compress_epi64 Contiguously store the active 64-bit integers in a (those with their respective bit set in writemask k) to dst, and pass through the remaining elements from src.
_mm_mask_compress_pd Contiguously store the active double-precision (64-bit) floating-point elements in a (those with their respective bit set in writemask k) to dst, and pass through the remaining elements from src.
_mm_mask_compress_ps Contiguously store the active single-precision (32-bit) floating-point elements in a (those with their respective bit set in writemask k) to dst, and pass through the remaining elements from src.
_mm_mask_compressstoreu_epi32 Contiguously store the active 32-bit integers in a (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm_mask_compressstoreu_epi64 Contiguously store the active 64-bit integers in a (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm_mask_compressstoreu_pd Contiguously store the active double-precision (64-bit) floating-point elements in a (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm_mask_compressstoreu_ps Contiguously store the active single-precision (32-bit) floating-point elements in a (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm_mask_cvt_roundps_ph Convert packed single-precision (32-bit) floating-point elements in a to packed half-precision (16-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm_mask_cvt_roundsd_ss Convert the lower double-precision (64-bit) floating-point element in b to a single-precision (32-bit) floating-point element, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
Rounding is done according to the rounding[3:0] parameter, which can be one of:\
_mm_mask_cvt_roundss_sd Convert the lower single-precision (32-bit) floating-point element in b to a double-precision (64-bit) floating-point element, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mask_cvtepi16_epi32 Sign extend packed 16-bit integers in a to packed 32-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtepi16_epi64 Sign extend packed 16-bit integers in a to packed 64-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtepi32_epi16 Convert packed 32-bit integers in a to packed 16-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtepi32_epi64 Sign extend packed 32-bit integers in a to packed 64-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtepi32_epi8 Convert packed 32-bit integers in a to packed 8-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtepi32_pd Convert packed signed 32-bit integers in a to packed double-precision (64-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtepi32_ps Convert packed signed 32-bit integers in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtepi32_storeu_epi16 Convert packed 32-bit integers in a to packed 16-bit integers with truncation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm_mask_cvtepi32_storeu_epi8 Convert packed 32-bit integers in a to packed 8-bit integers with truncation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm_mask_cvtepi64_epi16 Convert packed 64-bit integers in a to packed 16-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtepi64_epi32 Convert packed 64-bit integers in a to packed 32-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtepi64_epi8 Convert packed 64-bit integers in a to packed 8-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtepi64_storeu_epi16 Convert packed 64-bit integers in a to packed 16-bit integers with truncation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm_mask_cvtepi64_storeu_epi32 Convert packed 64-bit integers in a to packed 32-bit integers with truncation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm_mask_cvtepi64_storeu_epi8 Convert packed 64-bit integers in a to packed 8-bit integers with truncation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm_mask_cvtepi8_epi32 Sign extend packed 8-bit integers in a to packed 32-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtepi8_epi64 Sign extend packed 8-bit integers in the low 2 bytes of a to packed 64-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtepu16_epi32 Zero extend packed unsigned 16-bit integers in a to packed 32-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtepu16_epi64 Zero extend packed unsigned 16-bit integers in the low 4 bytes of a to packed 64-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtepu32_epi64 Zero extend packed unsigned 32-bit integers in a to packed 64-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtepu32_pd Convert packed unsigned 32-bit integers in a to packed double-precision (64-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtepu8_epi32 Zero extend packed unsigned 8-bit integers in the low 4 bytes of a to packed 32-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtepu8_epi64 Zero extend packed unsigned 8-bit integers in the low 2 bytes of a to packed 64-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtpd_epi32 Convert packed double-precision (64-bit) floating-point elements in a to packed 32-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtpd_epu32 Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtpd_ps Convert packed double-precision (64-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtph_ps Convert packed half-precision (16-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtps_epi32 Convert packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtps_epu32 Convert packed single-precision (32-bit) floating-point elements in a to packed unsigned 32-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtps_ph Convert packed single-precision (32-bit) floating-point elements in a to packed half-precision (16-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm_mask_cvtsd_ss Convert the lower double-precision (64-bit) floating-point element in b to a single-precision (32-bit) floating-point element, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_cvtsepi32_epi16 Convert packed signed 32-bit integers in a to packed 16-bit integers with signed saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtsepi32_epi8 Convert packed signed 32-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtsepi32_storeu_epi16 Convert packed signed 32-bit integers in a to packed 16-bit integers with signed saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm_mask_cvtsepi32_storeu_epi8 Convert packed signed 32-bit integers in a to packed 8-bit integers with signed saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm_mask_cvtsepi64_epi16 Convert packed signed 64-bit integers in a to packed 16-bit integers with signed saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtsepi64_epi32 Convert packed signed 64-bit integers in a to packed 32-bit integers with signed saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtsepi64_epi8 Convert packed signed 64-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtsepi64_storeu_epi16 Convert packed signed 64-bit integers in a to packed 16-bit integers with signed saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm_mask_cvtsepi64_storeu_epi32 Convert packed signed 64-bit integers in a to packed 32-bit integers with signed saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm_mask_cvtsepi64_storeu_epi8 Convert packed signed 64-bit integers in a to packed 8-bit integers with signed saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm_mask_cvtss_sd Convert the lower single-precision (32-bit) floating-point element in b to a double-precision (64-bit) floating-point element, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_cvttpd_epi32 Convert packed double-precision (64-bit) floating-point elements in a to packed 32-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvttpd_epu32 Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvttps_epi32 Convert packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvttps_epu32 Convert packed double-precision (32-bit) floating-point elements in a to packed unsigned 32-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtusepi32_epi16 Convert packed unsigned 32-bit integers in a to packed unsigned 16-bit integers with unsigned saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtusepi32_epi8 Convert packed unsigned 32-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtusepi32_storeu_epi16 Convert packed unsigned 32-bit integers in a to packed unsigned 16-bit integers with unsigned saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm_mask_cvtusepi32_storeu_epi8 Convert packed unsigned 32-bit integers in a to packed 8-bit integers with unsigned saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm_mask_cvtusepi64_epi16 Convert packed unsigned 64-bit integers in a to packed unsigned 16-bit integers with unsigned saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtusepi64_epi32 Convert packed unsigned 64-bit integers in a to packed unsigned 32-bit integers with unsigned saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtusepi64_epi8 Convert packed unsigned 64-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_cvtusepi64_storeu_epi16 Convert packed unsigned 64-bit integers in a to packed 16-bit integers with unsigned saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm_mask_cvtusepi64_storeu_epi32 Convert packed unsigned 64-bit integers in a to packed 32-bit integers with unsigned saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm_mask_cvtusepi64_storeu_epi8 Convert packed unsigned 64-bit integers in a to packed 8-bit integers with unsigned saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
_mm_mask_div_pd Divide packed double-precision (64-bit) floating-point elements in a by packed elements in b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_div_ps Divide packed single-precision (32-bit) floating-point elements in a by packed elements in b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_div_round_sd Divide the lower double-precision (64-bit) floating-point element in a by the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.\
_mm_mask_div_round_ss Divide the lower single-precision (32-bit) floating-point element in a by the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_mask_div_sd Divide the lower double-precision (64-bit) floating-point element in a by the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_div_ss Divide the lower single-precision (32-bit) floating-point element in a by the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_expand_epi32 Load contiguous active 32-bit integers from a (those with their respective bit set in mask k), and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_expand_epi64 Load contiguous active 64-bit integers from a (those with their respective bit set in mask k), and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_expand_pd Load contiguous active double-precision (64-bit) floating-point elements from a (those with their respective bit set in mask k), and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_expand_ps Load contiguous active single-precision (32-bit) floating-point elements from a (those with their respective bit set in mask k), and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_expandloadu_epi32 Load contiguous active 32-bit integers from unaligned memory at mem_addr (those with their respective bit set in mask k), and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_expandloadu_epi64 Load contiguous active 64-bit integers from unaligned memory at mem_addr (those with their respective bit set in mask k), and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_expandloadu_pd Load contiguous active double-precision (64-bit) floating-point elements from unaligned memory at mem_addr (those with their respective bit set in mask k), and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_expandloadu_ps Load contiguous active single-precision (32-bit) floating-point elements from unaligned memory at mem_addr (those with their respective bit set in mask k), and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_fixupimm_pd Fix up packed double-precision (64-bit) floating-point elements in a and b using packed 64-bit integers in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). imm8 is used to set the required flags reporting.
_mm_mask_fixupimm_ps Fix up packed single-precision (32-bit) floating-point elements in a and b using packed 32-bit integers in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). imm8 is used to set the required flags reporting.
_mm_mask_fixupimm_round_sd Fix up the lower double-precision (64-bit) floating-point elements in a and b using the lower 64-bit integer in c, store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper element from b to the upper element of dst. imm8 is used to set the required flags reporting.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mask_fixupimm_round_ss Fix up the lower single-precision (32-bit) floating-point elements in a and b using the lower 32-bit integer in c, store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper 3 packed elements from b to the upper elements of dst. imm8 is used to set the required flags reporting.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mask_fixupimm_sd Fix up the lower double-precision (64-bit) floating-point elements in a and b using the lower 64-bit integer in c, store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper element from b to the upper element of dst. imm8 is used to set the required flags reporting.
_mm_mask_fixupimm_ss Fix up the lower single-precision (32-bit) floating-point elements in a and b using the lower 32-bit integer in c, store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper 3 packed elements from b to the upper elements of dst. imm8 is used to set the required flags reporting.
_mm_mask_fmadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm_mask_fmadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm_mask_fmadd_round_sd Multiply the lower double-precision (64-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.\
_mm_mask_fmadd_round_ss Multiply the lower single-precision (32-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_mask_fmadd_sd Multiply the lower double-precision (64-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_fmadd_ss Multiply the lower single-precision (32-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_fmaddsub_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm_mask_fmaddsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm_mask_fmsub_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm_mask_fmsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm_mask_fmsub_round_sd Multiply the lower double-precision (64-bit) floating-point elements in a and b, and subtract the lower element in c from the intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.\
_mm_mask_fmsub_round_ss Multiply the lower single-precision (32-bit) floating-point elements in a and b, and subtract the lower element in c from the intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_mask_fmsub_sd Multiply the lower double-precision (64-bit) floating-point elements in a and b, and subtract the lower element in c from the intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_fmsub_ss Multiply the lower single-precision (32-bit) floating-point elements in a and b, and subtract the lower element in c from the intermediate result. Store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_fmsubadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm_mask_fmsubadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm_mask_fnmadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm_mask_fnmadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm_mask_fnmadd_round_sd Multiply the lower double-precision (64-bit) floating-point elements in a and b, and add the negated intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.\
_mm_mask_fnmadd_round_ss Multiply the lower single-precision (32-bit) floating-point elements in a and b, and add the negated intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_mask_fnmadd_sd Multiply the lower double-precision (64-bit) floating-point elements in a and b, and add the negated intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_fnmadd_ss Multiply the lower single-precision (32-bit) floating-point elements in a and b, and add the negated intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_fnmsub_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm_mask_fnmsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm_mask_fnmsub_round_sd Multiply the lower double-precision (64-bit) floating-point elements in a and b, and subtract the lower element in c from the negated intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.\
_mm_mask_fnmsub_round_ss Multiply the lower single-precision (32-bit) floating-point elements in a and b, and subtract the lower element in c from the negated intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_mask_fnmsub_sd Multiply the lower double-precision (64-bit) floating-point elements in a and b, and subtract the lower element in c from the negated intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_fnmsub_ss Multiply the lower single-precision (32-bit) floating-point elements in a and b, and subtract the lower element in c from the negated intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_getexp_pd Convert the exponent of each packed double-precision (64-bit) floating-point element in a to a double-precision (64-bit) floating-point number representing the integer exponent, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). This intrinsic essentially calculates floor(log2(x)) for each element.
_mm_mask_getexp_ps Convert the exponent of each packed single-precision (32-bit) floating-point element in a to a single-precision (32-bit) floating-point number representing the integer exponent, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). This intrinsic essentially calculates floor(log2(x)) for each element.
_mm_mask_getexp_round_sd Convert the exponent of the lower double-precision (64-bit) floating-point element in b to a double-precision (64-bit) floating-point number representing the integer exponent, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. This intrinsic essentially calculates floor(log2(x)) for the lower element.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mask_getexp_round_ss Convert the exponent of the lower single-precision (32-bit) floating-point element in b to a single-precision (32-bit) floating-point number representing the integer exponent, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. This intrinsic essentially calculates floor(log2(x)) for the lower element.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mask_getexp_sd Convert the exponent of the lower double-precision (64-bit) floating-point element in b to a double-precision (64-bit) floating-point number representing the integer exponent, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. This intrinsic essentially calculates floor(log2(x)) for the lower element.
_mm_mask_getexp_ss Convert the exponent of the lower single-precision (32-bit) floating-point element in b to a single-precision (32-bit) floating-point number representing the integer exponent, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. This intrinsic essentially calculates floor(log2(x)) for the lower element.
_mm_mask_getmant_pd Normalize the mantissas of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
_mm_mask_getmant_ps Normalize the mantissas of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
_mm_mask_getmant_round_sd Normalize the mantissas of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mask_getmant_round_ss Normalize the mantissas of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mask_getmant_sd Normalize the mantissas of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mask_getmant_ss Normalize the mantissas of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mask_i32scatter_epi32 Stores 4 32-bit integer elements from a to memory starting at location base_addr at packed 32-bit integer indices stored in vindex scaled by scale using writemask k (elements whose corresponding mask bit is not set are not written to memory).
_mm_mask_i32scatter_epi64 Stores 2 64-bit integer elements from a to memory starting at location base_addr at packed 32-bit integer indices stored in vindex scaled by scale using writemask k (elements whose corresponding mask bit is not set are not written to memory).
_mm_mask_i32scatter_pd Stores 2 double-precision (64-bit) floating-point elements from a to memory starting at location base_addr at packed 32-bit integer indices stored in vindex scaled by scale using writemask k (elements whose corresponding mask bit is not set are not written to memory).
_mm_mask_i32scatter_ps Stores 4 single-precision (32-bit) floating-point elements from a to memory starting at location base_addr at packed 32-bit integer indices stored in vindex scaled by scale using writemask k (elements whose corresponding mask bit is not set are not written to memory).
_mm_mask_i64scatter_epi32 Stores 2 32-bit integer elements from a to memory starting at location base_addr at packed 64-bit integer indices stored in vindex scaled by scale using writemask k (elements whose corresponding mask bit is not set are not written to memory).
_mm_mask_i64scatter_epi64 Stores 2 64-bit integer elements from a to memory starting at location base_addr at packed 64-bit integer indices stored in vindex scaled by scale using writemask k (elements whose corresponding mask bit is not set are not written to memory).
_mm_mask_i64scatter_pd Stores 2 double-precision (64-bit) floating-point elements from a to memory starting at location base_addr at packed 64-bit integer indices stored in vindex scaled by scale using writemask k (elements whose corresponding mask bit is not set are not written to memory).
_mm_mask_i64scatter_ps Stores 2 single-precision (32-bit) floating-point elements from a to memory starting at location base_addr at packed 64-bit integer indices stored in vindex scaled by scale using writemask k (elements whose corresponding
_mm_mask_load_epi32 Load packed 32-bit integers from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated.
_mm_mask_load_epi64 Load packed 64-bit integers from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated.
_mm_mask_load_pd Load packed double-precision (64-bit) floating-point elements from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated.
_mm_mask_load_ps Load packed single-precision (32-bit) floating-point elements from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated.
_mm_mask_load_sd Load a double-precision (64-bit) floating-point element from memory into the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and set the upper element of dst to zero. mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated.
_mm_mask_load_ss Load a single-precision (32-bit) floating-point element from memory into the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and set the upper
_mm_mask_loadu_epi32 Load packed 32-bit integers from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
_mm_mask_loadu_epi64 Load packed 64-bit integers from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
_mm_mask_loadu_pd Load packed double-precision (64-bit) floating-point elements from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
_mm_mask_loadu_ps Load packed single-precision (32-bit) floating-point elements from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
_mm_mask_max_epi32 Compare packed signed 32-bit integers in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_max_epi64 Compare packed signed 64-bit integers in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_max_epu32 Compare packed unsigned 32-bit integers in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_max_epu64 Compare packed unsigned 64-bit integers in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_max_pd Compare packed double-precision (64-bit) floating-point elements in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_max_ps Compare packed single-precision (32-bit) floating-point elements in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_max_round_sd Compare the lower double-precision (64-bit) floating-point elements in a and b, store the maximum value in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mask_max_round_ss Compare the lower single-precision (32-bit) floating-point elements in a and b, store the maximum value in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mask_max_sd Compare the lower double-precision (64-bit) floating-point elements in a and b, store the maximum value in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_max_ss Compare the lower single-precision (32-bit) floating-point elements in a and b, store the maximum value in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_min_epi32 Compare packed signed 32-bit integers in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_min_epi64 Compare packed signed 64-bit integers in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_min_epu32 Compare packed unsigned 32-bit integers in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_min_epu64 Compare packed unsigned 64-bit integers in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_min_pd Compare packed double-precision (64-bit) floating-point elements in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_min_ps Compare packed single-precision (32-bit) floating-point elements in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_min_round_sd Compare the lower double-precision (64-bit) floating-point elements in a and b, store the minimum value in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mask_min_round_ss Compare the lower single-precision (32-bit) floating-point elements in a and b, store the minimum value in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mask_min_sd Compare the lower double-precision (64-bit) floating-point elements in a and b, store the minimum value in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_min_ss Compare the lower single-precision (32-bit) floating-point elements in a and b, store the minimum value in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_mov_epi32 Move packed 32-bit integers from a to dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_mov_epi64 Move packed 64-bit integers from a to dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_mov_pd Move packed double-precision (64-bit) floating-point elements from a to dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_mov_ps Move packed single-precision (32-bit) floating-point elements from a to dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_move_sd Move the lower double-precision (64-bit) floating-point element from b to the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_move_ss Move the lower single-precision (32-bit) floating-point element from b to the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_movedup_pd Duplicate even-indexed double-precision (64-bit) floating-point elements from a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_movehdup_ps Duplicate odd-indexed single-precision (32-bit) floating-point elements from a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_moveldup_ps Duplicate even-indexed single-precision (32-bit) floating-point elements from a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_mul_epi32 Multiply the low signed 32-bit integers from each packed 64-bit element in a and b, and store the signed 64-bit results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_mul_epu32 Multiply the low unsigned 32-bit integers from each packed 64-bit element in a and b, and store the unsigned 64-bit results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_mul_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_mul_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_mul_round_sd Multiply the lower double-precision (64-bit) floating-point element in a and b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.\
_mm_mask_mul_round_ss Multiply the lower single-precision (32-bit) floating-point element in a and b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_mask_mul_sd Multiply the lower double-precision (64-bit) floating-point element in a and b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_mul_ss Multiply the lower single-precision (32-bit) floating-point element in a and b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_mullo_epi32 Multiply the packed 32-bit integers in a and b, producing intermediate 64-bit integers, and store the low 32 bits of the intermediate integers in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_or_epi32 Compute the bitwise OR of packed 32-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_or_epi64 Compute the bitwise OR of packed 64-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_permute_pd Shuffle double-precision (64-bit) floating-point elements in a within 128-bit lanes using the control in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_permute_ps Shuffle single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_permutevar_pd Shuffle double-precision (64-bit) floating-point elements in a within 128-bit lanes using the control in b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_permutevar_ps Shuffle single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_permutex2var_epi32 Shuffle 32-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm_mask_permutex2var_epi64 Shuffle 64-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm_mask_permutex2var_pd Shuffle double-precision (64-bit) floating-point elements in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm_mask_permutex2var_ps Shuffle single-precision (32-bit) floating-point elements in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
_mm_mask_rcp14_pd Compute the approximate reciprocal of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14.
_mm_mask_rcp14_ps Compute the approximate reciprocal of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14.
_mm_mask_rcp14_sd Compute the approximate reciprocal of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. The maximum relative error for this approximation is less than 2^-14.
_mm_mask_rcp14_ss Compute the approximate reciprocal of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. The maximum relative error for this approximation is less than 2^-14.
_mm_mask_rol_epi32 Rotate the bits in each packed 32-bit integer in a to the left by the number of bits specified in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_rol_epi64 Rotate the bits in each packed 64-bit integer in a to the left by the number of bits specified in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_rolv_epi32 Rotate the bits in each packed 32-bit integer in a to the left by the number of bits specified in the corresponding element of b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_rolv_epi64 Rotate the bits in each packed 64-bit integer in a to the left by the number of bits specified in the corresponding element of b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_ror_epi32 Rotate the bits in each packed 32-bit integer in a to the right by the number of bits specified in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_ror_epi64 Rotate the bits in each packed 64-bit integer in a to the right by the number of bits specified in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_rorv_epi32 Rotate the bits in each packed 32-bit integer in a to the right by the number of bits specified in the corresponding element of b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_rorv_epi64 Rotate the bits in each packed 64-bit integer in a to the right by the number of bits specified in the corresponding element of b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_roundscale_pd Round packed double-precision (64-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm_mask_roundscale_ps Round packed single-precision (32-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm_mask_roundscale_round_sd Round the lower double-precision (64-bit) floating-point element in b to the number of fraction bits specified by imm8, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm_mask_roundscale_round_ss Round the lower single-precision (32-bit) floating-point element in b to the number of fraction bits specified by imm8, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm_mask_roundscale_sd Round the lower double-precision (64-bit) floating-point element in b to the number of fraction bits specified by imm8, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm_mask_roundscale_ss Round the lower single-precision (32-bit) floating-point element in b to the number of fraction bits specified by imm8, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm_mask_rsqrt14_pd Compute the approximate reciprocal square root of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14.
_mm_mask_rsqrt14_ps Compute the approximate reciprocal square root of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14.
_mm_mask_rsqrt14_sd Compute the approximate reciprocal square root of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. The maximum relative error for this approximation is less than 2^-14.
_mm_mask_rsqrt14_ss Compute the approximate reciprocal square root of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. The maximum relative error for this approximation is less than 2^-14.
_mm_mask_scalef_pd Scale the packed double-precision (64-bit) floating-point elements in a using values from b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_scalef_ps Scale the packed single-precision (32-bit) floating-point elements in a using values from b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_scalef_round_sd Scale the packed double-precision (64-bit) floating-point elements in a using values from b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.\
_mm_mask_scalef_round_ss Scale the packed single-precision (32-bit) floating-point elements in a using values from b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_mask_scalef_sd Scale the packed double-precision (64-bit) floating-point elements in a using values from b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_scalef_ss Scale the packed single-precision (32-bit) floating-point elements in a using values from b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_set1_epi32 Broadcast 32-bit integer a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_set1_epi64 Broadcast 64-bit integer a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_shuffle_epi32 Shuffle 32-bit integers in a within 128-bit lanes using the control in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_shuffle_pd Shuffle double-precision (64-bit) floating-point elements within 128-bit lanes using the control in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_shuffle_ps Shuffle single-precision (32-bit) floating-point elements in a using the control in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_sll_epi32 Shift packed 32-bit integers in a left by count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_sll_epi64 Shift packed 64-bit integers in a left by count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_slli_epi32 Shift packed 32-bit integers in a left by imm8 while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_slli_epi64 Shift packed 64-bit integers in a left by imm8 while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_sllv_epi32 Shift packed 32-bit integers in a left by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_sllv_epi64 Shift packed 64-bit integers in a left by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_sqrt_pd Compute the square root of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_sqrt_ps Compute the square root of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_sqrt_round_sd Compute the square root of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.\
_mm_mask_sqrt_round_ss Compute the square root of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_mask_sqrt_sd Compute the square root of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_sqrt_ss Compute the square root of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_sra_epi32 Shift packed 32-bit integers in a right by count while shifting in sign bits, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_sra_epi64 Shift packed 64-bit integers in a right by count while shifting in sign bits, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_srai_epi32 Shift packed 32-bit integers in a right by imm8 while shifting in sign bits, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_srai_epi64 Shift packed 64-bit integers in a right by imm8 while shifting in sign bits, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_srav_epi32 Shift packed 32-bit integers in a right by the amount specified by the corresponding element in count while shifting in sign bits, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_srav_epi64 Shift packed 64-bit integers in a right by the amount specified by the corresponding element in count while shifting in sign bits, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_srl_epi32 Shift packed 32-bit integers in a right by count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_srl_epi64 Shift packed 64-bit integers in a right by count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_srli_epi32 Shift packed 32-bit integers in a right by imm8 while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_srli_epi64 Shift packed 64-bit integers in a right by imm8 while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_srlv_epi32 Shift packed 32-bit integers in a right by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_srlv_epi64 Shift packed 64-bit integers in a right by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_store_epi32 Store packed 32-bit integers from a into memory using writemask k. mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated.
_mm_mask_store_epi64 Store packed 64-bit integers from a into memory using writemask k. mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated.
_mm_mask_store_pd Store packed double-precision (64-bit) floating-point elements from a into memory using writemask k. mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated.
_mm_mask_store_ps Store packed single-precision (32-bit) floating-point elements from a into memory using writemask k. mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated.
_mm_mask_store_sd Store a double-precision (64-bit) floating-point element from a into memory using writemask k. mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated.
_mm_mask_store_ss Store a single-precision (32-bit) floating-point element from a into memory using writemask k. mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated.
_mm_mask_storeu_epi32 Store packed 32-bit integers from a into memory using writemask k. mem_addr does not need to be aligned on any particular boundary.
_mm_mask_storeu_epi64 Store packed 64-bit integers from a into memory using writemask k. mem_addr does not need to be aligned on any particular boundary.
_mm_mask_storeu_pd Store packed double-precision (64-bit) floating-point elements from a into memory using writemask k. mem_addr does not need to be aligned on any particular boundary.
_mm_mask_storeu_ps Store packed single-precision (32-bit) floating-point elements from a into memory using writemask k. mem_addr does not need to be aligned on any particular boundary.
_mm_mask_sub_epi32 Subtract packed 32-bit integers in b from packed 32-bit integers in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_sub_epi64 Subtract packed 64-bit integers in b from packed 64-bit integers in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_sub_pd Subtract packed double-precision (64-bit) floating-point elements in b from packed double-precision (64-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_sub_ps Subtract packed single-precision (32-bit) floating-point elements in b from packed single-precision (32-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_sub_round_sd Subtract the lower double-precision (64-bit) floating-point element in b from the lower double-precision (64-bit) floating-point element in a, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.\
_mm_mask_sub_round_ss Subtract the lower single-precision (32-bit) floating-point element in b from the lower single-precision (32-bit) floating-point element in a, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_mask_sub_sd Subtract the lower double-precision (64-bit) floating-point element in b from the lower double-precision (64-bit) floating-point element in a, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_sub_ss Subtract the lower single-precision (32-bit) floating-point element in b from the lower single-precision (32-bit) floating-point element in a, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_ternarylogic_epi32 Bitwise ternary logic that provides the capability to implement any three-operand binary function; the specific binary function is specified by value in imm8. For each bit in each packed 32-bit integer, the corresponding bit from src, a, and b are used to form a 3 bit index into imm8, and the value at that bit in imm8 is written to the corresponding bit in dst using writemask k at 32-bit granularity (32-bit elements are copied from src when the corresponding mask bit is not set).
_mm_mask_ternarylogic_epi64 Bitwise ternary logic that provides the capability to implement any three-operand binary function; the specific binary function is specified by value in imm8. For each bit in each packed 64-bit integer, the corresponding bit from src, a, and b are used to form a 3 bit index into imm8, and the value at that bit in imm8 is written to the corresponding bit in dst using writemask k at 64-bit granularity (64-bit elements are copied from src when the corresponding mask bit is not set).
_mm_mask_test_epi32_mask Compute the bitwise AND of packed 32-bit integers in a and b, producing intermediate 32-bit values, and set the corresponding bit in result mask k (subject to writemask k) if the intermediate value is non-zero.
_mm_mask_test_epi64_mask Compute the bitwise AND of packed 64-bit integers in a and b, producing intermediate 64-bit values, and set the corresponding bit in result mask k (subject to writemask k) if the intermediate value is non-zero.
_mm_mask_testn_epi32_mask Compute the bitwise NAND of packed 32-bit integers in a and b, producing intermediate 32-bit values, and set the corresponding bit in result mask k (subject to writemask k) if the intermediate value is zero.
_mm_mask_testn_epi64_mask Compute the bitwise NAND of packed 64-bit integers in a and b, producing intermediate 64-bit values, and set the corresponding bit in result mask k (subject to writemask k) if the intermediate value is zero.
_mm_mask_unpackhi_epi32 Unpack and interleave 32-bit integers from the high half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_unpackhi_epi64 Unpack and interleave 64-bit integers from the high half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_unpackhi_pd Unpack and interleave double-precision (64-bit) floating-point elements from the high half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_unpackhi_ps Unpack and interleave single-precision (32-bit) floating-point elements from the high half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_unpacklo_epi32 Unpack and interleave 32-bit integers from the low half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_unpacklo_epi64 Unpack and interleave 64-bit integers from the low half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_unpacklo_pd Unpack and interleave double-precision (64-bit) floating-point elements from the low half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_unpacklo_ps Unpack and interleave single-precision (32-bit) floating-point elements from the low half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_xor_epi32 Compute the bitwise XOR of packed 32-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mask_xor_epi64 Compute the bitwise XOR of packed 64-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_maskz_abs_epi32 Compute the absolute value of packed signed 32-bit integers in a, and store the unsigned results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_abs_epi64 Compute the absolute value of packed signed 64-bit integers in a, and store the unsigned results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_add_epi32 Add packed 32-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_add_epi64 Add packed 64-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_add_pd Add packed double-precision (64-bit) floating-point elements in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_add_ps Add packed single-precision (32-bit) floating-point elements in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_add_round_sd Add the lower double-precision (64-bit) floating-point element in a and b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.\
_mm_maskz_add_round_ss Add the lower single-precision (32-bit) floating-point element in a and b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_maskz_add_sd Add the lower double-precision (64-bit) floating-point element in a and b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_add_ss Add the lower single-precision (32-bit) floating-point element in a and b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_alignr_epi32 Concatenate a and b into a 32-byte immediate result, shift the result right by imm8 32-bit elements, and store the low 16 bytes (4 elements) in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_alignr_epi64 Concatenate a and b into a 32-byte immediate result, shift the result right by imm8 64-bit elements, and store the low 16 bytes (2 elements) in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_and_epi32 Compute the bitwise AND of packed 32-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_and_epi64 Compute the bitwise AND of packed 64-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_andnot_epi32 Compute the bitwise NOT of packed 32-bit integers in a and then AND with b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_andnot_epi64 Compute the bitwise NOT of packed 64-bit integers in a and then AND with b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_broadcastd_epi32 Broadcast the low packed 32-bit integer from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_broadcastq_epi64 Broadcast the low packed 64-bit integer from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_broadcastss_ps Broadcast the low single-precision (32-bit) floating-point element from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_compress_epi32 Contiguously store the active 32-bit integers in a (those with their respective bit set in zeromask k) to dst, and set the remaining elements to zero.
_mm_maskz_compress_epi64 Contiguously store the active 64-bit integers in a (those with their respective bit set in zeromask k) to dst, and set the remaining elements to zero.
_mm_maskz_compress_pd Contiguously store the active double-precision (64-bit) floating-point elements in a (those with their respective bit set in zeromask k) to dst, and set the remaining elements to zero.
_mm_maskz_compress_ps Contiguously store the active single-precision (32-bit) floating-point elements in a (those with their respective bit set in zeromask k) to dst, and set the remaining elements to zero.
_mm_maskz_cvt_roundps_ph Convert packed single-precision (32-bit) floating-point elements in a to packed half-precision (16-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm_maskz_cvt_roundsd_ss Convert the lower double-precision (64-bit) floating-point element in b to a single-precision (32-bit) floating-point element, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
Rounding is done according to the rounding[3:0] parameter, which can be one of:\
_mm_maskz_cvt_roundss_sd Convert the lower single-precision (32-bit) floating-point element in b to a double-precision (64-bit) floating-point element, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_maskz_cvtepi16_epi32 Sign extend packed 16-bit integers in a to packed 32-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtepi16_epi64 Sign extend packed 16-bit integers in a to packed 64-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtepi32_epi16 Convert packed 32-bit integers in a to packed 16-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtepi32_epi64 Sign extend packed 32-bit integers in a to packed 64-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtepi32_epi8 Convert packed 32-bit integers in a to packed 8-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtepi32_pd Convert packed signed 32-bit integers in a to packed double-precision (64-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtepi32_ps Convert packed signed 32-bit integers in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtepi64_epi16 Convert packed 64-bit integers in a to packed 16-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtepi64_epi32 Convert packed 64-bit integers in a to packed 32-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtepi64_epi8 Convert packed 64-bit integers in a to packed 8-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtepi8_epi32 Sign extend packed 8-bit integers in a to packed 32-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtepi8_epi64 Sign extend packed 8-bit integers in the low 2 bytes of a to packed 64-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtepu16_epi32 Zero extend packed unsigned 16-bit integers in a to packed 32-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtepu16_epi64 Zero extend packed unsigned 16-bit integers in the low 4 bytes of a to packed 64-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtepu32_epi64 Zero extend packed unsigned 32-bit integers in a to packed 64-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtepu32_pd Convert packed unsigned 32-bit integers in a to packed double-precision (64-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtepu8_epi32 Zero extend packed unsigned 8-bit integers in th elow 4 bytes of a to packed 32-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtepu8_epi64 Zero extend packed unsigned 8-bit integers in the low 2 bytes of a to packed 64-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtpd_epi32 Convert packed double-precision (64-bit) floating-point elements in a to packed 32-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtpd_epu32 Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtpd_ps Convert packed double-precision (64-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtph_ps Convert packed half-precision (16-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtps_epi32 Convert packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtps_epu32 Convert packed single-precision (32-bit) floating-point elements in a to packed unsigned 32-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtps_ph Convert packed single-precision (32-bit) floating-point elements in a to packed half-precision (16-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm_maskz_cvtsd_ss Convert the lower double-precision (64-bit) floating-point element in b to a single-precision (32-bit) floating-point element, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_cvtsepi32_epi16 Convert packed signed 32-bit integers in a to packed 16-bit integers with signed saturation, and store the results in dst.
_mm_maskz_cvtsepi32_epi8 Convert packed signed 32-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtsepi64_epi16 Convert packed signed 64-bit integers in a to packed 16-bit integers with signed saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtsepi64_epi32 Convert packed signed 64-bit integers in a to packed 32-bit integers with signed saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtsepi64_epi8 Convert packed signed 64-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtss_sd Convert the lower single-precision (32-bit) floating-point element in b to a double-precision (64-bit) floating-point element, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_cvttpd_epi32 Convert packed double-precision (64-bit) floating-point elements in a to packed 32-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvttpd_epu32 Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvttps_epi32 Convert packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvttps_epu32 Convert packed double-precision (32-bit) floating-point elements in a to packed unsigned 32-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtusepi32_epi16 Convert packed unsigned 32-bit integers in a to packed unsigned 16-bit integers with unsigned saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtusepi32_epi8 Convert packed unsigned 32-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtusepi64_epi16 Convert packed unsigned 64-bit integers in a to packed unsigned 16-bit integers with unsigned saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtusepi64_epi32 Convert packed unsigned 64-bit integers in a to packed unsigned 32-bit integers with unsigned saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_cvtusepi64_epi8 Convert packed unsigned 64-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_div_pd Divide packed double-precision (64-bit) floating-point elements in a by packed elements in b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_div_ps Divide packed single-precision (32-bit) floating-point elements in a by packed elements in b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_div_round_sd Divide the lower double-precision (64-bit) floating-point element in a by the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.\
_mm_maskz_div_round_ss Divide the lower single-precision (32-bit) floating-point element in a by the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_maskz_div_sd Divide the lower double-precision (64-bit) floating-point element in a by the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_div_ss Divide the lower single-precision (32-bit) floating-point element in a by the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_expand_epi32 Load contiguous active 32-bit integers from a (those with their respective bit set in mask k), and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_expand_epi64 Load contiguous active 64-bit integers from a (those with their respective bit set in mask k), and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_expand_pd Load contiguous active double-precision (64-bit) floating-point elements from a (those with their respective bit set in mask k), and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_expand_ps Load contiguous active single-precision (32-bit) floating-point elements from a (those with their respective bit set in mask k), and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_expandloadu_epi32 Load contiguous active 32-bit integers from unaligned memory at mem_addr (those with their respective bit set in mask k), and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_expandloadu_epi64 Load contiguous active 64-bit integers from unaligned memory at mem_addr (those with their respective bit set in mask k), and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_expandloadu_pd Load contiguous active double-precision (64-bit) floating-point elements from unaligned memory at mem_addr (those with their respective bit set in mask k), and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_expandloadu_ps Load contiguous active single-precision (32-bit) floating-point elements from unaligned memory at mem_addr (those with their respective bit set in mask k), and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_fixupimm_pd Fix up packed double-precision (64-bit) floating-point elements in a and b using packed 64-bit integers in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). imm8 is used to set the required flags reporting.
_mm_maskz_fixupimm_ps Fix up packed single-precision (32-bit) floating-point elements in a and b using packed 32-bit integers in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). imm8 is used to set the required flags reporting.
_mm_maskz_fixupimm_round_sd Fix up the lower double-precision (64-bit) floating-point elements in a and b using the lower 64-bit integer in c, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from b to the upper element of dst. imm8 is used to set the required flags reporting.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_maskz_fixupimm_round_ss Fix up the lower single-precision (32-bit) floating-point elements in a and b using the lower 32-bit integer in c, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from b to the upper elements of dst. imm8 is used to set the required flags reporting.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_maskz_fixupimm_sd Fix up the lower double-precision (64-bit) floating-point elements in a and b using the lower 64-bit integer in c, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from b to the upper element of dst. imm8 is used to set the required flags reporting.
_mm_maskz_fixupimm_ss Fix up the lower single-precision (32-bit) floating-point elements in a and b using the lower 32-bit integer in c, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from b to the upper elements of dst. imm8 is used to set the required flags reporting.
_mm_maskz_fmadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_fmadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_fmadd_round_sd Multiply the lower double-precision (64-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.\
_mm_maskz_fmadd_round_ss Multiply the lower single-precision (32-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_maskz_fmadd_sd Multiply the lower double-precision (64-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_fmadd_ss Multiply the lower single-precision (32-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_fmaddsub_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_fmaddsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_fmsub_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_fmsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_fmsub_round_sd Multiply the lower double-precision (64-bit) floating-point elements in a and b, and subtract the lower element in c from the intermediate result. Store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.\
_mm_maskz_fmsub_round_ss Multiply the lower single-precision (32-bit) floating-point elements in a and b, and subtract the lower element in c from the intermediate result. Store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_maskz_fmsub_sd Multiply the lower double-precision (64-bit) floating-point elements in a and b, and subtract the lower element in c from the intermediate result. Store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_fmsub_ss Multiply the lower single-precision (32-bit) floating-point elements in a and b, and subtract the lower element in c from the intermediate result. Store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_fmsubadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_fmsubadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_fnmadd_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_fnmadd_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_fnmadd_round_sd Multiply the lower double-precision (64-bit) floating-point elements in a and b, and add the negated intermediate result to the lower element in c. Store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.\
_mm_maskz_fnmadd_round_ss Multiply the lower single-precision (32-bit) floating-point elements in a and b, and add the negated intermediate result to the lower element in c. Store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_maskz_fnmadd_sd Multiply the lower double-precision (64-bit) floating-point elements in a and b, and add the negated intermediate result to the lower element in c. Store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_fnmadd_ss Multiply the lower single-precision (32-bit) floating-point elements in a and b, and add the negated intermediate result to the lower element in c. Store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_fnmsub_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_fnmsub_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_fnmsub_round_sd Multiply the lower double-precision (64-bit) floating-point elements in a and b, and subtract the lower element in c from the negated intermediate result. Store the result in dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.\
_mm_maskz_fnmsub_round_ss Multiply the lower single-precision (32-bit) floating-point elements in a and b, and subtract the lower element in c from the negated intermediate result. Store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_maskz_fnmsub_sd Multiply the lower double-precision (64-bit) floating-point elements in a and b, and subtract the lower element in c from the negated intermediate result. Store the result in dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_fnmsub_ss Multiply the lower single-precision (32-bit) floating-point elements in a and b, and subtract the lower element in c from the negated intermediate result. Store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_getexp_pd Convert the exponent of each packed double-precision (64-bit) floating-point element in a to a double-precision (64-bit) floating-point number representing the integer exponent, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). This intrinsic essentially calculates floor(log2(x)) for each element.
_mm_maskz_getexp_ps Convert the exponent of each packed single-precision (32-bit) floating-point element in a to a single-precision (32-bit) floating-point number representing the integer exponent, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). This intrinsic essentially calculates floor(log2(x)) for each element.
_mm_maskz_getexp_round_sd Convert the exponent of the lower double-precision (64-bit) floating-point element in b to a double-precision (64-bit) floating-point number representing the integer exponent, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. This intrinsic essentially calculates floor(log2(x)) for the lower element.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_maskz_getexp_round_ss Convert the exponent of the lower single-precision (32-bit) floating-point element in b to a single-precision (32-bit) floating-point number representing the integer exponent, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. This intrinsic essentially calculates floor(log2(x)) for the lower element.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_maskz_getexp_sd Convert the exponent of the lower double-precision (64-bit) floating-point element in b to a double-precision (64-bit) floating-point number representing the integer exponent, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. This intrinsic essentially calculates floor(log2(x)) for the lower element.
_mm_maskz_getexp_ss Convert the exponent of the lower single-precision (32-bit) floating-point element in b to a single-precision (32-bit) floating-point number representing the integer exponent, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. This intrinsic essentially calculates floor(log2(x)) for the lower element.
_mm_maskz_getmant_pd Normalize the mantissas of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
_mm_maskz_getmant_ps Normalize the mantissas of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
_mm_maskz_getmant_round_sd Normalize the mantissas of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_maskz_getmant_round_ss Normalize the mantissas of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_maskz_getmant_sd Normalize the mantissas of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_maskz_getmant_ss Normalize the mantissas of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign.
The mantissa is normalized to the interval specified by interv, which can take the following values:
_MM_MANT_NORM_1_2 // interval [1, 2)
_MM_MANT_NORM_p5_2 // interval [0.5, 2)
_MM_MANT_NORM_p5_1 // interval [0.5, 1)
_MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5)
The sign is determined by sc which can take the following values:
_MM_MANT_SIGN_src // sign = sign(src)
_MM_MANT_SIGN_zero // sign = 0
_MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_maskz_load_epi32 Load packed 32-bit integers from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated.
_mm_maskz_load_epi64 Load packed 64-bit integers from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated.
_mm_maskz_load_pd Load packed double-precision (64-bit) floating-point elements from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated.
_mm_maskz_load_ps Load packed single-precision (32-bit) floating-point elements from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated.
_mm_maskz_load_sd Load a double-precision (64-bit) floating-point element from memory into the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and set the upper element of dst to zero. mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated.
_mm_maskz_load_ss Load a single-precision (32-bit) floating-point element from memory into the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and set the upper 3 packed elements of dst to zero. mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated.
_mm_maskz_loadu_epi32 Load packed 32-bit integers from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
_mm_maskz_loadu_epi64 Load packed 64-bit integers from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
_mm_maskz_loadu_pd Load packed double-precision (64-bit) floating-point elements from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
_mm_maskz_loadu_ps Load packed single-precision (32-bit) floating-point elements from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
_mm_maskz_max_epi32 Compare packed signed 32-bit integers in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_max_epi64 Compare packed signed 64-bit integers in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_max_epu32 Compare packed unsigned 32-bit integers in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_max_epu64 Compare packed unsigned 64-bit integers in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_max_pd Compare packed double-precision (64-bit) floating-point elements in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_max_ps Compare packed single-precision (32-bit) floating-point elements in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_max_round_sd Compare the lower double-precision (64-bit) floating-point elements in a and b, store the maximum value in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_maskz_max_round_ss Compare the lower single-precision (32-bit) floating-point elements in a and b, store the maximum value in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_maskz_max_sd Compare the lower double-precision (64-bit) floating-point elements in a and b, store the maximum value in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_max_ss Compare the lower single-precision (32-bit) floating-point elements in a and b, store the maximum value in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_min_epi32 Compare packed signed 32-bit integers in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_min_epi64 Compare packed signed 64-bit integers in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_min_epu32 Compare packed unsigned 32-bit integers in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_min_epu64 Compare packed unsigned 64-bit integers in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_min_pd Compare packed double-precision (64-bit) floating-point elements in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_min_ps Compare packed single-precision (32-bit) floating-point elements in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_min_round_sd Compare the lower double-precision (64-bit) floating-point elements in a and b, store the minimum value in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_maskz_min_round_ss Compare the lower single-precision (32-bit) floating-point elements in a and b, store the minimum value in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_maskz_min_sd Compare the lower double-precision (64-bit) floating-point elements in a and b, store the minimum value in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_min_ss Compare the lower single-precision (32-bit) floating-point elements in a and b, store the minimum value in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_mov_epi32 Move packed 32-bit integers from a into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_mov_epi64 Move packed 64-bit integers from a into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_mov_pd Move packed double-precision (64-bit) floating-point elements from a into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_mov_ps Move packed single-precision (32-bit) floating-point elements from a into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_move_sd Move the lower double-precision (64-bit) floating-point element from b to the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_move_ss Move the lower single-precision (32-bit) floating-point element from b to the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_movedup_pd Duplicate even-indexed double-precision (64-bit) floating-point elements from a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_movehdup_ps Duplicate odd-indexed single-precision (32-bit) floating-point elements from a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_moveldup_ps Duplicate even-indexed single-precision (32-bit) floating-point elements from a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_mul_epi32 Multiply the low signed 32-bit integers from each packed 64-bit element in a and b, and store the signed 64-bit results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_mul_epu32 Multiply the low unsigned 32-bit integers from each packed 64-bit element in a and b, and store the unsigned 64-bit results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_mul_pd Multiply packed double-precision (64-bit) floating-point elements in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_mul_ps Multiply packed single-precision (32-bit) floating-point elements in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_mul_round_sd Multiply the lower double-precision (64-bit) floating-point element in a and b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.\
_mm_maskz_mul_round_ss Multiply the lower single-precision (32-bit) floating-point element in a and b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_maskz_mul_sd Multiply the lower double-precision (64-bit) floating-point element in a and b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_mul_ss Multiply the lower single-precision (32-bit) floating-point element in a and b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_mullo_epi32 Multiply the packed 32-bit integers in a and b, producing intermediate 64-bit integers, and store the low 32 bits of the intermediate integers in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_or_epi32 Compute the bitwise OR of packed 32-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_or_epi64 Compute the bitwise OR of packed 64-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_permute_pd Shuffle double-precision (64-bit) floating-point elements in a within 128-bit lanes using the control in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_permute_ps Shuffle single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_permutevar_pd Shuffle double-precision (64-bit) floating-point elements in a within 128-bit lanes using the control in b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_permutevar_ps Shuffle single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_permutex2var_epi32 Shuffle 32-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_permutex2var_epi64 Shuffle 64-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_permutex2var_pd Shuffle double-precision (64-bit) floating-point elements in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_permutex2var_ps Shuffle single-precision (32-bit) floating-point elements in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_rcp14_pd Compute the approximate reciprocal of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14.
_mm_maskz_rcp14_ps Compute the approximate reciprocal of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14.
_mm_maskz_rcp14_sd Compute the approximate reciprocal of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. The maximum relative error for this approximation is less than 2^-14.
_mm_maskz_rcp14_ss Compute the approximate reciprocal of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. The maximum relative error for this approximation is less than 2^-14.
_mm_maskz_rol_epi32 Rotate the bits in each packed 32-bit integer in a to the left by the number of bits specified in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_rol_epi64 Rotate the bits in each packed 64-bit integer in a to the left by the number of bits specified in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_rolv_epi32 Rotate the bits in each packed 32-bit integer in a to the left by the number of bits specified in the corresponding element of b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_rolv_epi64 Rotate the bits in each packed 64-bit integer in a to the left by the number of bits specified in the corresponding element of b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_ror_epi32 Rotate the bits in each packed 32-bit integer in a to the right by the number of bits specified in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_ror_epi64 Rotate the bits in each packed 64-bit integer in a to the right by the number of bits specified in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_rorv_epi32 Rotate the bits in each packed 32-bit integer in a to the right by the number of bits specified in the corresponding element of b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_rorv_epi64 Rotate the bits in each packed 64-bit integer in a to the right by the number of bits specified in the corresponding element of b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_roundscale_pd Round packed double-precision (64-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm_maskz_roundscale_ps Round packed single-precision (32-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm_maskz_roundscale_round_sd Round the lower double-precision (64-bit) floating-point element in b to the number of fraction bits specified by imm8, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm_maskz_roundscale_round_ss Round the lower single-precision (32-bit) floating-point element in b to the number of fraction bits specified by imm8, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm_maskz_roundscale_sd Round the lower double-precision (64-bit) floating-point element in b to the number of fraction bits specified by imm8, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm_maskz_roundscale_ss Round the lower single-precision (32-bit) floating-point element in b to the number of fraction bits specified by imm8, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm_maskz_rsqrt14_pd Compute the approximate reciprocal square root of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14.
_mm_maskz_rsqrt14_ps Compute the approximate reciprocal square root of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14.
_mm_maskz_rsqrt14_sd Compute the approximate reciprocal square root of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. The maximum relative error for this approximation is less than 2^-14.
_mm_maskz_rsqrt14_ss Compute the approximate reciprocal square root of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. The maximum relative error for this approximation is less than 2^-14.
_mm_maskz_scalef_pd Scale the packed double-precision (64-bit) floating-point elements in a using values from b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_scalef_ps Scale the packed single-precision (32-bit) floating-point elements in a using values from b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_scalef_round_sd Scale the packed double-precision (64-bit) floating-point elements in a using values from b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.\
_mm_maskz_scalef_round_ss Scale the packed single-precision (32-bit) floating-point elements in a using values from b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_maskz_scalef_sd Scale the packed double-precision (64-bit) floating-point elements in a using values from b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_scalef_ss Scale the packed single-precision (32-bit) floating-point elements in a using values from b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_set1_epi32 Broadcast 32-bit integer a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_set1_epi64 Broadcast 64-bit integer a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_shuffle_epi32 Shuffle 32-bit integers in a within 128-bit lanes using the control in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_shuffle_pd Shuffle double-precision (64-bit) floating-point elements within 128-bit lanes using the control in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_shuffle_ps Shuffle single-precision (32-bit) floating-point elements in a using the control in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_sll_epi32 Shift packed 32-bit integers in a left by count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_sll_epi64 Shift packed 64-bit integers in a left by count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_slli_epi32 Shift packed 32-bit integers in a left by imm8 while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_slli_epi64 Shift packed 64-bit integers in a left by imm8 while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_sllv_epi32 Shift packed 32-bit integers in a left by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_sllv_epi64 Shift packed 64-bit integers in a left by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_sqrt_pd Compute the square root of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_sqrt_ps Compute the square root of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_sqrt_round_sd Compute the square root of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.\
_mm_maskz_sqrt_round_ss Compute the square root of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_maskz_sqrt_sd Compute the square root of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_sqrt_ss Compute the square root of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_sra_epi32 Shift packed 32-bit integers in a right by count while shifting in sign bits, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_sra_epi64 Shift packed 64-bit integers in a right by count while shifting in sign bits, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_srai_epi32 Shift packed 32-bit integers in a right by imm8 while shifting in sign bits, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_srai_epi64 Shift packed 64-bit integers in a right by imm8 while shifting in sign bits, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_srav_epi32 Shift packed 32-bit integers in a right by the amount specified by the corresponding element in count while shifting in sign bits, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_srav_epi64 Shift packed 64-bit integers in a right by the amount specified by the corresponding element in count while shifting in sign bits, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_srl_epi32 Shift packed 32-bit integers in a right by count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_srl_epi64 Shift packed 64-bit integers in a right by count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_srli_epi32 Shift packed 32-bit integers in a right by imm8 while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_srli_epi64 Shift packed 64-bit integers in a right by imm8 while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_srlv_epi32 Shift packed 32-bit integers in a right by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_srlv_epi64 Shift packed 64-bit integers in a right by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_sub_epi32 Subtract packed 32-bit integers in b from packed 32-bit integers in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_sub_epi64 Subtract packed 64-bit integers in b from packed 64-bit integers in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_sub_pd Subtract packed double-precision (64-bit) floating-point elements in b from packed double-precision (64-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_sub_ps Subtract packed single-precision (32-bit) floating-point elements in b from packed single-precision (32-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_sub_round_sd Subtract the lower double-precision (64-bit) floating-point element in b from the lower double-precision (64-bit) floating-point element in a, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.\
_mm_maskz_sub_round_ss Subtract the lower single-precision (32-bit) floating-point element in b from the lower single-precision (32-bit) floating-point element in a, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_maskz_sub_sd Subtract the lower double-precision (64-bit) floating-point element in b from the lower double-precision (64-bit) floating-point element in a, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_sub_ss Subtract the lower single-precision (32-bit) floating-point element in b from the lower single-precision (32-bit) floating-point element in a, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_ternarylogic_epi32 Bitwise ternary logic that provides the capability to implement any three-operand binary function; the specific binary function is specified by value in imm8. For each bit in each packed 32-bit integer, the corresponding bit from a, b, and c are used to form a 3 bit index into imm8, and the value at that bit in imm8 is written to the corresponding bit in dst using zeromask k at 32-bit granularity (32-bit elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_ternarylogic_epi64 Bitwise ternary logic that provides the capability to implement any three-operand binary function; the specific binary function is specified by value in imm8. For each bit in each packed 64-bit integer, the corresponding bit from a, b, and c are used to form a 3 bit index into imm8, and the value at that bit in imm8 is written to the corresponding bit in dst using zeromask k at 64-bit granularity (64-bit elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_unpackhi_epi32 Unpack and interleave 32-bit integers from the high half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_unpackhi_epi64 Unpack and interleave 64-bit integers from the high half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_unpackhi_pd Unpack and interleave double-precision (64-bit) floating-point elements from the high half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_unpackhi_ps Unpack and interleave single-precision (32-bit) floating-point elements from the high half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_unpacklo_epi32 Unpack and interleave 32-bit integers from the low half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_unpacklo_epi64 Unpack and interleave 64-bit integers from the low half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_unpacklo_pd Unpack and interleave double-precision (64-bit) floating-point elements from the low half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_unpacklo_ps Unpack and interleave single-precision (32-bit) floating-point elements from the low half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_xor_epi32 Compute the bitwise XOR of packed 32-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_maskz_xor_epi64 Compute the bitwise XOR of packed 64-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
_mm_max_epi64 Compare packed signed 64-bit integers in a and b, and store packed maximum values in dst.
_mm_max_epu64 Compare packed unsigned 64-bit integers in a and b, and store packed maximum values in dst.
_mm_max_round_sd Compare the lower double-precision (64-bit) floating-point elements in a and b, store the maximum value in the lower element of dst, and copy the upper element from a to the upper element of dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_max_round_ss Compare the lower single-precision (32-bit) floating-point elements in a and b, store the maximum value in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_min_epi64 Compare packed signed 64-bit integers in a and b, and store packed minimum values in dst.
_mm_min_epu64 Compare packed unsigned 64-bit integers in a and b, and store packed minimum values in dst.
_mm_min_round_sd Compare the lower double-precision (64-bit) floating-point elements in a and b, store the minimum value in the lower element of dst , and copy the upper element from a to the upper element of dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_min_round_ss Compare the lower single-precision (32-bit) floating-point elements in a and b, store the minimum value in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mmask_i32gather_epi32 Loads 4 32-bit integer elements from memory starting at location base_addr at packed 32-bit integer indices stored in vindex scaled by scale using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mmask_i32gather_epi64 Loads 2 64-bit integer elements from memory starting at location base_addr at packed 32-bit integer indices stored in vindex scaled by scale using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mmask_i32gather_pd Loads 2 double-precision (64-bit) floating-point elements from memory starting at location base_addr at packed 32-bit integer indices stored in vindex scaled by scale using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mmask_i32gather_ps Loads 4 single-precision (32-bit) floating-point elements from memory starting at location base_addr at packed 32-bit integer indices stored in vindex scaled by scale using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mmask_i64gather_epi32 Loads 2 32-bit integer elements from memory starting at location base_addr at packed 64-bit integer indices stored in vindex scaled by scale using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mmask_i64gather_epi64 Loads 2 64-bit integer elements from memory starting at location base_addr at packed 64-bit integer indices stored in vindex scaled by scale using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mmask_i64gather_pd Loads 2 double-precision (64-bit) floating-point elements from memory starting at location base_addr at packed 64-bit integer indices stored in vindex scaled by scale using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mmask_i64gather_ps Loads 2 single-precision (32-bit) floating-point elements from memory starting at location base_addr at packed 64-bit integer indices stored in vindex scaled by scale using writemask k (elements are copied from src when the corresponding mask bit is not set).
_mm_mul_round_sd Multiply the lower double-precision (64-bit) floating-point element in a and b, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.\
_mm_mul_round_ss Multiply the lower single-precision (32-bit) floating-point element in a and b, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_or_epi32 Compute the bitwise OR of packed 32-bit integers in a and b, and store the results in dst.
_mm_or_epi64 Compute the bitwise OR of packed 64-bit integers in a and b, and store the resut in dst.
_mm_permutex2var_epi32 Shuffle 32-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst.
_mm_permutex2var_epi64 Shuffle 64-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst.
_mm_permutex2var_pd Shuffle double-precision (64-bit) floating-point elements in a and b across lanes using the corresponding selector and index in idx, and store the results in dst.
_mm_permutex2var_ps Shuffle single-precision (32-bit) floating-point elements in a and b across lanes using the corresponding selector and index in idx, and store the results in dst.
_mm_rcp14_pd Compute the approximate reciprocal of packed double-precision (64-bit) floating-point elements in a, and store the results in dst. The maximum relative error for this approximation is less than 2^-14.
_mm_rcp14_ps Compute the approximate reciprocal of packed single-precision (32-bit) floating-point elements in a, and store the results in dst. The maximum relative error for this approximation is less than 2^-14.
_mm_rcp14_sd Compute the approximate reciprocal of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst. The maximum relative error for this approximation is less than 2^-14.
_mm_rcp14_ss Compute the approximate reciprocal of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst. The maximum relative error for this approximation is less than 2^-14.
_mm_rol_epi32 Rotate the bits in each packed 32-bit integer in a to the left by the number of bits specified in imm8, and store the results in dst.
_mm_rol_epi64 Rotate the bits in each packed 64-bit integer in a to the left by the number of bits specified in imm8, and store the results in dst.
_mm_rolv_epi32 Rotate the bits in each packed 32-bit integer in a to the left by the number of bits specified in the corresponding element of b, and store the results in dst.
_mm_rolv_epi64 Rotate the bits in each packed 64-bit integer in a to the left by the number of bits specified in the corresponding element of b, and store the results in dst.
_mm_ror_epi32 Rotate the bits in each packed 32-bit integer in a to the right by the number of bits specified in imm8, and store the results in dst.
_mm_ror_epi64 Rotate the bits in each packed 64-bit integer in a to the right by the number of bits specified in imm8, and store the results in dst.
_mm_rorv_epi32 Rotate the bits in each packed 32-bit integer in a to the right by the number of bits specified in the corresponding element of b, and store the results in dst.
_mm_rorv_epi64 Rotate the bits in each packed 64-bit integer in a to the right by the number of bits specified in the corresponding element of b, and store the results in dst.
_mm_roundscale_pd Round packed double-precision (64-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst.
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm_roundscale_ps Round packed single-precision (32-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst.
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm_roundscale_round_sd Round the lower double-precision (64-bit) floating-point element in b to the number of fraction bits specified by imm8, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm_roundscale_round_ss Round the lower single-precision (32-bit) floating-point element in b to the number of fraction bits specified by imm8, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm_roundscale_sd Round the lower double-precision (64-bit) floating-point element in b to the number of fraction bits specified by imm8, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm_roundscale_ss Round the lower single-precision (32-bit) floating-point element in b to the number of fraction bits specified by imm8, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
Rounding is done according to the imm8[2:0] parameter, which can be one of:\
_mm_rsqrt14_pd Compute the approximate reciprocal square root of packed double-precision (64-bit) floating-point elements in a, and store the results in dst. The maximum relative error for this approximation is less than 2^-14.
_mm_rsqrt14_ps Compute the approximate reciprocal square root of packed single-precision (32-bit) floating-point elements in a, and store the results in dst. The maximum relative error for this approximation is less than 2^-14.
_mm_rsqrt14_sd Compute the approximate reciprocal square root of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst. The maximum relative error for this approximation is less than 2^-14.
_mm_rsqrt14_ss Compute the approximate reciprocal square root of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst. The maximum relative error for this approximation is less than 2^-14.
_mm_scalef_pd Scale the packed double-precision (64-bit) floating-point elements in a using values from b, and store the results in dst.
_mm_scalef_ps Scale the packed single-precision (32-bit) floating-point elements in a using values from b, and store the results in dst.
_mm_scalef_round_sd Scale the packed double-precision (64-bit) floating-point elements in a using values from b, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.\
_mm_scalef_round_ss Scale the packed single-precision (32-bit) floating-point elements in a using values from b, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_scalef_sd Scale the packed double-precision (64-bit) floating-point elements in a using values from b, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.
_mm_scalef_ss Scale the packed single-precision (32-bit) floating-point elements in a using values from b, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_sqrt_round_sd Compute the square root of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.\
_mm_sqrt_round_ss Compute the square root of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_sra_epi64 Shift packed 64-bit integers in a right by count while shifting in sign bits, and store the results in dst.
_mm_srai_epi64 Shift packed 64-bit integers in a right by imm8 while shifting in sign bits, and store the results in dst.
_mm_srav_epi64 Shift packed 64-bit integers in a right by the amount specified by the corresponding element in count while shifting in sign bits, and store the results in dst.
_mm_store_epi32 Store 128-bits (composed of 4 packed 32-bit integers) from a into memory. mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated.
_mm_store_epi64 Store 128-bits (composed of 2 packed 64-bit integers) from a into memory. mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated.
_mm_storeu_epi32 Store 128-bits (composed of 4 packed 32-bit integers) from a into memory. mem_addr does not need to be aligned on any particular boundary.
_mm_storeu_epi64 Store 128-bits (composed of 2 packed 64-bit integers) from a into memory. mem_addr does not need to be aligned on any particular boundary.
_mm_sub_round_sd Subtract the lower double-precision (64-bit) floating-point element in b from the lower double-precision (64-bit) floating-point element in a, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.\
_mm_sub_round_ss Subtract the lower single-precision (32-bit) floating-point element in b from the lower single-precision (32-bit) floating-point element in a, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.\
_mm_ternarylogic_epi32 Bitwise ternary logic that provides the capability to implement any three-operand binary function; the specific binary function is specified by value in imm8. For each bit in each packed 32-bit integer, the corresponding bit from a, b, and c are used to form a 3 bit index into imm8, and the value at that bit in imm8 is written to the corresponding bit in dst.
_mm_ternarylogic_epi64 Bitwise ternary logic that provides the capability to implement any three-operand binary function; the specific binary function is specified by value in imm8. For each bit in each packed 64-bit integer, the corresponding bit from a, b, and c are used to form a 3 bit index into imm8, and the value at that bit in imm8 is written to the corresponding bit in dst.
_mm_test_epi32_mask Compute the bitwise AND of packed 32-bit integers in a and b, producing intermediate 32-bit values, and set the corresponding bit in result mask k if the intermediate value is non-zero.
_mm_test_epi64_mask Compute the bitwise AND of packed 64-bit integers in a and b, producing intermediate 64-bit values, and set the corresponding bit in result mask k if the intermediate value is non-zero.
_mm_testn_epi32_mask Compute the bitwise NAND of packed 32-bit integers in a and b, producing intermediate 32-bit values, and set the corresponding bit in result mask k if the intermediate value is zero.
_mm_testn_epi64_mask Compute the bitwise NAND of packed 64-bit integers in a and b, producing intermediate 64-bit values, and set the corresponding bit in result mask k if the intermediate value is zero.
_mm_xor_epi32 Compute the bitwise XOR of packed 32-bit integers in a and b, and store the results in dst.
_mm_xor_epi64 Compute the bitwise XOR of packed 64-bit integers in a and b, and store the results in dst.
_store_mask16 Store 16-bit mask to memory
expandloadd_128
expandloadd_256
expandloadd_512
expandloadpd_128
expandloadpd_256
expandloadpd_512
expandloadps_128
expandloadps_256
expandloadps_512
expandloadq_128
expandloadq_256
expandloadq_512
vaddpd
vaddps
vaddsd
vaddss
vcmppd
vcmppd128
vcmppd256
vcmpps
vcmpps128
vcmpps256
vcmpsd
vcmpss
vcomisd
vcomiss
vcompresspd
vcompresspd128
vcompresspd256
vcompressps
vcompressps128
vcompressps256
vcompressstored
vcompressstored128
vcompressstored256
vcompressstorepd
vcompressstorepd128
vcompressstorepd256
vcompressstoreps
vcompressstoreps128
vcompressstoreps256
vcompressstoreq
vcompressstoreq128
vcompressstoreq256
vcvtdq2ps
vcvtpd2dq
vcvtpd2dq128
vcvtpd2ps
vcvtpd2ps128
vcvtpd2udq
vcvtpd2udq128
vcvtpd2udq256
vcvtph2ps
vcvtps2dq
vcvtps2pd
vcvtps2ph
vcvtps2ph128
vcvtps2ph256
vcvtps2udq
vcvtps2udq128
vcvtps2udq256
vcvtsd2si
vcvtsd2ss
vcvtsd2usi
vcvtsi2ss
vcvtss2sd
vcvtss2si
vcvtss2usi
vcvttpd2dq
vcvttpd2dq128
vcvttpd2udq
vcvttpd2udq128
vcvttpd2udq256
vcvttps2dq
vcvttps2udq
vcvttps2udq128
vcvttps2udq256
vcvttsd2si
vcvttsd2usi
vcvttss2si
vcvttss2usi
vcvtudq2ps
vcvtusi2ss
vdivpd
vdivps
vdivsd
vdivss
vexpandpd
vexpandpd128
vexpandpd256
vexpandps
vexpandps128
vexpandps256
vfixupimmpd
vfixupimmpd128
vfixupimmpd256
vfixupimmpdz
vfixupimmpdz128
vfixupimmpdz256
vfixupimmps
vfixupimmps128
vfixupimmps256
vfixupimmpsz
vfixupimmpsz128
vfixupimmpsz256
vfixupimmsd
vfixupimmsdz
vfixupimmss
vfixupimmssz
vfmadd132pdround
vfmadd132psround
vfmaddsdround
vfmaddssround
vfmaddsubpdround
vfmaddsubpsround
vgatherdpd
vgatherdpd_128
vgatherdpd_256
vgatherdps
vgatherdps_128
vgatherdps_256
vgatherqpd
vgatherqpd_128
vgatherqpd_256
vgatherqps
vgatherqps_128
vgatherqps_256
vgetexppd
vgetexppd128
vgetexppd256
vgetexpps
vgetexpps128
vgetexpps256
vgetexpsd
vgetexpss
vgetmantpd
vgetmantpd128
vgetmantpd256
vgetmantps
vgetmantps128
vgetmantps256
vgetmantsd
vgetmantss
vmaxpd
vmaxps
vmaxsd
vmaxss
vminpd
vminps
vminsd
vminss
vmulpd
vmulps
vmulsd
vmulss
vpcompressd
vpcompressd128
vpcompressd256
vpcompressq
vpcompressq128
vpcompressq256
vpermd
vpermi2d
vpermi2d128
vpermi2d256
vpermi2pd
vpermi2pd128
vpermi2pd256
vpermi2ps
vpermi2ps128
vpermi2ps256
vpermi2q
vpermi2q128
vpermi2q256
vpermilpd
vpermilps
vpermpd
vpermpd256
vpermps
vpermq
vpermq256
vpexpandd
vpexpandd128
vpexpandd256
vpexpandq
vpexpandq128
vpexpandq256
vpgatherdd
vpgatherdd_128
vpgatherdd_256
vpgatherdq
vpgatherdq_128
vpgatherdq_256
vpgatherqd
vpgatherqd_128
vpgatherqd_256
vpgatherqq
vpgatherqq_128
vpgatherqq_256
vpmovdb128
vpmovdb256
vpmovdbmem
vpmovdbmem128
vpmovdbmem256
vpmovdw128
vpmovdwmem
vpmovdwmem128
vpmovdwmem256
vpmovqb
vpmovqb128
vpmovqb256
vpmovqbmem
vpmovqbmem128
vpmovqbmem256
vpmovqd128
vpmovqdmem
vpmovqdmem128
vpmovqdmem256
vpmovqw128
vpmovqw256
vpmovqwmem
vpmovqwmem128
vpmovqwmem256
vpmovsdb
vpmovsdb128
vpmovsdb256
vpmovsdbmem
vpmovsdbmem128
vpmovsdbmem256
vpmovsdw
vpmovsdw128
vpmovsdw256
vpmovsdwmem
vpmovsdwmem128
vpmovsdwmem256
vpmovsqb
vpmovsqb128
vpmovsqb256
vpmovsqbmem
vpmovsqbmem128
vpmovsqbmem256
vpmovsqd
vpmovsqd128
vpmovsqd256
vpmovsqdmem
vpmovsqdmem128
vpmovsqdmem256
vpmovsqw
vpmovsqw128
vpmovsqw256
vpmovsqwmem
vpmovsqwmem128
vpmovsqwmem256
vpmovusdb
vpmovusdb128
vpmovusdb256
vpmovusdbmem
vpmovusdbmem128
vpmovusdbmem256
vpmovusdw
vpmovusdw128
vpmovusdw256
vpmovusdwmem
vpmovusdwmem128
vpmovusdwmem256
vpmovusqb
vpmovusqb128
vpmovusqb256
vpmovusqbmem
vpmovusqbmem128
vpmovusqbmem256
vpmovusqd
vpmovusqd128
vpmovusqd256
vpmovusqdmem
vpmovusqdmem128
vpmovusqdmem256
vpmovusqw
vpmovusqw128
vpmovusqw256
vpmovusqwmem
vpmovusqwmem128
vpmovusqwmem256
vpscatterdd
vpscatterdd_128
vpscatterdd_256
vpscatterdq
vpscatterdq_128
vpscatterdq_256
vpscatterqd
vpscatterqd_128
vpscatterqd_256
vpscatterqq
vpscatterqq_128
vpscatterqq_256
vpslld
vpsllq
vpsrad
vpsraq
vpsraq128
vpsraq256
vpsrld
vpsrlq
vpternlogd
vpternlogd128
vpternlogd256
vpternlogq
vpternlogq128
vpternlogq256
vrcp14pd
vrcp14pd128
vrcp14pd256
vrcp14ps
vrcp14ps128
vrcp14ps256
vrcp14sd
vrcp14ss
vrndscalepd
vrndscalepd128
vrndscalepd256
vrndscaleps
vrndscaleps128
vrndscaleps256
vrndscalesd
vrndscaless
vrsqrt14pd
vrsqrt14pd128
vrsqrt14pd256
vrsqrt14ps
vrsqrt14ps128
vrsqrt14ps256
vrsqrt14sd
vrsqrt14ss
vscalefpd
vscalefpd128
vscalefpd256
vscalefps
vscalefps128
vscalefps256
vscalefsd
vscalefss
vscatterdpd
vscatterdpd_128
vscatterdpd_256
vscatterdps
vscatterdps_128
vscatterdps_256
vscatterqpd
vscatterqpd_128
vscatterqpd_256
vscatterqps
vscatterqps_128
vscatterqps_256
vsqrtpd
vsqrtps
vsqrtsd
vsqrtss
vsubpd
vsubps
vsubsd
vsubss

Constants

_MM_CMPINT_EQ Equal
_MM_CMPINT_FALSE False
_MM_CMPINT_LE Less-than-or-equal
_MM_CMPINT_LT Less-than
_MM_CMPINT_NE Not-equal
_MM_CMPINT_NLE Not less-than-or-equal
_MM_CMPINT_NLT Not less-than
_MM_CMPINT_TRUE True
_MM_MANT_NORM_1_2 interval [1, 2)
_MM_MANT_NORM_P5_1 interval [0.5, 1)
_MM_MANT_NORM_P5_2 interval [0.5, 2)
_MM_MANT_NORM_P75_1P5 interval [0.75, 1.5)
_MM_MANT_SIGN_NAN DEST = NaN if sign(SRC) = 1
_MM_MANT_SIGN_SRC sign = sign(SRC)
_MM_MANT_SIGN_ZERO sign = 0
_MM_PERM_AAAA
_MM_PERM_AAAB
_MM_PERM_AAAC
_MM_PERM_AAAD
_MM_PERM_AABA
_MM_PERM_AABB
_MM_PERM_AABC
_MM_PERM_AABD
_MM_PERM_AACA
_MM_PERM_AACB
_MM_PERM_AACC
_MM_PERM_AACD
_MM_PERM_AADA
_MM_PERM_AADB
_MM_PERM_AADC
_MM_PERM_AADD
_MM_PERM_ABAA
_MM_PERM_ABAB
_MM_PERM_ABAC
_MM_PERM_ABAD
_MM_PERM_ABBA
_MM_PERM_ABBB
_MM_PERM_ABBC
_MM_PERM_ABBD
_MM_PERM_ABCA
_MM_PERM_ABCB
_MM_PERM_ABCC
_MM_PERM_ABCD
_MM_PERM_ABDA
_MM_PERM_ABDB
_MM_PERM_ABDC
_MM_PERM_ABDD
_MM_PERM_ACAA
_MM_PERM_ACAB
_MM_PERM_ACAC
_MM_PERM_ACAD
_MM_PERM_ACBA
_MM_PERM_ACBB
_MM_PERM_ACBC
_MM_PERM_ACBD
_MM_PERM_ACCA
_MM_PERM_ACCB
_MM_PERM_ACCC
_MM_PERM_ACCD
_MM_PERM_ACDA
_MM_PERM_ACDB
_MM_PERM_ACDC
_MM_PERM_ACDD
_MM_PERM_ADAA
_MM_PERM_ADAB
_MM_PERM_ADAC
_MM_PERM_ADAD
_MM_PERM_ADBA
_MM_PERM_ADBB
_MM_PERM_ADBC
_MM_PERM_ADBD
_MM_PERM_ADCA
_MM_PERM_ADCB
_MM_PERM_ADCC
_MM_PERM_ADCD
_MM_PERM_ADDA
_MM_PERM_ADDB
_MM_PERM_ADDC
_MM_PERM_ADDD
_MM_PERM_BAAA
_MM_PERM_BAAB
_MM_PERM_BAAC
_MM_PERM_BAAD
_MM_PERM_BABA
_MM_PERM_BABB
_MM_PERM_BABC
_MM_PERM_BABD
_MM_PERM_BACA
_MM_PERM_BACB
_MM_PERM_BACC
_MM_PERM_BACD
_MM_PERM_BADA
_MM_PERM_BADB
_MM_PERM_BADC
_MM_PERM_BADD
_MM_PERM_BBAA
_MM_PERM_BBAB
_MM_PERM_BBAC
_MM_PERM_BBAD
_MM_PERM_BBBA
_MM_PERM_BBBB
_MM_PERM_BBBC
_MM_PERM_BBBD
_MM_PERM_BBCA
_MM_PERM_BBCB
_MM_PERM_BBCC
_MM_PERM_BBCD
_MM_PERM_BBDA
_MM_PERM_BBDB
_MM_PERM_BBDC
_MM_PERM_BBDD
_MM_PERM_BCAA
_MM_PERM_BCAB
_MM_PERM_BCAC
_MM_PERM_BCAD
_MM_PERM_BCBA
_MM_PERM_BCBB
_MM_PERM_BCBC
_MM_PERM_BCBD
_MM_PERM_BCCA
_MM_PERM_BCCB
_MM_PERM_BCCC
_MM_PERM_BCCD
_MM_PERM_BCDA
_MM_PERM_BCDB
_MM_PERM_BCDC
_MM_PERM_BCDD
_MM_PERM_BDAA
_MM_PERM_BDAB
_MM_PERM_BDAC
_MM_PERM_BDAD
_MM_PERM_BDBA
_MM_PERM_BDBB
_MM_PERM_BDBC
_MM_PERM_BDBD
_MM_PERM_BDCA
_MM_PERM_BDCB
_MM_PERM_BDCC
_MM_PERM_BDCD
_MM_PERM_BDDA
_MM_PERM_BDDB
_MM_PERM_BDDC
_MM_PERM_BDDD
_MM_PERM_CAAA
_MM_PERM_CAAB
_MM_PERM_CAAC
_MM_PERM_CAAD
_MM_PERM_CABA
_MM_PERM_CABB
_MM_PERM_CABC
_MM_PERM_CABD
_MM_PERM_CACA
_MM_PERM_CACB
_MM_PERM_CACC
_MM_PERM_CACD
_MM_PERM_CADA
_MM_PERM_CADB
_MM_PERM_CADC
_MM_PERM_CADD
_MM_PERM_CBAA
_MM_PERM_CBAB
_MM_PERM_CBAC
_MM_PERM_CBAD
_MM_PERM_CBBA
_MM_PERM_CBBB
_MM_PERM_CBBC
_MM_PERM_CBBD
_MM_PERM_CBCA
_MM_PERM_CBCB
_MM_PERM_CBCC
_MM_PERM_CBCD
_MM_PERM_CBDA
_MM_PERM_CBDB
_MM_PERM_CBDC
_MM_PERM_CBDD
_MM_PERM_CCAA
_MM_PERM_CCAB
_MM_PERM_CCAC
_MM_PERM_CCAD
_MM_PERM_CCBA
_MM_PERM_CCBB
_MM_PERM_CCBC
_MM_PERM_CCBD
_MM_PERM_CCCA
_MM_PERM_CCCB
_MM_PERM_CCCC
_MM_PERM_CCCD
_MM_PERM_CCDA
_MM_PERM_CCDB
_MM_PERM_CCDC
_MM_PERM_CCDD
_MM_PERM_CDAA
_MM_PERM_CDAB
_MM_PERM_CDAC
_MM_PERM_CDAD
_MM_PERM_CDBA
_MM_PERM_CDBB
_MM_PERM_CDBC
_MM_PERM_CDBD
_MM_PERM_CDCA
_MM_PERM_CDCB
_MM_PERM_CDCC
_MM_PERM_CDCD
_MM_PERM_CDDA
_MM_PERM_CDDB
_MM_PERM_CDDC
_MM_PERM_CDDD
_MM_PERM_DAAA
_MM_PERM_DAAB
_MM_PERM_DAAC
_MM_PERM_DAAD
_MM_PERM_DABA
_MM_PERM_DABB
_MM_PERM_DABC
_MM_PERM_DABD
_MM_PERM_DACA
_MM_PERM_DACB
_MM_PERM_DACC
_MM_PERM_DACD
_MM_PERM_DADA
_MM_PERM_DADB
_MM_PERM_DADC
_MM_PERM_DADD
_MM_PERM_DBAA
_MM_PERM_DBAB
_MM_PERM_DBAC
_MM_PERM_DBAD
_MM_PERM_DBBA
_MM_PERM_DBBB
_MM_PERM_DBBC
_MM_PERM_DBBD
_MM_PERM_DBCA
_MM_PERM_DBCB
_MM_PERM_DBCC
_MM_PERM_DBCD
_MM_PERM_DBDA
_MM_PERM_DBDB
_MM_PERM_DBDC
_MM_PERM_DBDD
_MM_PERM_DCAA
_MM_PERM_DCAB
_MM_PERM_DCAC
_MM_PERM_DCAD
_MM_PERM_DCBA
_MM_PERM_DCBB
_MM_PERM_DCBC
_MM_PERM_DCBD
_MM_PERM_DCCA
_MM_PERM_DCCB
_MM_PERM_DCCC
_MM_PERM_DCCD
_MM_PERM_DCDA
_MM_PERM_DCDB
_MM_PERM_DCDC
_MM_PERM_DCDD
_MM_PERM_DDAA
_MM_PERM_DDAB
_MM_PERM_DDAC
_MM_PERM_DDAD
_MM_PERM_DDBA
_MM_PERM_DDBB
_MM_PERM_DDBC
_MM_PERM_DDBD
_MM_PERM_DDCA
_MM_PERM_DDCB
_MM_PERM_DDCC
_MM_PERM_DDCD
_MM_PERM_DDDA
_MM_PERM_DDDB
_MM_PERM_DDDC
_MM_PERM_DDDD