_mm_mask_reduce_round_sh
Classification
AVX-512, Special Math Functions, CPUID Test: AVX512_FP16
Header File
immintrin.h
Instruction
VREDUCESH xmm {k}, xmm, xmm {sae}, imm8
Synopsis
 _mm_mask_reduce_round_sh(__m128h src, __mmask8 k, __m128h a, __m128h b, int imm8, const int sae);
Description
Extract the reduced argument of the lower half-precision (16-bit) floating-point element in "b" by the number of bits specified by "imm8", store the result in the lower element of "dst" using writemask "k" (the element is copied from "src" when mask bit 0 is not set), and copy the upper 7 packed elements from "a" to the upper elements of "dst". [round_imm_note][sae_note]
Operation
DEFINE ReduceArgumentFP16(src[15:0], imm8[7:0]) {
	m[15:0] := FP16(imm8[7:4]) // number of fraction bits after the binary point to be preserved
	tmp[15:0] := POW(2.0, FP16(-m)) * ROUND(POW(2.0, FP16(m)) * src[15:0], imm8[3:0])
	tmp[15:0] := src[15:0] - tmp[15:0]
	IF IsInf(tmp[15:0])
		tmp[15:0] := FP16(0.0)
	FI
	RETURN tmp[15:0]
}
IF k[0]
	dst.fp16[0] := ReduceArgumentFP16(b.fp16[0], imm8)
ELSE
	dst.fp16[0] := src.fp16[0]
FI
dst[127:16] := a[127:16]
dst[MAX:128] := 0