_mm256_mask_reduce_mul_epi16
Classification
AVX-512, Arithmetic, CPUID Test: AVX512BW
Header File
immintrin.h
Synopsis
 _mm256_mask_reduce_mul_epi16(__mmask16 k, __m256i a);
Description
Reduce the packed 16-bit integers in "a" by multiplication using mask "k". Returns the sum of all active elements in "a".
Operation
DEFINE REDUCE_MUL(src, len) {
	IF len == 2
		RETURN src[15:0] * src[31:16]
	FI
	len := len / 2
	FOR j:= 0 to (len-1)
		i := j*16
		src[i+15:i] := src[i+15:i] * src[i+16*len+15:i+16*len]
	ENDFOR
	RETURN REDUCE_MUL(src[16*len-1:0], len)
}
tmp := a
FOR j := 0 to 15
	i := j*16
	IF k[j]
		tmp[i+15:i] := a[i+15:i]
	ELSE
		tmp[i+15:i] := 1
	FI
ENDFOR
dst[15:0] := REDUCE_MUL(tmp, 16)