_mm512_mask3_fmadd_round_ph
Classification
AVX-512, Arithmetic, CPUID Test: AVX512_FP16
Header File
immintrin.h
Instruction
VFMADD132PH zmm {k}, zmm, zmm {er}
Synopsis
 _mm512_mask3_fmadd_round_ph(__m512h a, __m512h b, __m512h c, __mmask32 k, const int rounding);
Description
Multiply packed half-precision (16-bit) floating-point elements in "a" and "b", add the intermediate result to packed elements in "c", and store the results in "dst" using writemask "k" (elements are copied from "c" when the corresponding mask bit is not set). [round_note]
Operation
FOR j := 0 to 31
	IF k[j]
		dst.fp16[j] := (a.fp16[j] * b.fp16[j]) + c.fp16[j]
	ELSE
		dst.fp16[j] := c.fp16[j]
	FI
ENDFOR
dst[MAX:512] := 0