Function core::arch::x86_64::_mm_dpbf16_ps

source · 
pub unsafe fn _mm_dpbf16_ps(src: __m128, a: __m128bh, b: __m128bh) -> __m128
🔬This is a nightly-only experimental API. (stdsimd #48556)
Available on (x86 or x86-64) and target feature avx512bf16,avx512vl and x86-64 only.
Expand description

计算 a 和 b 中 BF16 (16-bit) 浮点对的点积，将中间单精度 (32-bit) 浮点元素与 src 中的元素相加，并将结果存储在 dst 中。

Intel’s documentation