_mm256_mask_permutevar_ps
Classification
AVX-512, Miscellaneous, CPUID Test: AVX512F
Header File
Instruction
VPERMILPS ymm {k}, ymm, ymm
Synopsis
_mm256_mask_permutevar_ps(__m256 src, __mmask8 k, __m256 a, __m256i b);
Description
Shuffle single-precision (32-bit) floating-point elements in "a" within 128-bit lanes using the control in "b", 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], b[1:0])
tmp_dst[63:32] := SELECT4(a[127:0], b[33:32])
tmp_dst[95:64] := SELECT4(a[127:0], b[65:64])
tmp_dst[127:96] := SELECT4(a[127:0], b[97:96])
tmp_dst[159:128] := SELECT4(a[255:128], b[129:128])
tmp_dst[191:160] := SELECT4(a[255:128], b[161:160])
tmp_dst[223:192] := SELECT4(a[255:128], b[193:192])
tmp_dst[255:224] := SELECT4(a[255:128], b[225:224])
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