_mm_mask_cvtpbh_ps
Classification
AVX-512, Convert, CPUID Test: AVX512_BF16
Header File
immintrin.h
Synopsis
 _mm_mask_cvtpbh_ps(__m128 src, __mmask8 k, __m128bh a);
Description
Convert packed BF16 (16-bit) floating-point elements in "a" to packed single-precision (32-bit) floating-point elements, and store the results in "dst" using writemask "k" (elements are copied from "src" when the corresponding mask bit is not set). This intrinsic neither raises any floating point exceptions nor turns sNAN into qNAN.
Operation
FOR j := 0 to 3
	i := j*32
	m := j*16
	IF k[j]
		dst[i+31:i] := Convert_BF16_To_FP32(a[m+15:m])
	ELSE
		dst[i+31:i] := src[i+31:i]
	FI
ENDFOR
dst[MAX:128] := 0