Skip to main content

_tile_cvtrowps2bf16l

Function _tile_cvtrowps2bf16l 

Source
pub unsafe fn _tile_cvtrowps2bf16l(const TILE: i32, row: u32) -> __m512bh
🔬This is a nightly-only experimental API. (x86_amx_intrinsics #126622)
Available on x86-64 and target feature amx-avx512 and target feature avx10.2 only.
Expand description

Moves 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.