_mm512_mask_permute_ps
Classification
AVX-512, Swizzle, CPUID Test: AVX512F
Header File
immintrin.h
Instruction
VPERMILPS zmm {k}, zmm, imm8
Synopsis
 _mm512_mask_permute_ps(__m512 src, __mmask16 k, __m512 a, const int imm8);
Description
Shuffle single-precision (32-bit) floating-point elements 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])
tmp_dst[287:256] := SELECT4(a[383:256], imm8[1:0])
tmp_dst[319:288] := SELECT4(a[383:256], imm8[3:2])
tmp_dst[351:320] := SELECT4(a[383:256], imm8[5:4])
tmp_dst[383:352] := SELECT4(a[383:256], imm8[7:6])
tmp_dst[415:384] := SELECT4(a[511:384], imm8[1:0])
tmp_dst[447:416] := SELECT4(a[511:384], imm8[3:2])
tmp_dst[479:448] := SELECT4(a[511:384], imm8[5:4])
tmp_dst[511:480] := SELECT4(a[511:384], imm8[7:6])
FOR j := 0 to 15
	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:512] := 0