_mm256_mask_shuffle_epi32
Classification
AVX-512, Miscellaneous, CPUID Test: AVX512F
Header File
immintrin.h
Instruction
VPSHUFD ymm {k}, ymm, imm8
Synopsis
 _mm256_mask_shuffle_epi32(__m256i src, __mmask8 k, __m256i a, _MM_PERM_ENUM imm8);
Description
Shuffle 32-bit integers in "a" within 128-bit lanes using the control in "imm8", and store the results in "dst" using writemask "k" (elements are copied from "src" when the corresponding mask bit is not set).
Operation
DEFINE SELECT4(src, control) {
	CASE(control[1:0]) OF
	0:	tmp[31:0] := src[31:0]
	1:	tmp[31:0] := src[63:32]
	2:	tmp[31:0] := src[95:64]
	3:	tmp[31:0] := src[127:96]
	ESAC
	RETURN tmp[31:0]
}
tmp_dst[31:0] := SELECT4(a[127:0], imm8[1:0])
tmp_dst[63:32] := SELECT4(a[127:0], imm8[3:2])
tmp_dst[95:64] := SELECT4(a[127:0], imm8[5:4])
tmp_dst[127:96] := SELECT4(a[127:0], imm8[7:6])
tmp_dst[159:128] := SELECT4(a[255:128], imm8[1:0])
tmp_dst[191:160] := SELECT4(a[255:128], imm8[3:2])
tmp_dst[223:192] := SELECT4(a[255:128], imm8[5:4])
tmp_dst[255:224] := SELECT4(a[255:128], imm8[7:6])
FOR j := 0 to 7
	i := j*32
	IF k[j]
		dst[i+31:i] := tmp_dst[i+31:i]
	ELSE
		dst[i+31:i] := src[i+31:i]
	FI
ENDFOR
dst[MAX:256] := 0