Function __tile_dpfp16ps
#[target_feature(enable = "amx-fp16")]
pub unsafe fn __tile_dpfp16ps(dst: *mut __tile1024i, a: __tile1024i, b: __tile1024i)Compute 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.