_mm512_maskz_fmaddsub_round_ph
Classification
AVX-512, Arithmetic, CPUID Test: AVX512_FP16
Header File
Instruction
VFMADDSUB132PH zmm {z}, zmm, zmm {er}
Synopsis
_mm512_maskz_fmaddsub_round_ph(__mmask32 k, __m512h a, __m512h b, __m512h c, const int rounding);
Description
Multiply packed half-precision (16-bit) floating-point elements in "a" and "b", alternatively add and subtract packed elements in "c" to/from the intermediate result, and store the results in "dst" using zeromask "k" (elements are zeroed out when the corresponding mask bit is not set).
[round_note]
Operation
FOR j := 0 to 31
IF k[j]
IF ((j & 1) == 0)
dst.fp16[j] := (a.fp16[j] * b.fp16[j]) - c.fp16[j]
ELSE
dst.fp16[j] := (a.fp16[j] * b.fp16[j]) + c.fp16[j]
FI
ELSE
dst.fp16[j] := 0
FI
ENDFOR
dst[MAX:512] := 0