[llvm-commits] [llvm] r75749 - in /llvm/trunk/lib/Target/X86: X86InstrInfo.cpp X86InstrInfo.h
Evan Cheng
evan.cheng at apple.com
Tue Jul 14 23:10:07 PDT 2009
Author: evancheng
Date: Wed Jul 15 01:10:07 2009
New Revision: 75749
URL: http://llvm.org/viewvc/llvm-project?rev=75749&view=rev
Log:
Move load / store folding alignment require into the table(s).
Modified:
llvm/trunk/lib/Target/X86/X86InstrInfo.cpp
llvm/trunk/lib/Target/X86/X86InstrInfo.h
Modified: llvm/trunk/lib/Target/X86/X86InstrInfo.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86InstrInfo.cpp?rev=75749&r1=75748&r2=75749&view=diff
==============================================================================
--- llvm/trunk/lib/Target/X86/X86InstrInfo.cpp (original)
+++ llvm/trunk/lib/Target/X86/X86InstrInfo.cpp Wed Jul 15 01:10:07 2009
@@ -215,9 +215,10 @@
unsigned RegOp = OpTbl2Addr[i][0];
unsigned MemOp = OpTbl2Addr[i][1];
if (!RegOp2MemOpTable2Addr.insert(std::make_pair((unsigned*)RegOp,
- MemOp)).second)
+ std::make_pair(MemOp,0))).second)
assert(false && "Duplicated entries?");
- unsigned AuxInfo = 0 | (1 << 4) | (1 << 5); // Index 0,folded load and store
+ // Index 0, folded load and store, no alignment requirement.
+ unsigned AuxInfo = 0 | (1 << 4) | (1 << 5);
if (!MemOp2RegOpTable.insert(std::make_pair((unsigned*)MemOp,
std::make_pair(RegOp,
AuxInfo))).second)
@@ -225,93 +226,94 @@
}
// If the third value is 1, then it's folding either a load or a store.
- static const unsigned OpTbl0[][3] = {
- { X86::BT16ri8, X86::BT16mi8, 1 },
- { X86::BT32ri8, X86::BT32mi8, 1 },
- { X86::BT64ri8, X86::BT64mi8, 1 },
- { X86::CALL32r, X86::CALL32m, 1 },
- { X86::CALL64r, X86::CALL64m, 1 },
- { X86::CMP16ri, X86::CMP16mi, 1 },
- { X86::CMP16ri8, X86::CMP16mi8, 1 },
- { X86::CMP16rr, X86::CMP16mr, 1 },
- { X86::CMP32ri, X86::CMP32mi, 1 },
- { X86::CMP32ri8, X86::CMP32mi8, 1 },
- { X86::CMP32rr, X86::CMP32mr, 1 },
- { X86::CMP64ri32, X86::CMP64mi32, 1 },
- { X86::CMP64ri8, X86::CMP64mi8, 1 },
- { X86::CMP64rr, X86::CMP64mr, 1 },
- { X86::CMP8ri, X86::CMP8mi, 1 },
- { X86::CMP8rr, X86::CMP8mr, 1 },
- { X86::DIV16r, X86::DIV16m, 1 },
- { X86::DIV32r, X86::DIV32m, 1 },
- { X86::DIV64r, X86::DIV64m, 1 },
- { X86::DIV8r, X86::DIV8m, 1 },
- { X86::EXTRACTPSrr, X86::EXTRACTPSmr, 0 },
- { X86::FsMOVAPDrr, X86::MOVSDmr, 0 },
- { X86::FsMOVAPSrr, X86::MOVSSmr, 0 },
- { X86::IDIV16r, X86::IDIV16m, 1 },
- { X86::IDIV32r, X86::IDIV32m, 1 },
- { X86::IDIV64r, X86::IDIV64m, 1 },
- { X86::IDIV8r, X86::IDIV8m, 1 },
- { X86::IMUL16r, X86::IMUL16m, 1 },
- { X86::IMUL32r, X86::IMUL32m, 1 },
- { X86::IMUL64r, X86::IMUL64m, 1 },
- { X86::IMUL8r, X86::IMUL8m, 1 },
- { X86::JMP32r, X86::JMP32m, 1 },
- { X86::JMP64r, X86::JMP64m, 1 },
- { X86::MOV16ri, X86::MOV16mi, 0 },
- { X86::MOV16rr, X86::MOV16mr, 0 },
- { X86::MOV32ri, X86::MOV32mi, 0 },
- { X86::MOV32rr, X86::MOV32mr, 0 },
- { X86::MOV64ri32, X86::MOV64mi32, 0 },
- { X86::MOV64rr, X86::MOV64mr, 0 },
- { X86::MOV8ri, X86::MOV8mi, 0 },
- { X86::MOV8rr, X86::MOV8mr, 0 },
- { X86::MOV8rr_NOREX, X86::MOV8mr_NOREX, 0 },
- { X86::MOVAPDrr, X86::MOVAPDmr, 0 },
- { X86::MOVAPSrr, X86::MOVAPSmr, 0 },
- { X86::MOVDQArr, X86::MOVDQAmr, 0 },
- { X86::MOVPDI2DIrr, X86::MOVPDI2DImr, 0 },
- { X86::MOVPQIto64rr,X86::MOVPQI2QImr, 0 },
- { X86::MOVPS2SSrr, X86::MOVPS2SSmr, 0 },
- { X86::MOVSDrr, X86::MOVSDmr, 0 },
- { X86::MOVSDto64rr, X86::MOVSDto64mr, 0 },
- { X86::MOVSS2DIrr, X86::MOVSS2DImr, 0 },
- { X86::MOVSSrr, X86::MOVSSmr, 0 },
- { X86::MOVUPDrr, X86::MOVUPDmr, 0 },
- { X86::MOVUPSrr, X86::MOVUPSmr, 0 },
- { X86::MUL16r, X86::MUL16m, 1 },
- { X86::MUL32r, X86::MUL32m, 1 },
- { X86::MUL64r, X86::MUL64m, 1 },
- { X86::MUL8r, X86::MUL8m, 1 },
- { X86::SETAEr, X86::SETAEm, 0 },
- { X86::SETAr, X86::SETAm, 0 },
- { X86::SETBEr, X86::SETBEm, 0 },
- { X86::SETBr, X86::SETBm, 0 },
- { X86::SETEr, X86::SETEm, 0 },
- { X86::SETGEr, X86::SETGEm, 0 },
- { X86::SETGr, X86::SETGm, 0 },
- { X86::SETLEr, X86::SETLEm, 0 },
- { X86::SETLr, X86::SETLm, 0 },
- { X86::SETNEr, X86::SETNEm, 0 },
- { X86::SETNOr, X86::SETNOm, 0 },
- { X86::SETNPr, X86::SETNPm, 0 },
- { X86::SETNSr, X86::SETNSm, 0 },
- { X86::SETOr, X86::SETOm, 0 },
- { X86::SETPr, X86::SETPm, 0 },
- { X86::SETSr, X86::SETSm, 0 },
- { X86::TAILJMPr, X86::TAILJMPm, 1 },
- { X86::TEST16ri, X86::TEST16mi, 1 },
- { X86::TEST32ri, X86::TEST32mi, 1 },
- { X86::TEST64ri32, X86::TEST64mi32, 1 },
- { X86::TEST8ri, X86::TEST8mi, 1 }
+ static const unsigned OpTbl0[][4] = {
+ { X86::BT16ri8, X86::BT16mi8, 1, 0 },
+ { X86::BT32ri8, X86::BT32mi8, 1, 0 },
+ { X86::BT64ri8, X86::BT64mi8, 1, 0 },
+ { X86::CALL32r, X86::CALL32m, 1, 0 },
+ { X86::CALL64r, X86::CALL64m, 1, 0 },
+ { X86::CMP16ri, X86::CMP16mi, 1, 0 },
+ { X86::CMP16ri8, X86::CMP16mi8, 1, 0 },
+ { X86::CMP16rr, X86::CMP16mr, 1, 0 },
+ { X86::CMP32ri, X86::CMP32mi, 1, 0 },
+ { X86::CMP32ri8, X86::CMP32mi8, 1, 0 },
+ { X86::CMP32rr, X86::CMP32mr, 1, 0 },
+ { X86::CMP64ri32, X86::CMP64mi32, 1, 0 },
+ { X86::CMP64ri8, X86::CMP64mi8, 1, 0 },
+ { X86::CMP64rr, X86::CMP64mr, 1, 0 },
+ { X86::CMP8ri, X86::CMP8mi, 1, 0 },
+ { X86::CMP8rr, X86::CMP8mr, 1, 0 },
+ { X86::DIV16r, X86::DIV16m, 1, 0 },
+ { X86::DIV32r, X86::DIV32m, 1, 0 },
+ { X86::DIV64r, X86::DIV64m, 1, 0 },
+ { X86::DIV8r, X86::DIV8m, 1, 0 },
+ { X86::EXTRACTPSrr, X86::EXTRACTPSmr, 0, 16 },
+ { X86::FsMOVAPDrr, X86::MOVSDmr, 0, 0 },
+ { X86::FsMOVAPSrr, X86::MOVSSmr, 0, 0 },
+ { X86::IDIV16r, X86::IDIV16m, 1, 0 },
+ { X86::IDIV32r, X86::IDIV32m, 1, 0 },
+ { X86::IDIV64r, X86::IDIV64m, 1, 0 },
+ { X86::IDIV8r, X86::IDIV8m, 1, 0 },
+ { X86::IMUL16r, X86::IMUL16m, 1, 0 },
+ { X86::IMUL32r, X86::IMUL32m, 1, 0 },
+ { X86::IMUL64r, X86::IMUL64m, 1, 0 },
+ { X86::IMUL8r, X86::IMUL8m, 1, 0 },
+ { X86::JMP32r, X86::JMP32m, 1, 0 },
+ { X86::JMP64r, X86::JMP64m, 1, 0 },
+ { X86::MOV16ri, X86::MOV16mi, 0, 0 },
+ { X86::MOV16rr, X86::MOV16mr, 0, 0 },
+ { X86::MOV32ri, X86::MOV32mi, 0, 0 },
+ { X86::MOV32rr, X86::MOV32mr, 0, 0 },
+ { X86::MOV64ri32, X86::MOV64mi32, 0, 0 },
+ { X86::MOV64rr, X86::MOV64mr, 0, 0 },
+ { X86::MOV8ri, X86::MOV8mi, 0, 0 },
+ { X86::MOV8rr, X86::MOV8mr, 0, 0 },
+ { X86::MOV8rr_NOREX, X86::MOV8mr_NOREX, 0, 0 },
+ { X86::MOVAPDrr, X86::MOVAPDmr, 0, 16 },
+ { X86::MOVAPSrr, X86::MOVAPSmr, 0, 16 },
+ { X86::MOVDQArr, X86::MOVDQAmr, 0, 16 },
+ { X86::MOVPDI2DIrr, X86::MOVPDI2DImr, 0, 0 },
+ { X86::MOVPQIto64rr,X86::MOVPQI2QImr, 0, 0 },
+ { X86::MOVPS2SSrr, X86::MOVPS2SSmr, 0, 0 },
+ { X86::MOVSDrr, X86::MOVSDmr, 0, 0 },
+ { X86::MOVSDto64rr, X86::MOVSDto64mr, 0, 0 },
+ { X86::MOVSS2DIrr, X86::MOVSS2DImr, 0, 0 },
+ { X86::MOVSSrr, X86::MOVSSmr, 0, 0 },
+ { X86::MOVUPDrr, X86::MOVUPDmr, 0, 0 },
+ { X86::MOVUPSrr, X86::MOVUPSmr, 0, 0 },
+ { X86::MUL16r, X86::MUL16m, 1, 0 },
+ { X86::MUL32r, X86::MUL32m, 1, 0 },
+ { X86::MUL64r, X86::MUL64m, 1, 0 },
+ { X86::MUL8r, X86::MUL8m, 1, 0 },
+ { X86::SETAEr, X86::SETAEm, 0, 0 },
+ { X86::SETAr, X86::SETAm, 0, 0 },
+ { X86::SETBEr, X86::SETBEm, 0, 0 },
+ { X86::SETBr, X86::SETBm, 0, 0 },
+ { X86::SETEr, X86::SETEm, 0, 0 },
+ { X86::SETGEr, X86::SETGEm, 0, 0 },
+ { X86::SETGr, X86::SETGm, 0, 0 },
+ { X86::SETLEr, X86::SETLEm, 0, 0 },
+ { X86::SETLr, X86::SETLm, 0, 0 },
+ { X86::SETNEr, X86::SETNEm, 0, 0 },
+ { X86::SETNOr, X86::SETNOm, 0, 0 },
+ { X86::SETNPr, X86::SETNPm, 0, 0 },
+ { X86::SETNSr, X86::SETNSm, 0, 0 },
+ { X86::SETOr, X86::SETOm, 0, 0 },
+ { X86::SETPr, X86::SETPm, 0, 0 },
+ { X86::SETSr, X86::SETSm, 0, 0 },
+ { X86::TAILJMPr, X86::TAILJMPm, 1, 0 },
+ { X86::TEST16ri, X86::TEST16mi, 1, 0 },
+ { X86::TEST32ri, X86::TEST32mi, 1, 0 },
+ { X86::TEST64ri32, X86::TEST64mi32, 1, 0 },
+ { X86::TEST8ri, X86::TEST8mi, 1, 0 }
};
for (unsigned i = 0, e = array_lengthof(OpTbl0); i != e; ++i) {
unsigned RegOp = OpTbl0[i][0];
unsigned MemOp = OpTbl0[i][1];
+ unsigned Align = OpTbl0[i][3];
if (!RegOp2MemOpTable0.insert(std::make_pair((unsigned*)RegOp,
- MemOp)).second)
+ std::make_pair(MemOp,Align))).second)
assert(false && "Duplicated entries?");
unsigned FoldedLoad = OpTbl0[i][2];
// Index 0, folded load or store.
@@ -322,338 +324,342 @@
AmbEntries.push_back(MemOp);
}
- static const unsigned OpTbl1[][2] = {
- { X86::CMP16rr, X86::CMP16rm },
- { X86::CMP32rr, X86::CMP32rm },
- { X86::CMP64rr, X86::CMP64rm },
- { X86::CMP8rr, X86::CMP8rm },
- { X86::CVTSD2SSrr, X86::CVTSD2SSrm },
- { X86::CVTSI2SD64rr, X86::CVTSI2SD64rm },
- { X86::CVTSI2SDrr, X86::CVTSI2SDrm },
- { X86::CVTSI2SS64rr, X86::CVTSI2SS64rm },
- { X86::CVTSI2SSrr, X86::CVTSI2SSrm },
- { X86::CVTSS2SDrr, X86::CVTSS2SDrm },
- { X86::CVTTSD2SI64rr, X86::CVTTSD2SI64rm },
- { X86::CVTTSD2SIrr, X86::CVTTSD2SIrm },
- { X86::CVTTSS2SI64rr, X86::CVTTSS2SI64rm },
- { X86::CVTTSS2SIrr, X86::CVTTSS2SIrm },
- { X86::FsMOVAPDrr, X86::MOVSDrm },
- { X86::FsMOVAPSrr, X86::MOVSSrm },
- { X86::IMUL16rri, X86::IMUL16rmi },
- { X86::IMUL16rri8, X86::IMUL16rmi8 },
- { X86::IMUL32rri, X86::IMUL32rmi },
- { X86::IMUL32rri8, X86::IMUL32rmi8 },
- { X86::IMUL64rri32, X86::IMUL64rmi32 },
- { X86::IMUL64rri8, X86::IMUL64rmi8 },
- { X86::Int_CMPSDrr, X86::Int_CMPSDrm },
- { X86::Int_CMPSSrr, X86::Int_CMPSSrm },
- { X86::Int_COMISDrr, X86::Int_COMISDrm },
- { X86::Int_COMISSrr, X86::Int_COMISSrm },
- { X86::Int_CVTDQ2PDrr, X86::Int_CVTDQ2PDrm },
- { X86::Int_CVTDQ2PSrr, X86::Int_CVTDQ2PSrm },
- { X86::Int_CVTPD2DQrr, X86::Int_CVTPD2DQrm },
- { X86::Int_CVTPD2PSrr, X86::Int_CVTPD2PSrm },
- { X86::Int_CVTPS2DQrr, X86::Int_CVTPS2DQrm },
- { X86::Int_CVTPS2PDrr, X86::Int_CVTPS2PDrm },
- { X86::Int_CVTSD2SI64rr,X86::Int_CVTSD2SI64rm },
- { X86::Int_CVTSD2SIrr, X86::Int_CVTSD2SIrm },
- { X86::Int_CVTSD2SSrr, X86::Int_CVTSD2SSrm },
- { X86::Int_CVTSI2SD64rr,X86::Int_CVTSI2SD64rm },
- { X86::Int_CVTSI2SDrr, X86::Int_CVTSI2SDrm },
- { X86::Int_CVTSI2SS64rr,X86::Int_CVTSI2SS64rm },
- { X86::Int_CVTSI2SSrr, X86::Int_CVTSI2SSrm },
- { X86::Int_CVTSS2SDrr, X86::Int_CVTSS2SDrm },
- { X86::Int_CVTSS2SI64rr,X86::Int_CVTSS2SI64rm },
- { X86::Int_CVTSS2SIrr, X86::Int_CVTSS2SIrm },
- { X86::Int_CVTTPD2DQrr, X86::Int_CVTTPD2DQrm },
- { X86::Int_CVTTPS2DQrr, X86::Int_CVTTPS2DQrm },
- { X86::Int_CVTTSD2SI64rr,X86::Int_CVTTSD2SI64rm },
- { X86::Int_CVTTSD2SIrr, X86::Int_CVTTSD2SIrm },
- { X86::Int_CVTTSS2SI64rr,X86::Int_CVTTSS2SI64rm },
- { X86::Int_CVTTSS2SIrr, X86::Int_CVTTSS2SIrm },
- { X86::Int_UCOMISDrr, X86::Int_UCOMISDrm },
- { X86::Int_UCOMISSrr, X86::Int_UCOMISSrm },
- { X86::MOV16rr, X86::MOV16rm },
- { X86::MOV32rr, X86::MOV32rm },
- { X86::MOV64rr, X86::MOV64rm },
- { X86::MOV64toPQIrr, X86::MOVQI2PQIrm },
- { X86::MOV64toSDrr, X86::MOV64toSDrm },
- { X86::MOV8rr, X86::MOV8rm },
- { X86::MOVAPDrr, X86::MOVAPDrm },
- { X86::MOVAPSrr, X86::MOVAPSrm },
- { X86::MOVDDUPrr, X86::MOVDDUPrm },
- { X86::MOVDI2PDIrr, X86::MOVDI2PDIrm },
- { X86::MOVDI2SSrr, X86::MOVDI2SSrm },
- { X86::MOVDQArr, X86::MOVDQArm },
- { X86::MOVSD2PDrr, X86::MOVSD2PDrm },
- { X86::MOVSDrr, X86::MOVSDrm },
- { X86::MOVSHDUPrr, X86::MOVSHDUPrm },
- { X86::MOVSLDUPrr, X86::MOVSLDUPrm },
- { X86::MOVSS2PSrr, X86::MOVSS2PSrm },
- { X86::MOVSSrr, X86::MOVSSrm },
- { X86::MOVSX16rr8, X86::MOVSX16rm8 },
- { X86::MOVSX32rr16, X86::MOVSX32rm16 },
- { X86::MOVSX32rr8, X86::MOVSX32rm8 },
- { X86::MOVSX64rr16, X86::MOVSX64rm16 },
- { X86::MOVSX64rr32, X86::MOVSX64rm32 },
- { X86::MOVSX64rr8, X86::MOVSX64rm8 },
- { X86::MOVUPDrr, X86::MOVUPDrm },
- { X86::MOVUPSrr, X86::MOVUPSrm },
- { X86::MOVZDI2PDIrr, X86::MOVZDI2PDIrm },
- { X86::MOVZQI2PQIrr, X86::MOVZQI2PQIrm },
- { X86::MOVZPQILo2PQIrr, X86::MOVZPQILo2PQIrm },
- { X86::MOVZX16rr8, X86::MOVZX16rm8 },
- { X86::MOVZX32rr16, X86::MOVZX32rm16 },
- { X86::MOVZX32_NOREXrr8, X86::MOVZX32_NOREXrm8 },
- { X86::MOVZX32rr8, X86::MOVZX32rm8 },
- { X86::MOVZX64rr16, X86::MOVZX64rm16 },
- { X86::MOVZX64rr32, X86::MOVZX64rm32 },
- { X86::MOVZX64rr8, X86::MOVZX64rm8 },
- { X86::PSHUFDri, X86::PSHUFDmi },
- { X86::PSHUFHWri, X86::PSHUFHWmi },
- { X86::PSHUFLWri, X86::PSHUFLWmi },
- { X86::RCPPSr, X86::RCPPSm },
- { X86::RCPPSr_Int, X86::RCPPSm_Int },
- { X86::RSQRTPSr, X86::RSQRTPSm },
- { X86::RSQRTPSr_Int, X86::RSQRTPSm_Int },
- { X86::RSQRTSSr, X86::RSQRTSSm },
- { X86::RSQRTSSr_Int, X86::RSQRTSSm_Int },
- { X86::SQRTPDr, X86::SQRTPDm },
- { X86::SQRTPDr_Int, X86::SQRTPDm_Int },
- { X86::SQRTPSr, X86::SQRTPSm },
- { X86::SQRTPSr_Int, X86::SQRTPSm_Int },
- { X86::SQRTSDr, X86::SQRTSDm },
- { X86::SQRTSDr_Int, X86::SQRTSDm_Int },
- { X86::SQRTSSr, X86::SQRTSSm },
- { X86::SQRTSSr_Int, X86::SQRTSSm_Int },
- { X86::TEST16rr, X86::TEST16rm },
- { X86::TEST32rr, X86::TEST32rm },
- { X86::TEST64rr, X86::TEST64rm },
- { X86::TEST8rr, X86::TEST8rm },
+ static const unsigned OpTbl1[][3] = {
+ { X86::CMP16rr, X86::CMP16rm, 0 },
+ { X86::CMP32rr, X86::CMP32rm, 0 },
+ { X86::CMP64rr, X86::CMP64rm, 0 },
+ { X86::CMP8rr, X86::CMP8rm, 0 },
+ { X86::CVTSD2SSrr, X86::CVTSD2SSrm, 0 },
+ { X86::CVTSI2SD64rr, X86::CVTSI2SD64rm, 0 },
+ { X86::CVTSI2SDrr, X86::CVTSI2SDrm, 0 },
+ { X86::CVTSI2SS64rr, X86::CVTSI2SS64rm, 0 },
+ { X86::CVTSI2SSrr, X86::CVTSI2SSrm, 0 },
+ { X86::CVTSS2SDrr, X86::CVTSS2SDrm, 0 },
+ { X86::CVTTSD2SI64rr, X86::CVTTSD2SI64rm, 0 },
+ { X86::CVTTSD2SIrr, X86::CVTTSD2SIrm, 0 },
+ { X86::CVTTSS2SI64rr, X86::CVTTSS2SI64rm, 0 },
+ { X86::CVTTSS2SIrr, X86::CVTTSS2SIrm, 0 },
+ { X86::FsMOVAPDrr, X86::MOVSDrm, 0 },
+ { X86::FsMOVAPSrr, X86::MOVSSrm, 0 },
+ { X86::IMUL16rri, X86::IMUL16rmi, 0 },
+ { X86::IMUL16rri8, X86::IMUL16rmi8, 0 },
+ { X86::IMUL32rri, X86::IMUL32rmi, 0 },
+ { X86::IMUL32rri8, X86::IMUL32rmi8, 0 },
+ { X86::IMUL64rri32, X86::IMUL64rmi32, 0 },
+ { X86::IMUL64rri8, X86::IMUL64rmi8, 0 },
+ { X86::Int_CMPSDrr, X86::Int_CMPSDrm, 0 },
+ { X86::Int_CMPSSrr, X86::Int_CMPSSrm, 0 },
+ { X86::Int_COMISDrr, X86::Int_COMISDrm, 0 },
+ { X86::Int_COMISSrr, X86::Int_COMISSrm, 0 },
+ { X86::Int_CVTDQ2PDrr, X86::Int_CVTDQ2PDrm, 16 },
+ { X86::Int_CVTDQ2PSrr, X86::Int_CVTDQ2PSrm, 16 },
+ { X86::Int_CVTPD2DQrr, X86::Int_CVTPD2DQrm, 16 },
+ { X86::Int_CVTPD2PSrr, X86::Int_CVTPD2PSrm, 16 },
+ { X86::Int_CVTPS2DQrr, X86::Int_CVTPS2DQrm, 16 },
+ { X86::Int_CVTPS2PDrr, X86::Int_CVTPS2PDrm, 0 },
+ { X86::Int_CVTSD2SI64rr,X86::Int_CVTSD2SI64rm, 0 },
+ { X86::Int_CVTSD2SIrr, X86::Int_CVTSD2SIrm, 0 },
+ { X86::Int_CVTSD2SSrr, X86::Int_CVTSD2SSrm, 0 },
+ { X86::Int_CVTSI2SD64rr,X86::Int_CVTSI2SD64rm, 0 },
+ { X86::Int_CVTSI2SDrr, X86::Int_CVTSI2SDrm, 0 },
+ { X86::Int_CVTSI2SS64rr,X86::Int_CVTSI2SS64rm, 0 },
+ { X86::Int_CVTSI2SSrr, X86::Int_CVTSI2SSrm, 0 },
+ { X86::Int_CVTSS2SDrr, X86::Int_CVTSS2SDrm, 0 },
+ { X86::Int_CVTSS2SI64rr,X86::Int_CVTSS2SI64rm, 0 },
+ { X86::Int_CVTSS2SIrr, X86::Int_CVTSS2SIrm, 0 },
+ { X86::Int_CVTTPD2DQrr, X86::Int_CVTTPD2DQrm, 16 },
+ { X86::Int_CVTTPS2DQrr, X86::Int_CVTTPS2DQrm, 16 },
+ { X86::Int_CVTTSD2SI64rr,X86::Int_CVTTSD2SI64rm, 0 },
+ { X86::Int_CVTTSD2SIrr, X86::Int_CVTTSD2SIrm, 0 },
+ { X86::Int_CVTTSS2SI64rr,X86::Int_CVTTSS2SI64rm, 0 },
+ { X86::Int_CVTTSS2SIrr, X86::Int_CVTTSS2SIrm, 0 },
+ { X86::Int_UCOMISDrr, X86::Int_UCOMISDrm, 0 },
+ { X86::Int_UCOMISSrr, X86::Int_UCOMISSrm, 0 },
+ { X86::MOV16rr, X86::MOV16rm, 0 },
+ { X86::MOV32rr, X86::MOV32rm, 0 },
+ { X86::MOV64rr, X86::MOV64rm, 0 },
+ { X86::MOV64toPQIrr, X86::MOVQI2PQIrm, 0 },
+ { X86::MOV64toSDrr, X86::MOV64toSDrm, 0 },
+ { X86::MOV8rr, X86::MOV8rm, 0 },
+ { X86::MOVAPDrr, X86::MOVAPDrm, 16 },
+ { X86::MOVAPSrr, X86::MOVAPSrm, 16 },
+ { X86::MOVDDUPrr, X86::MOVDDUPrm, 0 },
+ { X86::MOVDI2PDIrr, X86::MOVDI2PDIrm, 0 },
+ { X86::MOVDI2SSrr, X86::MOVDI2SSrm, 0 },
+ { X86::MOVDQArr, X86::MOVDQArm, 16 },
+ { X86::MOVSD2PDrr, X86::MOVSD2PDrm, 0 },
+ { X86::MOVSDrr, X86::MOVSDrm, 0 },
+ { X86::MOVSHDUPrr, X86::MOVSHDUPrm, 16 },
+ { X86::MOVSLDUPrr, X86::MOVSLDUPrm, 16 },
+ { X86::MOVSS2PSrr, X86::MOVSS2PSrm, 0 },
+ { X86::MOVSSrr, X86::MOVSSrm, 0 },
+ { X86::MOVSX16rr8, X86::MOVSX16rm8, 0 },
+ { X86::MOVSX32rr16, X86::MOVSX32rm16, 0 },
+ { X86::MOVSX32rr8, X86::MOVSX32rm8, 0 },
+ { X86::MOVSX64rr16, X86::MOVSX64rm16, 0 },
+ { X86::MOVSX64rr32, X86::MOVSX64rm32, 0 },
+ { X86::MOVSX64rr8, X86::MOVSX64rm8, 0 },
+ { X86::MOVUPDrr, X86::MOVUPDrm, 16 },
+ { X86::MOVUPSrr, X86::MOVUPSrm, 16 },
+ { X86::MOVZDI2PDIrr, X86::MOVZDI2PDIrm, 0 },
+ { X86::MOVZQI2PQIrr, X86::MOVZQI2PQIrm, 0 },
+ { X86::MOVZPQILo2PQIrr, X86::MOVZPQILo2PQIrm, 16 },
+ { X86::MOVZX16rr8, X86::MOVZX16rm8, 0 },
+ { X86::MOVZX32rr16, X86::MOVZX32rm16, 0 },
+ { X86::MOVZX32_NOREXrr8, X86::MOVZX32_NOREXrm8, 0 },
+ { X86::MOVZX32rr8, X86::MOVZX32rm8, 0 },
+ { X86::MOVZX64rr16, X86::MOVZX64rm16, 0 },
+ { X86::MOVZX64rr32, X86::MOVZX64rm32, 0 },
+ { X86::MOVZX64rr8, X86::MOVZX64rm8, 0 },
+ { X86::PSHUFDri, X86::PSHUFDmi, 16 },
+ { X86::PSHUFHWri, X86::PSHUFHWmi, 16 },
+ { X86::PSHUFLWri, X86::PSHUFLWmi, 16 },
+ { X86::RCPPSr, X86::RCPPSm, 16 },
+ { X86::RCPPSr_Int, X86::RCPPSm_Int, 16 },
+ { X86::RSQRTPSr, X86::RSQRTPSm, 16 },
+ { X86::RSQRTPSr_Int, X86::RSQRTPSm_Int, 16 },
+ { X86::RSQRTSSr, X86::RSQRTSSm, 0 },
+ { X86::RSQRTSSr_Int, X86::RSQRTSSm_Int, 0 },
+ { X86::SQRTPDr, X86::SQRTPDm, 16 },
+ { X86::SQRTPDr_Int, X86::SQRTPDm_Int, 16 },
+ { X86::SQRTPSr, X86::SQRTPSm, 16 },
+ { X86::SQRTPSr_Int, X86::SQRTPSm_Int, 16 },
+ { X86::SQRTSDr, X86::SQRTSDm, 0 },
+ { X86::SQRTSDr_Int, X86::SQRTSDm_Int, 0 },
+ { X86::SQRTSSr, X86::SQRTSSm, 0 },
+ { X86::SQRTSSr_Int, X86::SQRTSSm_Int, 0 },
+ { X86::TEST16rr, X86::TEST16rm, 0 },
+ { X86::TEST32rr, X86::TEST32rm, 0 },
+ { X86::TEST64rr, X86::TEST64rm, 0 },
+ { X86::TEST8rr, X86::TEST8rm, 0 },
// FIXME: TEST*rr EAX,EAX ---> CMP [mem], 0
- { X86::UCOMISDrr, X86::UCOMISDrm },
- { X86::UCOMISSrr, X86::UCOMISSrm }
+ { X86::UCOMISDrr, X86::UCOMISDrm, 0 },
+ { X86::UCOMISSrr, X86::UCOMISSrm, 0 }
};
for (unsigned i = 0, e = array_lengthof(OpTbl1); i != e; ++i) {
unsigned RegOp = OpTbl1[i][0];
unsigned MemOp = OpTbl1[i][1];
+ unsigned Align = OpTbl1[i][2];
if (!RegOp2MemOpTable1.insert(std::make_pair((unsigned*)RegOp,
- MemOp)).second)
+ std::make_pair(MemOp,Align))).second)
assert(false && "Duplicated entries?");
- unsigned AuxInfo = 1 | (1 << 4); // Index 1, folded load
+ // Index 1, folded load
+ unsigned AuxInfo = 1 | (1 << 4);
if (RegOp != X86::FsMOVAPDrr && RegOp != X86::FsMOVAPSrr)
if (!MemOp2RegOpTable.insert(std::make_pair((unsigned*)MemOp,
std::make_pair(RegOp, AuxInfo))).second)
AmbEntries.push_back(MemOp);
}
- static const unsigned OpTbl2[][2] = {
- { X86::ADC32rr, X86::ADC32rm },
- { X86::ADC64rr, X86::ADC64rm },
- { X86::ADD16rr, X86::ADD16rm },
- { X86::ADD32rr, X86::ADD32rm },
- { X86::ADD64rr, X86::ADD64rm },
- { X86::ADD8rr, X86::ADD8rm },
- { X86::ADDPDrr, X86::ADDPDrm },
- { X86::ADDPSrr, X86::ADDPSrm },
- { X86::ADDSDrr, X86::ADDSDrm },
- { X86::ADDSSrr, X86::ADDSSrm },
- { X86::ADDSUBPDrr, X86::ADDSUBPDrm },
- { X86::ADDSUBPSrr, X86::ADDSUBPSrm },
- { X86::AND16rr, X86::AND16rm },
- { X86::AND32rr, X86::AND32rm },
- { X86::AND64rr, X86::AND64rm },
- { X86::AND8rr, X86::AND8rm },
- { X86::ANDNPDrr, X86::ANDNPDrm },
- { X86::ANDNPSrr, X86::ANDNPSrm },
- { X86::ANDPDrr, X86::ANDPDrm },
- { X86::ANDPSrr, X86::ANDPSrm },
- { X86::CMOVA16rr, X86::CMOVA16rm },
- { X86::CMOVA32rr, X86::CMOVA32rm },
- { X86::CMOVA64rr, X86::CMOVA64rm },
- { X86::CMOVAE16rr, X86::CMOVAE16rm },
- { X86::CMOVAE32rr, X86::CMOVAE32rm },
- { X86::CMOVAE64rr, X86::CMOVAE64rm },
- { X86::CMOVB16rr, X86::CMOVB16rm },
- { X86::CMOVB32rr, X86::CMOVB32rm },
- { X86::CMOVB64rr, X86::CMOVB64rm },
- { X86::CMOVBE16rr, X86::CMOVBE16rm },
- { X86::CMOVBE32rr, X86::CMOVBE32rm },
- { X86::CMOVBE64rr, X86::CMOVBE64rm },
- { X86::CMOVE16rr, X86::CMOVE16rm },
- { X86::CMOVE32rr, X86::CMOVE32rm },
- { X86::CMOVE64rr, X86::CMOVE64rm },
- { X86::CMOVG16rr, X86::CMOVG16rm },
- { X86::CMOVG32rr, X86::CMOVG32rm },
- { X86::CMOVG64rr, X86::CMOVG64rm },
- { X86::CMOVGE16rr, X86::CMOVGE16rm },
- { X86::CMOVGE32rr, X86::CMOVGE32rm },
- { X86::CMOVGE64rr, X86::CMOVGE64rm },
- { X86::CMOVL16rr, X86::CMOVL16rm },
- { X86::CMOVL32rr, X86::CMOVL32rm },
- { X86::CMOVL64rr, X86::CMOVL64rm },
- { X86::CMOVLE16rr, X86::CMOVLE16rm },
- { X86::CMOVLE32rr, X86::CMOVLE32rm },
- { X86::CMOVLE64rr, X86::CMOVLE64rm },
- { X86::CMOVNE16rr, X86::CMOVNE16rm },
- { X86::CMOVNE32rr, X86::CMOVNE32rm },
- { X86::CMOVNE64rr, X86::CMOVNE64rm },
- { X86::CMOVNO16rr, X86::CMOVNO16rm },
- { X86::CMOVNO32rr, X86::CMOVNO32rm },
- { X86::CMOVNO64rr, X86::CMOVNO64rm },
- { X86::CMOVNP16rr, X86::CMOVNP16rm },
- { X86::CMOVNP32rr, X86::CMOVNP32rm },
- { X86::CMOVNP64rr, X86::CMOVNP64rm },
- { X86::CMOVNS16rr, X86::CMOVNS16rm },
- { X86::CMOVNS32rr, X86::CMOVNS32rm },
- { X86::CMOVNS64rr, X86::CMOVNS64rm },
- { X86::CMOVO16rr, X86::CMOVO16rm },
- { X86::CMOVO32rr, X86::CMOVO32rm },
- { X86::CMOVO64rr, X86::CMOVO64rm },
- { X86::CMOVP16rr, X86::CMOVP16rm },
- { X86::CMOVP32rr, X86::CMOVP32rm },
- { X86::CMOVP64rr, X86::CMOVP64rm },
- { X86::CMOVS16rr, X86::CMOVS16rm },
- { X86::CMOVS32rr, X86::CMOVS32rm },
- { X86::CMOVS64rr, X86::CMOVS64rm },
- { X86::CMPPDrri, X86::CMPPDrmi },
- { X86::CMPPSrri, X86::CMPPSrmi },
- { X86::CMPSDrr, X86::CMPSDrm },
- { X86::CMPSSrr, X86::CMPSSrm },
- { X86::DIVPDrr, X86::DIVPDrm },
- { X86::DIVPSrr, X86::DIVPSrm },
- { X86::DIVSDrr, X86::DIVSDrm },
- { X86::DIVSSrr, X86::DIVSSrm },
- { X86::FsANDNPDrr, X86::FsANDNPDrm },
- { X86::FsANDNPSrr, X86::FsANDNPSrm },
- { X86::FsANDPDrr, X86::FsANDPDrm },
- { X86::FsANDPSrr, X86::FsANDPSrm },
- { X86::FsORPDrr, X86::FsORPDrm },
- { X86::FsORPSrr, X86::FsORPSrm },
- { X86::FsXORPDrr, X86::FsXORPDrm },
- { X86::FsXORPSrr, X86::FsXORPSrm },
- { X86::HADDPDrr, X86::HADDPDrm },
- { X86::HADDPSrr, X86::HADDPSrm },
- { X86::HSUBPDrr, X86::HSUBPDrm },
- { X86::HSUBPSrr, X86::HSUBPSrm },
- { X86::IMUL16rr, X86::IMUL16rm },
- { X86::IMUL32rr, X86::IMUL32rm },
- { X86::IMUL64rr, X86::IMUL64rm },
- { X86::MAXPDrr, X86::MAXPDrm },
- { X86::MAXPDrr_Int, X86::MAXPDrm_Int },
- { X86::MAXPSrr, X86::MAXPSrm },
- { X86::MAXPSrr_Int, X86::MAXPSrm_Int },
- { X86::MAXSDrr, X86::MAXSDrm },
- { X86::MAXSDrr_Int, X86::MAXSDrm_Int },
- { X86::MAXSSrr, X86::MAXSSrm },
- { X86::MAXSSrr_Int, X86::MAXSSrm_Int },
- { X86::MINPDrr, X86::MINPDrm },
- { X86::MINPDrr_Int, X86::MINPDrm_Int },
- { X86::MINPSrr, X86::MINPSrm },
- { X86::MINPSrr_Int, X86::MINPSrm_Int },
- { X86::MINSDrr, X86::MINSDrm },
- { X86::MINSDrr_Int, X86::MINSDrm_Int },
- { X86::MINSSrr, X86::MINSSrm },
- { X86::MINSSrr_Int, X86::MINSSrm_Int },
- { X86::MULPDrr, X86::MULPDrm },
- { X86::MULPSrr, X86::MULPSrm },
- { X86::MULSDrr, X86::MULSDrm },
- { X86::MULSSrr, X86::MULSSrm },
- { X86::OR16rr, X86::OR16rm },
- { X86::OR32rr, X86::OR32rm },
- { X86::OR64rr, X86::OR64rm },
- { X86::OR8rr, X86::OR8rm },
- { X86::ORPDrr, X86::ORPDrm },
- { X86::ORPSrr, X86::ORPSrm },
- { X86::PACKSSDWrr, X86::PACKSSDWrm },
- { X86::PACKSSWBrr, X86::PACKSSWBrm },
- { X86::PACKUSWBrr, X86::PACKUSWBrm },
- { X86::PADDBrr, X86::PADDBrm },
- { X86::PADDDrr, X86::PADDDrm },
- { X86::PADDQrr, X86::PADDQrm },
- { X86::PADDSBrr, X86::PADDSBrm },
- { X86::PADDSWrr, X86::PADDSWrm },
- { X86::PADDWrr, X86::PADDWrm },
- { X86::PANDNrr, X86::PANDNrm },
- { X86::PANDrr, X86::PANDrm },
- { X86::PAVGBrr, X86::PAVGBrm },
- { X86::PAVGWrr, X86::PAVGWrm },
- { X86::PCMPEQBrr, X86::PCMPEQBrm },
- { X86::PCMPEQDrr, X86::PCMPEQDrm },
- { X86::PCMPEQWrr, X86::PCMPEQWrm },
- { X86::PCMPGTBrr, X86::PCMPGTBrm },
- { X86::PCMPGTDrr, X86::PCMPGTDrm },
- { X86::PCMPGTWrr, X86::PCMPGTWrm },
- { X86::PINSRWrri, X86::PINSRWrmi },
- { X86::PMADDWDrr, X86::PMADDWDrm },
- { X86::PMAXSWrr, X86::PMAXSWrm },
- { X86::PMAXUBrr, X86::PMAXUBrm },
- { X86::PMINSWrr, X86::PMINSWrm },
- { X86::PMINUBrr, X86::PMINUBrm },
- { X86::PMULDQrr, X86::PMULDQrm },
- { X86::PMULHUWrr, X86::PMULHUWrm },
- { X86::PMULHWrr, X86::PMULHWrm },
- { X86::PMULLDrr, X86::PMULLDrm },
- { X86::PMULLDrr_int, X86::PMULLDrm_int },
- { X86::PMULLWrr, X86::PMULLWrm },
- { X86::PMULUDQrr, X86::PMULUDQrm },
- { X86::PORrr, X86::PORrm },
- { X86::PSADBWrr, X86::PSADBWrm },
- { X86::PSLLDrr, X86::PSLLDrm },
- { X86::PSLLQrr, X86::PSLLQrm },
- { X86::PSLLWrr, X86::PSLLWrm },
- { X86::PSRADrr, X86::PSRADrm },
- { X86::PSRAWrr, X86::PSRAWrm },
- { X86::PSRLDrr, X86::PSRLDrm },
- { X86::PSRLQrr, X86::PSRLQrm },
- { X86::PSRLWrr, X86::PSRLWrm },
- { X86::PSUBBrr, X86::PSUBBrm },
- { X86::PSUBDrr, X86::PSUBDrm },
- { X86::PSUBSBrr, X86::PSUBSBrm },
- { X86::PSUBSWrr, X86::PSUBSWrm },
- { X86::PSUBWrr, X86::PSUBWrm },
- { X86::PUNPCKHBWrr, X86::PUNPCKHBWrm },
- { X86::PUNPCKHDQrr, X86::PUNPCKHDQrm },
- { X86::PUNPCKHQDQrr, X86::PUNPCKHQDQrm },
- { X86::PUNPCKHWDrr, X86::PUNPCKHWDrm },
- { X86::PUNPCKLBWrr, X86::PUNPCKLBWrm },
- { X86::PUNPCKLDQrr, X86::PUNPCKLDQrm },
- { X86::PUNPCKLQDQrr, X86::PUNPCKLQDQrm },
- { X86::PUNPCKLWDrr, X86::PUNPCKLWDrm },
- { X86::PXORrr, X86::PXORrm },
- { X86::SBB32rr, X86::SBB32rm },
- { X86::SBB64rr, X86::SBB64rm },
- { X86::SHUFPDrri, X86::SHUFPDrmi },
- { X86::SHUFPSrri, X86::SHUFPSrmi },
- { X86::SUB16rr, X86::SUB16rm },
- { X86::SUB32rr, X86::SUB32rm },
- { X86::SUB64rr, X86::SUB64rm },
- { X86::SUB8rr, X86::SUB8rm },
- { X86::SUBPDrr, X86::SUBPDrm },
- { X86::SUBPSrr, X86::SUBPSrm },
- { X86::SUBSDrr, X86::SUBSDrm },
- { X86::SUBSSrr, X86::SUBSSrm },
+ static const unsigned OpTbl2[][3] = {
+ { X86::ADC32rr, X86::ADC32rm, 0 },
+ { X86::ADC64rr, X86::ADC64rm, 0 },
+ { X86::ADD16rr, X86::ADD16rm, 0 },
+ { X86::ADD32rr, X86::ADD32rm, 0 },
+ { X86::ADD64rr, X86::ADD64rm, 0 },
+ { X86::ADD8rr, X86::ADD8rm, 0 },
+ { X86::ADDPDrr, X86::ADDPDrm, 16 },
+ { X86::ADDPSrr, X86::ADDPSrm, 16 },
+ { X86::ADDSDrr, X86::ADDSDrm, 0 },
+ { X86::ADDSSrr, X86::ADDSSrm, 0 },
+ { X86::ADDSUBPDrr, X86::ADDSUBPDrm, 16 },
+ { X86::ADDSUBPSrr, X86::ADDSUBPSrm, 16 },
+ { X86::AND16rr, X86::AND16rm, 0 },
+ { X86::AND32rr, X86::AND32rm, 0 },
+ { X86::AND64rr, X86::AND64rm, 0 },
+ { X86::AND8rr, X86::AND8rm, 0 },
+ { X86::ANDNPDrr, X86::ANDNPDrm, 16 },
+ { X86::ANDNPSrr, X86::ANDNPSrm, 16 },
+ { X86::ANDPDrr, X86::ANDPDrm, 16 },
+ { X86::ANDPSrr, X86::ANDPSrm, 16 },
+ { X86::CMOVA16rr, X86::CMOVA16rm, 0 },
+ { X86::CMOVA32rr, X86::CMOVA32rm, 0 },
+ { X86::CMOVA64rr, X86::CMOVA64rm, 0 },
+ { X86::CMOVAE16rr, X86::CMOVAE16rm, 0 },
+ { X86::CMOVAE32rr, X86::CMOVAE32rm, 0 },
+ { X86::CMOVAE64rr, X86::CMOVAE64rm, 0 },
+ { X86::CMOVB16rr, X86::CMOVB16rm, 0 },
+ { X86::CMOVB32rr, X86::CMOVB32rm, 0 },
+ { X86::CMOVB64rr, X86::CMOVB64rm, 0 },
+ { X86::CMOVBE16rr, X86::CMOVBE16rm, 0 },
+ { X86::CMOVBE32rr, X86::CMOVBE32rm, 0 },
+ { X86::CMOVBE64rr, X86::CMOVBE64rm, 0 },
+ { X86::CMOVE16rr, X86::CMOVE16rm, 0 },
+ { X86::CMOVE32rr, X86::CMOVE32rm, 0 },
+ { X86::CMOVE64rr, X86::CMOVE64rm, 0 },
+ { X86::CMOVG16rr, X86::CMOVG16rm, 0 },
+ { X86::CMOVG32rr, X86::CMOVG32rm, 0 },
+ { X86::CMOVG64rr, X86::CMOVG64rm, 0 },
+ { X86::CMOVGE16rr, X86::CMOVGE16rm, 0 },
+ { X86::CMOVGE32rr, X86::CMOVGE32rm, 0 },
+ { X86::CMOVGE64rr, X86::CMOVGE64rm, 0 },
+ { X86::CMOVL16rr, X86::CMOVL16rm, 0 },
+ { X86::CMOVL32rr, X86::CMOVL32rm, 0 },
+ { X86::CMOVL64rr, X86::CMOVL64rm, 0 },
+ { X86::CMOVLE16rr, X86::CMOVLE16rm, 0 },
+ { X86::CMOVLE32rr, X86::CMOVLE32rm, 0 },
+ { X86::CMOVLE64rr, X86::CMOVLE64rm, 0 },
+ { X86::CMOVNE16rr, X86::CMOVNE16rm, 0 },
+ { X86::CMOVNE32rr, X86::CMOVNE32rm, 0 },
+ { X86::CMOVNE64rr, X86::CMOVNE64rm, 0 },
+ { X86::CMOVNO16rr, X86::CMOVNO16rm, 0 },
+ { X86::CMOVNO32rr, X86::CMOVNO32rm, 0 },
+ { X86::CMOVNO64rr, X86::CMOVNO64rm, 0 },
+ { X86::CMOVNP16rr, X86::CMOVNP16rm, 0 },
+ { X86::CMOVNP32rr, X86::CMOVNP32rm, 0 },
+ { X86::CMOVNP64rr, X86::CMOVNP64rm, 0 },
+ { X86::CMOVNS16rr, X86::CMOVNS16rm, 0 },
+ { X86::CMOVNS32rr, X86::CMOVNS32rm, 0 },
+ { X86::CMOVNS64rr, X86::CMOVNS64rm, 0 },
+ { X86::CMOVO16rr, X86::CMOVO16rm, 0 },
+ { X86::CMOVO32rr, X86::CMOVO32rm, 0 },
+ { X86::CMOVO64rr, X86::CMOVO64rm, 0 },
+ { X86::CMOVP16rr, X86::CMOVP16rm, 0 },
+ { X86::CMOVP32rr, X86::CMOVP32rm, 0 },
+ { X86::CMOVP64rr, X86::CMOVP64rm, 0 },
+ { X86::CMOVS16rr, X86::CMOVS16rm, 0 },
+ { X86::CMOVS32rr, X86::CMOVS32rm, 0 },
+ { X86::CMOVS64rr, X86::CMOVS64rm, 0 },
+ { X86::CMPPDrri, X86::CMPPDrmi, 16 },
+ { X86::CMPPSrri, X86::CMPPSrmi, 16 },
+ { X86::CMPSDrr, X86::CMPSDrm, 0 },
+ { X86::CMPSSrr, X86::CMPSSrm, 0 },
+ { X86::DIVPDrr, X86::DIVPDrm, 16 },
+ { X86::DIVPSrr, X86::DIVPSrm, 16 },
+ { X86::DIVSDrr, X86::DIVSDrm, 0 },
+ { X86::DIVSSrr, X86::DIVSSrm, 0 },
+ { X86::FsANDNPDrr, X86::FsANDNPDrm, 16 },
+ { X86::FsANDNPSrr, X86::FsANDNPSrm, 16 },
+ { X86::FsANDPDrr, X86::FsANDPDrm, 16 },
+ { X86::FsANDPSrr, X86::FsANDPSrm, 16 },
+ { X86::FsORPDrr, X86::FsORPDrm, 16 },
+ { X86::FsORPSrr, X86::FsORPSrm, 16 },
+ { X86::FsXORPDrr, X86::FsXORPDrm, 16 },
+ { X86::FsXORPSrr, X86::FsXORPSrm, 16 },
+ { X86::HADDPDrr, X86::HADDPDrm, 16 },
+ { X86::HADDPSrr, X86::HADDPSrm, 16 },
+ { X86::HSUBPDrr, X86::HSUBPDrm, 16 },
+ { X86::HSUBPSrr, X86::HSUBPSrm, 16 },
+ { X86::IMUL16rr, X86::IMUL16rm, 0 },
+ { X86::IMUL32rr, X86::IMUL32rm, 0 },
+ { X86::IMUL64rr, X86::IMUL64rm, 0 },
+ { X86::MAXPDrr, X86::MAXPDrm, 16 },
+ { X86::MAXPDrr_Int, X86::MAXPDrm_Int, 16 },
+ { X86::MAXPSrr, X86::MAXPSrm, 16 },
+ { X86::MAXPSrr_Int, X86::MAXPSrm_Int, 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, 16 },
+ { X86::MINPDrr_Int, X86::MINPDrm_Int, 16 },
+ { X86::MINPSrr, X86::MINPSrm, 16 },
+ { X86::MINPSrr_Int, X86::MINPSrm_Int, 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::MULPDrr, X86::MULPDrm, 16 },
+ { X86::MULPSrr, X86::MULPSrm, 16 },
+ { X86::MULSDrr, X86::MULSDrm, 0 },
+ { X86::MULSSrr, X86::MULSSrm, 0 },
+ { X86::OR16rr, X86::OR16rm, 0 },
+ { X86::OR32rr, X86::OR32rm, 0 },
+ { X86::OR64rr, X86::OR64rm, 0 },
+ { X86::OR8rr, X86::OR8rm, 0 },
+ { X86::ORPDrr, X86::ORPDrm, 16 },
+ { X86::ORPSrr, X86::ORPSrm, 16 },
+ { X86::PACKSSDWrr, X86::PACKSSDWrm, 16 },
+ { X86::PACKSSWBrr, X86::PACKSSWBrm, 16 },
+ { X86::PACKUSWBrr, X86::PACKUSWBrm, 16 },
+ { X86::PADDBrr, X86::PADDBrm, 16 },
+ { X86::PADDDrr, X86::PADDDrm, 16 },
+ { X86::PADDQrr, X86::PADDQrm, 16 },
+ { X86::PADDSBrr, X86::PADDSBrm, 16 },
+ { X86::PADDSWrr, X86::PADDSWrm, 16 },
+ { X86::PADDWrr, X86::PADDWrm, 16 },
+ { X86::PANDNrr, X86::PANDNrm, 16 },
+ { X86::PANDrr, X86::PANDrm, 16 },
+ { X86::PAVGBrr, X86::PAVGBrm, 16 },
+ { X86::PAVGWrr, X86::PAVGWrm, 16 },
+ { X86::PCMPEQBrr, X86::PCMPEQBrm, 16 },
+ { X86::PCMPEQDrr, X86::PCMPEQDrm, 16 },
+ { X86::PCMPEQWrr, X86::PCMPEQWrm, 16 },
+ { X86::PCMPGTBrr, X86::PCMPGTBrm, 16 },
+ { X86::PCMPGTDrr, X86::PCMPGTDrm, 16 },
+ { X86::PCMPGTWrr, X86::PCMPGTWrm, 16 },
+ { X86::PINSRWrri, X86::PINSRWrmi, 16 },
+ { X86::PMADDWDrr, X86::PMADDWDrm, 16 },
+ { X86::PMAXSWrr, X86::PMAXSWrm, 16 },
+ { X86::PMAXUBrr, X86::PMAXUBrm, 16 },
+ { X86::PMINSWrr, X86::PMINSWrm, 16 },
+ { X86::PMINUBrr, X86::PMINUBrm, 16 },
+ { X86::PMULDQrr, X86::PMULDQrm, 16 },
+ { X86::PMULHUWrr, X86::PMULHUWrm, 16 },
+ { X86::PMULHWrr, X86::PMULHWrm, 16 },
+ { X86::PMULLDrr, X86::PMULLDrm, 16 },
+ { X86::PMULLDrr_int, X86::PMULLDrm_int, 16 },
+ { X86::PMULLWrr, X86::PMULLWrm, 16 },
+ { X86::PMULUDQrr, X86::PMULUDQrm, 16 },
+ { X86::PORrr, X86::PORrm, 16 },
+ { X86::PSADBWrr, X86::PSADBWrm, 16 },
+ { X86::PSLLDrr, X86::PSLLDrm, 16 },
+ { X86::PSLLQrr, X86::PSLLQrm, 16 },
+ { X86::PSLLWrr, X86::PSLLWrm, 16 },
+ { X86::PSRADrr, X86::PSRADrm, 16 },
+ { X86::PSRAWrr, X86::PSRAWrm, 16 },
+ { X86::PSRLDrr, X86::PSRLDrm, 16 },
+ { X86::PSRLQrr, X86::PSRLQrm, 16 },
+ { X86::PSRLWrr, X86::PSRLWrm, 16 },
+ { X86::PSUBBrr, X86::PSUBBrm, 16 },
+ { X86::PSUBDrr, X86::PSUBDrm, 16 },
+ { X86::PSUBSBrr, X86::PSUBSBrm, 16 },
+ { X86::PSUBSWrr, X86::PSUBSWrm, 16 },
+ { X86::PSUBWrr, X86::PSUBWrm, 16 },
+ { X86::PUNPCKHBWrr, X86::PUNPCKHBWrm, 16 },
+ { X86::PUNPCKHDQrr, X86::PUNPCKHDQrm, 16 },
+ { X86::PUNPCKHQDQrr, X86::PUNPCKHQDQrm, 16 },
+ { X86::PUNPCKHWDrr, X86::PUNPCKHWDrm, 16 },
+ { X86::PUNPCKLBWrr, X86::PUNPCKLBWrm, 16 },
+ { X86::PUNPCKLDQrr, X86::PUNPCKLDQrm, 16 },
+ { X86::PUNPCKLQDQrr, X86::PUNPCKLQDQrm, 16 },
+ { X86::PUNPCKLWDrr, X86::PUNPCKLWDrm, 16 },
+ { X86::PXORrr, X86::PXORrm, 16 },
+ { X86::SBB32rr, X86::SBB32rm, 0 },
+ { X86::SBB64rr, X86::SBB64rm, 0 },
+ { X86::SHUFPDrri, X86::SHUFPDrmi, 16 },
+ { X86::SHUFPSrri, X86::SHUFPSrmi, 16 },
+ { X86::SUB16rr, X86::SUB16rm, 0 },
+ { X86::SUB32rr, X86::SUB32rm, 0 },
+ { X86::SUB64rr, X86::SUB64rm, 0 },
+ { X86::SUB8rr, X86::SUB8rm, 0 },
+ { X86::SUBPDrr, X86::SUBPDrm, 16 },
+ { X86::SUBPSrr, X86::SUBPSrm, 16 },
+ { X86::SUBSDrr, X86::SUBSDrm, 0 },
+ { X86::SUBSSrr, X86::SUBSSrm, 0 },
// FIXME: TEST*rr -> swapped operand of TEST*mr.
- { X86::UNPCKHPDrr, X86::UNPCKHPDrm },
- { X86::UNPCKHPSrr, X86::UNPCKHPSrm },
- { X86::UNPCKLPDrr, X86::UNPCKLPDrm },
- { X86::UNPCKLPSrr, X86::UNPCKLPSrm },
- { X86::XOR16rr, X86::XOR16rm },
- { X86::XOR32rr, X86::XOR32rm },
- { X86::XOR64rr, X86::XOR64rm },
- { X86::XOR8rr, X86::XOR8rm },
- { X86::XORPDrr, X86::XORPDrm },
- { X86::XORPSrr, X86::XORPSrm }
+ { X86::UNPCKHPDrr, X86::UNPCKHPDrm, 16 },
+ { X86::UNPCKHPSrr, X86::UNPCKHPSrm, 16 },
+ { X86::UNPCKLPDrr, X86::UNPCKLPDrm, 16 },
+ { X86::UNPCKLPSrr, X86::UNPCKLPSrm, 16 },
+ { X86::XOR16rr, X86::XOR16rm, 0 },
+ { X86::XOR32rr, X86::XOR32rm, 0 },
+ { X86::XOR64rr, X86::XOR64rm, 0 },
+ { X86::XOR8rr, X86::XOR8rm, 0 },
+ { X86::XORPDrr, X86::XORPDrm, 16 },
+ { X86::XORPSrr, X86::XORPSrm, 16 }
};
for (unsigned i = 0, e = array_lengthof(OpTbl2); i != e; ++i) {
unsigned RegOp = OpTbl2[i][0];
unsigned MemOp = OpTbl2[i][1];
+ unsigned Align = OpTbl2[i][2];
if (!RegOp2MemOpTable2.insert(std::make_pair((unsigned*)RegOp,
- MemOp)).second)
+ std::make_pair(MemOp,Align))).second)
assert(false && "Duplicated entries?");
- unsigned AuxInfo = 2 | (1 << 4); // Index 2, folded load
+ // Index 2, folded load
+ unsigned AuxInfo = 2 | (1 << 4);
if (!MemOp2RegOpTable.insert(std::make_pair((unsigned*)MemOp,
std::make_pair(RegOp, AuxInfo))).second)
AmbEntries.push_back(MemOp);
@@ -2142,8 +2148,9 @@
MachineInstr*
X86InstrInfo::foldMemoryOperandImpl(MachineFunction &MF,
MachineInstr *MI, unsigned i,
- const SmallVectorImpl<MachineOperand> &MOs) const{
- const DenseMap<unsigned*, unsigned> *OpcodeTablePtr = NULL;
+ const SmallVectorImpl<MachineOperand> &MOs,
+ unsigned Align) const {
+ const DenseMap<unsigned*, std::pair<unsigned,unsigned> > *OpcodeTablePtr=NULL;
bool isTwoAddrFold = false;
unsigned NumOps = MI->getDesc().getNumOperands();
bool isTwoAddr = NumOps > 1 &&
@@ -2179,13 +2186,16 @@
// If table selected...
if (OpcodeTablePtr) {
// Find the Opcode to fuse
- DenseMap<unsigned*, unsigned>::iterator I =
+ DenseMap<unsigned*, std::pair<unsigned,unsigned> >::iterator I =
OpcodeTablePtr->find((unsigned*)MI->getOpcode());
if (I != OpcodeTablePtr->end()) {
+ unsigned MinAlign = I->second.second;
+ if (Align < MinAlign)
+ return NULL;
if (isTwoAddrFold)
- NewMI = FuseTwoAddrInst(MF, I->second, MOs, MI, *this);
+ NewMI = FuseTwoAddrInst(MF, I->second.first, MOs, MI, *this);
else
- NewMI = FuseInst(MF, I->second, i, MOs, MI, *this);
+ NewMI = FuseInst(MF, I->second.first, i, MOs, MI, *this);
return NewMI;
}
}
@@ -2199,31 +2209,13 @@
MachineInstr* X86InstrInfo::foldMemoryOperandImpl(MachineFunction &MF,
MachineInstr *MI,
- const SmallVectorImpl<unsigned> &Ops,
+ const SmallVectorImpl<unsigned> &Ops,
int FrameIndex) const {
// Check switch flag
if (NoFusing) return NULL;
const MachineFrameInfo *MFI = MF.getFrameInfo();
unsigned Alignment = MFI->getObjectAlignment(FrameIndex);
- // FIXME: Move alignment requirement into tables?
- if (Alignment < 16) {
- switch (MI->getOpcode()) {
- default: break;
- // Not always safe to fold movsd into these instructions since their load
- // folding variants expects the address to be 16 byte aligned.
- case X86::FsANDNPDrr:
- case X86::FsANDNPSrr:
- case X86::FsANDPDrr:
- case X86::FsANDPSrr:
- case X86::FsORPDrr:
- case X86::FsORPSrr:
- case X86::FsXORPDrr:
- case X86::FsXORPSrr:
- return NULL;
- }
- }
-
if (Ops.size() == 2 && Ops[0] == 0 && Ops[1] == 1) {
unsigned NewOpc = 0;
switch (MI->getOpcode()) {
@@ -2241,12 +2233,12 @@
SmallVector<MachineOperand,4> MOs;
MOs.push_back(MachineOperand::CreateFI(FrameIndex));
- return foldMemoryOperandImpl(MF, MI, Ops[0], MOs);
+ return foldMemoryOperandImpl(MF, MI, Ops[0], MOs, Alignment);
}
MachineInstr* X86InstrInfo::foldMemoryOperandImpl(MachineFunction &MF,
MachineInstr *MI,
- const SmallVectorImpl<unsigned> &Ops,
+ const SmallVectorImpl<unsigned> &Ops,
MachineInstr *LoadMI) const {
// Check switch flag
if (NoFusing) return NULL;
@@ -2255,25 +2247,9 @@
unsigned Alignment = 0;
if (LoadMI->hasOneMemOperand())
Alignment = LoadMI->memoperands_begin()->getAlignment();
-
- // FIXME: Move alignment requirement into tables?
- if (Alignment < 16) {
- switch (MI->getOpcode()) {
- default: break;
- // Not always safe to fold movsd into these instructions since their load
- // folding variants expects the address to be 16 byte aligned.
- case X86::FsANDNPDrr:
- case X86::FsANDNPSrr:
- case X86::FsANDPDrr:
- case X86::FsANDPSrr:
- case X86::FsORPDrr:
- case X86::FsORPSrr:
- case X86::FsXORPDrr:
- case X86::FsXORPSrr:
- return NULL;
- }
- }
-
+ else if (LoadMI->getOpcode() == X86::V_SET0 ||
+ LoadMI->getOpcode() == X86::V_SETALLONES)
+ Alignment = 16;
if (Ops.size() == 2 && Ops[0] == 0 && Ops[1] == 1) {
unsigned NewOpc = 0;
switch (MI->getOpcode()) {
@@ -2325,7 +2301,7 @@
for (unsigned i = NumOps - X86AddrNumOperands; i != NumOps; ++i)
MOs.push_back(LoadMI->getOperand(i));
}
- return foldMemoryOperandImpl(MF, MI, Ops[0], MOs);
+ return foldMemoryOperandImpl(MF, MI, Ops[0], MOs, Alignment);
}
@@ -2357,7 +2333,7 @@
// Folding a memory location into the two-address part of a two-address
// instruction is different than folding it other places. It requires
// replacing the *two* registers with the memory location.
- const DenseMap<unsigned*, unsigned> *OpcodeTablePtr = NULL;
+ const DenseMap<unsigned*, std::pair<unsigned,unsigned> > *OpcodeTablePtr=NULL;
if (isTwoAddr && NumOps >= 2 && OpNum < 2) {
OpcodeTablePtr = &RegOp2MemOpTable2Addr;
} else if (OpNum == 0) { // If operand 0
@@ -2377,7 +2353,7 @@
if (OpcodeTablePtr) {
// Find the Opcode to fuse
- DenseMap<unsigned*, unsigned>::iterator I =
+ DenseMap<unsigned*, std::pair<unsigned,unsigned> >::iterator I =
OpcodeTablePtr->find((unsigned*)Opc);
if (I != OpcodeTablePtr->end())
return true;
Modified: llvm/trunk/lib/Target/X86/X86InstrInfo.h
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86InstrInfo.h?rev=75749&r1=75748&r2=75749&view=diff
==============================================================================
--- llvm/trunk/lib/Target/X86/X86InstrInfo.h (original)
+++ llvm/trunk/lib/Target/X86/X86InstrInfo.h Wed Jul 15 01:10:07 2009
@@ -427,10 +427,10 @@
/// RegOp2MemOpTable2Addr, RegOp2MemOpTable0, RegOp2MemOpTable1,
/// RegOp2MemOpTable2 - Load / store folding opcode maps.
///
- DenseMap<unsigned*, unsigned> RegOp2MemOpTable2Addr;
- DenseMap<unsigned*, unsigned> RegOp2MemOpTable0;
- DenseMap<unsigned*, unsigned> RegOp2MemOpTable1;
- DenseMap<unsigned*, unsigned> RegOp2MemOpTable2;
+ DenseMap<unsigned*, std::pair<unsigned,unsigned> > RegOp2MemOpTable2Addr;
+ DenseMap<unsigned*, std::pair<unsigned,unsigned> > RegOp2MemOpTable0;
+ DenseMap<unsigned*, std::pair<unsigned,unsigned> > RegOp2MemOpTable1;
+ DenseMap<unsigned*, std::pair<unsigned,unsigned> > RegOp2MemOpTable2;
/// MemOp2RegOpTable - Load / store unfolding opcode map.
///
@@ -602,9 +602,10 @@
private:
MachineInstr* foldMemoryOperandImpl(MachineFunction &MF,
- MachineInstr* MI,
- unsigned OpNum,
- const SmallVectorImpl<MachineOperand> &MOs) const;
+ MachineInstr* MI,
+ unsigned OpNum,
+ const SmallVectorImpl<MachineOperand> &MOs,
+ unsigned Alignment) const;
};
} // End llvm namespace
More information about the llvm-commits
mailing list