_mm_mask_reduce_ss
Classification
AVX-512, Miscellaneous, CPUID Test: AVX512DQ
Header File
immintrin.h
Instruction
VREDUCESS xmm {k}, xmm, xmm, imm8
Synopsis
 _mm_mask_reduce_ss(__m128 src, __mmask8 k, __m128 a, __m128 b, int imm8);
Description
Extract the reduced argument of the lower single-precision (32-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 3 packed elements from "a" to the upper elements of "dst". [round_imm_note]
Operation
DEFINE ReduceArgumentPS(src1[31:0], imm8[7:0]) {
	m[31:0] := FP32(imm8[7:4]) // number of fraction bits after the binary point to be preserved
	tmp[31:0] := POW(FP32(2.0), -m) * ROUND(POW(FP32(2.0), m) * src1[31:0], imm8[3:0])
	tmp[31:0] := src1[31:0] - tmp[31:0]
	IF IsInf(tmp[31:0])
		tmp[31:0] := FP32(0.0)
	FI
	RETURN tmp[31:0]
}
IF k[0]
	dst[31:0] := ReduceArgumentPS(b[31:0], imm8[7:0])
ELSE
	dst[31:0] := src[31:0]
FI
dst[127:32] := a[127:32]
dst[MAX:128] := 0