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::CVTSS2SIrr, X86::CVTSS2SIrm, 0 },
{ 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::CVTTPD2DQrr, X86::CVTTPD2DQrm, TB_ALIGN_16 },
{ X86::CVTTPS2DQrr, X86::CVTTPS2DQrm, TB_ALIGN_16 },
{ X86::VCVTSS2SIrr, X86::VCVTSS2SIrm, 0 },
{ X86::VCVTDQ2PSrr, X86::VCVTDQ2PSrm, 0 },
{ X86::VCVTPD2DQrr, X86::VCVTPD2DQXrm, 0 },
+ { X86::VCVTPD2PSrr, X86::VCVTPD2PSXrm, 0 },
{ X86::VCVTPS2DQrr, X86::VCVTPS2DQrm, 0 },
{ X86::VCVTTPD2DQrr, X86::VCVTTPD2DQXrm, 0 },
{ X86::VCVTTPS2DQrr, X86::VCVTTPS2DQrm, 0 },
// AVX 256-bit foldable instructions
{ X86::VCVTDQ2PSYrr, X86::VCVTDQ2PSYrm, 0 },
{ X86::VCVTPD2DQYrr, X86::VCVTPD2DQYrm, 0 },
+ { X86::VCVTPD2PSYrr, X86::VCVTPD2PSYrm, 0 },
{ X86::VCVTPS2DQYrr, X86::VCVTPS2DQYrm, 0 },
{ X86::VCVTTPD2DQYrr, X86::VCVTTPD2DQYrm, 0 },
{ X86::VCVTTPS2DQYrr, X86::VCVTTPS2DQYrm, 0 },
{ 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 },
// AES foldable instructions
{ X86::AESIMCrr, X86::AESIMCrm, TB_ALIGN_16 },
{ 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:
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;
}
projects / oota-llvm.git / blobdiff