Function core::arch::x86::_mm512_mask_cvtneps_pbh[][src]

pub unsafe fn _mm512_mask_cvtneps_pbh(
    src: __m256bh,
    k: __mmask16,
    a: __m512
) -> __m256bh
🔬 This is a nightly-only experimental API. (stdsimd #48556)
This is supported on x86 and target feature avx512bf16,avx512f only.
Expand description

将包装在 a 中的单精度 (32-bit) 浮点元素转换为包装的 BF16 (16-bit) 浮点元素,并使用 writemask k 将结果存储在 dst 中 (当相应的掩码位未设置时,元素从 src 复制)。

Intel’s documentation