Function core::arch::x86::_mm_maskz_dpbf16_ps[][src]

pub unsafe fn _mm_maskz_dpbf16_ps(
    k: __mmask8,
    src: __m128,
    a: __m128bh,
    b: __m128bh
) -> __m128
🔬 This is a nightly-only experimental API. (stdsimd #48556)
This is supported on x86 and target feature avx512bf16,avx512vl 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 中的元素进行累加,并将结果存储在 dst 中使用 zeromask k (当对应的掩码为位未设置)。

Intel’s documentation