TB_INDEX_1 = 1,
TB_INDEX_2 = 2,
TB_INDEX_3 = 3,
+ TB_INDEX_4 = 4,
TB_INDEX_MASK = 0xf,
// Do not insert the reverse map (MemOp -> RegOp) into the table.
{ X86::AND8rr, X86::AND8mr, 0 },
{ X86::DEC16r, X86::DEC16m, 0 },
{ X86::DEC32r, X86::DEC32m, 0 },
- { X86::DEC64_16r, X86::DEC64_16m, 0 },
- { X86::DEC64_32r, X86::DEC64_32m, 0 },
{ X86::DEC64r, X86::DEC64m, 0 },
{ X86::DEC8r, X86::DEC8m, 0 },
{ X86::INC16r, X86::INC16m, 0 },
{ X86::INC32r, X86::INC32m, 0 },
- { X86::INC64_16r, X86::INC64_16m, 0 },
- { X86::INC64_32r, X86::INC64_32m, 0 },
{ X86::INC64r, X86::INC64m, 0 },
{ X86::INC8r, X86::INC8m, 0 },
{ X86::NEG16r, X86::NEG16m, 0 },
{ X86::MUL32r, X86::MUL32m, TB_FOLDED_LOAD },
{ X86::MUL64r, X86::MUL64m, TB_FOLDED_LOAD },
{ X86::MUL8r, X86::MUL8m, TB_FOLDED_LOAD },
+ { X86::PEXTRDrr, X86::PEXTRDmr, TB_FOLDED_STORE },
+ { X86::PEXTRQrr, X86::PEXTRQmr, TB_FOLDED_STORE },
{ X86::SETAEr, X86::SETAEm, TB_FOLDED_STORE },
{ X86::SETAr, X86::SETAm, TB_FOLDED_STORE },
{ X86::SETBEr, X86::SETBEm, TB_FOLDED_STORE },
{ X86::VMOVSS2DIrr, X86::VMOVSS2DImr, TB_FOLDED_STORE },
{ X86::VMOVUPDrr, X86::VMOVUPDmr, TB_FOLDED_STORE },
{ X86::VMOVUPSrr, X86::VMOVUPSmr, TB_FOLDED_STORE },
+ { X86::VPEXTRDrr, X86::VPEXTRDmr, TB_FOLDED_STORE },
+ { X86::VPEXTRQrr, X86::VPEXTRQmr, TB_FOLDED_STORE },
// AVX 256-bit foldable instructions
{ X86::VEXTRACTI128rr, X86::VEXTRACTI128mr, TB_FOLDED_STORE | TB_ALIGN_16 },
{ X86::VMOVAPDYrr, X86::VMOVAPDYmr, TB_FOLDED_STORE | TB_ALIGN_32 },
{ X86::VMOVDQU8Z128rr, X86::VMOVDQU8Z128mr, TB_FOLDED_STORE },
{ X86::VMOVDQU16Z128rr, X86::VMOVDQU16Z128mr, TB_FOLDED_STORE },
{ X86::VMOVDQU32Z128rr, X86::VMOVDQU32Z128mr, TB_FOLDED_STORE },
- { X86::VMOVDQU64Z128rr, X86::VMOVDQU64Z128mr, TB_FOLDED_STORE }
+ { X86::VMOVDQU64Z128rr, X86::VMOVDQU64Z128mr, TB_FOLDED_STORE },
+ // F16C foldable instructions
+ { X86::VCVTPS2PHrr, X86::VCVTPS2PHmr, TB_FOLDED_STORE },
+ { X86::VCVTPS2PHYrr, X86::VCVTPS2PHYmr, TB_FOLDED_STORE }
};
for (unsigned i = 0, e = array_lengthof(OpTbl0); i != e; ++i) {
{ X86::CVTSD2SIrr, X86::CVTSD2SIrm, 0 },
{ X86::CVTSS2SI64rr, X86::CVTSS2SI64rm, 0 },
{ X86::CVTSS2SIrr, X86::CVTSS2SIrm, 0 },
+ { X86::CVTDQ2PDrr, X86::CVTDQ2PDrm, TB_ALIGN_16 },
+ { X86::CVTDQ2PSrr, X86::CVTDQ2PSrm, TB_ALIGN_16 },
+ { X86::CVTPD2DQrr, X86::CVTPD2DQrm, TB_ALIGN_16 },
+ { X86::CVTPD2PSrr, X86::CVTPD2PSrm, TB_ALIGN_16 },
+ { X86::CVTPS2DQrr, X86::CVTPS2DQrm, TB_ALIGN_16 },
+ { X86::CVTPS2PDrr, X86::CVTPS2PDrm, TB_ALIGN_16 },
{ X86::CVTTPD2DQrr, X86::CVTTPD2DQrm, TB_ALIGN_16 },
{ X86::CVTTPS2DQrr, X86::CVTTPS2DQrm, TB_ALIGN_16 },
{ X86::Int_CVTTSD2SI64rr,X86::Int_CVTTSD2SI64rm, 0 },
{ X86::PABSBrr128, X86::PABSBrm128, TB_ALIGN_16 },
{ X86::PABSDrr128, X86::PABSDrm128, TB_ALIGN_16 },
{ X86::PABSWrr128, X86::PABSWrm128, TB_ALIGN_16 },
+ { X86::PCMPESTRIrr, X86::PCMPESTRIrm, TB_ALIGN_16 },
+ { X86::PCMPESTRM128rr, X86::PCMPESTRM128rm, TB_ALIGN_16 },
+ { X86::PCMPISTRIrr, X86::PCMPISTRIrm, TB_ALIGN_16 },
+ { X86::PCMPISTRM128rr, X86::PCMPISTRM128rm, TB_ALIGN_16 },
+ { X86::PHMINPOSUWrr128, X86::PHMINPOSUWrm128, TB_ALIGN_16 },
+ { X86::PMOVSXBDrr, X86::PMOVSXBDrm, TB_ALIGN_16 },
+ { X86::PMOVSXBQrr, X86::PMOVSXBQrm, TB_ALIGN_16 },
+ { X86::PMOVSXBWrr, X86::PMOVSXBWrm, TB_ALIGN_16 },
+ { X86::PMOVSXDQrr, X86::PMOVSXDQrm, TB_ALIGN_16 },
+ { X86::PMOVSXWDrr, X86::PMOVSXWDrm, TB_ALIGN_16 },
+ { X86::PMOVSXWQrr, X86::PMOVSXWQrm, TB_ALIGN_16 },
+ { X86::PMOVZXBDrr, X86::PMOVZXBDrm, TB_ALIGN_16 },
+ { X86::PMOVZXBQrr, X86::PMOVZXBQrm, TB_ALIGN_16 },
+ { X86::PMOVZXBWrr, X86::PMOVZXBWrm, TB_ALIGN_16 },
+ { X86::PMOVZXDQrr, X86::PMOVZXDQrm, TB_ALIGN_16 },
+ { X86::PMOVZXWDrr, X86::PMOVZXWDrm, TB_ALIGN_16 },
+ { X86::PMOVZXWQrr, X86::PMOVZXWQrm, TB_ALIGN_16 },
{ X86::PSHUFDri, X86::PSHUFDmi, TB_ALIGN_16 },
{ X86::PSHUFHWri, X86::PSHUFHWmi, TB_ALIGN_16 },
{ X86::PSHUFLWri, X86::PSHUFLWmi, TB_ALIGN_16 },
+ { X86::PTESTrr, X86::PTESTrm, TB_ALIGN_16 },
{ X86::RCPPSr, X86::RCPPSm, TB_ALIGN_16 },
{ X86::RCPPSr_Int, X86::RCPPSm_Int, TB_ALIGN_16 },
+ { X86::ROUNDPDr, X86::ROUNDPDm, TB_ALIGN_16 },
+ { X86::ROUNDPSr, X86::ROUNDPSm, TB_ALIGN_16 },
{ X86::RSQRTPSr, X86::RSQRTPSm, TB_ALIGN_16 },
{ X86::RSQRTPSr_Int, X86::RSQRTPSm_Int, TB_ALIGN_16 },
{ X86::RSQRTSSr, X86::RSQRTSSm, 0 },
{ X86::VCVTSD2SIrr, X86::VCVTSD2SIrm, 0 },
{ X86::VCVTSS2SI64rr, X86::VCVTSS2SI64rm, 0 },
{ X86::VCVTSS2SIrr, X86::VCVTSS2SIrm, 0 },
+ { X86::VCVTDQ2PDrr, X86::VCVTDQ2PDrm, 0 },
+ { X86::VCVTDQ2PSrr, X86::VCVTDQ2PSrm, 0 },
+ { X86::VCVTPD2DQrr, X86::VCVTPD2DQXrm, 0 },
+ { X86::VCVTPD2PSrr, X86::VCVTPD2PSXrm, 0 },
+ { X86::VCVTPS2DQrr, X86::VCVTPS2DQrm, 0 },
+ { X86::VCVTPS2PDrr, X86::VCVTPS2PDrm, 0 },
+ { X86::VCVTTPD2DQrr, X86::VCVTTPD2DQXrm, 0 },
+ { X86::VCVTTPS2DQrr, X86::VCVTTPS2DQrm, 0 },
{ X86::VMOV64toPQIrr, X86::VMOVQI2PQIrm, 0 },
{ X86::VMOV64toSDrr, X86::VMOV64toSDrm, 0 },
{ X86::VMOVAPDrr, X86::VMOVAPDrm, TB_ALIGN_16 },
{ X86::VMOVDI2PDIrr, X86::VMOVDI2PDIrm, 0 },
{ X86::VMOVDI2SSrr, X86::VMOVDI2SSrm, 0 },
{ X86::VMOVDQArr, X86::VMOVDQArm, TB_ALIGN_16 },
- { X86::VMOVSLDUPrr, X86::VMOVSLDUPrm, TB_ALIGN_16 },
- { X86::VMOVSHDUPrr, X86::VMOVSHDUPrm, TB_ALIGN_16 },
+ { X86::VMOVSLDUPrr, X86::VMOVSLDUPrm, 0 },
+ { X86::VMOVSHDUPrr, X86::VMOVSHDUPrm, 0 },
{ X86::VMOVUPDrr, X86::VMOVUPDrm, 0 },
{ X86::VMOVUPSrr, X86::VMOVUPSrm, 0 },
{ X86::VMOVZQI2PQIrr, X86::VMOVZQI2PQIrm, 0 },
{ X86::VPABSBrr128, X86::VPABSBrm128, 0 },
{ X86::VPABSDrr128, X86::VPABSDrm128, 0 },
{ X86::VPABSWrr128, X86::VPABSWrm128, 0 },
+ { X86::VPCMPESTRIrr, X86::VPCMPESTRIrm, 0 },
+ { X86::VPCMPESTRM128rr, X86::VPCMPESTRM128rm, 0 },
+ { X86::VPCMPISTRIrr, X86::VPCMPISTRIrm, 0 },
+ { X86::VPCMPISTRM128rr, X86::VPCMPISTRM128rm, 0 },
+ { X86::VPHMINPOSUWrr128, X86::VPHMINPOSUWrm128, 0 },
{ X86::VPERMILPDri, X86::VPERMILPDmi, 0 },
{ X86::VPERMILPSri, X86::VPERMILPSmi, 0 },
+ { X86::VPMOVSXBDrr, X86::VPMOVSXBDrm, 0 },
+ { X86::VPMOVSXBQrr, X86::VPMOVSXBQrm, 0 },
+ { X86::VPMOVSXBWrr, X86::VPMOVSXBWrm, 0 },
+ { X86::VPMOVSXDQrr, X86::VPMOVSXDQrm, 0 },
+ { X86::VPMOVSXWDrr, X86::VPMOVSXWDrm, 0 },
+ { X86::VPMOVSXWQrr, X86::VPMOVSXWQrm, 0 },
+ { X86::VPMOVZXBDrr, X86::VPMOVZXBDrm, 0 },
+ { X86::VPMOVZXBQrr, X86::VPMOVZXBQrm, 0 },
+ { X86::VPMOVZXBWrr, X86::VPMOVZXBWrm, 0 },
+ { X86::VPMOVZXDQrr, X86::VPMOVZXDQrm, 0 },
+ { X86::VPMOVZXWDrr, X86::VPMOVZXWDrm, 0 },
+ { X86::VPMOVZXWQrr, X86::VPMOVZXWQrm, 0 },
{ X86::VPSHUFDri, X86::VPSHUFDmi, 0 },
{ X86::VPSHUFHWri, X86::VPSHUFHWmi, 0 },
{ X86::VPSHUFLWri, X86::VPSHUFLWmi, 0 },
+ { X86::VPTESTrr, X86::VPTESTrm, 0 },
{ X86::VRCPPSr, X86::VRCPPSm, 0 },
{ X86::VRCPPSr_Int, X86::VRCPPSm_Int, 0 },
+ { X86::VROUNDPDr, X86::VROUNDPDm, 0 },
+ { X86::VROUNDPSr, X86::VROUNDPSm, 0 },
{ X86::VRSQRTPSr, X86::VRSQRTPSm, 0 },
{ X86::VRSQRTPSr_Int, X86::VRSQRTPSm_Int, 0 },
{ X86::VSQRTPDr, X86::VSQRTPDm, 0 },
{ X86::VSQRTPSr, X86::VSQRTPSm, 0 },
+ { X86::VTESTPDrr, X86::VTESTPDrm, 0 },
+ { X86::VTESTPSrr, X86::VTESTPSrm, 0 },
{ X86::VUCOMISDrr, X86::VUCOMISDrm, 0 },
{ X86::VUCOMISSrr, X86::VUCOMISSrm, 0 },
{ X86::VBROADCASTSSrr, X86::VBROADCASTSSrm, TB_NO_REVERSE },
// AVX 256-bit foldable instructions
+ { X86::VCVTDQ2PDYrr, X86::VCVTDQ2PDYrm, 0 },
+ { X86::VCVTDQ2PSYrr, X86::VCVTDQ2PSYrm, 0 },
+ { X86::VCVTPD2DQYrr, X86::VCVTPD2DQYrm, 0 },
+ { X86::VCVTPD2PSYrr, X86::VCVTPD2PSYrm, 0 },
+ { X86::VCVTPS2DQYrr, X86::VCVTPS2DQYrm, 0 },
+ { X86::VCVTPS2PDYrr, X86::VCVTPS2PDYrm, 0 },
+ { X86::VCVTTPD2DQYrr, X86::VCVTTPD2DQYrm, 0 },
+ { X86::VCVTTPS2DQYrr, X86::VCVTTPS2DQYrm, 0 },
{ X86::VMOVAPDYrr, X86::VMOVAPDYrm, TB_ALIGN_32 },
{ X86::VMOVAPSYrr, X86::VMOVAPSYrm, TB_ALIGN_32 },
+ { X86::VMOVDDUPYrr, X86::VMOVDDUPYrm, 0 },
{ X86::VMOVDQAYrr, X86::VMOVDQAYrm, TB_ALIGN_32 },
+ { X86::VMOVSLDUPYrr, X86::VMOVSLDUPYrm, 0 },
+ { X86::VMOVSHDUPYrr, X86::VMOVSHDUPYrm, 0 },
{ X86::VMOVUPDYrr, X86::VMOVUPDYrm, 0 },
{ X86::VMOVUPSYrr, X86::VMOVUPSYrm, 0 },
{ X86::VPERMILPDYri, X86::VPERMILPDYmi, 0 },
{ X86::VPERMILPSYri, X86::VPERMILPSYmi, 0 },
{ X86::VRCPPSYr, X86::VRCPPSYm, 0 },
{ X86::VRCPPSYr_Int, X86::VRCPPSYm_Int, 0 },
+ { X86::VROUNDYPDr, X86::VROUNDYPDm, 0 },
+ { X86::VROUNDYPSr, X86::VROUNDYPSm, 0 },
{ X86::VRSQRTPSYr, X86::VRSQRTPSYm, 0 },
+ { X86::VRSQRTPSYr_Int, X86::VRSQRTPSYm_Int, 0 },
{ X86::VSQRTPDYr, X86::VSQRTPDYm, 0 },
{ X86::VSQRTPSYr, X86::VSQRTPSYm, 0 },
+ { X86::VTESTPDYrr, X86::VTESTPDYrm, 0 },
+ { X86::VTESTPSYrr, X86::VTESTPSYrm, 0 },
{ X86::VBROADCASTSSYrr, X86::VBROADCASTSSYrm, TB_NO_REVERSE },
{ X86::VBROADCASTSDYrr, X86::VBROADCASTSDYrm, TB_NO_REVERSE },
{ X86::VMOVUPSZrr, X86::VMOVUPSZrm, 0 },
{ X86::VPABSDZrr, X86::VPABSDZrm, 0 },
{ X86::VPABSQZrr, X86::VPABSQZrm, 0 },
+ { X86::VBROADCASTSSZr, X86::VBROADCASTSSZm, TB_NO_REVERSE },
+ { X86::VBROADCASTSDZr, X86::VBROADCASTSDZm, TB_NO_REVERSE },
// AVX-512 foldable instructions (256-bit versions)
{ X86::VMOVAPDZ256rr, X86::VMOVAPDZ256rm, TB_ALIGN_32 },
{ X86::VMOVAPSZ256rr, X86::VMOVAPSZ256rm, TB_ALIGN_32 },
{ X86::VMOVDQU64Z256rr, X86::VMOVDQU64Z256rm, 0 },
{ X86::VMOVUPDZ256rr, X86::VMOVUPDZ256rm, 0 },
{ X86::VMOVUPSZ256rr, X86::VMOVUPSZ256rm, 0 },
+ { X86::VBROADCASTSSZ256r, X86::VBROADCASTSSZ256m, TB_NO_REVERSE },
+ { X86::VBROADCASTSDZ256r, X86::VBROADCASTSDZ256m, TB_NO_REVERSE },
// AVX-512 foldable instructions (256-bit versions)
{ X86::VMOVAPDZ128rr, X86::VMOVAPDZ128rm, TB_ALIGN_16 },
{ X86::VMOVAPSZ128rr, X86::VMOVAPSZ128rm, TB_ALIGN_16 },
{ X86::VMOVDQU64Z128rr, X86::VMOVDQU64Z128rm, 0 },
{ X86::VMOVUPDZ128rr, X86::VMOVUPDZ128rm, 0 },
{ X86::VMOVUPSZ128rr, X86::VMOVUPSZ128rm, 0 },
-
+ { X86::VBROADCASTSSZ128r, X86::VBROADCASTSSZ128m, TB_NO_REVERSE },
+ // F16C foldable instructions
+ { X86::VCVTPH2PSrr, X86::VCVTPH2PSrm, 0 },
+ { X86::VCVTPH2PSYrr, X86::VCVTPH2PSYrm, 0 },
// AES foldable instructions
{ X86::AESIMCrr, X86::AESIMCrm, TB_ALIGN_16 },
{ X86::AESKEYGENASSIST128rr, X86::AESKEYGENASSIST128rm, TB_ALIGN_16 },
{ X86::ADDPDrr, X86::ADDPDrm, TB_ALIGN_16 },
{ X86::ADDPSrr, X86::ADDPSrm, TB_ALIGN_16 },
{ X86::ADDSDrr, X86::ADDSDrm, 0 },
+ { X86::ADDSDrr_Int, X86::ADDSDrm_Int, 0 },
{ X86::ADDSSrr, X86::ADDSSrm, 0 },
+ { X86::ADDSSrr_Int, X86::ADDSSrm_Int, 0 },
{ X86::ADDSUBPDrr, X86::ADDSUBPDrm, TB_ALIGN_16 },
{ X86::ADDSUBPSrr, X86::ADDSUBPSrm, TB_ALIGN_16 },
{ X86::AND16rr, X86::AND16rm, 0 },
{ X86::DIVPDrr, X86::DIVPDrm, TB_ALIGN_16 },
{ X86::DIVPSrr, X86::DIVPSrm, TB_ALIGN_16 },
{ X86::DIVSDrr, X86::DIVSDrm, 0 },
+ { X86::DIVSDrr_Int, X86::DIVSDrm_Int, 0 },
{ X86::DIVSSrr, X86::DIVSSrm, 0 },
+ { X86::DIVSSrr_Int, X86::DIVSSrm_Int, 0 },
+ { X86::DPPDrri, X86::DPPDrmi, TB_ALIGN_16 },
+ { X86::DPPSrri, X86::DPPSrmi, TB_ALIGN_16 },
{ X86::FsANDNPDrr, X86::FsANDNPDrm, TB_ALIGN_16 },
{ X86::FsANDNPSrr, X86::FsANDNPSrm, TB_ALIGN_16 },
{ X86::FsANDPDrr, X86::FsANDPDrm, TB_ALIGN_16 },
{ X86::MAXPDrr, X86::MAXPDrm, TB_ALIGN_16 },
{ X86::MAXPSrr, X86::MAXPSrm, TB_ALIGN_16 },
{ X86::MAXSDrr, X86::MAXSDrm, 0 },
+ { X86::MAXSDrr_Int, X86::MAXSDrm_Int, 0 },
{ X86::MAXSSrr, X86::MAXSSrm, 0 },
+ { X86::MAXSSrr_Int, X86::MAXSSrm_Int, 0 },
{ X86::MINPDrr, X86::MINPDrm, TB_ALIGN_16 },
{ X86::MINPSrr, X86::MINPSrm, TB_ALIGN_16 },
{ X86::MINSDrr, X86::MINSDrm, 0 },
+ { X86::MINSDrr_Int, X86::MINSDrm_Int, 0 },
{ X86::MINSSrr, X86::MINSSrm, 0 },
+ { X86::MINSSrr_Int, X86::MINSSrm_Int, 0 },
{ X86::MPSADBWrri, X86::MPSADBWrmi, TB_ALIGN_16 },
{ X86::MULPDrr, X86::MULPDrm, TB_ALIGN_16 },
{ X86::MULPSrr, X86::MULPSrm, TB_ALIGN_16 },
{ X86::MULSDrr, X86::MULSDrm, 0 },
+ { X86::MULSDrr_Int, X86::MULSDrm_Int, 0 },
{ X86::MULSSrr, X86::MULSSrm, 0 },
+ { X86::MULSSrr_Int, X86::MULSSrm_Int, 0 },
{ X86::OR16rr, X86::OR16rm, 0 },
{ X86::OR32rr, X86::OR32rm, 0 },
{ X86::OR64rr, X86::OR64rm, 0 },
{ X86::PANDrr, X86::PANDrm, TB_ALIGN_16 },
{ X86::PAVGBrr, X86::PAVGBrm, TB_ALIGN_16 },
{ X86::PAVGWrr, X86::PAVGWrm, TB_ALIGN_16 },
+ { X86::PBLENDVBrr0, X86::PBLENDVBrm0, TB_ALIGN_16 },
{ X86::PBLENDWrri, X86::PBLENDWrmi, TB_ALIGN_16 },
+ { X86::PCLMULQDQrr, X86::PCLMULQDQrm, TB_ALIGN_16 },
{ X86::PCMPEQBrr, X86::PCMPEQBrm, TB_ALIGN_16 },
{ X86::PCMPEQDrr, X86::PCMPEQDrm, TB_ALIGN_16 },
{ X86::PCMPEQQrr, X86::PCMPEQQrm, TB_ALIGN_16 },
{ X86::PHSUBDrr, X86::PHSUBDrm, TB_ALIGN_16 },
{ X86::PHSUBSWrr128, X86::PHSUBSWrm128, TB_ALIGN_16 },
{ X86::PHSUBWrr, X86::PHSUBWrm, TB_ALIGN_16 },
- { X86::PINSRWrri, X86::PINSRWrmi, TB_ALIGN_16 },
+ { X86::PINSRBrr, X86::PINSRBrm, 0 },
+ { X86::PINSRDrr, X86::PINSRDrm, 0 },
+ { X86::PINSRQrr, X86::PINSRQrm, 0 },
+ { X86::PINSRWrri, X86::PINSRWrmi, 0 },
{ X86::PMADDUBSWrr128, X86::PMADDUBSWrm128, TB_ALIGN_16 },
{ X86::PMADDWDrr, X86::PMADDWDrm, TB_ALIGN_16 },
{ X86::PMAXSWrr, X86::PMAXSWrm, TB_ALIGN_16 },
{ X86::PSRLWrr, X86::PSRLWrm, TB_ALIGN_16 },
{ X86::PSUBBrr, X86::PSUBBrm, TB_ALIGN_16 },
{ X86::PSUBDrr, X86::PSUBDrm, TB_ALIGN_16 },
+ { X86::PSUBQrr, X86::PSUBQrm, TB_ALIGN_16 },
{ X86::PSUBSBrr, X86::PSUBSBrm, TB_ALIGN_16 },
{ X86::PSUBSWrr, X86::PSUBSWrm, TB_ALIGN_16 },
+ { X86::PSUBUSBrr, X86::PSUBUSBrm, TB_ALIGN_16 },
+ { X86::PSUBUSWrr, X86::PSUBUSWrm, TB_ALIGN_16 },
{ X86::PSUBWrr, X86::PSUBWrm, TB_ALIGN_16 },
{ X86::PUNPCKHBWrr, X86::PUNPCKHBWrm, TB_ALIGN_16 },
{ X86::PUNPCKHDQrr, X86::PUNPCKHDQrm, TB_ALIGN_16 },
{ X86::SUBPDrr, X86::SUBPDrm, TB_ALIGN_16 },
{ X86::SUBPSrr, X86::SUBPSrm, TB_ALIGN_16 },
{ X86::SUBSDrr, X86::SUBSDrm, 0 },
+ { X86::SUBSDrr_Int, X86::SUBSDrm_Int, 0 },
{ X86::SUBSSrr, X86::SUBSSrm, 0 },
+ { X86::SUBSSrr_Int, X86::SUBSSrm_Int, 0 },
// FIXME: TEST*rr -> swapped operand of TEST*mr.
{ X86::UNPCKHPDrr, X86::UNPCKHPDrm, TB_ALIGN_16 },
{ X86::UNPCKHPSrr, X86::UNPCKHPSrm, TB_ALIGN_16 },
{ X86::Int_VCVTSI2SSrr, X86::Int_VCVTSI2SSrm, 0 },
{ X86::VCVTSS2SDrr, X86::VCVTSS2SDrm, 0 },
{ X86::Int_VCVTSS2SDrr, X86::Int_VCVTSS2SDrm, 0 },
- { X86::VCVTTPD2DQrr, X86::VCVTTPD2DQXrm, 0 },
- { X86::VCVTTPS2DQrr, X86::VCVTTPS2DQrm, 0 },
+ { X86::VRCPSSr, X86::VRCPSSm, 0 },
{ X86::VRSQRTSSr, X86::VRSQRTSSm, 0 },
{ X86::VSQRTSDr, X86::VSQRTSDm, 0 },
{ X86::VSQRTSSr, X86::VSQRTSSm, 0 },
{ X86::VADDPDrr, X86::VADDPDrm, 0 },
{ X86::VADDPSrr, X86::VADDPSrm, 0 },
{ X86::VADDSDrr, X86::VADDSDrm, 0 },
+ { X86::VADDSDrr_Int, X86::VADDSDrm_Int, 0 },
{ X86::VADDSSrr, X86::VADDSSrm, 0 },
+ { X86::VADDSSrr_Int, X86::VADDSSrm_Int, 0 },
{ X86::VADDSUBPDrr, X86::VADDSUBPDrm, 0 },
{ X86::VADDSUBPSrr, X86::VADDSUBPSrm, 0 },
{ X86::VANDNPDrr, X86::VANDNPDrm, 0 },
{ X86::VDIVPDrr, X86::VDIVPDrm, 0 },
{ X86::VDIVPSrr, X86::VDIVPSrm, 0 },
{ X86::VDIVSDrr, X86::VDIVSDrm, 0 },
+ { X86::VDIVSDrr_Int, X86::VDIVSDrm_Int, 0 },
{ X86::VDIVSSrr, X86::VDIVSSrm, 0 },
+ { X86::VDIVSSrr_Int, X86::VDIVSSrm_Int, 0 },
+ { X86::VDPPDrri, X86::VDPPDrmi, 0 },
+ { X86::VDPPSrri, X86::VDPPSrmi, 0 },
{ X86::VFsANDNPDrr, X86::VFsANDNPDrm, TB_ALIGN_16 },
{ X86::VFsANDNPSrr, X86::VFsANDNPSrm, TB_ALIGN_16 },
{ X86::VFsANDPDrr, X86::VFsANDPDrm, TB_ALIGN_16 },
{ X86::VMAXPDrr, X86::VMAXPDrm, 0 },
{ X86::VMAXPSrr, X86::VMAXPSrm, 0 },
{ X86::VMAXSDrr, X86::VMAXSDrm, 0 },
+ { X86::VMAXSDrr_Int, X86::VMAXSDrm_Int, 0 },
{ X86::VMAXSSrr, X86::VMAXSSrm, 0 },
+ { X86::VMAXSSrr_Int, X86::VMAXSSrm_Int, 0 },
{ X86::VMINPDrr, X86::VMINPDrm, 0 },
{ X86::VMINPSrr, X86::VMINPSrm, 0 },
{ X86::VMINSDrr, X86::VMINSDrm, 0 },
+ { X86::VMINSDrr_Int, X86::VMINSDrm_Int, 0 },
{ X86::VMINSSrr, X86::VMINSSrm, 0 },
+ { X86::VMINSSrr_Int, X86::VMINSSrm_Int, 0 },
{ X86::VMPSADBWrri, X86::VMPSADBWrmi, 0 },
{ X86::VMULPDrr, X86::VMULPDrm, 0 },
{ X86::VMULPSrr, X86::VMULPSrm, 0 },
{ X86::VMULSDrr, X86::VMULSDrm, 0 },
+ { X86::VMULSDrr_Int, X86::VMULSDrm_Int, 0 },
{ X86::VMULSSrr, X86::VMULSSrm, 0 },
+ { X86::VMULSSrr_Int, X86::VMULSSrm_Int, 0 },
{ X86::VORPDrr, X86::VORPDrm, 0 },
{ X86::VORPSrr, X86::VORPSrm, 0 },
{ X86::VPACKSSDWrr, X86::VPACKSSDWrm, 0 },
{ X86::VPANDrr, X86::VPANDrm, 0 },
{ X86::VPAVGBrr, X86::VPAVGBrm, 0 },
{ X86::VPAVGWrr, X86::VPAVGWrm, 0 },
+ { X86::VPBLENDVBrr, X86::VPBLENDVBrm, 0 },
{ X86::VPBLENDWrri, X86::VPBLENDWrmi, 0 },
+ { X86::VPCLMULQDQrr, X86::VPCLMULQDQrm, 0 },
{ X86::VPCMPEQBrr, X86::VPCMPEQBrm, 0 },
{ X86::VPCMPEQDrr, X86::VPCMPEQDrm, 0 },
{ X86::VPCMPEQQrr, X86::VPCMPEQQrm, 0 },
{ X86::VPHSUBWrr, X86::VPHSUBWrm, 0 },
{ X86::VPERMILPDrr, X86::VPERMILPDrm, 0 },
{ X86::VPERMILPSrr, X86::VPERMILPSrm, 0 },
+ { X86::VPINSRBrr, X86::VPINSRBrm, 0 },
+ { X86::VPINSRDrr, X86::VPINSRDrm, 0 },
+ { X86::VPINSRQrr, X86::VPINSRQrm, 0 },
{ X86::VPINSRWrri, X86::VPINSRWrmi, 0 },
{ X86::VPMADDUBSWrr128, X86::VPMADDUBSWrm128, 0 },
{ X86::VPMADDWDrr, X86::VPMADDWDrm, 0 },
{ X86::VPSRLWrr, X86::VPSRLWrm, 0 },
{ X86::VPSUBBrr, X86::VPSUBBrm, 0 },
{ X86::VPSUBDrr, X86::VPSUBDrm, 0 },
+ { X86::VPSUBQrr, X86::VPSUBQrm, 0 },
{ X86::VPSUBSBrr, X86::VPSUBSBrm, 0 },
{ X86::VPSUBSWrr, X86::VPSUBSWrm, 0 },
+ { X86::VPSUBUSBrr, X86::VPSUBUSBrm, 0 },
+ { X86::VPSUBUSWrr, X86::VPSUBUSWrm, 0 },
{ X86::VPSUBWrr, X86::VPSUBWrm, 0 },
{ X86::VPUNPCKHBWrr, X86::VPUNPCKHBWrm, 0 },
{ X86::VPUNPCKHDQrr, X86::VPUNPCKHDQrm, 0 },
{ X86::VSUBPDrr, X86::VSUBPDrm, 0 },
{ X86::VSUBPSrr, X86::VSUBPSrm, 0 },
{ X86::VSUBSDrr, X86::VSUBSDrm, 0 },
+ { X86::VSUBSDrr_Int, X86::VSUBSDrm_Int, 0 },
{ X86::VSUBSSrr, X86::VSUBSSrm, 0 },
+ { X86::VSUBSSrr_Int, X86::VSUBSSrm_Int, 0 },
{ X86::VUNPCKHPDrr, X86::VUNPCKHPDrm, 0 },
{ X86::VUNPCKHPSrr, X86::VUNPCKHPSrm, 0 },
{ X86::VUNPCKLPDrr, X86::VUNPCKLPDrm, 0 },
{ X86::VCMPPSYrri, X86::VCMPPSYrmi, 0 },
{ X86::VDIVPDYrr, X86::VDIVPDYrm, 0 },
{ X86::VDIVPSYrr, X86::VDIVPSYrm, 0 },
+ { X86::VDPPSYrri, X86::VDPPSYrmi, 0 },
{ X86::VHADDPDYrr, X86::VHADDPDYrm, 0 },
{ X86::VHADDPSYrr, X86::VHADDPSYrm, 0 },
{ X86::VHSUBPDYrr, X86::VHSUBPDYrm, 0 },
{ X86::VALIGNQrri, X86::VALIGNQrmi, 0 },
{ X86::VALIGNDrri, X86::VALIGNDrmi, 0 },
{ X86::VPMULUDQZrr, X86::VPMULUDQZrm, 0 },
+ { X86::VBROADCASTSSZrkz, X86::VBROADCASTSSZmkz, TB_NO_REVERSE },
+ { X86::VBROADCASTSDZrkz, X86::VBROADCASTSDZmkz, TB_NO_REVERSE },
+
+ // AVX-512{F,VL} foldable instructions
+ { X86::VBROADCASTSSZ256rkz, X86::VBROADCASTSSZ256mkz, TB_NO_REVERSE },
+ { X86::VBROADCASTSDZ256rkz, X86::VBROADCASTSDZ256mkz, TB_NO_REVERSE },
+ { X86::VBROADCASTSSZ128rkz, X86::VBROADCASTSSZ128mkz, TB_NO_REVERSE },
+
+ // AVX-512{F,VL} foldable instructions
+ { X86::VADDPDZ128rr, X86::VADDPDZ128rm, 0 },
+ { X86::VADDPDZ256rr, X86::VADDPDZ256rm, 0 },
+ { X86::VADDPSZ128rr, X86::VADDPSZ128rm, 0 },
+ { X86::VADDPSZ256rr, X86::VADDPSZ256rm, 0 },
// AES foldable instructions
{ X86::AESDECLASTrr, X86::AESDECLASTrm, TB_ALIGN_16 },
{ X86::VBLENDMPDZrr, X86::VBLENDMPDZrm, 0 },
{ X86::VBLENDMPSZrr, X86::VBLENDMPSZrm, 0 },
{ X86::VPBLENDMDZrr, X86::VPBLENDMDZrm, 0 },
- { X86::VPBLENDMQZrr, X86::VPBLENDMQZrm, 0 }
+ { X86::VPBLENDMQZrr, X86::VPBLENDMQZrm, 0 },
+ { X86::VBROADCASTSSZrk, X86::VBROADCASTSSZmk, TB_NO_REVERSE },
+ { X86::VBROADCASTSDZrk, X86::VBROADCASTSDZmk, TB_NO_REVERSE },
+ { X86::VBROADCASTSSZ256rk, X86::VBROADCASTSSZ256mk, TB_NO_REVERSE },
+ { X86::VBROADCASTSDZ256rk, X86::VBROADCASTSDZ256mk, TB_NO_REVERSE },
+ { X86::VBROADCASTSSZ128rk, X86::VBROADCASTSSZ128mk, TB_NO_REVERSE },
+ // AVX-512 arithmetic instructions
+ { X86::VADDPSZrrkz, X86::VADDPSZrmkz, 0 },
+ { X86::VADDPDZrrkz, X86::VADDPDZrmkz, 0 },
+ { X86::VSUBPSZrrkz, X86::VSUBPSZrmkz, 0 },
+ { X86::VSUBPDZrrkz, X86::VSUBPDZrmkz, 0 },
+ { X86::VMULPSZrrkz, X86::VMULPSZrmkz, 0 },
+ { X86::VMULPDZrrkz, X86::VMULPDZrmkz, 0 },
+ { X86::VDIVPSZrrkz, X86::VDIVPSZrmkz, 0 },
+ { X86::VDIVPDZrrkz, X86::VDIVPDZrmkz, 0 },
+ { X86::VMINPSZrrkz, X86::VMINPSZrmkz, 0 },
+ { X86::VMINPDZrrkz, X86::VMINPDZrmkz, 0 },
+ { X86::VMAXPSZrrkz, X86::VMAXPSZrmkz, 0 },
+ { X86::VMAXPDZrrkz, X86::VMAXPDZrmkz, 0 },
+ // AVX-512{F,VL} arithmetic instructions 256-bit
+ { X86::VADDPSZ256rrkz, X86::VADDPSZ256rmkz, 0 },
+ { X86::VADDPDZ256rrkz, X86::VADDPDZ256rmkz, 0 },
+ { X86::VSUBPSZ256rrkz, X86::VSUBPSZ256rmkz, 0 },
+ { X86::VSUBPDZ256rrkz, X86::VSUBPDZ256rmkz, 0 },
+ { X86::VMULPSZ256rrkz, X86::VMULPSZ256rmkz, 0 },
+ { X86::VMULPDZ256rrkz, X86::VMULPDZ256rmkz, 0 },
+ { X86::VDIVPSZ256rrkz, X86::VDIVPSZ256rmkz, 0 },
+ { X86::VDIVPDZ256rrkz, X86::VDIVPDZ256rmkz, 0 },
+ { X86::VMINPSZ256rrkz, X86::VMINPSZ256rmkz, 0 },
+ { X86::VMINPDZ256rrkz, X86::VMINPDZ256rmkz, 0 },
+ { X86::VMAXPSZ256rrkz, X86::VMAXPSZ256rmkz, 0 },
+ { X86::VMAXPDZ256rrkz, X86::VMAXPDZ256rmkz, 0 },
+ // AVX-512{F,VL} arithmetic instructions 128-bit
+ { X86::VADDPSZ128rrkz, X86::VADDPSZ128rmkz, 0 },
+ { X86::VADDPDZ128rrkz, X86::VADDPDZ128rmkz, 0 },
+ { X86::VSUBPSZ128rrkz, X86::VSUBPSZ128rmkz, 0 },
+ { X86::VSUBPDZ128rrkz, X86::VSUBPDZ128rmkz, 0 },
+ { X86::VMULPSZ128rrkz, X86::VMULPSZ128rmkz, 0 },
+ { X86::VMULPDZ128rrkz, X86::VMULPDZ128rmkz, 0 },
+ { X86::VDIVPSZ128rrkz, X86::VDIVPSZ128rmkz, 0 },
+ { X86::VDIVPDZ128rrkz, X86::VDIVPDZ128rmkz, 0 },
+ { X86::VMINPSZ128rrkz, X86::VMINPSZ128rmkz, 0 },
+ { X86::VMINPDZ128rrkz, X86::VMINPDZ128rmkz, 0 },
+ { X86::VMAXPSZ128rrkz, X86::VMAXPSZ128rmkz, 0 },
+ { X86::VMAXPDZ128rrkz, X86::VMAXPDZ128rmkz, 0 }
};
for (unsigned i = 0, e = array_lengthof(OpTbl3); i != e; ++i) {
Flags | TB_INDEX_3 | TB_FOLDED_LOAD);
}
+ static const X86OpTblEntry OpTbl4[] = {
+ // AVX-512 foldable instructions
+ { X86::VADDPSZrrk, X86::VADDPSZrmk, 0 },
+ { X86::VADDPDZrrk, X86::VADDPDZrmk, 0 },
+ { X86::VSUBPSZrrk, X86::VSUBPSZrmk, 0 },
+ { X86::VSUBPDZrrk, X86::VSUBPDZrmk, 0 },
+ { X86::VMULPSZrrk, X86::VMULPSZrmk, 0 },
+ { X86::VMULPDZrrk, X86::VMULPDZrmk, 0 },
+ { X86::VDIVPSZrrk, X86::VDIVPSZrmk, 0 },
+ { X86::VDIVPDZrrk, X86::VDIVPDZrmk, 0 },
+ { X86::VMINPSZrrk, X86::VMINPSZrmk, 0 },
+ { X86::VMINPDZrrk, X86::VMINPDZrmk, 0 },
+ { X86::VMAXPSZrrk, X86::VMAXPSZrmk, 0 },
+ { X86::VMAXPDZrrk, X86::VMAXPDZrmk, 0 },
+ // AVX-512{F,VL} foldable instructions 256-bit
+ { X86::VADDPSZ256rrk, X86::VADDPSZ256rmk, 0 },
+ { X86::VADDPDZ256rrk, X86::VADDPDZ256rmk, 0 },
+ { X86::VSUBPSZ256rrk, X86::VSUBPSZ256rmk, 0 },
+ { X86::VSUBPDZ256rrk, X86::VSUBPDZ256rmk, 0 },
+ { X86::VMULPSZ256rrk, X86::VMULPSZ256rmk, 0 },
+ { X86::VMULPDZ256rrk, X86::VMULPDZ256rmk, 0 },
+ { X86::VDIVPSZ256rrk, X86::VDIVPSZ256rmk, 0 },
+ { X86::VDIVPDZ256rrk, X86::VDIVPDZ256rmk, 0 },
+ { X86::VMINPSZ256rrk, X86::VMINPSZ256rmk, 0 },
+ { X86::VMINPDZ256rrk, X86::VMINPDZ256rmk, 0 },
+ { X86::VMAXPSZ256rrk, X86::VMAXPSZ256rmk, 0 },
+ { X86::VMAXPDZ256rrk, X86::VMAXPDZ256rmk, 0 },
+ // AVX-512{F,VL} foldable instructions 128-bit
+ { X86::VADDPSZ128rrk, X86::VADDPSZ128rmk, 0 },
+ { X86::VADDPDZ128rrk, X86::VADDPDZ128rmk, 0 },
+ { X86::VSUBPSZ128rrk, X86::VSUBPSZ128rmk, 0 },
+ { X86::VSUBPDZ128rrk, X86::VSUBPDZ128rmk, 0 },
+ { X86::VMULPSZ128rrk, X86::VMULPSZ128rmk, 0 },
+ { X86::VMULPDZ128rrk, X86::VMULPDZ128rmk, 0 },
+ { X86::VDIVPSZ128rrk, X86::VDIVPSZ128rmk, 0 },
+ { X86::VDIVPDZ128rrk, X86::VDIVPDZ128rmk, 0 },
+ { X86::VMINPSZ128rrk, X86::VMINPSZ128rmk, 0 },
+ { X86::VMINPDZ128rrk, X86::VMINPDZ128rmk, 0 },
+ { X86::VMAXPSZ128rrk, X86::VMAXPSZ128rmk, 0 },
+ { X86::VMAXPDZ128rrk, X86::VMAXPDZ128rmk, 0 }
+ };
+
+ for (unsigned i = 0, e = array_lengthof(OpTbl4); i != e; ++i) {
+ unsigned RegOp = OpTbl4[i].RegOp;
+ unsigned MemOp = OpTbl4[i].MemOp;
+ unsigned Flags = OpTbl4[i].Flags;
+ AddTableEntry(RegOp2MemOpTable4, MemOp2RegOpTable,
+ RegOp, MemOp,
+ // Index 4, folded load
+ Flags | TB_INDEX_4 | TB_FOLDED_LOAD);
+ }
}
void
case X86::VMOVAPSrm:
case X86::VMOVAPDrm:
case X86::VMOVDQArm:
+ case X86::VMOVUPSYrm:
case X86::VMOVAPSYrm:
+ case X86::VMOVUPDYrm:
case X86::VMOVAPDYrm:
+ case X86::VMOVDQUYrm:
case X86::VMOVDQAYrm:
case X86::MMX_MOVD64rm:
case X86::MMX_MOVQ64rm:
case X86::VMOVAPSmr:
case X86::VMOVAPDmr:
case X86::VMOVDQAmr:
+ case X86::VMOVUPSYmr:
case X86::VMOVAPSYmr:
+ case X86::VMOVUPDYmr:
case X86::VMOVAPDYmr:
+ case X86::VMOVDQUYmr:
case X86::VMOVDQAYmr:
case X86::VMOVUPSZmr:
case X86::VMOVAPSZmr:
break;
}
case X86::INC16r:
- case X86::INC64_16r:
addRegOffset(MIB, leaInReg, true, 1);
break;
case X86::DEC16r:
- case X86::DEC64_16r:
addRegOffset(MIB, leaInReg, true, -1);
break;
case X86::ADD16ri:
unsigned MIOpc = MI->getOpcode();
switch (MIOpc) {
+ default: return nullptr;
case X86::SHL64ri: {
assert(MI->getNumOperands() >= 3 && "Unknown shift instruction!");
unsigned ShAmt = getTruncatedShiftCount(MI, 2);
.addReg(0).addImm(1 << ShAmt).addOperand(Src).addImm(0).addReg(0);
break;
}
- default: {
+ case X86::INC64r:
+ case X86::INC32r: {
+ assert(MI->getNumOperands() >= 2 && "Unknown inc instruction!");
+ unsigned Opc = MIOpc == X86::INC64r ? X86::LEA64r
+ : (is64Bit ? X86::LEA64_32r : X86::LEA32r);
+ bool isKill, isUndef;
+ unsigned SrcReg;
+ MachineOperand ImplicitOp = MachineOperand::CreateReg(0, false);
+ if (!classifyLEAReg(MI, Src, Opc, /*AllowSP=*/ false,
+ SrcReg, isKill, isUndef, ImplicitOp))
+ return nullptr;
- switch (MIOpc) {
- default: return nullptr;
- case X86::INC64r:
- case X86::INC32r:
- case X86::INC64_32r: {
- assert(MI->getNumOperands() >= 2 && "Unknown inc instruction!");
- unsigned Opc = MIOpc == X86::INC64r ? X86::LEA64r
- : (is64Bit ? X86::LEA64_32r : X86::LEA32r);
- bool isKill, isUndef;
- unsigned SrcReg;
- MachineOperand ImplicitOp = MachineOperand::CreateReg(0, false);
- if (!classifyLEAReg(MI, Src, Opc, /*AllowSP=*/ false,
- SrcReg, isKill, isUndef, ImplicitOp))
- return nullptr;
+ MachineInstrBuilder MIB = BuildMI(MF, MI->getDebugLoc(), get(Opc))
+ .addOperand(Dest)
+ .addReg(SrcReg, getKillRegState(isKill) | getUndefRegState(isUndef));
+ if (ImplicitOp.getReg() != 0)
+ MIB.addOperand(ImplicitOp);
- MachineInstrBuilder MIB = BuildMI(MF, MI->getDebugLoc(), get(Opc))
- .addOperand(Dest)
- .addReg(SrcReg, getKillRegState(isKill) | getUndefRegState(isUndef));
- if (ImplicitOp.getReg() != 0)
- MIB.addOperand(ImplicitOp);
+ NewMI = addOffset(MIB, 1);
+ break;
+ }
+ case X86::INC16r:
+ if (DisableLEA16)
+ return is64Bit ? convertToThreeAddressWithLEA(MIOpc, MFI, MBBI, LV)
+ : nullptr;
+ assert(MI->getNumOperands() >= 2 && "Unknown inc instruction!");
+ NewMI = addOffset(BuildMI(MF, MI->getDebugLoc(), get(X86::LEA16r))
+ .addOperand(Dest).addOperand(Src), 1);
+ break;
+ case X86::DEC64r:
+ case X86::DEC32r: {
+ assert(MI->getNumOperands() >= 2 && "Unknown dec instruction!");
+ unsigned Opc = MIOpc == X86::DEC64r ? X86::LEA64r
+ : (is64Bit ? X86::LEA64_32r : X86::LEA32r);
- NewMI = addOffset(MIB, 1);
- break;
- }
- case X86::INC16r:
- case X86::INC64_16r:
- if (DisableLEA16)
- return is64Bit ? convertToThreeAddressWithLEA(MIOpc, MFI, MBBI, LV)
- : nullptr;
- assert(MI->getNumOperands() >= 2 && "Unknown inc instruction!");
- NewMI = addOffset(BuildMI(MF, MI->getDebugLoc(), get(X86::LEA16r))
- .addOperand(Dest).addOperand(Src), 1);
- break;
- case X86::DEC64r:
- case X86::DEC32r:
- case X86::DEC64_32r: {
- assert(MI->getNumOperands() >= 2 && "Unknown dec instruction!");
- unsigned Opc = MIOpc == X86::DEC64r ? X86::LEA64r
- : (is64Bit ? X86::LEA64_32r : X86::LEA32r);
-
- bool isKill, isUndef;
- unsigned SrcReg;
- MachineOperand ImplicitOp = MachineOperand::CreateReg(0, false);
- if (!classifyLEAReg(MI, Src, Opc, /*AllowSP=*/ false,
- SrcReg, isKill, isUndef, ImplicitOp))
- return nullptr;
+ bool isKill, isUndef;
+ unsigned SrcReg;
+ MachineOperand ImplicitOp = MachineOperand::CreateReg(0, false);
+ if (!classifyLEAReg(MI, Src, Opc, /*AllowSP=*/ false,
+ SrcReg, isKill, isUndef, ImplicitOp))
+ return nullptr;
- MachineInstrBuilder MIB = BuildMI(MF, MI->getDebugLoc(), get(Opc))
- .addOperand(Dest)
- .addReg(SrcReg, getUndefRegState(isUndef) | getKillRegState(isKill));
- if (ImplicitOp.getReg() != 0)
- MIB.addOperand(ImplicitOp);
+ MachineInstrBuilder MIB = BuildMI(MF, MI->getDebugLoc(), get(Opc))
+ .addOperand(Dest)
+ .addReg(SrcReg, getUndefRegState(isUndef) | getKillRegState(isKill));
+ if (ImplicitOp.getReg() != 0)
+ MIB.addOperand(ImplicitOp);
- NewMI = addOffset(MIB, -1);
+ NewMI = addOffset(MIB, -1);
- break;
- }
- case X86::DEC16r:
- case X86::DEC64_16r:
- if (DisableLEA16)
- return is64Bit ? convertToThreeAddressWithLEA(MIOpc, MFI, MBBI, LV)
- : nullptr;
- assert(MI->getNumOperands() >= 2 && "Unknown dec instruction!");
- NewMI = addOffset(BuildMI(MF, MI->getDebugLoc(), get(X86::LEA16r))
- .addOperand(Dest).addOperand(Src), -1);
- break;
- case X86::ADD64rr:
- case X86::ADD64rr_DB:
- case X86::ADD32rr:
- case X86::ADD32rr_DB: {
- assert(MI->getNumOperands() >= 3 && "Unknown add instruction!");
- unsigned Opc;
- if (MIOpc == X86::ADD64rr || MIOpc == X86::ADD64rr_DB)
- Opc = X86::LEA64r;
- else
- Opc = is64Bit ? X86::LEA64_32r : X86::LEA32r;
+ break;
+ }
+ case X86::DEC16r:
+ if (DisableLEA16)
+ return is64Bit ? convertToThreeAddressWithLEA(MIOpc, MFI, MBBI, LV)
+ : nullptr;
+ assert(MI->getNumOperands() >= 2 && "Unknown dec instruction!");
+ NewMI = addOffset(BuildMI(MF, MI->getDebugLoc(), get(X86::LEA16r))
+ .addOperand(Dest).addOperand(Src), -1);
+ break;
+ case X86::ADD64rr:
+ case X86::ADD64rr_DB:
+ case X86::ADD32rr:
+ case X86::ADD32rr_DB: {
+ assert(MI->getNumOperands() >= 3 && "Unknown add instruction!");
+ unsigned Opc;
+ if (MIOpc == X86::ADD64rr || MIOpc == X86::ADD64rr_DB)
+ Opc = X86::LEA64r;
+ else
+ Opc = is64Bit ? X86::LEA64_32r : X86::LEA32r;
- bool isKill, isUndef;
- unsigned SrcReg;
- MachineOperand ImplicitOp = MachineOperand::CreateReg(0, false);
- if (!classifyLEAReg(MI, Src, Opc, /*AllowSP=*/ true,
- SrcReg, isKill, isUndef, ImplicitOp))
- return nullptr;
+ bool isKill, isUndef;
+ unsigned SrcReg;
+ MachineOperand ImplicitOp = MachineOperand::CreateReg(0, false);
+ if (!classifyLEAReg(MI, Src, Opc, /*AllowSP=*/ true,
+ SrcReg, isKill, isUndef, ImplicitOp))
+ return nullptr;
- const MachineOperand &Src2 = MI->getOperand(2);
- bool isKill2, isUndef2;
- unsigned SrcReg2;
- MachineOperand ImplicitOp2 = MachineOperand::CreateReg(0, false);
- if (!classifyLEAReg(MI, Src2, Opc, /*AllowSP=*/ false,
- SrcReg2, isKill2, isUndef2, ImplicitOp2))
- return nullptr;
+ const MachineOperand &Src2 = MI->getOperand(2);
+ bool isKill2, isUndef2;
+ unsigned SrcReg2;
+ MachineOperand ImplicitOp2 = MachineOperand::CreateReg(0, false);
+ if (!classifyLEAReg(MI, Src2, Opc, /*AllowSP=*/ false,
+ SrcReg2, isKill2, isUndef2, ImplicitOp2))
+ return nullptr;
- MachineInstrBuilder MIB = BuildMI(MF, MI->getDebugLoc(), get(Opc))
- .addOperand(Dest);
- if (ImplicitOp.getReg() != 0)
- MIB.addOperand(ImplicitOp);
- if (ImplicitOp2.getReg() != 0)
- MIB.addOperand(ImplicitOp2);
+ MachineInstrBuilder MIB = BuildMI(MF, MI->getDebugLoc(), get(Opc))
+ .addOperand(Dest);
+ if (ImplicitOp.getReg() != 0)
+ MIB.addOperand(ImplicitOp);
+ if (ImplicitOp2.getReg() != 0)
+ MIB.addOperand(ImplicitOp2);
- NewMI = addRegReg(MIB, SrcReg, isKill, SrcReg2, isKill2);
+ NewMI = addRegReg(MIB, SrcReg, isKill, SrcReg2, isKill2);
- // Preserve undefness of the operands.
- NewMI->getOperand(1).setIsUndef(isUndef);
- NewMI->getOperand(3).setIsUndef(isUndef2);
+ // Preserve undefness of the operands.
+ NewMI->getOperand(1).setIsUndef(isUndef);
+ NewMI->getOperand(3).setIsUndef(isUndef2);
- if (LV && Src2.isKill())
- LV->replaceKillInstruction(SrcReg2, MI, NewMI);
- break;
- }
- case X86::ADD16rr:
- case X86::ADD16rr_DB: {
- if (DisableLEA16)
- return is64Bit ? convertToThreeAddressWithLEA(MIOpc, MFI, MBBI, LV)
- : nullptr;
- assert(MI->getNumOperands() >= 3 && "Unknown add instruction!");
- unsigned Src2 = MI->getOperand(2).getReg();
- bool isKill2 = MI->getOperand(2).isKill();
- NewMI = addRegReg(BuildMI(MF, MI->getDebugLoc(), get(X86::LEA16r))
- .addOperand(Dest),
- Src.getReg(), Src.isKill(), Src2, isKill2);
-
- // Preserve undefness of the operands.
- bool isUndef = MI->getOperand(1).isUndef();
- bool isUndef2 = MI->getOperand(2).isUndef();
- NewMI->getOperand(1).setIsUndef(isUndef);
- NewMI->getOperand(3).setIsUndef(isUndef2);
-
- if (LV && isKill2)
- LV->replaceKillInstruction(Src2, MI, NewMI);
- break;
- }
- case X86::ADD64ri32:
- case X86::ADD64ri8:
- case X86::ADD64ri32_DB:
- case X86::ADD64ri8_DB:
- assert(MI->getNumOperands() >= 3 && "Unknown add instruction!");
- NewMI = addOffset(BuildMI(MF, MI->getDebugLoc(), get(X86::LEA64r))
- .addOperand(Dest).addOperand(Src),
- MI->getOperand(2).getImm());
- break;
- case X86::ADD32ri:
- case X86::ADD32ri8:
- case X86::ADD32ri_DB:
- case X86::ADD32ri8_DB: {
- assert(MI->getNumOperands() >= 3 && "Unknown add instruction!");
- unsigned Opc = is64Bit ? X86::LEA64_32r : X86::LEA32r;
-
- bool isKill, isUndef;
- unsigned SrcReg;
- MachineOperand ImplicitOp = MachineOperand::CreateReg(0, false);
- if (!classifyLEAReg(MI, Src, Opc, /*AllowSP=*/ true,
- SrcReg, isKill, isUndef, ImplicitOp))
- return nullptr;
+ if (LV && Src2.isKill())
+ LV->replaceKillInstruction(SrcReg2, MI, NewMI);
+ break;
+ }
+ case X86::ADD16rr:
+ case X86::ADD16rr_DB: {
+ if (DisableLEA16)
+ return is64Bit ? convertToThreeAddressWithLEA(MIOpc, MFI, MBBI, LV)
+ : nullptr;
+ assert(MI->getNumOperands() >= 3 && "Unknown add instruction!");
+ unsigned Src2 = MI->getOperand(2).getReg();
+ bool isKill2 = MI->getOperand(2).isKill();
+ NewMI = addRegReg(BuildMI(MF, MI->getDebugLoc(), get(X86::LEA16r))
+ .addOperand(Dest),
+ Src.getReg(), Src.isKill(), Src2, isKill2);
+
+ // Preserve undefness of the operands.
+ bool isUndef = MI->getOperand(1).isUndef();
+ bool isUndef2 = MI->getOperand(2).isUndef();
+ NewMI->getOperand(1).setIsUndef(isUndef);
+ NewMI->getOperand(3).setIsUndef(isUndef2);
+
+ if (LV && isKill2)
+ LV->replaceKillInstruction(Src2, MI, NewMI);
+ break;
+ }
+ case X86::ADD64ri32:
+ case X86::ADD64ri8:
+ case X86::ADD64ri32_DB:
+ case X86::ADD64ri8_DB:
+ assert(MI->getNumOperands() >= 3 && "Unknown add instruction!");
+ NewMI = addOffset(BuildMI(MF, MI->getDebugLoc(), get(X86::LEA64r))
+ .addOperand(Dest).addOperand(Src),
+ MI->getOperand(2).getImm());
+ break;
+ case X86::ADD32ri:
+ case X86::ADD32ri8:
+ case X86::ADD32ri_DB:
+ case X86::ADD32ri8_DB: {
+ assert(MI->getNumOperands() >= 3 && "Unknown add instruction!");
+ unsigned Opc = is64Bit ? X86::LEA64_32r : X86::LEA32r;
+
+ bool isKill, isUndef;
+ unsigned SrcReg;
+ MachineOperand ImplicitOp = MachineOperand::CreateReg(0, false);
+ if (!classifyLEAReg(MI, Src, Opc, /*AllowSP=*/ true,
+ SrcReg, isKill, isUndef, ImplicitOp))
+ return nullptr;
- MachineInstrBuilder MIB = BuildMI(MF, MI->getDebugLoc(), get(Opc))
- .addOperand(Dest)
- .addReg(SrcReg, getUndefRegState(isUndef) | getKillRegState(isKill));
- if (ImplicitOp.getReg() != 0)
- MIB.addOperand(ImplicitOp);
+ MachineInstrBuilder MIB = BuildMI(MF, MI->getDebugLoc(), get(Opc))
+ .addOperand(Dest)
+ .addReg(SrcReg, getUndefRegState(isUndef) | getKillRegState(isKill));
+ if (ImplicitOp.getReg() != 0)
+ MIB.addOperand(ImplicitOp);
- NewMI = addOffset(MIB, MI->getOperand(2).getImm());
- break;
- }
- case X86::ADD16ri:
- case X86::ADD16ri8:
- case X86::ADD16ri_DB:
- case X86::ADD16ri8_DB:
- if (DisableLEA16)
- return is64Bit ? convertToThreeAddressWithLEA(MIOpc, MFI, MBBI, LV)
- : nullptr;
- assert(MI->getNumOperands() >= 3 && "Unknown add instruction!");
- NewMI = addOffset(BuildMI(MF, MI->getDebugLoc(), get(X86::LEA16r))
- .addOperand(Dest).addOperand(Src),
- MI->getOperand(2).getImm());
- break;
- }
+ NewMI = addOffset(MIB, MI->getOperand(2).getImm());
+ break;
}
+ case X86::ADD16ri:
+ case X86::ADD16ri8:
+ case X86::ADD16ri_DB:
+ case X86::ADD16ri8_DB:
+ if (DisableLEA16)
+ return is64Bit ? convertToThreeAddressWithLEA(MIOpc, MFI, MBBI, LV)
+ : nullptr;
+ assert(MI->getNumOperands() >= 3 && "Unknown add instruction!");
+ NewMI = addOffset(BuildMI(MF, MI->getDebugLoc(), get(X86::LEA16r))
+ .addOperand(Dest).addOperand(Src),
+ MI->getOperand(2).getImm());
+ break;
}
if (!NewMI) return nullptr;
MI->getOperand(3).setImm(Size-Amt);
return TargetInstrInfo::commuteInstruction(MI, NewMI);
}
+ case X86::BLENDPDrri:
+ case X86::BLENDPSrri:
+ case X86::PBLENDWrri:
+ case X86::VBLENDPDrri:
+ case X86::VBLENDPSrri:
+ case X86::VBLENDPDYrri:
+ case X86::VBLENDPSYrri:
+ case X86::VPBLENDDrri:
+ case X86::VPBLENDWrri:
+ case X86::VPBLENDDYrri:
+ case X86::VPBLENDWYrri:{
+ unsigned Mask;
+ switch (MI->getOpcode()) {
+ default: llvm_unreachable("Unreachable!");
+ case X86::BLENDPDrri: Mask = 0x03; break;
+ case X86::BLENDPSrri: Mask = 0x0F; break;
+ case X86::PBLENDWrri: Mask = 0xFF; break;
+ case X86::VBLENDPDrri: Mask = 0x03; break;
+ case X86::VBLENDPSrri: Mask = 0x0F; break;
+ case X86::VBLENDPDYrri: Mask = 0x0F; break;
+ case X86::VBLENDPSYrri: Mask = 0xFF; break;
+ case X86::VPBLENDDrri: Mask = 0x0F; break;
+ case X86::VPBLENDWrri: Mask = 0xFF; break;
+ case X86::VPBLENDDYrri: Mask = 0xFF; break;
+ case X86::VPBLENDWYrri: Mask = 0xFF; break;
+ }
+ // Only the least significant bits of Imm are used.
+ unsigned Imm = MI->getOperand(3).getImm() & Mask;
+ if (NewMI) {
+ MachineFunction &MF = *MI->getParent()->getParent();
+ MI = MF.CloneMachineInstr(MI);
+ NewMI = false;
+ }
+ MI->getOperand(3).setImm(Mask ^ Imm);
+ return TargetInstrInfo::commuteInstruction(MI, NewMI);
+ }
+ case X86::PCLMULQDQrr:
+ case X86::VPCLMULQDQrr:{
+ // SRC1 64bits = Imm[0] ? SRC1[127:64] : SRC1[63:0]
+ // SRC2 64bits = Imm[4] ? SRC2[127:64] : SRC2[63:0]
+ unsigned Imm = MI->getOperand(3).getImm();
+ unsigned Src1Hi = Imm & 0x01;
+ unsigned Src2Hi = Imm & 0x10;
+ if (NewMI) {
+ MachineFunction &MF = *MI->getParent()->getParent();
+ MI = MF.CloneMachineInstr(MI);
+ NewMI = false;
+ }
+ MI->getOperand(3).setImm((Src1Hi << 4) | (Src2Hi >> 4));
+ return TargetInstrInfo::commuteInstruction(MI, NewMI);
+ }
+ case X86::CMPPDrri:
+ case X86::CMPPSrri:
+ case X86::VCMPPDrri:
+ case X86::VCMPPSrri:
+ case X86::VCMPPDYrri:
+ case X86::VCMPPSYrri: {
+ // Float comparison can be safely commuted for
+ // Ordered/Unordered/Equal/NotEqual tests
+ unsigned Imm = MI->getOperand(3).getImm() & 0x7;
+ switch (Imm) {
+ case 0x00: // EQUAL
+ case 0x03: // UNORDERED
+ case 0x04: // NOT EQUAL
+ case 0x07: // ORDERED
+ if (NewMI) {
+ MachineFunction &MF = *MI->getParent()->getParent();
+ MI = MF.CloneMachineInstr(MI);
+ NewMI = false;
+ }
+ return TargetInstrInfo::commuteInstruction(MI, NewMI);
+ default:
+ return nullptr;
+ }
+ }
case X86::CMOVB16rr: case X86::CMOVB32rr: case X86::CMOVB64rr:
case X86::CMOVAE16rr: case X86::CMOVAE32rr: case X86::CMOVAE64rr:
case X86::CMOVE16rr: case X86::CMOVE32rr: case X86::CMOVE64rr:
bool X86InstrInfo::findCommutedOpIndices(MachineInstr *MI, unsigned &SrcOpIdx1,
unsigned &SrcOpIdx2) const {
switch (MI->getOpcode()) {
+ case X86::BLENDPDrri:
+ case X86::BLENDPSrri:
+ case X86::PBLENDWrri:
+ case X86::VBLENDPDrri:
+ case X86::VBLENDPSrri:
+ case X86::VBLENDPDYrri:
+ case X86::VBLENDPSYrri:
+ case X86::VPBLENDDrri:
+ case X86::VPBLENDDYrri:
+ case X86::VPBLENDWrri:
+ case X86::VPBLENDWYrri:
+ SrcOpIdx1 = 1;
+ SrcOpIdx2 = 2;
+ return true;
+ case X86::CMPPDrri:
+ case X86::CMPPSrri:
+ case X86::VCMPPDrri:
+ case X86::VCMPPSrri:
+ case X86::VCMPPDYrri:
+ case X86::VCMPPSYrri: {
+ // Float comparison can be safely commuted for
+ // Ordered/Unordered/Equal/NotEqual tests
+ unsigned Imm = MI->getOperand(3).getImm() & 0x7;
+ switch (Imm) {
+ case 0x00: // EQUAL
+ case 0x03: // UNORDERED
+ case 0x04: // NOT EQUAL
+ case 0x07: // ORDERED
+ SrcOpIdx1 = 1;
+ SrcOpIdx2 = 2;
+ return true;
+ }
+ return false;
+ }
case X86::VFMADDPDr231r:
case X86::VFMADDPSr231r:
case X86::VFMADDSDr231r:
static X86::CondCode getCondFromBranchOpc(unsigned BrOpc) {
switch (BrOpc) {
default: return X86::COND_INVALID;
- case X86::JE_4: return X86::COND_E;
- case X86::JNE_4: return X86::COND_NE;
- case X86::JL_4: return X86::COND_L;
- case X86::JLE_4: return X86::COND_LE;
- case X86::JG_4: return X86::COND_G;
- case X86::JGE_4: return X86::COND_GE;
- case X86::JB_4: return X86::COND_B;
- case X86::JBE_4: return X86::COND_BE;
- case X86::JA_4: return X86::COND_A;
- case X86::JAE_4: return X86::COND_AE;
- case X86::JS_4: return X86::COND_S;
- case X86::JNS_4: return X86::COND_NS;
- case X86::JP_4: return X86::COND_P;
- case X86::JNP_4: return X86::COND_NP;
- case X86::JO_4: return X86::COND_O;
- case X86::JNO_4: return X86::COND_NO;
+ case X86::JE_1: return X86::COND_E;
+ case X86::JNE_1: return X86::COND_NE;
+ case X86::JL_1: return X86::COND_L;
+ case X86::JLE_1: return X86::COND_LE;
+ case X86::JG_1: return X86::COND_G;
+ case X86::JGE_1: return X86::COND_GE;
+ case X86::JB_1: return X86::COND_B;
+ case X86::JBE_1: return X86::COND_BE;
+ case X86::JA_1: return X86::COND_A;
+ case X86::JAE_1: return X86::COND_AE;
+ case X86::JS_1: return X86::COND_S;
+ case X86::JNS_1: return X86::COND_NS;
+ case X86::JP_1: return X86::COND_P;
+ case X86::JNP_1: return X86::COND_NP;
+ case X86::JO_1: return X86::COND_O;
+ case X86::JNO_1: return X86::COND_NO;
}
}
unsigned X86::GetCondBranchFromCond(X86::CondCode CC) {
switch (CC) {
default: llvm_unreachable("Illegal condition code!");
- case X86::COND_E: return X86::JE_4;
- case X86::COND_NE: return X86::JNE_4;
- case X86::COND_L: return X86::JL_4;
- case X86::COND_LE: return X86::JLE_4;
- case X86::COND_G: return X86::JG_4;
- case X86::COND_GE: return X86::JGE_4;
- case X86::COND_B: return X86::JB_4;
- case X86::COND_BE: return X86::JBE_4;
- case X86::COND_A: return X86::JA_4;
- case X86::COND_AE: return X86::JAE_4;
- case X86::COND_S: return X86::JS_4;
- case X86::COND_NS: return X86::JNS_4;
- case X86::COND_P: return X86::JP_4;
- case X86::COND_NP: return X86::JNP_4;
- case X86::COND_O: return X86::JO_4;
- case X86::COND_NO: return X86::JNO_4;
+ case X86::COND_E: return X86::JE_1;
+ case X86::COND_NE: return X86::JNE_1;
+ case X86::COND_L: return X86::JL_1;
+ case X86::COND_LE: return X86::JLE_1;
+ case X86::COND_G: return X86::JG_1;
+ case X86::COND_GE: return X86::JGE_1;
+ case X86::COND_B: return X86::JB_1;
+ case X86::COND_BE: return X86::JBE_1;
+ case X86::COND_A: return X86::JA_1;
+ case X86::COND_AE: return X86::JAE_1;
+ case X86::COND_S: return X86::JS_1;
+ case X86::COND_NS: return X86::JNS_1;
+ case X86::COND_P: return X86::JP_1;
+ case X86::COND_NP: return X86::JNP_1;
+ case X86::COND_O: return X86::JO_1;
+ case X86::COND_NO: return X86::JNO_1;
}
}
return true;
// Handle unconditional branches.
- if (I->getOpcode() == X86::JMP_4) {
+ if (I->getOpcode() == X86::JMP_1) {
UnCondBrIter = I;
if (!AllowModify) {
BuildMI(MBB, UnCondBrIter, MBB.findDebugLoc(I), get(JNCC))
.addMBB(UnCondBrIter->getOperand(0).getMBB());
- BuildMI(MBB, UnCondBrIter, MBB.findDebugLoc(I), get(X86::JMP_4))
+ BuildMI(MBB, UnCondBrIter, MBB.findDebugLoc(I), get(X86::JMP_1))
.addMBB(TargetBB);
OldInst->eraseFromParent();
--I;
if (I->isDebugValue())
continue;
- if (I->getOpcode() != X86::JMP_4 &&
+ if (I->getOpcode() != X86::JMP_1 &&
getCondFromBranchOpc(I->getOpcode()) == X86::COND_INVALID)
break;
// Remove the branch.
if (Cond.empty()) {
// Unconditional branch?
assert(!FBB && "Unconditional branch with multiple successors!");
- BuildMI(&MBB, DL, get(X86::JMP_4)).addMBB(TBB);
+ BuildMI(&MBB, DL, get(X86::JMP_1)).addMBB(TBB);
return 1;
}
switch (CC) {
case X86::COND_NP_OR_E:
// Synthesize NP_OR_E with two branches.
- BuildMI(&MBB, DL, get(X86::JNP_4)).addMBB(TBB);
+ BuildMI(&MBB, DL, get(X86::JNP_1)).addMBB(TBB);
++Count;
- BuildMI(&MBB, DL, get(X86::JE_4)).addMBB(TBB);
+ BuildMI(&MBB, DL, get(X86::JE_1)).addMBB(TBB);
++Count;
break;
case X86::COND_NE_OR_P:
// Synthesize NE_OR_P with two branches.
- BuildMI(&MBB, DL, get(X86::JNE_4)).addMBB(TBB);
+ BuildMI(&MBB, DL, get(X86::JNE_1)).addMBB(TBB);
++Count;
- BuildMI(&MBB, DL, get(X86::JP_4)).addMBB(TBB);
+ BuildMI(&MBB, DL, get(X86::JP_1)).addMBB(TBB);
++Count;
break;
default: {
}
if (FBB) {
// Two-way Conditional branch. Insert the second branch.
- BuildMI(&MBB, DL, get(X86::JMP_4)).addMBB(FBB);
+ BuildMI(&MBB, DL, get(X86::JMP_1)).addMBB(FBB);
++Count;
}
return Count;
case X86::SUB16rr: case X86::SUB8rr: case X86::SUB64rm:
case X86::SUB32rm: case X86::SUB16rm: case X86::SUB8rm:
case X86::DEC64r: case X86::DEC32r: case X86::DEC16r: case X86::DEC8r:
- case X86::DEC64_32r: case X86::DEC64_16r:
case X86::ADD64ri32: case X86::ADD64ri8: case X86::ADD32ri:
case X86::ADD32ri8: case X86::ADD16ri: case X86::ADD16ri8:
case X86::ADD8ri: case X86::ADD64rr: case X86::ADD32rr:
case X86::ADD16rr: case X86::ADD8rr: case X86::ADD64rm:
case X86::ADD32rm: case X86::ADD16rm: case X86::ADD8rm:
case X86::INC64r: case X86::INC32r: case X86::INC16r: case X86::INC8r:
- case X86::INC64_32r: case X86::INC64_16r:
case X86::AND64ri32: case X86::AND64ri8: case X86::AND32ri:
case X86::AND32ri8: case X86::AND16ri: case X86::AND16ri8:
case X86::AND8ri: case X86::AND64rr: case X86::AND32rr:
unsigned Flag = MachineMemOperand::MOLoad | MachineMemOperand::MOInvariant;
MachineMemOperand *MMO = MBB.getParent()->
getMachineMemOperand(MachinePointerInfo::getGOT(), Flag, 8, 8);
- MachineBasicBlock::iterator I = MIB;
+ MachineBasicBlock::iterator I = MIB.getInstr();
BuildMI(MBB, I, DL, TII.get(X86::MOV64rm), Reg).addReg(X86::RIP).addImm(1)
.addReg(0).addGlobalAddress(GV, 0, X86II::MO_GOTPCREL).addReg(0)
case X86::TEST8ri_NOREX:
MI->setDesc(get(X86::TEST8ri));
return true;
- case X86::KSET0B:
+ case X86::KSET0B:
case X86::KSET0W: return Expand2AddrUndef(MIB, get(X86::KXORWrr));
case X86::KSET1B:
case X86::KSET1W: return Expand2AddrUndef(MIB, get(X86::KXNORWrr));
OpcodeTablePtr = &RegOp2MemOpTable2;
} else if (i == 3) {
OpcodeTablePtr = &RegOp2MemOpTable3;
+ } else if (i == 4) {
+ OpcodeTablePtr = &RegOp2MemOpTable4;
}
// If table selected...
static bool hasPartialRegUpdate(unsigned Opcode) {
switch (Opcode) {
case X86::CVTSI2SSrr:
+ case X86::CVTSI2SSrm:
case X86::CVTSI2SS64rr:
+ case X86::CVTSI2SS64rm:
case X86::CVTSI2SDrr:
+ case X86::CVTSI2SDrm:
case X86::CVTSI2SD64rr:
+ case X86::CVTSI2SD64rm:
case X86::CVTSD2SSrr:
+ case X86::CVTSD2SSrm:
case X86::Int_CVTSD2SSrr:
+ case X86::Int_CVTSD2SSrm:
case X86::CVTSS2SDrr:
+ case X86::CVTSS2SDrm:
case X86::Int_CVTSS2SDrr:
+ case X86::Int_CVTSS2SDrm:
case X86::RCPSSr:
+ case X86::RCPSSm:
case X86::RCPSSr_Int:
+ case X86::RCPSSm_Int:
case X86::ROUNDSDr:
+ case X86::ROUNDSDm:
case X86::ROUNDSDr_Int:
case X86::ROUNDSSr:
+ case X86::ROUNDSSm:
case X86::ROUNDSSr_Int:
case X86::RSQRTSSr:
+ case X86::RSQRTSSm:
case X86::RSQRTSSr_Int:
+ case X86::RSQRTSSm_Int:
case X86::SQRTSSr:
+ case X86::SQRTSSm:
case X86::SQRTSSr_Int:
+ case X86::SQRTSSm_Int:
+ case X86::SQRTSDr:
+ case X86::SQRTSDm:
+ case X86::SQRTSDr_Int:
+ case X86::SQRTSDm_Int:
return true;
}
static bool hasUndefRegUpdate(unsigned Opcode) {
switch (Opcode) {
case X86::VCVTSI2SSrr:
+ case X86::VCVTSI2SSrm:
case X86::Int_VCVTSI2SSrr:
+ case X86::Int_VCVTSI2SSrm:
case X86::VCVTSI2SS64rr:
+ case X86::VCVTSI2SS64rm:
case X86::Int_VCVTSI2SS64rr:
+ case X86::Int_VCVTSI2SS64rm:
case X86::VCVTSI2SDrr:
+ case X86::VCVTSI2SDrm:
case X86::Int_VCVTSI2SDrr:
+ case X86::Int_VCVTSI2SDrm:
case X86::VCVTSI2SD64rr:
+ case X86::VCVTSI2SD64rm:
case X86::Int_VCVTSI2SD64rr:
+ case X86::Int_VCVTSI2SD64rm:
case X86::VCVTSD2SSrr:
+ case X86::VCVTSD2SSrm:
case X86::Int_VCVTSD2SSrr:
+ case X86::Int_VCVTSD2SSrm:
case X86::VCVTSS2SDrr:
+ case X86::VCVTSS2SDrm:
case X86::Int_VCVTSS2SDrr:
+ case X86::Int_VCVTSS2SDrm:
case X86::VRCPSSr:
+ case X86::VRCPSSm:
+ case X86::VRCPSSm_Int:
case X86::VROUNDSDr:
+ case X86::VROUNDSDm:
case X86::VROUNDSDr_Int:
case X86::VROUNDSSr:
+ case X86::VROUNDSSm:
case X86::VROUNDSSr_Int:
case X86::VRSQRTSSr:
+ case X86::VRSQRTSSm:
+ case X86::VRSQRTSSm_Int:
case X86::VSQRTSSr:
-
- // AVX-512
+ case X86::VSQRTSSm:
+ case X86::VSQRTSSm_Int:
+ case X86::VSQRTSDr:
+ case X86::VSQRTSDm:
+ case X86::VSQRTSDm_Int:
+ // AVX-512
case X86::VCVTSD2SSZrr:
+ case X86::VCVTSD2SSZrm:
case X86::VCVTSS2SDZrr:
+ case X86::VCVTSS2SDZrm:
return true;
}
switch(Second->getOpcode()) {
default:
return false;
- case X86::JE_4:
- case X86::JNE_4:
- case X86::JL_4:
- case X86::JLE_4:
- case X86::JG_4:
- case X86::JGE_4:
+ case X86::JE_1:
+ case X86::JNE_1:
+ case X86::JL_1:
+ case X86::JLE_1:
+ case X86::JG_1:
+ case X86::JGE_1:
FuseKind = FuseInc;
break;
- case X86::JB_4:
- case X86::JBE_4:
- case X86::JA_4:
- case X86::JAE_4:
+ case X86::JB_1:
+ case X86::JBE_1:
+ case X86::JA_1:
+ case X86::JAE_1:
FuseKind = FuseCmp;
break;
- case X86::JS_4:
- case X86::JNS_4:
- case X86::JP_4:
- case X86::JNP_4:
- case X86::JO_4:
- case X86::JNO_4:
+ case X86::JS_1:
+ case X86::JNS_1:
+ case X86::JP_1:
+ case X86::JNP_1:
+ case X86::JO_1:
+ case X86::JNO_1:
FuseKind = FuseTest;
break;
}
return FuseKind == FuseCmp || FuseKind == FuseInc;
case X86::INC16r:
case X86::INC32r:
- case X86::INC64_16r:
- case X86::INC64_32r:
case X86::INC64r:
case X86::INC8r:
case X86::DEC16r:
case X86::DEC32r:
- case X86::DEC64_16r:
- case X86::DEC64_32r:
case X86::DEC64r:
case X86::DEC8r:
return FuseKind == FuseInc;
NopInst.setOpcode(X86::NOOP);
}
+// This code must remain in sync with getJumpInstrTableEntryBound in this class!
+// In particular, getJumpInstrTableEntryBound must always return an upper bound
+// on the encoding lengths of the instructions generated by
+// getUnconditionalBranch and getTrap.
void X86InstrInfo::getUnconditionalBranch(
MCInst &Branch, const MCSymbolRefExpr *BranchTarget) const {
- Branch.setOpcode(X86::JMP_4);
+ Branch.setOpcode(X86::JMP_1);
Branch.addOperand(MCOperand::CreateExpr(BranchTarget));
}
+// This code must remain in sync with getJumpInstrTableEntryBound in this class!
+// In particular, getJumpInstrTableEntryBound must always return an upper bound
+// on the encoding lengths of the instructions generated by
+// getUnconditionalBranch and getTrap.
void X86InstrInfo::getTrap(MCInst &MI) const {
MI.setOpcode(X86::TRAP);
}
+// See getTrap and getUnconditionalBranch for conditions on the value returned
+// by this function.
+unsigned X86InstrInfo::getJumpInstrTableEntryBound() const {
+ // 5 bytes suffice: JMP_4 Symbol@PLT is uses 1 byte (E9) for the JMP_4 and 4
+ // bytes for the symbol offset. And TRAP is ud2, which is two bytes (0F 0B).
+ return 5;
+}
+
bool X86InstrInfo::isHighLatencyDef(int opc) const {
switch (opc) {
default: return false;