__tile_cmmimfp16psPerform matrix multiplication of two tiles containing complex elements and accumulate the results into a packed single precision tile.
Each dword element in input tiles a and b is interpreted as a complex number with FP16 real part and FP16 imaginary part.
Calculates the imaginary part of the result. For each possible combination of (row of a, column of b),
it performs a set of multiplication and accumulations on all corresponding complex numbers (one from a and one from b).
The imaginary part of the a element is multiplied with the real part of the corresponding b element, and the real part of
the a element is multiplied with the imaginary part of the corresponding b elements. The two accumulated results are added,
and then accumulated into the corresponding row and column of dst.
The shape of the tile is specified in the struct of __tile1024i. The register of the tile is allocated by the compiler.
__tile_cmmrlfp16psPerform matrix multiplication of two tiles containing complex elements and accumulate the results into a packed single precision tile.
Each dword element in input tiles a and b is interpreted as a complex number with FP16 real part and FP16 imaginary part.
Calculates the real part of the result. For each possible combination of (row of a, column of b),
it performs a set of multiplication and accumulations on all corresponding complex numbers (one from a and one from b).
The real part of the a element is multiplied with the real part of the corresponding b element, and the negated imaginary part of
the a element is multiplied with the imaginary part of the corresponding b elements.
The two accumulated results are added, and then accumulated into the corresponding row and column of dst.
The shape of the tile is specified in the struct of __tile1024i. The register of the tile is allocated by the compiler.
__tile_cvtrowd2psMoves a row from a tile register to a zmm register, converting the packed 32-bit signed integer
elements to packed single-precision (32-bit) floating-point elements.
The shape of the tile is specified in the struct of __tile1024i. The register of the tile is allocated by the compiler.
__tile_cvtrowps2bf16hMoves a row from a tile register to a zmm register, converting the packed single-precision (32-bit)
floating-point elements to packed BF16 (16-bit) floating-point elements. The resulting
16-bit elements are placed in the high 16-bits within each 32-bit element of the returned vector.
The shape of the tile is specified in the struct of __tile1024i. The register of the tile is allocated by the compiler.
__tile_cvtrowps2bf16lMoves a row from a tile register to a zmm register, converting the packed single-precision (32-bit)
floating-point elements to packed BF16 (16-bit) floating-point elements. The resulting
16-bit elements are placed in the low 16-bits within each 32-bit element of the returned vector.
The shape of the tile is specified in the struct of __tile1024i. The register of the tile is allocated by the compiler.
__tile_cvtrowps2phhMoves a row from a tile register to a zmm register, converting the packed single-precision (32-bit)
floating-point elements to packed half-precision (16-bit) floating-point elements. The resulting
16-bit elements are placed in the high 16-bits within each 32-bit element of the returned vector.
The shape of the tile is specified in the struct of __tile1024i. The register of the tile is allocated by the compiler.
__tile_cvtrowps2phlMoves a row from a tile register to a zmm register, converting the packed single-precision (32-bit)
floating-point elements to packed half-precision (16-bit) floating-point elements. The resulting
16-bit elements are placed in the low 16-bits within each 32-bit element of the returned vector.
The shape of the tile is specified in the struct of __tile1024i. The register of the tile is allocated by the compiler.
__tile_dpbf16psCompute dot-product of FP16 (16-bit) floating-point pairs in tiles a and b,
accumulating the intermediate single-precision (32-bit) floating-point elements
with elements in dst, and store the 32-bit result back to tile dst. The shape of the tile
is specified in the struct of __tile1024i. The register of the tile is allocated by the compiler.
__tile_dpbf8psCompute dot-product of BF8 (8-bit E5M2) floating-point elements in tile a and BF8 (8-bit E5M2)
floating-point elements in tile b, accumulating the intermediate single-precision
(32-bit) floating-point elements with elements in dst, and store the 32-bit result
back to tile dst.
The shape of the tile is specified in the struct of __tile1024i. The register of the tile is allocated by the compiler.
__tile_dpbhf8psCompute dot-product of BF8 (8-bit E5M2) floating-point elements in tile a and HF8
(8-bit E4M3) floating-point elements in tile b, accumulating the intermediate single-precision
(32-bit) floating-point elements with elements in dst, and store the 32-bit result
back to tile dst.
The shape of the tile is specified in the struct of __tile1024i. The register of the tile is allocated by the compiler.
__tile_dpbssdCompute dot-product of bytes in tiles with a source/destination accumulator.
Multiply groups of 4 adjacent pairs of signed 8-bit integers in a with corresponding
signed 8-bit integers in b, producing 4 intermediate 32-bit results.
Sum these 4 results with the corresponding 32-bit integer in dst, and store the 32-bit result back to tile dst.
The shape of the tile is specified in the struct of __tile1024i. The register of the tile is allocated by the compiler.
__tile_dpbsudCompute dot-product of bytes in tiles with a source/destination accumulator.
Multiply groups of 4 adjacent pairs of signed 8-bit integers in a with corresponding
unsigned 8-bit integers in b, producing 4 intermediate 32-bit results.
Sum these 4 results with the corresponding 32-bit integer in dst, and store the 32-bit result back to tile dst.
The shape of the tile is specified in the struct of __tile1024i. The register of the tile is allocated by the compiler.
__tile_dpbusdCompute dot-product of bytes in tiles with a source/destination accumulator.
Multiply groups of 4 adjacent pairs of unsigned 8-bit integers in a with corresponding
signed 8-bit integers in b, producing 4 intermediate 32-bit results.
Sum these 4 results with the corresponding 32-bit integer in dst, and store the 32-bit result back to tile dst.
The shape of the tile is specified in the struct of __tile1024i. The register of the tile is allocated by the compiler.
__tile_dpbuudCompute dot-product of bytes in tiles with a source/destination accumulator.
Multiply groups of 4 adjacent pairs of unsigned 8-bit integers in a with corresponding
unsigned 8-bit integers in b, producing 4 intermediate 32-bit results.
Sum these 4 results with the corresponding 32-bit integer in dst, and store the 32-bit result back to tile dst.
The shape of the tile is specified in the struct of __tile1024i. The register of the tile is allocated by the compiler.
__tile_dpfp16psCompute dot-product of FP16 (16-bit) floating-point pairs in tiles a and b,
accumulating the intermediate single-precision (32-bit) floating-point elements
with elements in dst, and store the 32-bit result back to tile dst.
The shape of the tile is specified in the struct of __tile1024i. The register of the tile is allocated by the compiler.
__tile_dphbf8psCompute dot-product of HF8 (8-bit E4M3) floating-point elements in tile a and BF8
(8-bit E5M2) floating-point elements in tile b, accumulating the intermediate single-precision
(32-bit) floating-point elements with elements in dst, and store the 32-bit result
back to tile dst.
The shape of the tile is specified in the struct of __tile1024i. The register of the tile is allocated by the compiler.
__tile_dphf8psCompute dot-product of HF8 (8-bit E4M3) floating-point elements in tile a and HF8 (8-bit E4M3)
floating-point elements in tile b, accumulating the intermediate single-precision
(32-bit) floating-point elements with elements in dst, and store the 32-bit result
back to tile dst.
The shape of the tile is specified in the struct of __tile1024i. The register of the tile is allocated by the compiler.
__tile_loaddLoad tile rows from memory specified by base address and stride into destination tile dst. The shape
of the tile is specified in the struct of __tile1024i. The register of the tile is allocated by the compiler.
__tile_loaddrsLoad tile rows from memory specified by base address and stride into destination tile dst.
The shape of the tile is specified in the struct of __tile1024i. The register of the tile is allocated by the compiler.
Additionally, this intrinsic indicates the source memory location is likely to become
read-shared by multiple processors, i.e., read in the future by at least one other processor
before it is written, assuming it is ever written in the future.
__tile_movrowMoves one row of tile data into a zmm vector register
The shape of the tile is specified in the struct of __tile1024i. The register of the tile is allocated by the compiler.
__tile_storedStore the tile specified by src to memory specified by base address and stride. The shape of the tile
is specified in the struct of __tile1024i. The register of the tile is allocated by the compiler.
__tile_stream_loaddLoad tile rows from memory specified by base address and stride into destination tile dst. The shape
of the tile is specified in the struct of __tile1024i. The register of the tile is allocated by the compiler.
This intrinsic provides a hint to the implementation that the data will likely not be reused in the
near future and the data caching can be optimized accordingly.
__tile_stream_loaddrsLoad tile rows from memory specified by base address and stride into destination tile dst.
The shape of the tile is specified in the struct of __tile1024i. The register of the tile is allocated by the compiler.
Provides a hint to the implementation that the data would be reused but does not need
to be resident in the nearest cache levels.
Additionally, this intrinsic indicates the source memory location is likely to become
read-shared by multiple processors, i.e., read in the future by at least one other processor
before it is written, assuming it is ever written in the future.
__tile_zeroZero the tile specified by dst. The shape of the tile is specified in the struct of __tile1024i.
The register of the tile is allocated by the compiler.
_tile_cmmimfp16psPerform matrix multiplication of two tiles containing complex elements and accumulate the results into a packed single precision tile.
Each dword element in input tiles a and b is interpreted as a complex number with FP16 real part and FP16 imaginary part.
Calculates the imaginary part of the result. For each possible combination of (row of a, column of b),
it performs a set of multiplication and accumulations on all corresponding complex numbers (one from a and one from b).
The imaginary part of the a element is multiplied with the real part of the corresponding b element, and the real part of
the a element is multiplied with the imaginary part of the corresponding b elements. The two accumulated results are added,
and then accumulated into the corresponding row and column of dst.
_tile_cmmrlfp16psPerform matrix multiplication of two tiles containing complex elements and accumulate the results into a packed single precision tile.
Each dword element in input tiles a and b is interpreted as a complex number with FP16 real part and FP16 imaginary part.
Calculates the real part of the result. For each possible combination of (row of a, column of b),
it performs a set of multiplication and accumulations on all corresponding complex numbers (one from a and one from b).
The real part of the a element is multiplied with the real part of the corresponding b element, and the negated imaginary part of
the a element is multiplied with the imaginary part of the corresponding b elements.
The two accumulated results are added, and then accumulated into the corresponding row and column of dst.
_tile_cvtrowd2psMoves a row from a tile register to a zmm register, converting the packed 32-bit signed integer
elements to packed single-precision (32-bit) floating-point elements.
_tile_cvtrowd2psiMoves a row from a tile register to a zmm register, converting the packed 32-bit signed integer
elements to packed single-precision (32-bit) floating-point elements.
_tile_cvtrowps2bf16hMoves a row from a tile register to a zmm register, converting the packed single-precision (32-bit)
floating-point elements to packed BF16 (16-bit) floating-point elements. The resulting
16-bit elements are placed in the high 16-bits within each 32-bit element of the returned vector.
_tile_cvtrowps2bf16hiMoves a row from a tile register to a zmm register, converting the packed single-precision (32-bit)
floating-point elements to packed BF16 (16-bit) floating-point elements. The resulting
16-bit elements are placed in the high 16-bits within each 32-bit element of the returned vector.
_tile_cvtrowps2bf16lMoves a row from a tile register to a zmm register, converting the packed single-precision (32-bit)
floating-point elements to packed BF16 (16-bit) floating-point elements. The resulting
16-bit elements are placed in the low 16-bits within each 32-bit element of the returned vector.
_tile_cvtrowps2bf16liMoves a row from a tile register to a zmm register, converting the packed single-precision (32-bit)
floating-point elements to packed BF16 (16-bit) floating-point elements. The resulting
16-bit elements are placed in the low 16-bits within each 32-bit element of the returned vector.
_tile_cvtrowps2phhMoves a row from a tile register to a zmm register, converting the packed single-precision (32-bit)
floating-point elements to packed half-precision (16-bit) floating-point elements. The resulting
16-bit elements are placed in the high 16-bits within each 32-bit element of the returned vector.
_tile_cvtrowps2phhiMoves a row from a tile register to a zmm register, converting the packed single-precision (32-bit)
floating-point elements to packed half-precision (16-bit) floating-point elements. The resulting
16-bit elements are placed in the high 16-bits within each 32-bit element of the returned vector.
_tile_cvtrowps2phlMoves a row from a tile register to a zmm register, converting the packed single-precision (32-bit)
floating-point elements to packed half-precision (16-bit) floating-point elements. The resulting
16-bit elements are placed in the low 16-bits within each 32-bit element of the returned vector.
_tile_cvtrowps2phliMoves a row from a tile register to a zmm register, converting the packed single-precision (32-bit)
floating-point elements to packed half-precision (16-bit) floating-point elements. The resulting
16-bit elements are placed in the low 16-bits within each 32-bit element of the returned vector.
_tile_dpbf16psCompute dot-product of BF16 (16-bit) floating-point pairs in tiles a and b,
accumulating the intermediate single-precision (32-bit) floating-point elements
with elements in dst, and store the 32-bit result back to tile dst.
_tile_dpbf8psCompute dot-product of BF8 (8-bit E5M2) floating-point elements in tile a and BF8 (8-bit E5M2)
floating-point elements in tile b, accumulating the intermediate single-precision
(32-bit) floating-point elements with elements in dst, and store the 32-bit result
back to tile dst.
_tile_dpbhf8psCompute dot-product of BF8 (8-bit E5M2) floating-point elements in tile a and HF8
(8-bit E4M3) floating-point elements in tile b, accumulating the intermediate single-precision
(32-bit) floating-point elements with elements in dst, and store the 32-bit result
back to tile dst.
_tile_dpbssdCompute dot-product of bytes in tiles with a source/destination accumulator.
Multiply groups of 4 adjacent pairs of signed 8-bit integers in a with corresponding
signed 8-bit integers in b, producing 4 intermediate 32-bit results.
Sum these 4 results with the corresponding 32-bit integer in dst, and store the 32-bit result back to tile dst.
_tile_dpbsudCompute dot-product of bytes in tiles with a source/destination accumulator.
Multiply groups of 4 adjacent pairs of signed 8-bit integers in a with corresponding
unsigned 8-bit integers in b, producing 4 intermediate 32-bit results.
Sum these 4 results with the corresponding 32-bit integer in dst, and store the 32-bit result back to tile dst.
_tile_dpbusdCompute dot-product of bytes in tiles with a source/destination accumulator.
Multiply groups of 4 adjacent pairs of unsigned 8-bit integers in a with corresponding
signed 8-bit integers in b, producing 4 intermediate 32-bit results.
Sum these 4 results with the corresponding 32-bit integer in dst, and store the 32-bit result back to tile dst.
_tile_dpbuudCompute dot-product of bytes in tiles with a source/destination accumulator.
Multiply groups of 4 adjacent pairs of unsigned 8-bit integers in a with corresponding
unsigned 8-bit integers in b, producing 4 intermediate 32-bit results.
Sum these 4 results with the corresponding 32-bit integer in dst, and store the 32-bit result back to tile dst.
_tile_dpfp16psCompute dot-product of FP16 (16-bit) floating-point pairs in tiles a and b,
accumulating the intermediate single-precision (32-bit) floating-point elements
with elements in dst, and store the 32-bit result back to tile dst.
_tile_dphbf8psCompute dot-product of HF8 (8-bit E4M3) floating-point elements in tile a and BF8
(8-bit E5M2) floating-point elements in tile b, accumulating the intermediate single-precision
(32-bit) floating-point elements with elements in dst, and store the 32-bit result
back to tile dst.
_tile_dphf8psCompute dot-product of HF8 (8-bit E4M3) floating-point elements in tile a and HF8 (8-bit E4M3)
floating-point elements in tile b, accumulating the intermediate single-precision
(32-bit) floating-point elements with elements in dst, and store the 32-bit result
back to tile dst.
_tile_loadconfigLoad tile configuration from a 64-byte memory location specified by mem_addr.
The tile configuration format is specified below, and includes the tile type pallette,
the number of bytes per row, and the number of rows. If the specified pallette_id is zero,
that signifies the init state for both the tile config and the tile data, and the tiles are zeroed.
Any invalid configurations will result in #GP fault.
_tile_loaddLoad tile rows from memory specified by base address and stride into destination tile dst using the tile configuration previously configured via _tile_loadconfig.
_tile_loaddrsLoad tile rows from memory specified by base address and stride into destination tile dst
using the tile configuration previously configured via _tile_loadconfig.
Additionally, this intrinsic indicates the source memory location is likely to become
read-shared by multiple processors, i.e., read in the future by at least one other processor
before it is written, assuming it is ever written in the future.
_tile_movrowMoves one row of tile data into a zmm vector register
_tile_movrowiMoves one row of tile data into a zmm vector register
_tile_releaseRelease the tile configuration to return to the init state, which releases all storage it currently holds.
_tile_storeconfigStores the current tile configuration to a 64-byte memory location specified by mem_addr.
The tile configuration format is as specified in _tile_loadconfig, and includes the tile type pallette,
the number of bytes per row, and the number of rows. If tiles are not configured, all zeroes will be stored to memory.
_tile_storedStore the tile specified by src to memory specified by base address and stride using the tile configuration previously configured via _tile_loadconfig.
_tile_stream_loaddLoad tile rows from memory specified by base address and stride into destination tile dst using the tile configuration
previously configured via _tile_loadconfig. This intrinsic provides a hint to the implementation that the data will
likely not be reused in the near future and the data caching can be optimized accordingly.
_tile_stream_loaddrsLoad tile rows from memory specified by base address and stride into destination tile dst
using the tile configuration previously configured via _tile_loadconfig.
Provides a hint to the implementation that the data would be reused but does not need
to be resident in the nearest cache levels.
Additionally, this intrinsic indicates the source memory location is likely to become
read-shared by multiple processors, i.e., read in the future by at least one other processor
before it is written, assuming it is ever written in the future.