VPDPWSSD — Multiply and Add Signed Word IntegersInstruction Operand EncodingDescriptionMultiplies the individual signed words of the first source operand by the corresponding signed words of the second source operand, producing intermediate signed, doubleword results. The adjacent doubleword results are then summed and accumulated in the destination operand.This instruction supports memory fault suppression.OperationVPDPWSSD dest, src1, src2 (VEX encoded versions)VL=(128, 256)KL=VL/32ORIGDEST := DESTFOR i := 0 TO KL-1:p1dword := SIGN_EXTEND(SRC1.word[2*i+0]) * SIGN_EXTEND(SRC2.word[2*i+0] )p2dword := SIGN_EXTEND(SRC1.word[2*i+1]) * SIGN_EXTEND(SRC2.word[2*i+1] )DEST.dword[i] := ORIGDEST.dword[i] + p1dword + p2dwordDEST[MAX_VL-1:VL] := 0Opcode/InstructionOp/En64/32 bit Mode SupportCPUID Feature FlagDescriptionVEX.128.66.0F38.W0 52 /r VPDPWSSD xmm1, xmm2, xmm3/m128AV/VAVX-VNNIMultiply groups of 2 pairs signed words in xmm3/m128 with corresponding signed words of xmm2, summing those products and adding them to doubleword result in xmm1.VEX.256.66.0F38.W0 52 /rVPDPWSSD ymm1, ymm2, ymm3/m256AV/VAVX-VNNIMultiply groups of 2 pairs signed words in ymm3/m256 with corresponding signed words of ymm2, summing those products and adding them to doubleword result in ymm1.EVEX.128.66.0F38.W0 52 /rVPDPWSSD xmm1{k1}{z}, xmm2, xmm3/m128/m32bcstBV/VAVX512_VNNIAVX512VLMultiply groups of 2 pairs signed words in xmm3/m128/m32bcst with corresponding signed words of xmm2, summing those products and adding them to doubleword result in xmm1, under writemask k1.EVEX.256.66.0F38.W0 52 /rVPDPWSSD ymm1{k1}{z}, ymm2, ymm3/m256/m32bcstBV/VAVX512_VNNIAVX512VLMultiply groups of 2 pairs signed words in ymm3/m256/m32bcst with corresponding signed words of ymm2, summing those products and adding them to doubleword result in ymm1, under writemask k1.EVEX.512.66.0F38.W0 52 /rVPDPWSSD zmm1{k1}{z}, zmm2, zmm3/m512/m32bcstBV/VAVX512_VNNIMultiply groups of 2 pairs signed words in zmm3/m512/m32bcst with corresponding signed words of zmm2, summing those products and adding them to doubleword result in zmm1, under writemask k1.Op/EnTupleOperand 1Operand 2Operand 3Operand 4ANAModRM:reg (r, w)VEX.vvvv (r)ModRM:r/m (r)NABFullModRM:reg (r, w)EVEX.vvvv (r)ModRM:r/m (r)NA
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.