image/svg+xmlVBLENDMPD/VBLENDMPS—Blend Float64/Float32 Vectors Using an OpMask ControlInstruction Operand EncodingDescriptionPerforms an element-by-element blending between float64/float32 elements in the first source operand (the second operand) with the elements in the second source operand (the third operand) using an opmask register as select control. The blended result is written to the destination register.The destination and first source operands are ZMM/YMM/XMM registers. The second source operand can be a ZMM/YMM/XMM register, a 512/256/128-bit memory location or a 512/256/128-bit vector broadcasted from a 64-bit memory location.The opmask register is not used as a writemask for this instruction. Instead, the mask is used as an element selector: every element of the destination is conditionally selected between first source or second source using the value of the related mask bit (0 for first source operand, 1 for second source operand).If EVEX.z is set, the elements with corresponding mask bit value of 0 in the destination operand are zeroed.Opcode/InstructionOp / En64/32 bit Mode SupportCPUID Feature FlagDescriptionEVEX.128.66.0F38.W1 65 /rVBLENDMPD xmm1 {k1}{z}, xmm2, xmm3/m128/m64bcstAV/VAVX512VLAVX512FBlend double-precision vector xmm2 and double-precision vector xmm3/m128/m64bcst and store the result in xmm1, under control mask.EVEX.256.66.0F38.W1 65 /rVBLENDMPD ymm1 {k1}{z}, ymm2, ymm3/m256/m64bcstAV/VAVX512VLAVX512FBlend double-precision vector ymm2 and double-precision vector ymm3/m256/m64bcst and store the result in ymm1, under control mask.EVEX.512.66.0F38.W1 65 /rVBLENDMPD zmm1 {k1}{z}, zmm2, zmm3/m512/m64bcstAV/VAVX512FBlend double-precision vector zmm2 and double-precision vector zmm3/m512/m64bcst and store the result in zmm1, under control mask.EVEX.128.66.0F38.W0 65 /rVBLENDMPS xmm1 {k1}{z}, xmm2, xmm3/m128/m32bcstAV/VAVX512VLAVX512FBlend single-precision vector xmm2 and single-precision vector xmm3/m128/m32bcst and store the result in xmm1, under control mask.EVEX.256.66.0F38.W0 65 /rVBLENDMPS ymm1 {k1}{z}, ymm2, ymm3/m256/m32bcstAV/VAVX512VLAVX512FBlend single-precision vector ymm2 and single-precision vector ymm3/m256/m32bcst and store the result in ymm1, under control mask.EVEX.512.66.0F38.W0 65 /rVBLENDMPS zmm1 {k1}{z}, zmm2, zmm3/m512/m32bcstAV/VAVX512FBlend single-precision vector zmm2 and single-precision vector zmm3/m512/m32bcst using k1 as select control and store the result in zmm1.Op/EnTuple TypeOperand 1Operand 2Operand 3Operand 4AFullModRM:reg (w)EVEX.vvvv (r)ModRM:r/m (r)NA

image/svg+xmlOperationVBLENDMPD (EVEX encoded versions)(KL, VL) = (2, 128), (4, 256), (8, 512)FOR j := 0 TO KL-1i := j * 64IF k1[j] OR *no controlmask*THENIF (EVEX.b = 1) AND (SRC2 *is memory*)THENDEST[i+63:i] := SRC2[63:0]ELSE DEST[i+63:i] := SRC2[i+63:i]FI;ELSE IF *merging-masking*; merging-maskingTHEN DEST[i+63:i] := SRC1[i+63:i]ELSE ; zeroing-maskingDEST[i+63:i] := 0FI;FI;ENDFORDEST[MAXVL-1:VL] := 0VBLENDMPS (EVEX encoded versions)(KL, VL) = (4, 128), (8, 256), (16, 512)FOR j := 0 TO KL-1i := j * 32IF k1[j] OR *no controlmask*THENIF (EVEX.b = 1) AND (SRC2 *is memory*)THENDEST[i+31:i] := SRC2[31:0]ELSE DEST[i+31:i] := SRC2[i+31:i]FI;ELSE IF *merging-masking*; merging-maskingTHEN DEST[i+31:i] := SRC1[i+31:i]ELSE ; zeroing-maskingDEST[i+31:i] := 0FI;FI;ENDFORDEST[MAXVL-1:VL] := 0

image/svg+xmlIntel C/C++ Compiler Intrinsic EquivalentVBLENDMPD __m512d _mm512_mask_blend_pd(__mmask8 k, __m512d a, __m512d b);VBLENDMPD __m256d _mm256_mask_blend_pd(__mmask8 k, __m256d a, __m256d b);VBLENDMPD __m128d _mm_mask_blend_pd(__mmask8 k, __m128d a, __m128d b);VBLENDMPS __m512 _mm512_mask_blend_ps(__mmask16 k, __m512 a, __m512 b);VBLENDMPS __m256 _mm256_mask_blend_ps(__mmask8 k, __m256 a, __m256 b);VBLENDMPS __m128 _mm_mask_blend_ps(__mmask8 k, __m128 a, __m128 b);SIMD Floating-Point ExceptionsNoneOther ExceptionsSee Table2-49, “Type E4 Class Exception Conditions”.

This UNOFFICIAL reference was generated from the official Intel® 64 and IA-32 Architectures Software Developer’s Manual by a dumb script. There is no guarantee that some parts aren't mangled or broken and is distributed WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.