_mm512_mask_unpacklo_ps
Classification
AVX-512, Swizzle, CPUID Test: AVX512F
Header File
Instruction
VUNPCKLPS zmm {k}, zmm, zmm
Synopsis
_mm512_mask_unpacklo_ps(__m512 src, __mmask16 k, __m512 a, __m512 b);
Description
Unpack and interleave single-precision (32-bit) floating-point elements from the low half of each 128-bit lane in "a" and "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 INTERLEAVE_DWORDS(src1[127:0], src2[127:0]) {
dst[31:0] := src1[31:0]
dst[63:32] := src2[31:0]
dst[95:64] := src1[63:32]
dst[127:96] := src2[63:32]
RETURN dst[127:0]
}
tmp_dst[127:0] := INTERLEAVE_DWORDS(a[127:0], b[127:0])
tmp_dst[255:128] := INTERLEAVE_DWORDS(a[255:128], b[255:128])
tmp_dst[383:256] := INTERLEAVE_DWORDS(a[383:256], b[383:256])
tmp_dst[511:384] := INTERLEAVE_DWORDS(a[511:384], b[511:384])
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