#include "llvm/CodeGen/MachineFrameInfo.h"
#include "llvm/CodeGen/MachineInstrBuilder.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
-#include "llvm/DerivedTypes.h"
-#include "llvm/LLVMContext.h"
+#include "llvm/CodeGen/StackMaps.h"
+#include "llvm/IR/DerivedTypes.h"
+#include "llvm/IR/Function.h"
+#include "llvm/IR/LLVMContext.h"
#include "llvm/MC/MCAsmInfo.h"
+#include "llvm/MC/MCExpr.h"
#include "llvm/MC/MCInst.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Target/TargetOptions.h"
#include <limits>
-#define GET_INSTRINFO_CTOR
-#include "X86GenInstrInfo.inc"
-
using namespace llvm;
+#define DEBUG_TYPE "x86-instr-info"
+
+#define GET_INSTRINFO_CTOR_DTOR
+#include "X86GenInstrInfo.inc"
+
static cl::opt<bool>
NoFusing("disable-spill-fusing",
cl::desc("Disable fusing of spill code into instructions"));
TB_ALIGN_NONE = 0 << TB_ALIGN_SHIFT,
TB_ALIGN_16 = 16 << TB_ALIGN_SHIFT,
TB_ALIGN_32 = 32 << TB_ALIGN_SHIFT,
+ TB_ALIGN_64 = 64 << TB_ALIGN_SHIFT,
TB_ALIGN_MASK = 0xff << TB_ALIGN_SHIFT
};
uint16_t Flags;
};
-X86InstrInfo::X86InstrInfo(X86TargetMachine &tm)
- : X86GenInstrInfo((tm.getSubtarget<X86Subtarget>().is64Bit()
- ? X86::ADJCALLSTACKDOWN64
- : X86::ADJCALLSTACKDOWN32),
- (tm.getSubtarget<X86Subtarget>().is64Bit()
- ? X86::ADJCALLSTACKUP64
- : X86::ADJCALLSTACKUP32)),
- TM(tm), RI(tm, *this) {
+// Pin the vtable to this file.
+void X86InstrInfo::anchor() {}
+
+X86InstrInfo::X86InstrInfo(X86Subtarget &STI)
+ : X86GenInstrInfo(
+ (STI.isTarget64BitLP64() ? X86::ADJCALLSTACKDOWN64 : X86::ADJCALLSTACKDOWN32),
+ (STI.isTarget64BitLP64() ? X86::ADJCALLSTACKUP64 : X86::ADJCALLSTACKUP32)),
+ Subtarget(STI), RI(STI) {
static const X86OpTblEntry OpTbl2Addr[] = {
{ X86::ADC32ri, X86::ADC32mi, 0 },
{ X86::DIV32r, X86::DIV32m, TB_FOLDED_LOAD },
{ X86::DIV64r, X86::DIV64m, TB_FOLDED_LOAD },
{ X86::DIV8r, X86::DIV8m, TB_FOLDED_LOAD },
- { X86::EXTRACTPSrr, X86::EXTRACTPSmr, TB_FOLDED_STORE | TB_ALIGN_16 },
- { X86::FsMOVAPDrr, X86::MOVSDmr, TB_FOLDED_STORE | TB_NO_REVERSE },
- { X86::FsMOVAPSrr, X86::MOVSSmr, TB_FOLDED_STORE | TB_NO_REVERSE },
+ { X86::EXTRACTPSrr, X86::EXTRACTPSmr, TB_FOLDED_STORE },
{ X86::IDIV16r, X86::IDIV16m, TB_FOLDED_LOAD },
{ X86::IDIV32r, X86::IDIV32m, TB_FOLDED_LOAD },
{ X86::IDIV64r, X86::IDIV64m, TB_FOLDED_LOAD },
{ X86::TEST64ri32, X86::TEST64mi32, TB_FOLDED_LOAD },
{ X86::TEST8ri, X86::TEST8mi, TB_FOLDED_LOAD },
// AVX 128-bit versions of foldable instructions
- { X86::VEXTRACTPSrr,X86::VEXTRACTPSmr, TB_FOLDED_STORE | TB_ALIGN_16 },
- { X86::FsVMOVAPDrr, X86::VMOVSDmr, TB_FOLDED_STORE | TB_NO_REVERSE },
- { X86::FsVMOVAPSrr, X86::VMOVSSmr, TB_FOLDED_STORE | TB_NO_REVERSE },
+ { X86::VEXTRACTPSrr,X86::VEXTRACTPSmr, TB_FOLDED_STORE },
{ X86::VEXTRACTF128rr, X86::VEXTRACTF128mr, TB_FOLDED_STORE | TB_ALIGN_16 },
{ X86::VMOVAPDrr, X86::VMOVAPDmr, TB_FOLDED_STORE | TB_ALIGN_16 },
{ X86::VMOVAPSrr, X86::VMOVAPSmr, TB_FOLDED_STORE | TB_ALIGN_16 },
{ X86::VMOVAPSYrr, X86::VMOVAPSYmr, TB_FOLDED_STORE | TB_ALIGN_32 },
{ X86::VMOVDQAYrr, X86::VMOVDQAYmr, TB_FOLDED_STORE | TB_ALIGN_32 },
{ X86::VMOVUPDYrr, X86::VMOVUPDYmr, TB_FOLDED_STORE },
- { X86::VMOVUPSYrr, X86::VMOVUPSYmr, TB_FOLDED_STORE }
+ { X86::VMOVUPSYrr, X86::VMOVUPSYmr, TB_FOLDED_STORE },
+ // AVX-512 foldable instructions
+ { X86::VMOVPDI2DIZrr, X86::VMOVPDI2DIZmr, TB_FOLDED_STORE },
+ { X86::VMOVAPDZrr, X86::VMOVAPDZmr, TB_FOLDED_STORE | TB_ALIGN_64 },
+ { X86::VMOVAPSZrr, X86::VMOVAPSZmr, TB_FOLDED_STORE | TB_ALIGN_64 },
+ { X86::VMOVDQA32Zrr, X86::VMOVDQA32Zmr, TB_FOLDED_STORE | TB_ALIGN_64 },
+ { X86::VMOVDQA64Zrr, X86::VMOVDQA64Zmr, TB_FOLDED_STORE | TB_ALIGN_64 },
+ { X86::VMOVUPDZrr, X86::VMOVUPDZmr, TB_FOLDED_STORE },
+ { X86::VMOVUPSZrr, X86::VMOVUPSZmr, TB_FOLDED_STORE },
+ { X86::VMOVDQU8Zrr, X86::VMOVDQU8Zmr, TB_FOLDED_STORE },
+ { X86::VMOVDQU16Zrr, X86::VMOVDQU16Zmr, TB_FOLDED_STORE },
+ { X86::VMOVDQU32Zrr, X86::VMOVDQU32Zmr, TB_FOLDED_STORE },
+ { X86::VMOVDQU64Zrr, X86::VMOVDQU64Zmr, TB_FOLDED_STORE },
+ // AVX-512 foldable instructions (256-bit versions)
+ { X86::VMOVAPDZ256rr, X86::VMOVAPDZ256mr, TB_FOLDED_STORE | TB_ALIGN_32 },
+ { X86::VMOVAPSZ256rr, X86::VMOVAPSZ256mr, TB_FOLDED_STORE | TB_ALIGN_32 },
+ { X86::VMOVDQA32Z256rr, X86::VMOVDQA32Z256mr, TB_FOLDED_STORE | TB_ALIGN_32 },
+ { X86::VMOVDQA64Z256rr, X86::VMOVDQA64Z256mr, TB_FOLDED_STORE | TB_ALIGN_32 },
+ { X86::VMOVUPDZ256rr, X86::VMOVUPDZ256mr, TB_FOLDED_STORE },
+ { X86::VMOVUPSZ256rr, X86::VMOVUPSZ256mr, TB_FOLDED_STORE },
+ { X86::VMOVDQU8Z256rr, X86::VMOVDQU8Z256mr, TB_FOLDED_STORE },
+ { X86::VMOVDQU16Z256rr, X86::VMOVDQU16Z256mr, TB_FOLDED_STORE },
+ { X86::VMOVDQU32Z256rr, X86::VMOVDQU32Z256mr, TB_FOLDED_STORE },
+ { X86::VMOVDQU64Z256rr, X86::VMOVDQU64Z256mr, TB_FOLDED_STORE },
+ // AVX-512 foldable instructions (128-bit versions)
+ { X86::VMOVAPDZ128rr, X86::VMOVAPDZ128mr, TB_FOLDED_STORE | TB_ALIGN_16 },
+ { X86::VMOVAPSZ128rr, X86::VMOVAPSZ128mr, TB_FOLDED_STORE | TB_ALIGN_16 },
+ { X86::VMOVDQA32Z128rr, X86::VMOVDQA32Z128mr, TB_FOLDED_STORE | TB_ALIGN_16 },
+ { X86::VMOVDQA64Z128rr, X86::VMOVDQA64Z128mr, TB_FOLDED_STORE | TB_ALIGN_16 },
+ { X86::VMOVUPDZ128rr, X86::VMOVUPDZ128mr, TB_FOLDED_STORE },
+ { X86::VMOVUPSZ128rr, X86::VMOVUPSZ128mr, TB_FOLDED_STORE },
+ { 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 }
};
for (unsigned i = 0, e = array_lengthof(OpTbl0); i != e; ++i) {
{ X86::CVTTSD2SIrr, X86::CVTTSD2SIrm, 0 },
{ X86::CVTTSS2SI64rr, X86::CVTTSS2SI64rm, 0 },
{ X86::CVTTSS2SIrr, X86::CVTTSS2SIrm, 0 },
- { X86::FsMOVAPDrr, X86::MOVSDrm, TB_NO_REVERSE },
- { X86::FsMOVAPSrr, X86::MOVSSrm, TB_NO_REVERSE },
{ X86::IMUL16rri, X86::IMUL16rmi, 0 },
{ X86::IMUL16rri8, X86::IMUL16rmi8, 0 },
{ X86::IMUL32rri, X86::IMUL32rmi, 0 },
{ X86::MOVSX64rr8, X86::MOVSX64rm8, 0 },
{ X86::MOVUPDrr, X86::MOVUPDrm, TB_ALIGN_16 },
{ X86::MOVUPSrr, X86::MOVUPSrm, 0 },
- { X86::MOVZDI2PDIrr, X86::MOVZDI2PDIrm, 0 },
{ X86::MOVZQI2PQIrr, X86::MOVZQI2PQIrm, 0 },
{ X86::MOVZPQILo2PQIrr, X86::MOVZPQILo2PQIrm, TB_ALIGN_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::PABSBrr128, X86::PABSBrm128, TB_ALIGN_16 },
{ X86::PABSDrr128, X86::PABSDrm128, TB_ALIGN_16 },
{ X86::PABSWrr128, X86::PABSWrm128, TB_ALIGN_16 },
{ X86::RSQRTSSr, X86::RSQRTSSm, 0 },
{ X86::RSQRTSSr_Int, X86::RSQRTSSm_Int, 0 },
{ X86::SQRTPDr, X86::SQRTPDm, TB_ALIGN_16 },
- { X86::SQRTPDr_Int, X86::SQRTPDm_Int, TB_ALIGN_16 },
{ X86::SQRTPSr, X86::SQRTPSm, TB_ALIGN_16 },
- { X86::SQRTPSr_Int, X86::SQRTPSm_Int, TB_ALIGN_16 },
{ X86::SQRTSDr, X86::SQRTSDm, 0 },
{ X86::SQRTSDr_Int, X86::SQRTSDm_Int, 0 },
{ X86::SQRTSSr, X86::SQRTSSm, 0 },
{ X86::VCVTSD2SIrr, X86::VCVTSD2SIrm, 0 },
{ X86::VCVTSS2SI64rr, X86::VCVTSS2SI64rm, 0 },
{ X86::VCVTSS2SIrr, X86::VCVTSS2SIrm, 0 },
- { X86::FsVMOVAPDrr, X86::VMOVSDrm, TB_NO_REVERSE },
- { X86::FsVMOVAPSrr, X86::VMOVSSrm, TB_NO_REVERSE },
{ X86::VMOV64toPQIrr, X86::VMOVQI2PQIrm, 0 },
{ X86::VMOV64toSDrr, X86::VMOV64toSDrm, 0 },
{ X86::VMOVAPDrr, X86::VMOVAPDrm, TB_ALIGN_16 },
{ X86::VMOVDQArr, X86::VMOVDQArm, TB_ALIGN_16 },
{ X86::VMOVSLDUPrr, X86::VMOVSLDUPrm, TB_ALIGN_16 },
{ X86::VMOVSHDUPrr, X86::VMOVSHDUPrm, TB_ALIGN_16 },
- { X86::VMOVUPDrr, X86::VMOVUPDrm, TB_ALIGN_16 },
+ { X86::VMOVUPDrr, X86::VMOVUPDrm, 0 },
{ X86::VMOVUPSrr, X86::VMOVUPSrm, 0 },
- { X86::VMOVZDI2PDIrr, X86::VMOVZDI2PDIrm, 0 },
{ X86::VMOVZQI2PQIrr, X86::VMOVZQI2PQIrm, 0 },
{ X86::VMOVZPQILo2PQIrr,X86::VMOVZPQILo2PQIrm, TB_ALIGN_16 },
- { X86::VPABSBrr128, X86::VPABSBrm128, TB_ALIGN_16 },
- { X86::VPABSDrr128, X86::VPABSDrm128, TB_ALIGN_16 },
- { X86::VPABSWrr128, X86::VPABSWrm128, TB_ALIGN_16 },
- { X86::VPERMILPDri, X86::VPERMILPDmi, TB_ALIGN_16 },
- { X86::VPERMILPSri, X86::VPERMILPSmi, TB_ALIGN_16 },
- { X86::VPSHUFDri, X86::VPSHUFDmi, TB_ALIGN_16 },
- { X86::VPSHUFHWri, X86::VPSHUFHWmi, TB_ALIGN_16 },
- { X86::VPSHUFLWri, X86::VPSHUFLWmi, TB_ALIGN_16 },
- { X86::VRCPPSr, X86::VRCPPSm, TB_ALIGN_16 },
- { X86::VRCPPSr_Int, X86::VRCPPSm_Int, TB_ALIGN_16 },
- { X86::VRSQRTPSr, X86::VRSQRTPSm, TB_ALIGN_16 },
- { X86::VRSQRTPSr_Int, X86::VRSQRTPSm_Int, TB_ALIGN_16 },
- { X86::VSQRTPDr, X86::VSQRTPDm, TB_ALIGN_16 },
- { X86::VSQRTPDr_Int, X86::VSQRTPDm_Int, TB_ALIGN_16 },
- { X86::VSQRTPSr, X86::VSQRTPSm, TB_ALIGN_16 },
- { X86::VSQRTPSr_Int, X86::VSQRTPSm_Int, TB_ALIGN_16 },
+ { X86::VPABSBrr128, X86::VPABSBrm128, 0 },
+ { X86::VPABSDrr128, X86::VPABSDrm128, 0 },
+ { X86::VPABSWrr128, X86::VPABSWrm128, 0 },
+ { X86::VPERMILPDri, X86::VPERMILPDmi, 0 },
+ { X86::VPERMILPSri, X86::VPERMILPSmi, 0 },
+ { X86::VPSHUFDri, X86::VPSHUFDmi, 0 },
+ { X86::VPSHUFHWri, X86::VPSHUFHWmi, 0 },
+ { X86::VPSHUFLWri, X86::VPSHUFLWmi, 0 },
+ { X86::VRCPPSr, X86::VRCPPSm, 0 },
+ { X86::VRCPPSr_Int, X86::VRCPPSm_Int, 0 },
+ { X86::VRSQRTPSr, X86::VRSQRTPSm, 0 },
+ { X86::VRSQRTPSr_Int, X86::VRSQRTPSm_Int, 0 },
+ { X86::VSQRTPDr, X86::VSQRTPDm, 0 },
+ { X86::VSQRTPSr, X86::VSQRTPSm, 0 },
{ X86::VUCOMISDrr, X86::VUCOMISDrm, 0 },
{ X86::VUCOMISSrr, X86::VUCOMISSrm, 0 },
{ X86::VBROADCASTSSrr, X86::VBROADCASTSSrm, TB_NO_REVERSE },
{ X86::VMOVDQAYrr, X86::VMOVDQAYrm, TB_ALIGN_32 },
{ X86::VMOVUPDYrr, X86::VMOVUPDYrm, 0 },
{ X86::VMOVUPSYrr, X86::VMOVUPSYrm, 0 },
- { X86::VPERMILPDYri, X86::VPERMILPDYmi, TB_ALIGN_32 },
- { X86::VPERMILPSYri, X86::VPERMILPSYmi, TB_ALIGN_32 },
-
- // AVX2 foldable instructions
- { X86::VPABSBrr256, X86::VPABSBrm256, TB_ALIGN_32 },
- { X86::VPABSDrr256, X86::VPABSDrm256, TB_ALIGN_32 },
- { X86::VPABSWrr256, X86::VPABSWrm256, TB_ALIGN_32 },
- { X86::VPSHUFDYri, X86::VPSHUFDYmi, TB_ALIGN_32 },
- { X86::VPSHUFHWYri, X86::VPSHUFHWYmi, TB_ALIGN_32 },
- { X86::VPSHUFLWYri, X86::VPSHUFLWYmi, TB_ALIGN_32 },
- { X86::VRCPPSYr, X86::VRCPPSYm, TB_ALIGN_32 },
- { X86::VRCPPSYr_Int, X86::VRCPPSYm_Int, TB_ALIGN_32 },
- { X86::VRSQRTPSYr, X86::VRSQRTPSYm, TB_ALIGN_32 },
- { X86::VRSQRTPSYr_Int, X86::VRSQRTPSYm_Int, TB_ALIGN_32 },
- { X86::VSQRTPDYr, X86::VSQRTPDYm, TB_ALIGN_32 },
- { X86::VSQRTPDYr_Int, X86::VSQRTPDYm_Int, TB_ALIGN_32 },
- { X86::VSQRTPSYr, X86::VSQRTPSYm, TB_ALIGN_32 },
- { X86::VSQRTPSYr_Int, X86::VSQRTPSYm_Int, TB_ALIGN_32 },
+ { X86::VPERMILPDYri, X86::VPERMILPDYmi, 0 },
+ { X86::VPERMILPSYri, X86::VPERMILPSYmi, 0 },
+ { X86::VRCPPSYr, X86::VRCPPSYm, 0 },
+ { X86::VRCPPSYr_Int, X86::VRCPPSYm_Int, 0 },
+ { X86::VRSQRTPSYr, X86::VRSQRTPSYm, 0 },
+ { X86::VSQRTPDYr, X86::VSQRTPDYm, 0 },
+ { X86::VSQRTPSYr, X86::VSQRTPSYm, 0 },
{ X86::VBROADCASTSSYrr, X86::VBROADCASTSSYrm, TB_NO_REVERSE },
{ X86::VBROADCASTSDYrr, X86::VBROADCASTSDYrm, TB_NO_REVERSE },
- // BMI/BMI2/LZCNT/POPCNT foldable instructions
+ // AVX2 foldable instructions
+ { X86::VPABSBrr256, X86::VPABSBrm256, 0 },
+ { X86::VPABSDrr256, X86::VPABSDrm256, 0 },
+ { X86::VPABSWrr256, X86::VPABSWrm256, 0 },
+ { X86::VPSHUFDYri, X86::VPSHUFDYmi, 0 },
+ { X86::VPSHUFHWYri, X86::VPSHUFHWYmi, 0 },
+ { X86::VPSHUFLWYri, X86::VPSHUFLWYmi, 0 },
+
+ // BMI/BMI2/LZCNT/POPCNT/TBM foldable instructions
{ X86::BEXTR32rr, X86::BEXTR32rm, 0 },
{ X86::BEXTR64rr, X86::BEXTR64rm, 0 },
+ { X86::BEXTRI32ri, X86::BEXTRI32mi, 0 },
+ { X86::BEXTRI64ri, X86::BEXTRI64mi, 0 },
+ { X86::BLCFILL32rr, X86::BLCFILL32rm, 0 },
+ { X86::BLCFILL64rr, X86::BLCFILL64rm, 0 },
+ { X86::BLCI32rr, X86::BLCI32rm, 0 },
+ { X86::BLCI64rr, X86::BLCI64rm, 0 },
+ { X86::BLCIC32rr, X86::BLCIC32rm, 0 },
+ { X86::BLCIC64rr, X86::BLCIC64rm, 0 },
+ { X86::BLCMSK32rr, X86::BLCMSK32rm, 0 },
+ { X86::BLCMSK64rr, X86::BLCMSK64rm, 0 },
+ { X86::BLCS32rr, X86::BLCS32rm, 0 },
+ { X86::BLCS64rr, X86::BLCS64rm, 0 },
+ { X86::BLSFILL32rr, X86::BLSFILL32rm, 0 },
+ { X86::BLSFILL64rr, X86::BLSFILL64rm, 0 },
{ X86::BLSI32rr, X86::BLSI32rm, 0 },
{ X86::BLSI64rr, X86::BLSI64rm, 0 },
+ { X86::BLSIC32rr, X86::BLSIC32rm, 0 },
+ { X86::BLSIC64rr, X86::BLSIC64rm, 0 },
{ X86::BLSMSK32rr, X86::BLSMSK32rm, 0 },
{ X86::BLSMSK64rr, X86::BLSMSK64rm, 0 },
{ X86::BLSR32rr, X86::BLSR32rm, 0 },
{ X86::SHRX64rr, X86::SHRX64rm, 0 },
{ X86::SHLX32rr, X86::SHLX32rm, 0 },
{ X86::SHLX64rr, X86::SHLX64rm, 0 },
+ { X86::T1MSKC32rr, X86::T1MSKC32rm, 0 },
+ { X86::T1MSKC64rr, X86::T1MSKC64rm, 0 },
{ X86::TZCNT16rr, X86::TZCNT16rm, 0 },
{ X86::TZCNT32rr, X86::TZCNT32rm, 0 },
{ X86::TZCNT64rr, X86::TZCNT64rm, 0 },
+ { X86::TZMSK32rr, X86::TZMSK32rm, 0 },
+ { X86::TZMSK64rr, X86::TZMSK64rm, 0 },
+
+ // AVX-512 foldable instructions
+ { X86::VMOV64toPQIZrr, X86::VMOVQI2PQIZrm, 0 },
+ { X86::VMOVDI2SSZrr, X86::VMOVDI2SSZrm, 0 },
+ { X86::VMOVAPDZrr, X86::VMOVAPDZrm, TB_ALIGN_64 },
+ { X86::VMOVAPSZrr, X86::VMOVAPSZrm, TB_ALIGN_64 },
+ { X86::VMOVDQA32Zrr, X86::VMOVDQA32Zrm, TB_ALIGN_64 },
+ { X86::VMOVDQA64Zrr, X86::VMOVDQA64Zrm, TB_ALIGN_64 },
+ { X86::VMOVDQU8Zrr, X86::VMOVDQU8Zrm, 0 },
+ { X86::VMOVDQU16Zrr, X86::VMOVDQU16Zrm, 0 },
+ { X86::VMOVDQU32Zrr, X86::VMOVDQU32Zrm, 0 },
+ { X86::VMOVDQU64Zrr, X86::VMOVDQU64Zrm, 0 },
+ { X86::VMOVUPDZrr, X86::VMOVUPDZrm, 0 },
+ { X86::VMOVUPSZrr, X86::VMOVUPSZrm, 0 },
+ { X86::VPABSDZrr, X86::VPABSDZrm, 0 },
+ { X86::VPABSQZrr, X86::VPABSQZrm, 0 },
+ // AVX-512 foldable instructions (256-bit versions)
+ { X86::VMOVAPDZ256rr, X86::VMOVAPDZ256rm, TB_ALIGN_32 },
+ { X86::VMOVAPSZ256rr, X86::VMOVAPSZ256rm, TB_ALIGN_32 },
+ { X86::VMOVDQA32Z256rr, X86::VMOVDQA32Z256rm, TB_ALIGN_32 },
+ { X86::VMOVDQA64Z256rr, X86::VMOVDQA64Z256rm, TB_ALIGN_32 },
+ { X86::VMOVDQU8Z256rr, X86::VMOVDQU8Z256rm, 0 },
+ { X86::VMOVDQU16Z256rr, X86::VMOVDQU16Z256rm, 0 },
+ { X86::VMOVDQU32Z256rr, X86::VMOVDQU32Z256rm, 0 },
+ { X86::VMOVDQU64Z256rr, X86::VMOVDQU64Z256rm, 0 },
+ { X86::VMOVUPDZ256rr, X86::VMOVUPDZ256rm, 0 },
+ { X86::VMOVUPSZ256rr, X86::VMOVUPSZ256rm, 0 },
+ // AVX-512 foldable instructions (256-bit versions)
+ { X86::VMOVAPDZ128rr, X86::VMOVAPDZ128rm, TB_ALIGN_16 },
+ { X86::VMOVAPSZ128rr, X86::VMOVAPSZ128rm, TB_ALIGN_16 },
+ { X86::VMOVDQA32Z128rr, X86::VMOVDQA32Z128rm, TB_ALIGN_16 },
+ { X86::VMOVDQA64Z128rr, X86::VMOVDQA64Z128rm, TB_ALIGN_16 },
+ { X86::VMOVDQU8Z128rr, X86::VMOVDQU8Z128rm, 0 },
+ { X86::VMOVDQU16Z128rr, X86::VMOVDQU16Z128rm, 0 },
+ { X86::VMOVDQU32Z128rr, X86::VMOVDQU32Z128rm, 0 },
+ { X86::VMOVDQU64Z128rr, X86::VMOVDQU64Z128rm, 0 },
+ { X86::VMOVUPDZ128rr, X86::VMOVUPDZ128rm, 0 },
+ { X86::VMOVUPSZ128rr, X86::VMOVUPSZ128rm, 0 },
+
+ // AES foldable instructions
+ { X86::AESIMCrr, X86::AESIMCrm, TB_ALIGN_16 },
+ { X86::AESKEYGENASSIST128rr, X86::AESKEYGENASSIST128rm, TB_ALIGN_16 },
+ { X86::VAESIMCrr, X86::VAESIMCrm, TB_ALIGN_16 },
+ { X86::VAESKEYGENASSIST128rr, X86::VAESKEYGENASSIST128rm, TB_ALIGN_16 }
};
for (unsigned i = 0, e = array_lengthof(OpTbl1); i != e; ++i) {
{ X86::Int_CVTSI2SSrr, X86::Int_CVTSI2SSrm, 0 },
{ X86::Int_CVTSS2SDrr, X86::Int_CVTSS2SDrm, 0 },
{ X86::MAXPDrr, X86::MAXPDrm, TB_ALIGN_16 },
- { X86::MAXPDrr_Int, X86::MAXPDrm_Int, TB_ALIGN_16 },
{ X86::MAXPSrr, X86::MAXPSrm, TB_ALIGN_16 },
- { X86::MAXPSrr_Int, X86::MAXPSrm_Int, 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::MINPDrr_Int, X86::MINPDrm_Int, TB_ALIGN_16 },
{ X86::MINPSrr, X86::MINPSrm, TB_ALIGN_16 },
- { X86::MINPSrr_Int, X86::MINPSrm_Int, 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::VFsORPSrr, X86::VFsORPSrm, TB_ALIGN_16 },
{ X86::VFsXORPDrr, X86::VFsXORPDrm, TB_ALIGN_16 },
{ X86::VFsXORPSrr, X86::VFsXORPSrm, TB_ALIGN_16 },
- { X86::VHADDPDrr, X86::VHADDPDrm, TB_ALIGN_16 },
- { X86::VHADDPSrr, X86::VHADDPSrm, TB_ALIGN_16 },
- { X86::VHSUBPDrr, X86::VHSUBPDrm, TB_ALIGN_16 },
- { X86::VHSUBPSrr, X86::VHSUBPSrm, TB_ALIGN_16 },
+ { X86::VHADDPDrr, X86::VHADDPDrm, 0 },
+ { X86::VHADDPSrr, X86::VHADDPSrm, 0 },
+ { X86::VHSUBPDrr, X86::VHSUBPDrm, 0 },
+ { X86::VHSUBPSrr, X86::VHSUBPSrm, 0 },
{ X86::Int_VCMPSDrr, X86::Int_VCMPSDrm, 0 },
{ X86::Int_VCMPSSrr, X86::Int_VCMPSSrm, 0 },
- { X86::VMAXPDrr, X86::VMAXPDrm, TB_ALIGN_16 },
- { X86::VMAXPDrr_Int, X86::VMAXPDrm_Int, TB_ALIGN_16 },
- { X86::VMAXPSrr, X86::VMAXPSrm, TB_ALIGN_16 },
- { X86::VMAXPSrr_Int, X86::VMAXPSrm_Int, 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, TB_ALIGN_16 },
- { X86::VMINPDrr_Int, X86::VMINPDrm_Int, TB_ALIGN_16 },
- { X86::VMINPSrr, X86::VMINPSrm, TB_ALIGN_16 },
- { X86::VMINPSrr_Int, X86::VMINPSrm_Int, TB_ALIGN_16 },
+ { 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, TB_ALIGN_16 },
- { X86::VMULPDrr, X86::VMULPDrm, TB_ALIGN_16 },
- { X86::VMULPSrr, X86::VMULPSrm, TB_ALIGN_16 },
+ { X86::VMPSADBWrri, X86::VMPSADBWrmi, 0 },
+ { X86::VMULPDrr, X86::VMULPDrm, 0 },
+ { X86::VMULPSrr, X86::VMULPSrm, 0 },
{ X86::VMULSDrr, X86::VMULSDrm, 0 },
{ X86::VMULSSrr, X86::VMULSSrm, 0 },
{ X86::VORPDrr, X86::VORPDrm, 0 },
{ X86::VHSUBPSYrr, X86::VHSUBPSYrm, 0 },
{ X86::VINSERTF128rr, X86::VINSERTF128rm, 0 },
{ X86::VMAXPDYrr, X86::VMAXPDYrm, 0 },
- { X86::VMAXPDYrr_Int, X86::VMAXPDYrm_Int, 0 },
{ X86::VMAXPSYrr, X86::VMAXPSYrm, 0 },
- { X86::VMAXPSYrr_Int, X86::VMAXPSYrm_Int, 0 },
{ X86::VMINPDYrr, X86::VMINPDYrm, 0 },
- { X86::VMINPDYrr_Int, X86::VMINPDYrm_Int, 0 },
{ X86::VMINPSYrr, X86::VMINPSYrm, 0 },
- { X86::VMINPSYrr_Int, X86::VMINPSYrm_Int, 0 },
{ X86::VMULPDYrr, X86::VMULPDYrm, 0 },
{ X86::VMULPSYrr, X86::VMULPSYrm, 0 },
{ X86::VORPDYrr, X86::VORPDYrm, 0 },
{ X86::PDEP64rr, X86::PDEP64rm, 0 },
{ X86::PEXT32rr, X86::PEXT32rm, 0 },
{ X86::PEXT64rr, X86::PEXT64rm, 0 },
+
+ // AVX-512 foldable instructions
+ { X86::VADDPSZrr, X86::VADDPSZrm, 0 },
+ { X86::VADDPDZrr, X86::VADDPDZrm, 0 },
+ { X86::VSUBPSZrr, X86::VSUBPSZrm, 0 },
+ { X86::VSUBPDZrr, X86::VSUBPDZrm, 0 },
+ { X86::VMULPSZrr, X86::VMULPSZrm, 0 },
+ { X86::VMULPDZrr, X86::VMULPDZrm, 0 },
+ { X86::VDIVPSZrr, X86::VDIVPSZrm, 0 },
+ { X86::VDIVPDZrr, X86::VDIVPDZrm, 0 },
+ { X86::VMINPSZrr, X86::VMINPSZrm, 0 },
+ { X86::VMINPDZrr, X86::VMINPDZrm, 0 },
+ { X86::VMAXPSZrr, X86::VMAXPSZrm, 0 },
+ { X86::VMAXPDZrr, X86::VMAXPDZrm, 0 },
+ { X86::VPADDDZrr, X86::VPADDDZrm, 0 },
+ { X86::VPADDQZrr, X86::VPADDQZrm, 0 },
+ { X86::VPERMPDZri, X86::VPERMPDZmi, 0 },
+ { X86::VPERMPSZrr, X86::VPERMPSZrm, 0 },
+ { X86::VPMAXSDZrr, X86::VPMAXSDZrm, 0 },
+ { X86::VPMAXSQZrr, X86::VPMAXSQZrm, 0 },
+ { X86::VPMAXUDZrr, X86::VPMAXUDZrm, 0 },
+ { X86::VPMAXUQZrr, X86::VPMAXUQZrm, 0 },
+ { X86::VPMINSDZrr, X86::VPMINSDZrm, 0 },
+ { X86::VPMINSQZrr, X86::VPMINSQZrm, 0 },
+ { X86::VPMINUDZrr, X86::VPMINUDZrm, 0 },
+ { X86::VPMINUQZrr, X86::VPMINUQZrm, 0 },
+ { X86::VPMULDQZrr, X86::VPMULDQZrm, 0 },
+ { X86::VPSLLVDZrr, X86::VPSLLVDZrm, 0 },
+ { X86::VPSLLVQZrr, X86::VPSLLVQZrm, 0 },
+ { X86::VPSRAVDZrr, X86::VPSRAVDZrm, 0 },
+ { X86::VPSRLVDZrr, X86::VPSRLVDZrm, 0 },
+ { X86::VPSRLVQZrr, X86::VPSRLVQZrm, 0 },
+ { X86::VPSUBDZrr, X86::VPSUBDZrm, 0 },
+ { X86::VPSUBQZrr, X86::VPSUBQZrm, 0 },
+ { X86::VSHUFPDZrri, X86::VSHUFPDZrmi, 0 },
+ { X86::VSHUFPSZrri, X86::VSHUFPSZrmi, 0 },
+ { X86::VALIGNQrri, X86::VALIGNQrmi, 0 },
+ { X86::VALIGNDrri, X86::VALIGNDrmi, 0 },
+ { X86::VPMULUDQZrr, X86::VPMULUDQZrm, 0 },
+
+ // AES foldable instructions
+ { X86::AESDECLASTrr, X86::AESDECLASTrm, TB_ALIGN_16 },
+ { X86::AESDECrr, X86::AESDECrm, TB_ALIGN_16 },
+ { X86::AESENCLASTrr, X86::AESENCLASTrm, TB_ALIGN_16 },
+ { X86::AESENCrr, X86::AESENCrm, TB_ALIGN_16 },
+ { X86::VAESDECLASTrr, X86::VAESDECLASTrm, TB_ALIGN_16 },
+ { X86::VAESDECrr, X86::VAESDECrm, TB_ALIGN_16 },
+ { X86::VAESENCLASTrr, X86::VAESENCLASTrm, TB_ALIGN_16 },
+ { X86::VAESENCrr, X86::VAESENCrm, TB_ALIGN_16 },
+
+ // SHA foldable instructions
+ { X86::SHA1MSG1rr, X86::SHA1MSG1rm, TB_ALIGN_16 },
+ { X86::SHA1MSG2rr, X86::SHA1MSG2rm, TB_ALIGN_16 },
+ { X86::SHA1NEXTErr, X86::SHA1NEXTErm, TB_ALIGN_16 },
+ { X86::SHA1RNDS4rri, X86::SHA1RNDS4rmi, TB_ALIGN_16 },
+ { X86::SHA256MSG1rr, X86::SHA256MSG1rm, TB_ALIGN_16 },
+ { X86::SHA256MSG2rr, X86::SHA256MSG2rm, TB_ALIGN_16 },
+ { X86::SHA256RNDS2rr, X86::SHA256RNDS2rm, TB_ALIGN_16 },
};
for (unsigned i = 0, e = array_lengthof(OpTbl2); i != e; ++i) {
static const X86OpTblEntry OpTbl3[] = {
// FMA foldable instructions
- { X86::VFMADDSSr231r, X86::VFMADDSSr231m, 0 },
- { X86::VFMADDSDr231r, X86::VFMADDSDr231m, 0 },
- { X86::VFMADDSSr132r, X86::VFMADDSSr132m, 0 },
- { X86::VFMADDSDr132r, X86::VFMADDSDr132m, 0 },
- { X86::VFMADDSSr213r, X86::VFMADDSSr213m, 0 },
- { X86::VFMADDSDr213r, X86::VFMADDSDr213m, 0 },
- { X86::VFMADDSSr213r_Int, X86::VFMADDSSr213m_Int, 0 },
- { X86::VFMADDSDr213r_Int, X86::VFMADDSDr213m_Int, 0 },
-
- { X86::VFMADDPSr231r, X86::VFMADDPSr231m, TB_ALIGN_16 },
- { X86::VFMADDPDr231r, X86::VFMADDPDr231m, TB_ALIGN_16 },
- { X86::VFMADDPSr132r, X86::VFMADDPSr132m, TB_ALIGN_16 },
- { X86::VFMADDPDr132r, X86::VFMADDPDr132m, TB_ALIGN_16 },
- { X86::VFMADDPSr213r, X86::VFMADDPSr213m, TB_ALIGN_16 },
- { X86::VFMADDPDr213r, X86::VFMADDPDr213m, TB_ALIGN_16 },
- { X86::VFMADDPSr231rY, X86::VFMADDPSr231mY, TB_ALIGN_32 },
- { X86::VFMADDPDr231rY, X86::VFMADDPDr231mY, TB_ALIGN_32 },
- { X86::VFMADDPSr132rY, X86::VFMADDPSr132mY, TB_ALIGN_32 },
- { X86::VFMADDPDr132rY, X86::VFMADDPDr132mY, TB_ALIGN_32 },
- { X86::VFMADDPSr213rY, X86::VFMADDPSr213mY, TB_ALIGN_32 },
- { X86::VFMADDPDr213rY, X86::VFMADDPDr213mY, TB_ALIGN_32 },
-
- { X86::VFNMADDSSr231r, X86::VFNMADDSSr231m, 0 },
- { X86::VFNMADDSDr231r, X86::VFNMADDSDr231m, 0 },
- { X86::VFNMADDSSr132r, X86::VFNMADDSSr132m, 0 },
- { X86::VFNMADDSDr132r, X86::VFNMADDSDr132m, 0 },
- { X86::VFNMADDSSr213r, X86::VFNMADDSSr213m, 0 },
- { X86::VFNMADDSDr213r, X86::VFNMADDSDr213m, 0 },
- { X86::VFNMADDSSr213r_Int, X86::VFNMADDSSr213m_Int, 0 },
- { X86::VFNMADDSDr213r_Int, X86::VFNMADDSDr213m_Int, 0 },
-
- { X86::VFNMADDPSr231r, X86::VFNMADDPSr231m, TB_ALIGN_16 },
- { X86::VFNMADDPDr231r, X86::VFNMADDPDr231m, TB_ALIGN_16 },
- { X86::VFNMADDPSr132r, X86::VFNMADDPSr132m, TB_ALIGN_16 },
- { X86::VFNMADDPDr132r, X86::VFNMADDPDr132m, TB_ALIGN_16 },
- { X86::VFNMADDPSr213r, X86::VFNMADDPSr213m, TB_ALIGN_16 },
- { X86::VFNMADDPDr213r, X86::VFNMADDPDr213m, TB_ALIGN_16 },
- { X86::VFNMADDPSr231rY, X86::VFNMADDPSr231mY, TB_ALIGN_32 },
- { X86::VFNMADDPDr231rY, X86::VFNMADDPDr231mY, TB_ALIGN_32 },
- { X86::VFNMADDPSr132rY, X86::VFNMADDPSr132mY, TB_ALIGN_32 },
- { X86::VFNMADDPDr132rY, X86::VFNMADDPDr132mY, TB_ALIGN_32 },
- { X86::VFNMADDPSr213rY, X86::VFNMADDPSr213mY, TB_ALIGN_32 },
- { X86::VFNMADDPDr213rY, X86::VFNMADDPDr213mY, TB_ALIGN_32 },
-
- { X86::VFMSUBSSr231r, X86::VFMSUBSSr231m, 0 },
- { X86::VFMSUBSDr231r, X86::VFMSUBSDr231m, 0 },
- { X86::VFMSUBSSr132r, X86::VFMSUBSSr132m, 0 },
- { X86::VFMSUBSDr132r, X86::VFMSUBSDr132m, 0 },
- { X86::VFMSUBSSr213r, X86::VFMSUBSSr213m, 0 },
- { X86::VFMSUBSDr213r, X86::VFMSUBSDr213m, 0 },
- { X86::VFMSUBSSr213r_Int, X86::VFMSUBSSr213m_Int, 0 },
- { X86::VFMSUBSDr213r_Int, X86::VFMSUBSDr213m_Int, 0 },
-
- { X86::VFMSUBPSr231r, X86::VFMSUBPSr231m, TB_ALIGN_16 },
- { X86::VFMSUBPDr231r, X86::VFMSUBPDr231m, TB_ALIGN_16 },
- { X86::VFMSUBPSr132r, X86::VFMSUBPSr132m, TB_ALIGN_16 },
- { X86::VFMSUBPDr132r, X86::VFMSUBPDr132m, TB_ALIGN_16 },
- { X86::VFMSUBPSr213r, X86::VFMSUBPSr213m, TB_ALIGN_16 },
- { X86::VFMSUBPDr213r, X86::VFMSUBPDr213m, TB_ALIGN_16 },
- { X86::VFMSUBPSr231rY, X86::VFMSUBPSr231mY, TB_ALIGN_32 },
- { X86::VFMSUBPDr231rY, X86::VFMSUBPDr231mY, TB_ALIGN_32 },
- { X86::VFMSUBPSr132rY, X86::VFMSUBPSr132mY, TB_ALIGN_32 },
- { X86::VFMSUBPDr132rY, X86::VFMSUBPDr132mY, TB_ALIGN_32 },
- { X86::VFMSUBPSr213rY, X86::VFMSUBPSr213mY, TB_ALIGN_32 },
- { X86::VFMSUBPDr213rY, X86::VFMSUBPDr213mY, TB_ALIGN_32 },
-
- { X86::VFNMSUBSSr231r, X86::VFNMSUBSSr231m, 0 },
- { X86::VFNMSUBSDr231r, X86::VFNMSUBSDr231m, 0 },
- { X86::VFNMSUBSSr132r, X86::VFNMSUBSSr132m, 0 },
- { X86::VFNMSUBSDr132r, X86::VFNMSUBSDr132m, 0 },
- { X86::VFNMSUBSSr213r, X86::VFNMSUBSSr213m, 0 },
- { X86::VFNMSUBSDr213r, X86::VFNMSUBSDr213m, 0 },
- { X86::VFNMSUBSSr213r_Int, X86::VFNMSUBSSr213m_Int, 0 },
- { X86::VFNMSUBSDr213r_Int, X86::VFNMSUBSDr213m_Int, 0 },
-
- { X86::VFNMSUBPSr231r, X86::VFNMSUBPSr231m, TB_ALIGN_16 },
- { X86::VFNMSUBPDr231r, X86::VFNMSUBPDr231m, TB_ALIGN_16 },
- { X86::VFNMSUBPSr132r, X86::VFNMSUBPSr132m, TB_ALIGN_16 },
- { X86::VFNMSUBPDr132r, X86::VFNMSUBPDr132m, TB_ALIGN_16 },
- { X86::VFNMSUBPSr213r, X86::VFNMSUBPSr213m, TB_ALIGN_16 },
- { X86::VFNMSUBPDr213r, X86::VFNMSUBPDr213m, TB_ALIGN_16 },
- { X86::VFNMSUBPSr231rY, X86::VFNMSUBPSr231mY, TB_ALIGN_32 },
- { X86::VFNMSUBPDr231rY, X86::VFNMSUBPDr231mY, TB_ALIGN_32 },
- { X86::VFNMSUBPSr132rY, X86::VFNMSUBPSr132mY, TB_ALIGN_32 },
- { X86::VFNMSUBPDr132rY, X86::VFNMSUBPDr132mY, TB_ALIGN_32 },
- { X86::VFNMSUBPSr213rY, X86::VFNMSUBPSr213mY, TB_ALIGN_32 },
- { X86::VFNMSUBPDr213rY, X86::VFNMSUBPDr213mY, TB_ALIGN_32 },
-
- { X86::VFMADDSUBPSr231r, X86::VFMADDSUBPSr231m, TB_ALIGN_16 },
- { X86::VFMADDSUBPDr231r, X86::VFMADDSUBPDr231m, TB_ALIGN_16 },
- { X86::VFMADDSUBPSr132r, X86::VFMADDSUBPSr132m, TB_ALIGN_16 },
- { X86::VFMADDSUBPDr132r, X86::VFMADDSUBPDr132m, TB_ALIGN_16 },
- { X86::VFMADDSUBPSr213r, X86::VFMADDSUBPSr213m, TB_ALIGN_16 },
- { X86::VFMADDSUBPDr213r, X86::VFMADDSUBPDr213m, TB_ALIGN_16 },
- { X86::VFMADDSUBPSr231rY, X86::VFMADDSUBPSr231mY, TB_ALIGN_32 },
- { X86::VFMADDSUBPDr231rY, X86::VFMADDSUBPDr231mY, TB_ALIGN_32 },
- { X86::VFMADDSUBPSr132rY, X86::VFMADDSUBPSr132mY, TB_ALIGN_32 },
- { X86::VFMADDSUBPDr132rY, X86::VFMADDSUBPDr132mY, TB_ALIGN_32 },
- { X86::VFMADDSUBPSr213rY, X86::VFMADDSUBPSr213mY, TB_ALIGN_32 },
- { X86::VFMADDSUBPDr213rY, X86::VFMADDSUBPDr213mY, TB_ALIGN_32 },
-
- { X86::VFMSUBADDPSr231r, X86::VFMSUBADDPSr231m, TB_ALIGN_16 },
- { X86::VFMSUBADDPDr231r, X86::VFMSUBADDPDr231m, TB_ALIGN_16 },
- { X86::VFMSUBADDPSr132r, X86::VFMSUBADDPSr132m, TB_ALIGN_16 },
- { X86::VFMSUBADDPDr132r, X86::VFMSUBADDPDr132m, TB_ALIGN_16 },
- { X86::VFMSUBADDPSr213r, X86::VFMSUBADDPSr213m, TB_ALIGN_16 },
- { X86::VFMSUBADDPDr213r, X86::VFMSUBADDPDr213m, TB_ALIGN_16 },
- { X86::VFMSUBADDPSr231rY, X86::VFMSUBADDPSr231mY, TB_ALIGN_32 },
- { X86::VFMSUBADDPDr231rY, X86::VFMSUBADDPDr231mY, TB_ALIGN_32 },
- { X86::VFMSUBADDPSr132rY, X86::VFMSUBADDPSr132mY, TB_ALIGN_32 },
- { X86::VFMSUBADDPDr132rY, X86::VFMSUBADDPDr132mY, TB_ALIGN_32 },
- { X86::VFMSUBADDPSr213rY, X86::VFMSUBADDPSr213mY, TB_ALIGN_32 },
- { X86::VFMSUBADDPDr213rY, X86::VFMSUBADDPDr213mY, TB_ALIGN_32 },
+ { X86::VFMADDSSr231r, X86::VFMADDSSr231m, TB_ALIGN_NONE },
+ { X86::VFMADDSDr231r, X86::VFMADDSDr231m, TB_ALIGN_NONE },
+ { X86::VFMADDSSr132r, X86::VFMADDSSr132m, TB_ALIGN_NONE },
+ { X86::VFMADDSDr132r, X86::VFMADDSDr132m, TB_ALIGN_NONE },
+ { X86::VFMADDSSr213r, X86::VFMADDSSr213m, TB_ALIGN_NONE },
+ { X86::VFMADDSDr213r, X86::VFMADDSDr213m, TB_ALIGN_NONE },
+
+ { X86::VFMADDPSr231r, X86::VFMADDPSr231m, TB_ALIGN_NONE },
+ { X86::VFMADDPDr231r, X86::VFMADDPDr231m, TB_ALIGN_NONE },
+ { X86::VFMADDPSr132r, X86::VFMADDPSr132m, TB_ALIGN_NONE },
+ { X86::VFMADDPDr132r, X86::VFMADDPDr132m, TB_ALIGN_NONE },
+ { X86::VFMADDPSr213r, X86::VFMADDPSr213m, TB_ALIGN_NONE },
+ { X86::VFMADDPDr213r, X86::VFMADDPDr213m, TB_ALIGN_NONE },
+ { X86::VFMADDPSr231rY, X86::VFMADDPSr231mY, TB_ALIGN_NONE },
+ { X86::VFMADDPDr231rY, X86::VFMADDPDr231mY, TB_ALIGN_NONE },
+ { X86::VFMADDPSr132rY, X86::VFMADDPSr132mY, TB_ALIGN_NONE },
+ { X86::VFMADDPDr132rY, X86::VFMADDPDr132mY, TB_ALIGN_NONE },
+ { X86::VFMADDPSr213rY, X86::VFMADDPSr213mY, TB_ALIGN_NONE },
+ { X86::VFMADDPDr213rY, X86::VFMADDPDr213mY, TB_ALIGN_NONE },
+
+ { X86::VFNMADDSSr231r, X86::VFNMADDSSr231m, TB_ALIGN_NONE },
+ { X86::VFNMADDSDr231r, X86::VFNMADDSDr231m, TB_ALIGN_NONE },
+ { X86::VFNMADDSSr132r, X86::VFNMADDSSr132m, TB_ALIGN_NONE },
+ { X86::VFNMADDSDr132r, X86::VFNMADDSDr132m, TB_ALIGN_NONE },
+ { X86::VFNMADDSSr213r, X86::VFNMADDSSr213m, TB_ALIGN_NONE },
+ { X86::VFNMADDSDr213r, X86::VFNMADDSDr213m, TB_ALIGN_NONE },
+
+ { X86::VFNMADDPSr231r, X86::VFNMADDPSr231m, TB_ALIGN_NONE },
+ { X86::VFNMADDPDr231r, X86::VFNMADDPDr231m, TB_ALIGN_NONE },
+ { X86::VFNMADDPSr132r, X86::VFNMADDPSr132m, TB_ALIGN_NONE },
+ { X86::VFNMADDPDr132r, X86::VFNMADDPDr132m, TB_ALIGN_NONE },
+ { X86::VFNMADDPSr213r, X86::VFNMADDPSr213m, TB_ALIGN_NONE },
+ { X86::VFNMADDPDr213r, X86::VFNMADDPDr213m, TB_ALIGN_NONE },
+ { X86::VFNMADDPSr231rY, X86::VFNMADDPSr231mY, TB_ALIGN_NONE },
+ { X86::VFNMADDPDr231rY, X86::VFNMADDPDr231mY, TB_ALIGN_NONE },
+ { X86::VFNMADDPSr132rY, X86::VFNMADDPSr132mY, TB_ALIGN_NONE },
+ { X86::VFNMADDPDr132rY, X86::VFNMADDPDr132mY, TB_ALIGN_NONE },
+ { X86::VFNMADDPSr213rY, X86::VFNMADDPSr213mY, TB_ALIGN_NONE },
+ { X86::VFNMADDPDr213rY, X86::VFNMADDPDr213mY, TB_ALIGN_NONE },
+
+ { X86::VFMSUBSSr231r, X86::VFMSUBSSr231m, TB_ALIGN_NONE },
+ { X86::VFMSUBSDr231r, X86::VFMSUBSDr231m, TB_ALIGN_NONE },
+ { X86::VFMSUBSSr132r, X86::VFMSUBSSr132m, TB_ALIGN_NONE },
+ { X86::VFMSUBSDr132r, X86::VFMSUBSDr132m, TB_ALIGN_NONE },
+ { X86::VFMSUBSSr213r, X86::VFMSUBSSr213m, TB_ALIGN_NONE },
+ { X86::VFMSUBSDr213r, X86::VFMSUBSDr213m, TB_ALIGN_NONE },
+
+ { X86::VFMSUBPSr231r, X86::VFMSUBPSr231m, TB_ALIGN_NONE },
+ { X86::VFMSUBPDr231r, X86::VFMSUBPDr231m, TB_ALIGN_NONE },
+ { X86::VFMSUBPSr132r, X86::VFMSUBPSr132m, TB_ALIGN_NONE },
+ { X86::VFMSUBPDr132r, X86::VFMSUBPDr132m, TB_ALIGN_NONE },
+ { X86::VFMSUBPSr213r, X86::VFMSUBPSr213m, TB_ALIGN_NONE },
+ { X86::VFMSUBPDr213r, X86::VFMSUBPDr213m, TB_ALIGN_NONE },
+ { X86::VFMSUBPSr231rY, X86::VFMSUBPSr231mY, TB_ALIGN_NONE },
+ { X86::VFMSUBPDr231rY, X86::VFMSUBPDr231mY, TB_ALIGN_NONE },
+ { X86::VFMSUBPSr132rY, X86::VFMSUBPSr132mY, TB_ALIGN_NONE },
+ { X86::VFMSUBPDr132rY, X86::VFMSUBPDr132mY, TB_ALIGN_NONE },
+ { X86::VFMSUBPSr213rY, X86::VFMSUBPSr213mY, TB_ALIGN_NONE },
+ { X86::VFMSUBPDr213rY, X86::VFMSUBPDr213mY, TB_ALIGN_NONE },
+
+ { X86::VFNMSUBSSr231r, X86::VFNMSUBSSr231m, TB_ALIGN_NONE },
+ { X86::VFNMSUBSDr231r, X86::VFNMSUBSDr231m, TB_ALIGN_NONE },
+ { X86::VFNMSUBSSr132r, X86::VFNMSUBSSr132m, TB_ALIGN_NONE },
+ { X86::VFNMSUBSDr132r, X86::VFNMSUBSDr132m, TB_ALIGN_NONE },
+ { X86::VFNMSUBSSr213r, X86::VFNMSUBSSr213m, TB_ALIGN_NONE },
+ { X86::VFNMSUBSDr213r, X86::VFNMSUBSDr213m, TB_ALIGN_NONE },
+
+ { X86::VFNMSUBPSr231r, X86::VFNMSUBPSr231m, TB_ALIGN_NONE },
+ { X86::VFNMSUBPDr231r, X86::VFNMSUBPDr231m, TB_ALIGN_NONE },
+ { X86::VFNMSUBPSr132r, X86::VFNMSUBPSr132m, TB_ALIGN_NONE },
+ { X86::VFNMSUBPDr132r, X86::VFNMSUBPDr132m, TB_ALIGN_NONE },
+ { X86::VFNMSUBPSr213r, X86::VFNMSUBPSr213m, TB_ALIGN_NONE },
+ { X86::VFNMSUBPDr213r, X86::VFNMSUBPDr213m, TB_ALIGN_NONE },
+ { X86::VFNMSUBPSr231rY, X86::VFNMSUBPSr231mY, TB_ALIGN_NONE },
+ { X86::VFNMSUBPDr231rY, X86::VFNMSUBPDr231mY, TB_ALIGN_NONE },
+ { X86::VFNMSUBPSr132rY, X86::VFNMSUBPSr132mY, TB_ALIGN_NONE },
+ { X86::VFNMSUBPDr132rY, X86::VFNMSUBPDr132mY, TB_ALIGN_NONE },
+ { X86::VFNMSUBPSr213rY, X86::VFNMSUBPSr213mY, TB_ALIGN_NONE },
+ { X86::VFNMSUBPDr213rY, X86::VFNMSUBPDr213mY, TB_ALIGN_NONE },
+
+ { X86::VFMADDSUBPSr231r, X86::VFMADDSUBPSr231m, TB_ALIGN_NONE },
+ { X86::VFMADDSUBPDr231r, X86::VFMADDSUBPDr231m, TB_ALIGN_NONE },
+ { X86::VFMADDSUBPSr132r, X86::VFMADDSUBPSr132m, TB_ALIGN_NONE },
+ { X86::VFMADDSUBPDr132r, X86::VFMADDSUBPDr132m, TB_ALIGN_NONE },
+ { X86::VFMADDSUBPSr213r, X86::VFMADDSUBPSr213m, TB_ALIGN_NONE },
+ { X86::VFMADDSUBPDr213r, X86::VFMADDSUBPDr213m, TB_ALIGN_NONE },
+ { X86::VFMADDSUBPSr231rY, X86::VFMADDSUBPSr231mY, TB_ALIGN_NONE },
+ { X86::VFMADDSUBPDr231rY, X86::VFMADDSUBPDr231mY, TB_ALIGN_NONE },
+ { X86::VFMADDSUBPSr132rY, X86::VFMADDSUBPSr132mY, TB_ALIGN_NONE },
+ { X86::VFMADDSUBPDr132rY, X86::VFMADDSUBPDr132mY, TB_ALIGN_NONE },
+ { X86::VFMADDSUBPSr213rY, X86::VFMADDSUBPSr213mY, TB_ALIGN_NONE },
+ { X86::VFMADDSUBPDr213rY, X86::VFMADDSUBPDr213mY, TB_ALIGN_NONE },
+
+ { X86::VFMSUBADDPSr231r, X86::VFMSUBADDPSr231m, TB_ALIGN_NONE },
+ { X86::VFMSUBADDPDr231r, X86::VFMSUBADDPDr231m, TB_ALIGN_NONE },
+ { X86::VFMSUBADDPSr132r, X86::VFMSUBADDPSr132m, TB_ALIGN_NONE },
+ { X86::VFMSUBADDPDr132r, X86::VFMSUBADDPDr132m, TB_ALIGN_NONE },
+ { X86::VFMSUBADDPSr213r, X86::VFMSUBADDPSr213m, TB_ALIGN_NONE },
+ { X86::VFMSUBADDPDr213r, X86::VFMSUBADDPDr213m, TB_ALIGN_NONE },
+ { X86::VFMSUBADDPSr231rY, X86::VFMSUBADDPSr231mY, TB_ALIGN_NONE },
+ { X86::VFMSUBADDPDr231rY, X86::VFMSUBADDPDr231mY, TB_ALIGN_NONE },
+ { X86::VFMSUBADDPSr132rY, X86::VFMSUBADDPSr132mY, TB_ALIGN_NONE },
+ { X86::VFMSUBADDPDr132rY, X86::VFMSUBADDPDr132mY, TB_ALIGN_NONE },
+ { X86::VFMSUBADDPSr213rY, X86::VFMSUBADDPSr213mY, TB_ALIGN_NONE },
+ { X86::VFMSUBADDPDr213rY, X86::VFMSUBADDPDr213mY, TB_ALIGN_NONE },
// FMA4 foldable patterns
{ X86::VFMADDSS4rr, X86::VFMADDSS4rm, 0 },
{ X86::VFMSUBADDPD4rr, X86::VFMSUBADDPD4rm, TB_ALIGN_16 },
{ X86::VFMSUBADDPS4rrY, X86::VFMSUBADDPS4rmY, TB_ALIGN_32 },
{ X86::VFMSUBADDPD4rrY, X86::VFMSUBADDPD4rmY, TB_ALIGN_32 },
+ // AVX-512 VPERMI instructions with 3 source operands.
+ { X86::VPERMI2Drr, X86::VPERMI2Drm, 0 },
+ { X86::VPERMI2Qrr, X86::VPERMI2Qrm, 0 },
+ { X86::VPERMI2PSrr, X86::VPERMI2PSrm, 0 },
+ { X86::VPERMI2PDrr, X86::VPERMI2PDrm, 0 },
+ { X86::VBLENDMPDZrr, X86::VBLENDMPDZrm, 0 },
+ { X86::VBLENDMPSZrr, X86::VBLENDMPSZrm, 0 },
+ { X86::VPBLENDMDZrr, X86::VPBLENDMDZrm, 0 },
+ { X86::VPBLENDMQZrr, X86::VPBLENDMQZrm, 0 }
};
for (unsigned i = 0, e = array_lengthof(OpTbl3); i != e; ++i) {
case X86::MOVSX32rr8:
case X86::MOVZX32rr8:
case X86::MOVSX64rr8:
- case X86::MOVZX64rr8:
- if (!TM.getSubtarget<X86Subtarget>().is64Bit())
+ if (!Subtarget.is64Bit())
// It's not always legal to reference the low 8-bit of the larger
// register in 32-bit mode.
return false;
case X86::MOVSX32rr16:
case X86::MOVZX32rr16:
case X86::MOVSX64rr16:
- case X86::MOVZX64rr16:
- case X86::MOVSX64rr32:
- case X86::MOVZX64rr32: {
+ case X86::MOVSX64rr32: {
if (MI.getOperand(0).getSubReg() || MI.getOperand(1).getSubReg())
// Be conservative.
return false;
case X86::MOVSX32rr8:
case X86::MOVZX32rr8:
case X86::MOVSX64rr8:
- case X86::MOVZX64rr8:
SubIdx = X86::sub_8bit;
break;
case X86::MOVSX32rr16:
case X86::MOVZX32rr16:
case X86::MOVSX64rr16:
- case X86::MOVZX64rr16:
SubIdx = X86::sub_16bit;
break;
case X86::MOVSX64rr32:
- case X86::MOVZX64rr32:
SubIdx = X86::sub_32bit;
break;
}
/// operand and follow operands form a reference to the stack frame.
bool X86InstrInfo::isFrameOperand(const MachineInstr *MI, unsigned int Op,
int &FrameIndex) const {
- if (MI->getOperand(Op).isFI() && MI->getOperand(Op+1).isImm() &&
- MI->getOperand(Op+2).isReg() && MI->getOperand(Op+3).isImm() &&
- MI->getOperand(Op+1).getImm() == 1 &&
- MI->getOperand(Op+2).getReg() == 0 &&
- MI->getOperand(Op+3).getImm() == 0) {
- FrameIndex = MI->getOperand(Op).getIndex();
+ if (MI->getOperand(Op+X86::AddrBaseReg).isFI() &&
+ MI->getOperand(Op+X86::AddrScaleAmt).isImm() &&
+ MI->getOperand(Op+X86::AddrIndexReg).isReg() &&
+ MI->getOperand(Op+X86::AddrDisp).isImm() &&
+ MI->getOperand(Op+X86::AddrScaleAmt).getImm() == 1 &&
+ MI->getOperand(Op+X86::AddrIndexReg).getReg() == 0 &&
+ MI->getOperand(Op+X86::AddrDisp).getImm() == 0) {
+ FrameIndex = MI->getOperand(Op+X86::AddrBaseReg).getIndex();
return true;
}
return false;
case X86::VMOVDQAYrm:
case X86::MMX_MOVD64rm:
case X86::MMX_MOVQ64rm:
+ case X86::VMOVAPSZrm:
+ case X86::VMOVUPSZrm:
return true;
}
}
case X86::VMOVAPSYmr:
case X86::VMOVAPDYmr:
case X86::VMOVDQAYmr:
+ case X86::VMOVUPSZmr:
+ case X86::VMOVAPSZmr:
case X86::MMX_MOVD64mr:
case X86::MMX_MOVQ64mr:
case X86::MMX_MOVNTQmr:
if (!TargetRegisterInfo::isVirtualRegister(BaseReg))
return false;
bool isPICBase = false;
- for (MachineRegisterInfo::def_iterator I = MRI.def_begin(BaseReg),
- E = MRI.def_end(); I != E; ++I) {
- MachineInstr *DefMI = I.getOperand().getParent();
+ for (MachineRegisterInfo::def_instr_iterator I = MRI.def_instr_begin(BaseReg),
+ E = MRI.def_instr_end(); I != E; ++I) {
+ MachineInstr *DefMI = &*I;
if (DefMI->getOpcode() != X86::MOVPC32r)
return false;
assert(!isPICBase && "More than one PIC base?");
case X86::FsMOVAPSrm:
case X86::FsMOVAPDrm: {
// Loads from constant pools are trivially rematerializable.
- if (MI->getOperand(1).isReg() &&
- MI->getOperand(2).isImm() &&
- MI->getOperand(3).isReg() && MI->getOperand(3).getReg() == 0 &&
+ if (MI->getOperand(1+X86::AddrBaseReg).isReg() &&
+ MI->getOperand(1+X86::AddrScaleAmt).isImm() &&
+ MI->getOperand(1+X86::AddrIndexReg).isReg() &&
+ MI->getOperand(1+X86::AddrIndexReg).getReg() == 0 &&
MI->isInvariantLoad(AA)) {
- unsigned BaseReg = MI->getOperand(1).getReg();
+ unsigned BaseReg = MI->getOperand(1+X86::AddrBaseReg).getReg();
if (BaseReg == 0 || BaseReg == X86::RIP)
return true;
// Allow re-materialization of PIC load.
- if (!ReMatPICStubLoad && MI->getOperand(4).isGlobal())
+ if (!ReMatPICStubLoad && MI->getOperand(1+X86::AddrDisp).isGlobal())
return false;
const MachineFunction &MF = *MI->getParent()->getParent();
const MachineRegisterInfo &MRI = MF.getRegInfo();
case X86::LEA32r:
case X86::LEA64r: {
- if (MI->getOperand(2).isImm() &&
- MI->getOperand(3).isReg() && MI->getOperand(3).getReg() == 0 &&
- !MI->getOperand(4).isReg()) {
+ if (MI->getOperand(1+X86::AddrScaleAmt).isImm() &&
+ MI->getOperand(1+X86::AddrIndexReg).isReg() &&
+ MI->getOperand(1+X86::AddrIndexReg).getReg() == 0 &&
+ !MI->getOperand(1+X86::AddrDisp).isReg()) {
// lea fi#, lea GV, etc. are all rematerializable.
- if (!MI->getOperand(1).isReg())
+ if (!MI->getOperand(1+X86::AddrBaseReg).isReg())
return true;
- unsigned BaseReg = MI->getOperand(1).getReg();
+ unsigned BaseReg = MI->getOperand(1+X86::AddrBaseReg).getReg();
if (BaseReg == 0)
return true;
// Allow re-materialization of lea PICBase + x.
return true;
}
-/// isSafeToClobberEFLAGS - Return true if it's safe insert an instruction that
-/// would clobber the EFLAGS condition register. Note the result may be
-/// conservative. If it cannot definitely determine the safety after visiting
-/// a few instructions in each direction it assumes it's not safe.
-static bool isSafeToClobberEFLAGS(MachineBasicBlock &MBB,
- MachineBasicBlock::iterator I) {
+bool X86InstrInfo::isSafeToClobberEFLAGS(MachineBasicBlock &MBB,
+ MachineBasicBlock::iterator I) const {
MachineBasicBlock::iterator E = MBB.end();
// For compile time consideration, if we are not able to determine the
unsigned DestReg, unsigned SubIdx,
const MachineInstr *Orig,
const TargetRegisterInfo &TRI) const {
- DebugLoc DL = Orig->getDebugLoc();
-
- // MOV32r0 etc. are implemented with xor which clobbers condition code.
- // Re-materialize them as movri instructions to avoid side effects.
- bool Clone = true;
+ // MOV32r0 is implemented with a xor which clobbers condition code.
+ // Re-materialize it as movri instructions to avoid side effects.
unsigned Opc = Orig->getOpcode();
- switch (Opc) {
- default: break;
- case X86::MOV8r0:
- case X86::MOV16r0:
- case X86::MOV32r0:
- case X86::MOV64r0: {
- if (!isSafeToClobberEFLAGS(MBB, I)) {
- switch (Opc) {
- default: llvm_unreachable("Unreachable!");
- case X86::MOV8r0: Opc = X86::MOV8ri; break;
- case X86::MOV16r0: Opc = X86::MOV16ri; break;
- case X86::MOV32r0: Opc = X86::MOV32ri; break;
- case X86::MOV64r0: Opc = X86::MOV64ri64i32; break;
- }
- Clone = false;
- }
- break;
- }
- }
-
- if (Clone) {
+ if (Opc == X86::MOV32r0 && !isSafeToClobberEFLAGS(MBB, I)) {
+ DebugLoc DL = Orig->getDebugLoc();
+ BuildMI(MBB, I, DL, get(X86::MOV32ri)).addOperand(Orig->getOperand(0))
+ .addImm(0);
+ } else {
MachineInstr *MI = MBB.getParent()->CloneMachineInstr(Orig);
MBB.insert(I, MI);
- } else {
- BuildMI(MBB, I, DL, get(Opc)).addOperand(Orig->getOperand(0)).addImm(0);
}
- MachineInstr *NewMI = prior(I);
+ MachineInstr *NewMI = std::prev(I);
NewMI->substituteRegister(Orig->getOperand(0).getReg(), DestReg, SubIdx, TRI);
}
return false;
}
+/// getTruncatedShiftCount - check whether the shift count for a machine operand
+/// is non-zero.
+inline static unsigned getTruncatedShiftCount(MachineInstr *MI,
+ unsigned ShiftAmtOperandIdx) {
+ // The shift count is six bits with the REX.W prefix and five bits without.
+ unsigned ShiftCountMask = (MI->getDesc().TSFlags & X86II::REX_W) ? 63 : 31;
+ unsigned Imm = MI->getOperand(ShiftAmtOperandIdx).getImm();
+ return Imm & ShiftCountMask;
+}
+
+/// isTruncatedShiftCountForLEA - check whether the given shift count is appropriate
+/// can be represented by a LEA instruction.
+inline static bool isTruncatedShiftCountForLEA(unsigned ShAmt) {
+ // Left shift instructions can be transformed into load-effective-address
+ // instructions if we can encode them appropriately.
+ // A LEA instruction utilizes a SIB byte to encode it's scale factor.
+ // The SIB.scale field is two bits wide which means that we can encode any
+ // shift amount less than 4.
+ return ShAmt < 4 && ShAmt > 0;
+}
+
+bool X86InstrInfo::classifyLEAReg(MachineInstr *MI, const MachineOperand &Src,
+ unsigned Opc, bool AllowSP,
+ unsigned &NewSrc, bool &isKill, bool &isUndef,
+ MachineOperand &ImplicitOp) const {
+ MachineFunction &MF = *MI->getParent()->getParent();
+ const TargetRegisterClass *RC;
+ if (AllowSP) {
+ RC = Opc != X86::LEA32r ? &X86::GR64RegClass : &X86::GR32RegClass;
+ } else {
+ RC = Opc != X86::LEA32r ?
+ &X86::GR64_NOSPRegClass : &X86::GR32_NOSPRegClass;
+ }
+ unsigned SrcReg = Src.getReg();
+
+ // For both LEA64 and LEA32 the register already has essentially the right
+ // type (32-bit or 64-bit) we may just need to forbid SP.
+ if (Opc != X86::LEA64_32r) {
+ NewSrc = SrcReg;
+ isKill = Src.isKill();
+ isUndef = Src.isUndef();
+
+ if (TargetRegisterInfo::isVirtualRegister(NewSrc) &&
+ !MF.getRegInfo().constrainRegClass(NewSrc, RC))
+ return false;
+
+ return true;
+ }
+
+ // This is for an LEA64_32r and incoming registers are 32-bit. One way or
+ // another we need to add 64-bit registers to the final MI.
+ if (TargetRegisterInfo::isPhysicalRegister(SrcReg)) {
+ ImplicitOp = Src;
+ ImplicitOp.setImplicit();
+
+ NewSrc = getX86SubSuperRegister(Src.getReg(), MVT::i64);
+ MachineBasicBlock::LivenessQueryResult LQR =
+ MI->getParent()->computeRegisterLiveness(&getRegisterInfo(), NewSrc, MI);
+
+ switch (LQR) {
+ case MachineBasicBlock::LQR_Unknown:
+ // We can't give sane liveness flags to the instruction, abandon LEA
+ // formation.
+ return false;
+ case MachineBasicBlock::LQR_Live:
+ isKill = MI->killsRegister(SrcReg);
+ isUndef = false;
+ break;
+ default:
+ // The physreg itself is dead, so we have to use it as an <undef>.
+ isKill = false;
+ isUndef = true;
+ break;
+ }
+ } else {
+ // Virtual register of the wrong class, we have to create a temporary 64-bit
+ // vreg to feed into the LEA.
+ NewSrc = MF.getRegInfo().createVirtualRegister(RC);
+ BuildMI(*MI->getParent(), MI, MI->getDebugLoc(),
+ get(TargetOpcode::COPY))
+ .addReg(NewSrc, RegState::Define | RegState::Undef, X86::sub_32bit)
+ .addOperand(Src);
+
+ // Which is obviously going to be dead after we're done with it.
+ isKill = true;
+ isUndef = false;
+ }
+
+ // We've set all the parameters without issue.
+ return true;
+}
+
/// convertToThreeAddressWithLEA - Helper for convertToThreeAddress when
/// 16-bit LEA is disabled, use 32-bit LEA to form 3-address code by promoting
/// to a 32-bit superregister and then truncating back down to a 16-bit
bool isDead = MI->getOperand(0).isDead();
bool isKill = MI->getOperand(1).isKill();
- unsigned Opc = TM.getSubtarget<X86Subtarget>().is64Bit()
- ? X86::LEA64_32r : X86::LEA32r;
MachineRegisterInfo &RegInfo = MFI->getParent()->getRegInfo();
- unsigned leaInReg = RegInfo.createVirtualRegister(&X86::GR32_NOSPRegClass);
unsigned leaOutReg = RegInfo.createVirtualRegister(&X86::GR32RegClass);
+ unsigned Opc, leaInReg;
+ if (Subtarget.is64Bit()) {
+ Opc = X86::LEA64_32r;
+ leaInReg = RegInfo.createVirtualRegister(&X86::GR64_NOSPRegClass);
+ } else {
+ Opc = X86::LEA32r;
+ leaInReg = RegInfo.createVirtualRegister(&X86::GR32_NOSPRegClass);
+ }
// Build and insert into an implicit UNDEF value. This is OK because
// well be shifting and then extracting the lower 16-bits.
unsigned Src2 = MI->getOperand(2).getReg();
bool isKill2 = MI->getOperand(2).isKill();
unsigned leaInReg2 = 0;
- MachineInstr *InsMI2 = 0;
+ MachineInstr *InsMI2 = nullptr;
if (Src == Src2) {
// ADD16rr %reg1028<kill>, %reg1028
// just a single insert_subreg.
addRegReg(MIB, leaInReg, true, leaInReg, false);
} else {
- leaInReg2 = RegInfo.createVirtualRegister(&X86::GR32_NOSPRegClass);
+ if (Subtarget.is64Bit())
+ leaInReg2 = RegInfo.createVirtualRegister(&X86::GR64_NOSPRegClass);
+ else
+ leaInReg2 = RegInfo.createVirtualRegister(&X86::GR32_NOSPRegClass);
// Build and insert into an implicit UNDEF value. This is OK because
// well be shifting and then extracting the lower 16-bits.
BuildMI(*MFI, &*MIB, MI->getDebugLoc(), get(X86::IMPLICIT_DEF),leaInReg2);
MachineBasicBlock::iterator &MBBI,
LiveVariables *LV) const {
MachineInstr *MI = MBBI;
+
+ // The following opcodes also sets the condition code register(s). Only
+ // convert them to equivalent lea if the condition code register def's
+ // are dead!
+ if (hasLiveCondCodeDef(MI))
+ return nullptr;
+
MachineFunction &MF = *MI->getParent()->getParent();
// All instructions input are two-addr instructions. Get the known operands.
const MachineOperand &Dest = MI->getOperand(0);
const MachineOperand &Src = MI->getOperand(1);
- MachineInstr *NewMI = NULL;
+ MachineInstr *NewMI = nullptr;
// FIXME: 16-bit LEA's are really slow on Athlons, but not bad on P4's. When
// we have better subtarget support, enable the 16-bit LEA generation here.
// 16-bit LEA is also slow on Core2.
bool DisableLEA16 = true;
- bool is64Bit = TM.getSubtarget<X86Subtarget>().is64Bit();
+ bool is64Bit = Subtarget.is64Bit();
unsigned MIOpc = MI->getOpcode();
switch (MIOpc) {
- case X86::SHUFPSrri: {
- assert(MI->getNumOperands() == 4 && "Unknown shufps instruction!");
- if (!TM.getSubtarget<X86Subtarget>().hasSSE2()) return 0;
-
- unsigned B = MI->getOperand(1).getReg();
- unsigned C = MI->getOperand(2).getReg();
- if (B != C) return 0;
- unsigned M = MI->getOperand(3).getImm();
- NewMI = BuildMI(MF, MI->getDebugLoc(), get(X86::PSHUFDri))
- .addOperand(Dest).addOperand(Src).addImm(M);
- break;
- }
- case X86::SHUFPDrri: {
- assert(MI->getNumOperands() == 4 && "Unknown shufpd instruction!");
- if (!TM.getSubtarget<X86Subtarget>().hasSSE2()) return 0;
-
- unsigned B = MI->getOperand(1).getReg();
- unsigned C = MI->getOperand(2).getReg();
- if (B != C) return 0;
- unsigned M = MI->getOperand(3).getImm();
-
- // Convert to PSHUFD mask.
- M = ((M & 1) << 1) | ((M & 1) << 3) | ((M & 2) << 4) | ((M & 2) << 6)| 0x44;
-
- NewMI = BuildMI(MF, MI->getDebugLoc(), get(X86::PSHUFDri))
- .addOperand(Dest).addOperand(Src).addImm(M);
- break;
- }
case X86::SHL64ri: {
assert(MI->getNumOperands() >= 3 && "Unknown shift instruction!");
- // NOTE: LEA doesn't produce flags like shift does, but LLVM never uses
- // the flags produced by a shift yet, so this is safe.
- unsigned ShAmt = MI->getOperand(2).getImm();
- if (ShAmt == 0 || ShAmt >= 4) return 0;
+ unsigned ShAmt = getTruncatedShiftCount(MI, 2);
+ if (!isTruncatedShiftCountForLEA(ShAmt)) return nullptr;
// LEA can't handle RSP.
if (TargetRegisterInfo::isVirtualRegister(Src.getReg()) &&
!MF.getRegInfo().constrainRegClass(Src.getReg(),
&X86::GR64_NOSPRegClass))
- return 0;
+ return nullptr;
NewMI = BuildMI(MF, MI->getDebugLoc(), get(X86::LEA64r))
.addOperand(Dest)
}
case X86::SHL32ri: {
assert(MI->getNumOperands() >= 3 && "Unknown shift instruction!");
- // NOTE: LEA doesn't produce flags like shift does, but LLVM never uses
- // the flags produced by a shift yet, so this is safe.
- unsigned ShAmt = MI->getOperand(2).getImm();
- if (ShAmt == 0 || ShAmt >= 4) return 0;
-
- // LEA can't handle ESP.
- if (TargetRegisterInfo::isVirtualRegister(Src.getReg()) &&
- !MF.getRegInfo().constrainRegClass(Src.getReg(),
- &X86::GR32_NOSPRegClass))
- return 0;
+ unsigned ShAmt = getTruncatedShiftCount(MI, 2);
+ if (!isTruncatedShiftCountForLEA(ShAmt)) return nullptr;
unsigned Opc = is64Bit ? X86::LEA64_32r : X86::LEA32r;
- NewMI = BuildMI(MF, MI->getDebugLoc(), get(Opc))
+
+ // LEA can't handle ESP.
+ 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(0).addImm(1 << ShAmt).addOperand(Src).addImm(0).addReg(0);
+ .addReg(0).addImm(1 << ShAmt)
+ .addReg(SrcReg, getKillRegState(isKill) | getUndefRegState(isUndef))
+ .addImm(0).addReg(0);
+ if (ImplicitOp.getReg() != 0)
+ MIB.addOperand(ImplicitOp);
+ NewMI = MIB;
+
break;
}
case X86::SHL16ri: {
assert(MI->getNumOperands() >= 3 && "Unknown shift instruction!");
- // NOTE: LEA doesn't produce flags like shift does, but LLVM never uses
- // the flags produced by a shift yet, so this is safe.
- unsigned ShAmt = MI->getOperand(2).getImm();
- if (ShAmt == 0 || ShAmt >= 4) return 0;
+ unsigned ShAmt = getTruncatedShiftCount(MI, 2);
+ if (!isTruncatedShiftCountForLEA(ShAmt)) return nullptr;
if (DisableLEA16)
- return is64Bit ? convertToThreeAddressWithLEA(MIOpc, MFI, MBBI, LV) : 0;
+ return is64Bit ? convertToThreeAddressWithLEA(MIOpc, MFI, MBBI, LV) : nullptr;
NewMI = BuildMI(MF, MI->getDebugLoc(), get(X86::LEA16r))
.addOperand(Dest)
.addReg(0).addImm(1 << ShAmt).addOperand(Src).addImm(0).addReg(0);
break;
}
default: {
- // The following opcodes also sets the condition code register(s). Only
- // convert them to equivalent lea if the condition code register def's
- // are dead!
- if (hasLiveCondCodeDef(MI))
- return 0;
switch (MIOpc) {
- default: return 0;
+ 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);
- const TargetRegisterClass *RC = MIOpc == X86::INC64r ?
- (const TargetRegisterClass*)&X86::GR64_NOSPRegClass :
- (const TargetRegisterClass*)&X86::GR32_NOSPRegClass;
-
- // LEA can't handle RSP.
- if (TargetRegisterInfo::isVirtualRegister(Src.getReg()) &&
- !MF.getRegInfo().constrainRegClass(Src.getReg(), RC))
- return 0;
-
- NewMI = addOffset(BuildMI(MF, MI->getDebugLoc(), get(Opc))
- .addOperand(Dest).addOperand(Src), 1);
+ 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);
+
+ NewMI = addOffset(MIB, 1);
break;
}
case X86::INC16r:
case X86::INC64_16r:
if (DisableLEA16)
- return is64Bit ? convertToThreeAddressWithLEA(MIOpc, MFI, MBBI, LV) : 0;
+ 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);
assert(MI->getNumOperands() >= 2 && "Unknown dec instruction!");
unsigned Opc = MIOpc == X86::DEC64r ? X86::LEA64r
: (is64Bit ? X86::LEA64_32r : X86::LEA32r);
- const TargetRegisterClass *RC = MIOpc == X86::DEC64r ?
- (const TargetRegisterClass*)&X86::GR64_NOSPRegClass :
- (const TargetRegisterClass*)&X86::GR32_NOSPRegClass;
- // LEA can't handle RSP.
- if (TargetRegisterInfo::isVirtualRegister(Src.getReg()) &&
- !MF.getRegInfo().constrainRegClass(Src.getReg(), RC))
- return 0;
-
- NewMI = addOffset(BuildMI(MF, MI->getDebugLoc(), get(Opc))
- .addOperand(Dest).addOperand(Src), -1);
+
+ 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);
+
+ NewMI = addOffset(MIB, -1);
+
break;
}
case X86::DEC16r:
case X86::DEC64_16r:
if (DisableLEA16)
- return is64Bit ? convertToThreeAddressWithLEA(MIOpc, MFI, MBBI, LV) : 0;
+ 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);
case X86::ADD32rr_DB: {
assert(MI->getNumOperands() >= 3 && "Unknown add instruction!");
unsigned Opc;
- const TargetRegisterClass *RC;
- if (MIOpc == X86::ADD64rr || MIOpc == X86::ADD64rr_DB) {
+ if (MIOpc == X86::ADD64rr || MIOpc == X86::ADD64rr_DB)
Opc = X86::LEA64r;
- RC = &X86::GR64_NOSPRegClass;
- } else {
+ else
Opc = is64Bit ? X86::LEA64_32r : X86::LEA32r;
- RC = &X86::GR32_NOSPRegClass;
- }
-
- unsigned Src2 = MI->getOperand(2).getReg();
- bool isKill2 = MI->getOperand(2).isKill();
-
- // LEA can't handle RSP.
- if (TargetRegisterInfo::isVirtualRegister(Src2) &&
- !MF.getRegInfo().constrainRegClass(Src2, RC))
- return 0;
-
- NewMI = addRegReg(BuildMI(MF, MI->getDebugLoc(), get(Opc))
- .addOperand(Dest),
- Src.getReg(), Src.isKill(), Src2, isKill2);
+ 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;
+
+ 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);
// 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);
+ 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) : 0;
+ 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();
case X86::ADD32ri8_DB: {
assert(MI->getNumOperands() >= 3 && "Unknown add instruction!");
unsigned Opc = is64Bit ? X86::LEA64_32r : X86::LEA32r;
- NewMI = addOffset(BuildMI(MF, MI->getDebugLoc(), get(Opc))
- .addOperand(Dest).addOperand(Src),
- MI->getOperand(2).getImm());
+
+ 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);
+
+ NewMI = addOffset(MIB, MI->getOperand(2).getImm());
break;
}
case X86::ADD16ri:
case X86::ADD16ri_DB:
case X86::ADD16ri8_DB:
if (DisableLEA16)
- return is64Bit ? convertToThreeAddressWithLEA(MIOpc, MFI, MBBI, LV) : 0;
+ 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),
}
}
- if (!NewMI) return 0;
+ if (!NewMI) return nullptr;
if (LV) { // Update live variables
if (Src.isKill())
}
}
+bool X86InstrInfo::findCommutedOpIndices(MachineInstr *MI, unsigned &SrcOpIdx1,
+ unsigned &SrcOpIdx2) const {
+ switch (MI->getOpcode()) {
+ case X86::VFMADDPDr231r:
+ case X86::VFMADDPSr231r:
+ case X86::VFMADDSDr231r:
+ case X86::VFMADDSSr231r:
+ case X86::VFMSUBPDr231r:
+ case X86::VFMSUBPSr231r:
+ case X86::VFMSUBSDr231r:
+ case X86::VFMSUBSSr231r:
+ case X86::VFNMADDPDr231r:
+ case X86::VFNMADDPSr231r:
+ case X86::VFNMADDSDr231r:
+ case X86::VFNMADDSSr231r:
+ case X86::VFNMSUBPDr231r:
+ case X86::VFNMSUBPSr231r:
+ case X86::VFNMSUBSDr231r:
+ case X86::VFNMSUBSSr231r:
+ case X86::VFMADDPDr231rY:
+ case X86::VFMADDPSr231rY:
+ case X86::VFMSUBPDr231rY:
+ case X86::VFMSUBPSr231rY:
+ case X86::VFNMADDPDr231rY:
+ case X86::VFNMADDPSr231rY:
+ case X86::VFNMSUBPDr231rY:
+ case X86::VFNMSUBPSr231rY:
+ SrcOpIdx1 = 2;
+ SrcOpIdx2 = 3;
+ return true;
+ default:
+ return TargetInstrInfo::findCommutedOpIndices(MI, SrcOpIdx1, SrcOpIdx2);
+ }
+}
+
static X86::CondCode getCondFromBranchOpc(unsigned BrOpc) {
switch (BrOpc) {
default: return X86::COND_INVALID;
/// getSETFromCond - Return a set opcode for the given condition and
/// whether it has memory operand.
-static unsigned getSETFromCond(X86::CondCode CC,
- bool HasMemoryOperand) {
+unsigned X86::getSETFromCond(CondCode CC, bool HasMemoryOperand) {
static const uint16_t Opc[16][2] = {
{ X86::SETAr, X86::SETAm },
{ X86::SETAEr, X86::SETAEm },
{ X86::SETSr, X86::SETSm }
};
- assert(CC < 16 && "Can only handle standard cond codes");
+ assert(CC <= LAST_VALID_COND && "Can only handle standard cond codes");
return Opc[CC][HasMemoryOperand ? 1 : 0];
}
/// getCMovFromCond - Return a cmov opcode for the given condition,
/// register size in bytes, and operand type.
-static unsigned getCMovFromCond(X86::CondCode CC, unsigned RegBytes,
- bool HasMemoryOperand) {
+unsigned X86::getCMovFromCond(CondCode CC, unsigned RegBytes,
+ bool HasMemoryOperand) {
static const uint16_t Opc[32][3] = {
{ X86::CMOVA16rr, X86::CMOVA32rr, X86::CMOVA64rr },
{ X86::CMOVAE16rr, X86::CMOVAE32rr, X86::CMOVAE64rr },
}
// If the block has any instructions after a JMP, delete them.
- while (llvm::next(I) != MBB.end())
- llvm::next(I)->eraseFromParent();
+ while (std::next(I) != MBB.end())
+ std::next(I)->eraseFromParent();
Cond.clear();
- FBB = 0;
+ FBB = nullptr;
// Delete the JMP if it's equivalent to a fall-through.
if (MBB.isLayoutSuccessor(I->getOperand(0).getMBB())) {
- TBB = 0;
+ TBB = nullptr;
I->eraseFromParent();
I = MBB.end();
UnCondBrIter = MBB.end();
unsigned TrueReg, unsigned FalseReg,
int &CondCycles, int &TrueCycles, int &FalseCycles) const {
// Not all subtargets have cmov instructions.
- if (!TM.getSubtarget<X86Subtarget>().hasCMov())
+ if (!Subtarget.hasCMov())
return false;
if (Cond.size() != 1)
return false;
// Try and copy between VR128/VR64 and GR64 registers.
static unsigned CopyToFromAsymmetricReg(unsigned DestReg, unsigned SrcReg,
- bool HasAVX) {
+ const X86Subtarget &Subtarget) {
+
// SrcReg(VR128) -> DestReg(GR64)
// SrcReg(VR64) -> DestReg(GR64)
// SrcReg(GR64) -> DestReg(VR128)
// SrcReg(GR64) -> DestReg(VR64)
+ bool HasAVX = Subtarget.hasAVX();
+ bool HasAVX512 = Subtarget.hasAVX512();
if (X86::GR64RegClass.contains(DestReg)) {
- if (X86::VR128RegClass.contains(SrcReg))
+ if (X86::VR128XRegClass.contains(SrcReg))
// Copy from a VR128 register to a GR64 register.
- return HasAVX ? X86::VMOVPQIto64rr : X86::MOVPQIto64rr;
+ return HasAVX512 ? X86::VMOVPQIto64Zrr: (HasAVX ? X86::VMOVPQIto64rr :
+ X86::MOVPQIto64rr);
if (X86::VR64RegClass.contains(SrcReg))
// Copy from a VR64 register to a GR64 register.
return X86::MOVSDto64rr;
} else if (X86::GR64RegClass.contains(SrcReg)) {
// Copy from a GR64 register to a VR128 register.
- if (X86::VR128RegClass.contains(DestReg))
- return HasAVX ? X86::VMOV64toPQIrr : X86::MOV64toPQIrr;
+ if (X86::VR128XRegClass.contains(DestReg))
+ return HasAVX512 ? X86::VMOV64toPQIZrr: (HasAVX ? X86::VMOV64toPQIrr :
+ X86::MOV64toPQIrr);
// Copy from a GR64 register to a VR64 register.
if (X86::VR64RegClass.contains(DestReg))
return X86::MOV64toSDrr;
// SrcReg(FR32) -> DestReg(GR32)
// SrcReg(GR32) -> DestReg(FR32)
- if (X86::GR32RegClass.contains(DestReg) && X86::FR32RegClass.contains(SrcReg))
+ if (X86::GR32RegClass.contains(DestReg) && X86::FR32XRegClass.contains(SrcReg))
// Copy from a FR32 register to a GR32 register.
- return HasAVX ? X86::VMOVSS2DIrr : X86::MOVSS2DIrr;
+ return HasAVX512 ? X86::VMOVSS2DIZrr : (HasAVX ? X86::VMOVSS2DIrr : X86::MOVSS2DIrr);
- if (X86::FR32RegClass.contains(DestReg) && X86::GR32RegClass.contains(SrcReg))
+ if (X86::FR32XRegClass.contains(DestReg) && X86::GR32RegClass.contains(SrcReg))
// Copy from a GR32 register to a FR32 register.
- return HasAVX ? X86::VMOVDI2SSrr : X86::MOVDI2SSrr;
+ return HasAVX512 ? X86::VMOVDI2SSZrr : (HasAVX ? X86::VMOVDI2SSrr : X86::MOVDI2SSrr);
+ return 0;
+}
+inline static bool MaskRegClassContains(unsigned Reg) {
+ return X86::VK8RegClass.contains(Reg) ||
+ X86::VK16RegClass.contains(Reg) ||
+ X86::VK32RegClass.contains(Reg) ||
+ X86::VK64RegClass.contains(Reg) ||
+ X86::VK1RegClass.contains(Reg);
+}
+static
+unsigned copyPhysRegOpcode_AVX512(unsigned& DestReg, unsigned& SrcReg) {
+ if (X86::VR128XRegClass.contains(DestReg, SrcReg) ||
+ X86::VR256XRegClass.contains(DestReg, SrcReg) ||
+ X86::VR512RegClass.contains(DestReg, SrcReg)) {
+ DestReg = get512BitSuperRegister(DestReg);
+ SrcReg = get512BitSuperRegister(SrcReg);
+ return X86::VMOVAPSZrr;
+ }
+ if (MaskRegClassContains(DestReg) &&
+ MaskRegClassContains(SrcReg))
+ return X86::KMOVWkk;
+ if (MaskRegClassContains(DestReg) &&
+ (X86::GR32RegClass.contains(SrcReg) ||
+ X86::GR16RegClass.contains(SrcReg) ||
+ X86::GR8RegClass.contains(SrcReg))) {
+ SrcReg = getX86SubSuperRegister(SrcReg, MVT::i32);
+ return X86::KMOVWkr;
+ }
+ if ((X86::GR32RegClass.contains(DestReg) ||
+ X86::GR16RegClass.contains(DestReg) ||
+ X86::GR8RegClass.contains(DestReg)) &&
+ MaskRegClassContains(SrcReg)) {
+ DestReg = getX86SubSuperRegister(DestReg, MVT::i32);
+ return X86::KMOVWrk;
+ }
return 0;
}
unsigned DestReg, unsigned SrcReg,
bool KillSrc) const {
// First deal with the normal symmetric copies.
- bool HasAVX = TM.getSubtarget<X86Subtarget>().hasAVX();
- unsigned Opc;
+ bool HasAVX = Subtarget.hasAVX();
+ bool HasAVX512 = Subtarget.hasAVX512();
+ unsigned Opc = 0;
if (X86::GR64RegClass.contains(DestReg, SrcReg))
Opc = X86::MOV64rr;
else if (X86::GR32RegClass.contains(DestReg, SrcReg))
// Copying to or from a physical H register on x86-64 requires a NOREX
// move. Otherwise use a normal move.
if ((isHReg(DestReg) || isHReg(SrcReg)) &&
- TM.getSubtarget<X86Subtarget>().is64Bit()) {
+ Subtarget.is64Bit()) {
Opc = X86::MOV8rr_NOREX;
// Both operands must be encodable without an REX prefix.
assert(X86::GR8_NOREXRegClass.contains(SrcReg, DestReg) &&
"8-bit H register can not be copied outside GR8_NOREX");
} else
Opc = X86::MOV8rr;
- } else if (X86::VR128RegClass.contains(DestReg, SrcReg))
+ }
+ else if (X86::VR64RegClass.contains(DestReg, SrcReg))
+ Opc = X86::MMX_MOVQ64rr;
+ else if (HasAVX512)
+ Opc = copyPhysRegOpcode_AVX512(DestReg, SrcReg);
+ else if (X86::VR128RegClass.contains(DestReg, SrcReg))
Opc = HasAVX ? X86::VMOVAPSrr : X86::MOVAPSrr;
else if (X86::VR256RegClass.contains(DestReg, SrcReg))
Opc = X86::VMOVAPSYrr;
- else if (X86::VR64RegClass.contains(DestReg, SrcReg))
- Opc = X86::MMX_MOVQ64rr;
- else
- Opc = CopyToFromAsymmetricReg(DestReg, SrcReg, HasAVX);
+ if (!Opc)
+ Opc = CopyToFromAsymmetricReg(DestReg, SrcReg, Subtarget);
if (Opc) {
BuildMI(MBB, MI, DL, get(Opc), DestReg)
// Moving EFLAGS to / from another register requires a push and a pop.
// Notice that we have to adjust the stack if we don't want to clobber the
- // first frame index. See X86FrameLowering.cpp - colobbersTheStack.
+ // first frame index. See X86FrameLowering.cpp - clobbersTheStack.
if (SrcReg == X86::EFLAGS) {
if (X86::GR64RegClass.contains(DestReg)) {
BuildMI(MBB, MI, DL, get(X86::PUSHF64));
static unsigned getLoadStoreRegOpcode(unsigned Reg,
const TargetRegisterClass *RC,
bool isStackAligned,
- const TargetMachine &TM,
+ const X86Subtarget &STI,
bool load) {
- bool HasAVX = TM.getSubtarget<X86Subtarget>().hasAVX();
+ if (STI.hasAVX512()) {
+ if (X86::VK8RegClass.hasSubClassEq(RC) ||
+ X86::VK16RegClass.hasSubClassEq(RC))
+ return load ? X86::KMOVWkm : X86::KMOVWmk;
+ if (RC->getSize() == 4 && X86::FR32XRegClass.hasSubClassEq(RC))
+ return load ? X86::VMOVSSZrm : X86::VMOVSSZmr;
+ if (RC->getSize() == 8 && X86::FR64XRegClass.hasSubClassEq(RC))
+ return load ? X86::VMOVSDZrm : X86::VMOVSDZmr;
+ if (X86::VR512RegClass.hasSubClassEq(RC))
+ return load ? X86::VMOVUPSZrm : X86::VMOVUPSZmr;
+ }
+
+ bool HasAVX = STI.hasAVX();
switch (RC->getSize()) {
default:
llvm_unreachable("Unknown spill size");
case 1:
assert(X86::GR8RegClass.hasSubClassEq(RC) && "Unknown 1-byte regclass");
- if (TM.getSubtarget<X86Subtarget>().is64Bit())
+ if (STI.is64Bit())
// Copying to or from a physical H register on x86-64 requires a NOREX
// move. Otherwise use a normal move.
if (isHReg(Reg) || X86::GR8_ABCD_HRegClass.hasSubClassEq(RC))
assert(X86::RFP80RegClass.hasSubClassEq(RC) && "Unknown 10-byte regclass");
return load ? X86::LD_Fp80m : X86::ST_FpP80m;
case 16: {
- assert(X86::VR128RegClass.hasSubClassEq(RC) && "Unknown 16-byte regclass");
+ assert((X86::VR128RegClass.hasSubClassEq(RC) ||
+ X86::VR128XRegClass.hasSubClassEq(RC))&& "Unknown 16-byte regclass");
// If stack is realigned we can use aligned stores.
if (isStackAligned)
return load ?
(HasAVX ? X86::VMOVUPSmr : X86::MOVUPSmr);
}
case 32:
- assert(X86::VR256RegClass.hasSubClassEq(RC) && "Unknown 32-byte regclass");
+ assert((X86::VR256RegClass.hasSubClassEq(RC) ||
+ X86::VR256XRegClass.hasSubClassEq(RC)) && "Unknown 32-byte regclass");
// If stack is realigned we can use aligned stores.
if (isStackAligned)
return load ? X86::VMOVAPSYrm : X86::VMOVAPSYmr;
else
return load ? X86::VMOVUPSYrm : X86::VMOVUPSYmr;
+ case 64:
+ assert(X86::VR512RegClass.hasSubClassEq(RC) && "Unknown 64-byte regclass");
+ if (isStackAligned)
+ return load ? X86::VMOVAPSZrm : X86::VMOVAPSZmr;
+ else
+ return load ? X86::VMOVUPSZrm : X86::VMOVUPSZmr;
}
}
static unsigned getStoreRegOpcode(unsigned SrcReg,
const TargetRegisterClass *RC,
bool isStackAligned,
- TargetMachine &TM) {
- return getLoadStoreRegOpcode(SrcReg, RC, isStackAligned, TM, false);
+ const X86Subtarget &STI) {
+ return getLoadStoreRegOpcode(SrcReg, RC, isStackAligned, STI, false);
}
static unsigned getLoadRegOpcode(unsigned DestReg,
const TargetRegisterClass *RC,
bool isStackAligned,
- const TargetMachine &TM) {
- return getLoadStoreRegOpcode(DestReg, RC, isStackAligned, TM, true);
+ const X86Subtarget &STI) {
+ return getLoadStoreRegOpcode(DestReg, RC, isStackAligned, STI, true);
}
void X86InstrInfo::storeRegToStackSlot(MachineBasicBlock &MBB,
const MachineFunction &MF = *MBB.getParent();
assert(MF.getFrameInfo()->getObjectSize(FrameIdx) >= RC->getSize() &&
"Stack slot too small for store");
- unsigned Alignment = RC->getSize() == 32 ? 32 : 16;
- bool isAligned = (TM.getFrameLowering()->getStackAlignment() >= Alignment) ||
- RI.canRealignStack(MF);
- unsigned Opc = getStoreRegOpcode(SrcReg, RC, isAligned, TM);
+ unsigned Alignment = std::max<uint32_t>(RC->getSize(), 16);
+ bool isAligned = (MF.getTarget()
+ .getSubtargetImpl()
+ ->getFrameLowering()
+ ->getStackAlignment() >= Alignment) ||
+ RI.canRealignStack(MF);
+ unsigned Opc = getStoreRegOpcode(SrcReg, RC, isAligned, Subtarget);
DebugLoc DL = MBB.findDebugLoc(MI);
addFrameReference(BuildMI(MBB, MI, DL, get(Opc)), FrameIdx)
.addReg(SrcReg, getKillRegState(isKill));
MachineInstr::mmo_iterator MMOBegin,
MachineInstr::mmo_iterator MMOEnd,
SmallVectorImpl<MachineInstr*> &NewMIs) const {
- unsigned Alignment = RC->getSize() == 32 ? 32 : 16;
+ unsigned Alignment = std::max<uint32_t>(RC->getSize(), 16);
bool isAligned = MMOBegin != MMOEnd &&
(*MMOBegin)->getAlignment() >= Alignment;
- unsigned Opc = getStoreRegOpcode(SrcReg, RC, isAligned, TM);
+ unsigned Opc = getStoreRegOpcode(SrcReg, RC, isAligned, Subtarget);
DebugLoc DL;
MachineInstrBuilder MIB = BuildMI(MF, DL, get(Opc));
for (unsigned i = 0, e = Addr.size(); i != e; ++i)
const TargetRegisterClass *RC,
const TargetRegisterInfo *TRI) const {
const MachineFunction &MF = *MBB.getParent();
- unsigned Alignment = RC->getSize() == 32 ? 32 : 16;
- bool isAligned = (TM.getFrameLowering()->getStackAlignment() >= Alignment) ||
- RI.canRealignStack(MF);
- unsigned Opc = getLoadRegOpcode(DestReg, RC, isAligned, TM);
+ unsigned Alignment = std::max<uint32_t>(RC->getSize(), 16);
+ bool isAligned = (MF.getTarget()
+ .getSubtargetImpl()
+ ->getFrameLowering()
+ ->getStackAlignment() >= Alignment) ||
+ RI.canRealignStack(MF);
+ unsigned Opc = getLoadRegOpcode(DestReg, RC, isAligned, Subtarget);
DebugLoc DL = MBB.findDebugLoc(MI);
addFrameReference(BuildMI(MBB, MI, DL, get(Opc), DestReg), FrameIdx);
}
MachineInstr::mmo_iterator MMOBegin,
MachineInstr::mmo_iterator MMOEnd,
SmallVectorImpl<MachineInstr*> &NewMIs) const {
- unsigned Alignment = RC->getSize() == 32 ? 32 : 16;
+ unsigned Alignment = std::max<uint32_t>(RC->getSize(), 16);
bool isAligned = MMOBegin != MMOEnd &&
(*MMOBegin)->getAlignment() >= Alignment;
- unsigned Opc = getLoadRegOpcode(DestReg, RC, isAligned, TM);
+ unsigned Opc = getLoadRegOpcode(DestReg, RC, isAligned, Subtarget);
DebugLoc DL;
MachineInstrBuilder MIB = BuildMI(MF, DL, get(Opc), DestReg);
for (unsigned i = 0, e = Addr.size(); i != e; ++i)
inline static bool isDefConvertible(MachineInstr *MI) {
switch (MI->getOpcode()) {
default: return false;
+
+ // The shift instructions only modify ZF if their shift count is non-zero.
+ // N.B.: The processor truncates the shift count depending on the encoding.
+ case X86::SAR8ri: case X86::SAR16ri: case X86::SAR32ri:case X86::SAR64ri:
+ case X86::SHR8ri: case X86::SHR16ri: case X86::SHR32ri:case X86::SHR64ri:
+ return getTruncatedShiftCount(MI, 2) != 0;
+
+ // Some left shift instructions can be turned into LEA instructions but only
+ // if their flags aren't used. Avoid transforming such instructions.
+ case X86::SHL8ri: case X86::SHL16ri: case X86::SHL32ri:case X86::SHL64ri:{
+ unsigned ShAmt = getTruncatedShiftCount(MI, 2);
+ if (isTruncatedShiftCountForLEA(ShAmt)) return false;
+ return ShAmt != 0;
+ }
+
+ case X86::SHRD16rri8:case X86::SHRD32rri8:case X86::SHRD64rri8:
+ case X86::SHLD16rri8:case X86::SHLD32rri8:case X86::SHLD64rri8:
+ return getTruncatedShiftCount(MI, 3) != 0;
+
case X86::SUB64ri32: case X86::SUB64ri8: case X86::SUB32ri:
case X86::SUB32ri8: case X86::SUB16ri: case X86::SUB16ri8:
case X86::SUB8ri: case X86::SUB64rr: case X86::SUB32rr:
case X86::OR8ri: case X86::OR64rr: case X86::OR32rr:
case X86::OR16rr: case X86::OR8rr: case X86::OR64rm:
case X86::OR32rm: case X86::OR16rm: case X86::OR8rm:
+ case X86::NEG8r: case X86::NEG16r: case X86::NEG32r: case X86::NEG64r:
+ case X86::SAR8r1: case X86::SAR16r1: case X86::SAR32r1:case X86::SAR64r1:
+ case X86::SHR8r1: case X86::SHR16r1: case X86::SHR32r1:case X86::SHR64r1:
+ case X86::SHL8r1: case X86::SHL16r1: case X86::SHL32r1:case X86::SHL64r1:
+ case X86::ADC32ri: case X86::ADC32ri8:
+ case X86::ADC32rr: case X86::ADC64ri32:
+ case X86::ADC64ri8: case X86::ADC64rr:
+ case X86::SBB32ri: case X86::SBB32ri8:
+ case X86::SBB32rr: case X86::SBB64ri32:
+ case X86::SBB64ri8: case X86::SBB64rr:
case X86::ANDN32rr: case X86::ANDN32rm:
case X86::ANDN64rr: case X86::ANDN64rm:
+ case X86::BEXTR32rr: case X86::BEXTR64rr:
+ case X86::BEXTR32rm: case X86::BEXTR64rm:
+ case X86::BLSI32rr: case X86::BLSI32rm:
+ case X86::BLSI64rr: case X86::BLSI64rm:
+ case X86::BLSMSK32rr:case X86::BLSMSK32rm:
+ case X86::BLSMSK64rr:case X86::BLSMSK64rm:
+ case X86::BLSR32rr: case X86::BLSR32rm:
+ case X86::BLSR64rr: case X86::BLSR64rm:
+ case X86::BZHI32rr: case X86::BZHI32rm:
+ case X86::BZHI64rr: case X86::BZHI64rm:
+ case X86::LZCNT16rr: case X86::LZCNT16rm:
+ case X86::LZCNT32rr: case X86::LZCNT32rm:
+ case X86::LZCNT64rr: case X86::LZCNT64rm:
+ case X86::POPCNT16rr:case X86::POPCNT16rm:
+ case X86::POPCNT32rr:case X86::POPCNT32rm:
+ case X86::POPCNT64rr:case X86::POPCNT64rm:
+ case X86::TZCNT16rr: case X86::TZCNT16rm:
+ case X86::TZCNT32rr: case X86::TZCNT32rm:
+ case X86::TZCNT64rr: case X86::TZCNT64rm:
return true;
}
}
+/// isUseDefConvertible - check whether the use can be converted
+/// to remove a comparison against zero.
+static X86::CondCode isUseDefConvertible(MachineInstr *MI) {
+ switch (MI->getOpcode()) {
+ default: return X86::COND_INVALID;
+ case X86::LZCNT16rr: case X86::LZCNT16rm:
+ case X86::LZCNT32rr: case X86::LZCNT32rm:
+ case X86::LZCNT64rr: case X86::LZCNT64rm:
+ return X86::COND_B;
+ case X86::POPCNT16rr:case X86::POPCNT16rm:
+ case X86::POPCNT32rr:case X86::POPCNT32rm:
+ case X86::POPCNT64rr:case X86::POPCNT64rm:
+ return X86::COND_E;
+ case X86::TZCNT16rr: case X86::TZCNT16rm:
+ case X86::TZCNT32rr: case X86::TZCNT32rm:
+ case X86::TZCNT64rr: case X86::TZCNT64rm:
+ return X86::COND_B;
+ }
+}
+
/// optimizeCompareInstr - Check if there exists an earlier instruction that
/// operates on the same source operands and sets flags in the same way as
/// Compare; remove Compare if possible.
// If we are comparing against zero, check whether we can use MI to update
// EFLAGS. If MI is not in the same BB as CmpInstr, do not optimize.
bool IsCmpZero = (SrcReg2 == 0 && CmpValue == 0);
- if (IsCmpZero && (MI->getParent() != CmpInstr->getParent() ||
- !isDefConvertible(MI)))
+ if (IsCmpZero && MI->getParent() != CmpInstr->getParent())
return false;
+ // If we have a use of the source register between the def and our compare
+ // instruction we can eliminate the compare iff the use sets EFLAGS in the
+ // right way.
+ bool ShouldUpdateCC = false;
+ X86::CondCode NewCC = X86::COND_INVALID;
+ if (IsCmpZero && !isDefConvertible(MI)) {
+ // Scan forward from the use until we hit the use we're looking for or the
+ // compare instruction.
+ for (MachineBasicBlock::iterator J = MI;; ++J) {
+ // Do we have a convertible instruction?
+ NewCC = isUseDefConvertible(J);
+ if (NewCC != X86::COND_INVALID && J->getOperand(1).isReg() &&
+ J->getOperand(1).getReg() == SrcReg) {
+ assert(J->definesRegister(X86::EFLAGS) && "Must be an EFLAGS def!");
+ ShouldUpdateCC = true; // Update CC later on.
+ // This is not a def of SrcReg, but still a def of EFLAGS. Keep going
+ // with the new def.
+ MI = Def = J;
+ break;
+ }
+
+ if (J == I)
+ return false;
+ }
+ }
+
// We are searching for an earlier instruction that can make CmpInstr
// redundant and that instruction will be saved in Sub.
- MachineInstr *Sub = NULL;
+ MachineInstr *Sub = nullptr;
const TargetRegisterInfo *TRI = &getRegisterInfo();
// We iterate backward, starting from the instruction before CmpInstr and
RE = CmpInstr->getParent() == MI->getParent() ?
MachineBasicBlock::reverse_iterator(++Def) /* points to MI */ :
CmpInstr->getParent()->rend();
- MachineInstr *Movr0Inst = 0;
+ MachineInstr *Movr0Inst = nullptr;
for (; RI != RE; ++RI) {
MachineInstr *Instr = &*RI;
// Check whether CmpInstr can be made redundant by the current instruction.
// MOV32r0 etc. are implemented with xor which clobbers condition code.
// They are safe to move up, if the definition to EFLAGS is dead and
// earlier instructions do not read or write EFLAGS.
- if (!Movr0Inst && (Instr->getOpcode() == X86::MOV8r0 ||
- Instr->getOpcode() == X86::MOV16r0 ||
- Instr->getOpcode() == X86::MOV32r0 ||
- Instr->getOpcode() == X86::MOV64r0) &&
+ if (!Movr0Inst && Instr->getOpcode() == X86::MOV32r0 &&
Instr->registerDefIsDead(X86::EFLAGS, TRI)) {
Movr0Inst = Instr;
continue;
continue;
// EFLAGS is used by this instruction.
- X86::CondCode OldCC;
+ X86::CondCode OldCC = X86::COND_INVALID;
bool OpcIsSET = false;
if (IsCmpZero || IsSwapped) {
// We decode the condition code from opcode.
// CF and OF are used, we can't perform this optimization.
return false;
}
+
+ // If we're updating the condition code check if we have to reverse the
+ // condition.
+ if (ShouldUpdateCC)
+ switch (OldCC) {
+ default:
+ return false;
+ case X86::COND_E:
+ break;
+ case X86::COND_NE:
+ NewCC = GetOppositeBranchCondition(NewCC);
+ break;
+ }
} else if (IsSwapped) {
// If we have SUB(r1, r2) and CMP(r2, r1), the condition code needs
// to be changed from r2 > r1 to r1 < r2, from r2 < r1 to r1 > r2, etc.
// We swap the condition code and synthesize the new opcode.
- X86::CondCode NewCC = getSwappedCondition(OldCC);
+ NewCC = getSwappedCondition(OldCC);
if (NewCC == X86::COND_INVALID) return false;
+ }
+ if ((ShouldUpdateCC || IsSwapped) && NewCC != OldCC) {
// Synthesize the new opcode.
bool HasMemoryOperand = Instr.hasOneMemOperand();
unsigned NewOpc;
// The instruction to be updated is either Sub or MI.
Sub = IsCmpZero ? MI : Sub;
- // Move Movr0Inst to the place right before Sub.
+ // Move Movr0Inst to the appropriate place before Sub.
if (Movr0Inst) {
- Sub->getParent()->remove(Movr0Inst);
- Sub->getParent()->insert(MachineBasicBlock::iterator(Sub), Movr0Inst);
+ // Look backwards until we find a def that doesn't use the current EFLAGS.
+ Def = Sub;
+ MachineBasicBlock::reverse_iterator
+ InsertI = MachineBasicBlock::reverse_iterator(++Def),
+ InsertE = Sub->getParent()->rend();
+ for (; InsertI != InsertE; ++InsertI) {
+ MachineInstr *Instr = &*InsertI;
+ if (!Instr->readsRegister(X86::EFLAGS, TRI) &&
+ Instr->modifiesRegister(X86::EFLAGS, TRI)) {
+ Sub->getParent()->remove(Movr0Inst);
+ Instr->getParent()->insert(MachineBasicBlock::iterator(Instr),
+ Movr0Inst);
+ break;
+ }
+ }
+ if (InsertI == InsertE)
+ return false;
}
// Make sure Sub instruction defines EFLAGS and mark the def live.
- unsigned LastOperand = Sub->getNumOperands() - 1;
- assert(Sub->getNumOperands() >= 2 &&
- Sub->getOperand(LastOperand).isReg() &&
- Sub->getOperand(LastOperand).getReg() == X86::EFLAGS &&
- "EFLAGS should be the last operand of SUB, ADD, OR, XOR, AND");
- Sub->getOperand(LastOperand).setIsDef(true);
- Sub->getOperand(LastOperand).setIsDead(false);
+ unsigned i = 0, e = Sub->getNumOperands();
+ for (; i != e; ++i) {
+ MachineOperand &MO = Sub->getOperand(i);
+ if (MO.isReg() && MO.isDef() && MO.getReg() == X86::EFLAGS) {
+ MO.setIsDead(false);
+ break;
+ }
+ }
+ assert(i != e && "Unable to locate a def EFLAGS operand");
+
CmpInstr->eraseFromParent();
// Modify the condition code of instructions in OpsToUpdate.
/// operand at the use. We fold the load instructions if load defines a virtual
/// register, the virtual register is used once in the same BB, and the
/// instructions in-between do not load or store, and have no side effects.
-MachineInstr* X86InstrInfo::
-optimizeLoadInstr(MachineInstr *MI, const MachineRegisterInfo *MRI,
- unsigned &FoldAsLoadDefReg,
- MachineInstr *&DefMI) const {
+MachineInstr *X86InstrInfo::optimizeLoadInstr(MachineInstr *MI,
+ const MachineRegisterInfo *MRI,
+ unsigned &FoldAsLoadDefReg,
+ MachineInstr *&DefMI) const {
if (FoldAsLoadDefReg == 0)
- return 0;
+ return nullptr;
// To be conservative, if there exists another load, clear the load candidate.
if (MI->mayLoad()) {
FoldAsLoadDefReg = 0;
- return 0;
+ return nullptr;
}
// Check whether we can move DefMI here.
DefMI = MRI->getVRegDef(FoldAsLoadDefReg);
assert(DefMI);
bool SawStore = false;
- if (!DefMI->isSafeToMove(this, 0, SawStore))
- return 0;
-
- // We try to commute MI if possible.
- unsigned IdxEnd = (MI->isCommutable()) ? 2 : 1;
- for (unsigned Idx = 0; Idx < IdxEnd; Idx++) {
- // Collect information about virtual register operands of MI.
- unsigned SrcOperandId = 0;
- bool FoundSrcOperand = false;
- for (unsigned i = 0, e = MI->getDesc().getNumOperands(); i != e; ++i) {
- MachineOperand &MO = MI->getOperand(i);
- if (!MO.isReg())
- continue;
- unsigned Reg = MO.getReg();
- if (Reg != FoldAsLoadDefReg)
- continue;
- // Do not fold if we have a subreg use or a def or multiple uses.
- if (MO.getSubReg() || MO.isDef() || FoundSrcOperand)
- return 0;
+ if (!DefMI->isSafeToMove(this, nullptr, SawStore))
+ return nullptr;
- SrcOperandId = i;
- FoundSrcOperand = true;
- }
- if (!FoundSrcOperand) return 0;
-
- // Check whether we can fold the def into SrcOperandId.
- SmallVector<unsigned, 8> Ops;
- Ops.push_back(SrcOperandId);
- MachineInstr *FoldMI = foldMemoryOperand(MI, Ops, DefMI);
- if (FoldMI) {
- FoldAsLoadDefReg = 0;
- return FoldMI;
- }
-
- if (Idx == 1) {
- // MI was changed but it didn't help, commute it back!
- commuteInstruction(MI, false);
- return 0;
- }
+ // Collect information about virtual register operands of MI.
+ unsigned SrcOperandId = 0;
+ bool FoundSrcOperand = false;
+ for (unsigned i = 0, e = MI->getDesc().getNumOperands(); i != e; ++i) {
+ MachineOperand &MO = MI->getOperand(i);
+ if (!MO.isReg())
+ continue;
+ unsigned Reg = MO.getReg();
+ if (Reg != FoldAsLoadDefReg)
+ continue;
+ // Do not fold if we have a subreg use or a def or multiple uses.
+ if (MO.getSubReg() || MO.isDef() || FoundSrcOperand)
+ return nullptr;
- // Check whether we can commute MI and enable folding.
- if (MI->isCommutable()) {
- MachineInstr *NewMI = commuteInstruction(MI, false);
- // Unable to commute.
- if (!NewMI) return 0;
- if (NewMI != MI) {
- // New instruction. It doesn't need to be kept.
- NewMI->eraseFromParent();
- return 0;
- }
- }
+ SrcOperandId = i;
+ FoundSrcOperand = true;
}
- return 0;
+ if (!FoundSrcOperand)
+ return nullptr;
+
+ // Check whether we can fold the def into SrcOperandId.
+ SmallVector<unsigned, 8> Ops;
+ Ops.push_back(SrcOperandId);
+ MachineInstr *FoldMI = foldMemoryOperand(MI, Ops, DefMI);
+ if (FoldMI) {
+ FoldAsLoadDefReg = 0;
+ return FoldMI;
+ }
+
+ return nullptr;
}
/// Expand2AddrUndef - Expand a single-def pseudo instruction to a two-addr
return true;
}
+// LoadStackGuard has so far only been implemented for 64-bit MachO. Different
+// code sequence is needed for other targets.
+static void expandLoadStackGuard(MachineInstrBuilder &MIB,
+ const TargetInstrInfo &TII) {
+ MachineBasicBlock &MBB = *MIB->getParent();
+ DebugLoc DL = MIB->getDebugLoc();
+ unsigned Reg = MIB->getOperand(0).getReg();
+ const GlobalValue *GV =
+ cast<GlobalValue>((*MIB->memoperands_begin())->getValue());
+ unsigned Flag = MachineMemOperand::MOLoad | MachineMemOperand::MOInvariant;
+ MachineMemOperand *MMO = MBB.getParent()->
+ getMachineMemOperand(MachinePointerInfo::getGOT(), Flag, 8, 8);
+ MachineBasicBlock::iterator I = MIB;
+
+ BuildMI(MBB, I, DL, TII.get(X86::MOV64rm), Reg).addReg(X86::RIP).addImm(1)
+ .addReg(0).addGlobalAddress(GV, 0, X86II::MO_GOTPCREL).addReg(0)
+ .addMemOperand(MMO);
+ MIB->setDebugLoc(DL);
+ MIB->setDesc(TII.get(X86::MOV64rm));
+ MIB.addReg(Reg, RegState::Kill).addImm(1).addReg(0).addImm(0).addReg(0);
+}
+
bool X86InstrInfo::expandPostRAPseudo(MachineBasicBlock::iterator MI) const {
- bool HasAVX = TM.getSubtarget<X86Subtarget>().hasAVX();
+ bool HasAVX = Subtarget.hasAVX();
MachineInstrBuilder MIB(*MI->getParent()->getParent(), MI);
switch (MI->getOpcode()) {
+ case X86::MOV32r0:
+ return Expand2AddrUndef(MIB, get(X86::XOR32rr));
case X86::SETB_C8r:
return Expand2AddrUndef(MIB, get(X86::SBB8rr));
case X86::SETB_C16r:
case X86::AVX_SET0:
assert(HasAVX && "AVX not supported");
return Expand2AddrUndef(MIB, get(X86::VXORPSYrr));
+ case X86::AVX512_512_SET0:
+ return Expand2AddrUndef(MIB, get(X86::VPXORDZrr));
case X86::V_SETALLONES:
return Expand2AddrUndef(MIB, get(HasAVX ? X86::VPCMPEQDrr : X86::PCMPEQDrr));
case X86::AVX2_SETALLONES:
case X86::TEST8ri_NOREX:
MI->setDesc(get(X86::TEST8ri));
return true;
+ case X86::KSET0B:
+ case X86::KSET0W: return Expand2AddrUndef(MIB, get(X86::KXORWrr));
+ case X86::KSET1B:
+ case X86::KSET1W: return Expand2AddrUndef(MIB, get(X86::KXNORWrr));
+ case TargetOpcode::LOAD_STACK_GUARD:
+ expandLoadStackGuard(MIB, *this);
+ return true;
}
return false;
}
-MachineInstr*
-X86InstrInfo::emitFrameIndexDebugValue(MachineFunction &MF,
- int FrameIx, uint64_t Offset,
- const MDNode *MDPtr,
- DebugLoc DL) const {
- X86AddressMode AM;
- AM.BaseType = X86AddressMode::FrameIndexBase;
- AM.Base.FrameIndex = FrameIx;
- MachineInstrBuilder MIB = BuildMI(MF, DL, get(X86::DBG_VALUE));
- addFullAddress(MIB, AM).addImm(Offset).addMetadata(MDPtr);
- return &*MIB;
-}
-
static MachineInstr *FuseTwoAddrInst(MachineFunction &MF, unsigned Opcode,
const SmallVectorImpl<MachineOperand> &MOs,
MachineInstr *MI,
X86InstrInfo::foldMemoryOperandImpl(MachineFunction &MF,
MachineInstr *MI, unsigned i,
const SmallVectorImpl<MachineOperand> &MOs,
- unsigned Size, unsigned Align) const {
- const DenseMap<unsigned, std::pair<unsigned,unsigned> > *OpcodeTablePtr = 0;
+ unsigned Size, unsigned Align,
+ bool AllowCommute) const {
+ const DenseMap<unsigned,
+ std::pair<unsigned,unsigned> > *OpcodeTablePtr = nullptr;
+ bool isCallRegIndirect = Subtarget.callRegIndirect();
bool isTwoAddrFold = false;
+
+ // Atom favors register form of call. So, we do not fold loads into calls
+ // when X86Subtarget is Atom.
+ if (isCallRegIndirect &&
+ (MI->getOpcode() == X86::CALL32r || MI->getOpcode() == X86::CALL64r)) {
+ return nullptr;
+ }
+
unsigned NumOps = MI->getDesc().getNumOperands();
bool isTwoAddr = NumOps > 1 &&
MI->getDesc().getOperandConstraint(1, MCOI::TIED_TO) != -1;
// X86II::MO_GOT_ABSOLUTE_ADDRESS after folding.
if (MI->getOpcode() == X86::ADD32ri &&
MI->getOperand(2).getTargetFlags() == X86II::MO_GOT_ABSOLUTE_ADDRESS)
- return NULL;
+ return nullptr;
- MachineInstr *NewMI = NULL;
+ MachineInstr *NewMI = nullptr;
// 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.
OpcodeTablePtr = &RegOp2MemOpTable2Addr;
isTwoAddrFold = true;
} else if (i == 0) { // If operand 0
- unsigned Opc = 0;
- switch (MI->getOpcode()) {
- default: break;
- case X86::MOV64r0: Opc = X86::MOV64mi32; break;
- case X86::MOV32r0: Opc = X86::MOV32mi; break;
- case X86::MOV16r0: Opc = X86::MOV16mi; break;
- case X86::MOV8r0: Opc = X86::MOV8mi; break;
+ if (MI->getOpcode() == X86::MOV32r0) {
+ NewMI = MakeM0Inst(*this, X86::MOV32mi, MOs, MI);
+ if (NewMI)
+ return NewMI;
}
- if (Opc)
- NewMI = MakeM0Inst(*this, Opc, MOs, MI);
- if (NewMI)
- return NewMI;
OpcodeTablePtr = &RegOp2MemOpTable0;
} else if (i == 1) {
unsigned Opcode = I->second.first;
unsigned MinAlign = (I->second.second & TB_ALIGN_MASK) >> TB_ALIGN_SHIFT;
if (Align < MinAlign)
- return NULL;
+ return nullptr;
bool NarrowToMOV32rm = false;
if (Size) {
unsigned RCSize = getRegClass(MI->getDesc(), i, &RI, MF)->getSize();
// Check if it's safe to fold the load. If the size of the object is
// narrower than the load width, then it's not.
if (Opcode != X86::MOV64rm || RCSize != 8 || Size != 4)
- return NULL;
+ return nullptr;
// If this is a 64-bit load, but the spill slot is 32, then we can do
- // a 32-bit load which is implicitly zero-extended. This likely is due
- // to liveintervalanalysis remat'ing a load from stack slot.
+ // a 32-bit load which is implicitly zero-extended. This likely is
+ // due to live interval analysis remat'ing a load from stack slot.
if (MI->getOperand(0).getSubReg() || MI->getOperand(1).getSubReg())
- return NULL;
+ return nullptr;
Opcode = X86::MOV32rm;
NarrowToMOV32rm = true;
}
// to a 32-bit one.
unsigned DstReg = NewMI->getOperand(0).getReg();
if (TargetRegisterInfo::isPhysicalRegister(DstReg))
- NewMI->getOperand(0).setReg(RI.getSubReg(DstReg,
- X86::sub_32bit));
+ NewMI->getOperand(0).setReg(RI.getSubReg(DstReg, X86::sub_32bit));
else
NewMI->getOperand(0).setSubReg(X86::sub_32bit);
}
}
}
+ // If the instruction and target operand are commutable, commute the
+ // instruction and try again.
+ if (AllowCommute) {
+ unsigned OriginalOpIdx = i, CommuteOpIdx1, CommuteOpIdx2;
+ if (findCommutedOpIndices(MI, CommuteOpIdx1, CommuteOpIdx2)) {
+ bool HasDef = MI->getDesc().getNumDefs();
+ unsigned Reg0 = HasDef ? MI->getOperand(0).getReg() : 0;
+ unsigned Reg1 = MI->getOperand(CommuteOpIdx1).getReg();
+ unsigned Reg2 = MI->getOperand(CommuteOpIdx2).getReg();
+ bool Tied0 =
+ 0 == MI->getDesc().getOperandConstraint(CommuteOpIdx1, MCOI::TIED_TO);
+ bool Tied1 =
+ 0 == MI->getDesc().getOperandConstraint(CommuteOpIdx2, MCOI::TIED_TO);
+
+ // If either of the commutable operands are tied to the destination
+ // then we can not commute + fold.
+ if ((HasDef && Reg0 == Reg1 && Tied0) ||
+ (HasDef && Reg0 == Reg2 && Tied1))
+ return nullptr;
+
+ if ((CommuteOpIdx1 == OriginalOpIdx) ||
+ (CommuteOpIdx2 == OriginalOpIdx)) {
+ MachineInstr *CommutedMI = commuteInstruction(MI, false);
+ if (!CommutedMI) {
+ // Unable to commute.
+ return nullptr;
+ }
+ if (CommutedMI != MI) {
+ // New instruction. We can't fold from this.
+ CommutedMI->eraseFromParent();
+ return nullptr;
+ }
+
+ // Attempt to fold with the commuted version of the instruction.
+ unsigned CommuteOp =
+ (CommuteOpIdx1 == OriginalOpIdx ? CommuteOpIdx2 : CommuteOpIdx1);
+ NewMI = foldMemoryOperandImpl(MF, MI, CommuteOp, MOs, Size, Align,
+ /*AllowCommute=*/false);
+ if (NewMI)
+ return NewMI;
+
+ // Folding failed again - undo the commute before returning.
+ MachineInstr *UncommutedMI = commuteInstruction(MI, false);
+ if (!UncommutedMI) {
+ // Unable to commute.
+ return nullptr;
+ }
+ if (UncommutedMI != MI) {
+ // New instruction. It doesn't need to be kept.
+ UncommutedMI->eraseFromParent();
+ return nullptr;
+ }
+
+ // Return here to prevent duplicate fuse failure report.
+ return nullptr;
+ }
+ }
+ }
+
// No fusion
if (PrintFailedFusing && !MI->isCopy())
dbgs() << "We failed to fuse operand " << i << " in " << *MI;
- return NULL;
+ return nullptr;
}
/// hasPartialRegUpdate - Return true for all instructions that only update
case X86::RSQRTSSr_Int:
case X86::SQRTSSr:
case X86::SQRTSSr_Int:
- // AVX encoded versions
- case X86::VCVTSD2SSrr:
- case X86::Int_VCVTSD2SSrr:
- case X86::VCVTSS2SDrr:
- case X86::Int_VCVTSS2SDrr:
- case X86::VRCPSSr:
- case X86::VROUNDSDr:
- case X86::VROUNDSDr_Int:
- case X86::VROUNDSSr:
- case X86::VROUNDSSr_Int:
- case X86::VRSQRTSSr:
- case X86::VSQRTSSr:
return true;
}
return 16;
}
+// Return true for any instruction the copies the high bits of the first source
+// operand into the unused high bits of the destination operand.
+static bool hasUndefRegUpdate(unsigned Opcode) {
+ switch (Opcode) {
+ case X86::VCVTSI2SSrr:
+ case X86::Int_VCVTSI2SSrr:
+ case X86::VCVTSI2SS64rr:
+ case X86::Int_VCVTSI2SS64rr:
+ case X86::VCVTSI2SDrr:
+ case X86::Int_VCVTSI2SDrr:
+ case X86::VCVTSI2SD64rr:
+ case X86::Int_VCVTSI2SD64rr:
+ case X86::VCVTSD2SSrr:
+ case X86::Int_VCVTSD2SSrr:
+ case X86::VCVTSS2SDrr:
+ case X86::Int_VCVTSS2SDrr:
+ case X86::VRCPSSr:
+ case X86::VROUNDSDr:
+ case X86::VROUNDSDr_Int:
+ case X86::VROUNDSSr:
+ case X86::VROUNDSSr_Int:
+ case X86::VRSQRTSSr:
+ case X86::VSQRTSSr:
+
+ // AVX-512
+ case X86::VCVTSD2SSZrr:
+ case X86::VCVTSS2SDZrr:
+ return true;
+ }
+
+ return false;
+}
+
+/// Inform the ExeDepsFix pass how many idle instructions we would like before
+/// certain undef register reads.
+///
+/// This catches the VCVTSI2SD family of instructions:
+///
+/// vcvtsi2sdq %rax, %xmm0<undef>, %xmm14
+///
+/// We should to be careful *not* to catch VXOR idioms which are presumably
+/// handled specially in the pipeline:
+///
+/// vxorps %xmm1<undef>, %xmm1<undef>, %xmm1
+///
+/// Like getPartialRegUpdateClearance, this makes a strong assumption that the
+/// high bits that are passed-through are not live.
+unsigned X86InstrInfo::
+getUndefRegClearance(const MachineInstr *MI, unsigned &OpNum,
+ const TargetRegisterInfo *TRI) const {
+ if (!hasUndefRegUpdate(MI->getOpcode()))
+ return 0;
+
+ // Set the OpNum parameter to the first source operand.
+ OpNum = 1;
+
+ const MachineOperand &MO = MI->getOperand(OpNum);
+ if (MO.isUndef() && TargetRegisterInfo::isPhysicalRegister(MO.getReg())) {
+ // Use the same magic number as getPartialRegUpdateClearance.
+ return 16;
+ }
+ return 0;
+}
+
void X86InstrInfo::
breakPartialRegDependency(MachineBasicBlock::iterator MI, unsigned OpNum,
const TargetRegisterInfo *TRI) const {
unsigned Reg = MI->getOperand(OpNum).getReg();
+ // If MI kills this register, the false dependence is already broken.
+ if (MI->killsRegister(Reg, TRI))
+ return;
if (X86::VR128RegClass.contains(Reg)) {
// These instructions are all floating point domain, so xorps is the best
// choice.
- bool HasAVX = TM.getSubtarget<X86Subtarget>().hasAVX();
+ bool HasAVX = Subtarget.hasAVX();
unsigned Opc = HasAVX ? X86::VXORPSrr : X86::XORPSrr;
BuildMI(*MI->getParent(), MI, MI->getDebugLoc(), get(Opc), Reg)
.addReg(Reg, RegState::Undef).addReg(Reg, RegState::Undef);
MI->addRegisterKilled(Reg, TRI, true);
}
-MachineInstr* X86InstrInfo::foldMemoryOperandImpl(MachineFunction &MF,
- MachineInstr *MI,
- const SmallVectorImpl<unsigned> &Ops,
- int FrameIndex) const {
+MachineInstr*
+X86InstrInfo::foldMemoryOperandImpl(MachineFunction &MF, MachineInstr *MI,
+ const SmallVectorImpl<unsigned> &Ops,
+ int FrameIndex) const {
// Check switch flag
- if (NoFusing) return NULL;
+ if (NoFusing) return nullptr;
// Unless optimizing for size, don't fold to avoid partial
// register update stalls
- if (!MF.getFunction()->getFnAttributes().
- hasAttribute(Attribute::OptimizeForSize) &&
+ if (!MF.getFunction()->getAttributes().
+ hasAttribute(AttributeSet::FunctionIndex, Attribute::OptimizeForSize) &&
hasPartialRegUpdate(MI->getOpcode()))
- return 0;
+ return nullptr;
const MachineFrameInfo *MFI = MF.getFrameInfo();
unsigned Size = MFI->getObjectSize(FrameIndex);
unsigned Alignment = MFI->getObjectAlignment(FrameIndex);
+ // If the function stack isn't realigned we don't want to fold instructions
+ // that need increased alignment.
+ if (!RI.needsStackRealignment(MF))
+ Alignment = std::min(Alignment, MF.getTarget()
+ .getSubtargetImpl()
+ ->getFrameLowering()
+ ->getStackAlignment());
if (Ops.size() == 2 && Ops[0] == 0 && Ops[1] == 1) {
unsigned NewOpc = 0;
unsigned RCSize = 0;
switch (MI->getOpcode()) {
- default: return NULL;
+ default: return nullptr;
case X86::TEST8rr: NewOpc = X86::CMP8ri; RCSize = 1; break;
case X86::TEST16rr: NewOpc = X86::CMP16ri8; RCSize = 2; break;
case X86::TEST32rr: NewOpc = X86::CMP32ri8; RCSize = 4; break;
// Check if it's safe to fold the load. If the size of the object is
// narrower than the load width, then it's not.
if (Size < RCSize)
- return NULL;
+ return nullptr;
// Change to CMPXXri r, 0 first.
MI->setDesc(get(NewOpc));
MI->getOperand(1).ChangeToImmediate(0);
} else if (Ops.size() != 1)
- return NULL;
+ return nullptr;
SmallVector<MachineOperand,4> MOs;
MOs.push_back(MachineOperand::CreateFI(FrameIndex));
- return foldMemoryOperandImpl(MF, MI, Ops[0], MOs, Size, Alignment);
+ return foldMemoryOperandImpl(MF, MI, Ops[0], MOs,
+ Size, Alignment, /*AllowCommute=*/true);
+}
+
+static bool isPartialRegisterLoad(const MachineInstr &LoadMI,
+ const MachineFunction &MF) {
+ unsigned Opc = LoadMI.getOpcode();
+ unsigned RegSize =
+ MF.getRegInfo().getRegClass(LoadMI.getOperand(0).getReg())->getSize();
+
+ if ((Opc == X86::MOVSSrm || Opc == X86::VMOVSSrm) && RegSize > 4)
+ // These instructions only load 32 bits, we can't fold them if the
+ // destination register is wider than 32 bits (4 bytes).
+ return true;
+
+ if ((Opc == X86::MOVSDrm || Opc == X86::VMOVSDrm) && RegSize > 8)
+ // These instructions only load 64 bits, we can't fold them if the
+ // destination register is wider than 64 bits (8 bytes).
+ return true;
+
+ return false;
}
MachineInstr* X86InstrInfo::foldMemoryOperandImpl(MachineFunction &MF,
MachineInstr *MI,
const SmallVectorImpl<unsigned> &Ops,
MachineInstr *LoadMI) const {
+ // If loading from a FrameIndex, fold directly from the FrameIndex.
+ unsigned NumOps = LoadMI->getDesc().getNumOperands();
+ int FrameIndex;
+ if (isLoadFromStackSlot(LoadMI, FrameIndex)) {
+ if (isPartialRegisterLoad(*LoadMI, MF))
+ return nullptr;
+ return foldMemoryOperandImpl(MF, MI, Ops, FrameIndex);
+ }
+
// Check switch flag
- if (NoFusing) return NULL;
+ if (NoFusing) return nullptr;
// Unless optimizing for size, don't fold to avoid partial
// register update stalls
- if (!MF.getFunction()->getFnAttributes().
- hasAttribute(Attribute::OptimizeForSize) &&
+ if (!MF.getFunction()->getAttributes().
+ hasAttribute(AttributeSet::FunctionIndex, Attribute::OptimizeForSize) &&
hasPartialRegUpdate(MI->getOpcode()))
- return 0;
+ return nullptr;
// Determine the alignment of the load.
unsigned Alignment = 0;
Alignment = 4;
break;
default:
- return 0;
+ return nullptr;
}
if (Ops.size() == 2 && Ops[0] == 0 && Ops[1] == 1) {
unsigned NewOpc = 0;
switch (MI->getOpcode()) {
- default: return NULL;
+ default: return nullptr;
case X86::TEST8rr: NewOpc = X86::CMP8ri; break;
case X86::TEST16rr: NewOpc = X86::CMP16ri8; break;
case X86::TEST32rr: NewOpc = X86::CMP32ri8; break;
MI->setDesc(get(NewOpc));
MI->getOperand(1).ChangeToImmediate(0);
} else if (Ops.size() != 1)
- return NULL;
+ return nullptr;
// Make sure the subregisters match.
// Otherwise we risk changing the size of the load.
if (LoadMI->getOperand(0).getSubReg() != MI->getOperand(Ops[0]).getSubReg())
- return NULL;
+ return nullptr;
SmallVector<MachineOperand,X86::AddrNumOperands> MOs;
switch (LoadMI->getOpcode()) {
// Create a constant-pool entry and operands to load from it.
// Medium and large mode can't fold loads this way.
- if (TM.getCodeModel() != CodeModel::Small &&
- TM.getCodeModel() != CodeModel::Kernel)
- return NULL;
+ if (MF.getTarget().getCodeModel() != CodeModel::Small &&
+ MF.getTarget().getCodeModel() != CodeModel::Kernel)
+ return nullptr;
// x86-32 PIC requires a PIC base register for constant pools.
unsigned PICBase = 0;
- if (TM.getRelocationModel() == Reloc::PIC_) {
- if (TM.getSubtarget<X86Subtarget>().is64Bit())
+ if (MF.getTarget().getRelocationModel() == Reloc::PIC_) {
+ if (Subtarget.is64Bit())
PICBase = X86::RIP;
else
// FIXME: PICBase = getGlobalBaseReg(&MF);
// This doesn't work for several reasons.
// 1. GlobalBaseReg may have been spilled.
// 2. It may not be live at MI.
- return NULL;
+ return nullptr;
}
// Create a constant-pool entry.
break;
}
default: {
- if ((LoadMI->getOpcode() == X86::MOVSSrm ||
- LoadMI->getOpcode() == X86::VMOVSSrm) &&
- MF.getRegInfo().getRegClass(LoadMI->getOperand(0).getReg())->getSize()
- > 4)
- // These instructions only load 32 bits, we can't fold them if the
- // destination register is wider than 32 bits (4 bytes).
- return NULL;
- if ((LoadMI->getOpcode() == X86::MOVSDrm ||
- LoadMI->getOpcode() == X86::VMOVSDrm) &&
- MF.getRegInfo().getRegClass(LoadMI->getOperand(0).getReg())->getSize()
- > 8)
- // These instructions only load 64 bits, we can't fold them if the
- // destination register is wider than 64 bits (8 bytes).
- return NULL;
+ if (isPartialRegisterLoad(*LoadMI, MF))
+ return nullptr;
// Folding a normal load. Just copy the load's address operands.
- unsigned NumOps = LoadMI->getDesc().getNumOperands();
for (unsigned i = NumOps - X86::AddrNumOperands; i != NumOps; ++i)
MOs.push_back(LoadMI->getOperand(i));
break;
}
}
- return foldMemoryOperandImpl(MF, MI, Ops[0], MOs, 0, Alignment);
+ return foldMemoryOperandImpl(MF, MI, Ops[0], MOs,
+ /*Size=*/0, Alignment, /*AllowCommute=*/true);
}
// 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, std::pair<unsigned,unsigned> > *OpcodeTablePtr = 0;
+ const DenseMap<unsigned,
+ std::pair<unsigned,unsigned> > *OpcodeTablePtr = nullptr;
if (isTwoAddr && NumOps >= 2 && OpNum < 2) {
OpcodeTablePtr = &RegOp2MemOpTable2Addr;
} else if (OpNum == 0) { // If operand 0
- switch (Opc) {
- case X86::MOV8r0:
- case X86::MOV16r0:
- case X86::MOV32r0:
- case X86::MOV64r0: return true;
- default: break;
- }
+ if (Opc == X86::MOV32r0)
+ return true;
+
OpcodeTablePtr = &RegOp2MemOpTable0;
} else if (OpNum == 1) {
OpcodeTablePtr = &RegOp2MemOpTable1;
const TargetRegisterClass *RC = getRegClass(MCID, Index, &RI, MF);
if (!MI->hasOneMemOperand() &&
RC == &X86::VR128RegClass &&
- !TM.getSubtarget<X86Subtarget>().isUnalignedMemAccessFast())
+ !Subtarget.isUnalignedMemAccessFast())
// Without memoperands, loadRegFromAddr and storeRegToStackSlot will
// conservatively assume the address is unaligned. That's bad for
// performance.
std::vector<SDValue> AddrOps;
std::vector<SDValue> BeforeOps;
std::vector<SDValue> AfterOps;
- DebugLoc dl = N->getDebugLoc();
+ SDLoc dl(N);
unsigned NumOps = N->getNumOperands();
for (unsigned i = 0; i != NumOps-1; ++i) {
SDValue Op = N->getOperand(i);
AddrOps.push_back(Chain);
// Emit the load instruction.
- SDNode *Load = 0;
+ SDNode *Load = nullptr;
if (FoldedLoad) {
EVT VT = *RC->vt_begin();
std::pair<MachineInstr::mmo_iterator,
cast<MachineSDNode>(N)->memoperands_end());
if (!(*MMOs.first) &&
RC == &X86::VR128RegClass &&
- !TM.getSubtarget<X86Subtarget>().isUnalignedMemAccessFast())
+ !Subtarget.isUnalignedMemAccessFast())
// Do not introduce a slow unaligned load.
return false;
unsigned Alignment = RC->getSize() == 32 ? 32 : 16;
bool isAligned = (*MMOs.first) &&
(*MMOs.first)->getAlignment() >= Alignment;
- Load = DAG.getMachineNode(getLoadRegOpcode(0, RC, isAligned, TM), dl,
- VT, MVT::Other, &AddrOps[0], AddrOps.size());
+ Load = DAG.getMachineNode(getLoadRegOpcode(0, RC, isAligned, Subtarget), dl,
+ VT, MVT::Other, AddrOps);
NewNodes.push_back(Load);
// Preserve memory reference information.
// Emit the data processing instruction.
std::vector<EVT> VTs;
- const TargetRegisterClass *DstRC = 0;
+ const TargetRegisterClass *DstRC = nullptr;
if (MCID.getNumDefs() > 0) {
DstRC = getRegClass(MCID, 0, &RI, MF);
VTs.push_back(*DstRC->vt_begin());
if (Load)
BeforeOps.push_back(SDValue(Load, 0));
std::copy(AfterOps.begin(), AfterOps.end(), std::back_inserter(BeforeOps));
- SDNode *NewNode= DAG.getMachineNode(Opc, dl, VTs, &BeforeOps[0],
- BeforeOps.size());
+ SDNode *NewNode= DAG.getMachineNode(Opc, dl, VTs, BeforeOps);
NewNodes.push_back(NewNode);
// Emit the store instruction.
cast<MachineSDNode>(N)->memoperands_end());
if (!(*MMOs.first) &&
RC == &X86::VR128RegClass &&
- !TM.getSubtarget<X86Subtarget>().isUnalignedMemAccessFast())
+ !Subtarget.isUnalignedMemAccessFast())
// Do not introduce a slow unaligned store.
return false;
unsigned Alignment = RC->getSize() == 32 ? 32 : 16;
bool isAligned = (*MMOs.first) &&
(*MMOs.first)->getAlignment() >= Alignment;
- SDNode *Store = DAG.getMachineNode(getStoreRegOpcode(0, DstRC,
- isAligned, TM),
- dl, MVT::Other,
- &AddrOps[0], AddrOps.size());
+ SDNode *Store =
+ DAG.getMachineNode(getStoreRegOpcode(0, DstRC, isAligned, Subtarget),
+ dl, MVT::Other, AddrOps);
NewNodes.push_back(Store);
// Preserve memory reference information.
default:
// XMM registers. In 64-bit mode we can be a bit more aggressive since we
// have 16 of them to play with.
- if (TM.getSubtargetImpl()->is64Bit()) {
+ if (Subtarget.is64Bit()) {
if (NumLoads >= 3)
return false;
} else if (NumLoads) {
return true;
}
+bool X86InstrInfo::shouldScheduleAdjacent(MachineInstr* First,
+ MachineInstr *Second) const {
+ // Check if this processor supports macro-fusion. Since this is a minor
+ // heuristic, we haven't specifically reserved a feature. hasAVX is a decent
+ // proxy for SandyBridge+.
+ if (!Subtarget.hasAVX())
+ return false;
+
+ enum {
+ FuseTest,
+ FuseCmp,
+ FuseInc
+ } FuseKind;
+
+ 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:
+ FuseKind = FuseInc;
+ break;
+ case X86::JB_4:
+ case X86::JBE_4:
+ case X86::JA_4:
+ case X86::JAE_4:
+ 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:
+ FuseKind = FuseTest;
+ break;
+ }
+ switch (First->getOpcode()) {
+ default:
+ return false;
+ case X86::TEST8rr:
+ case X86::TEST16rr:
+ case X86::TEST32rr:
+ case X86::TEST64rr:
+ case X86::TEST8ri:
+ case X86::TEST16ri:
+ case X86::TEST32ri:
+ case X86::TEST32i32:
+ case X86::TEST64i32:
+ case X86::TEST64ri32:
+ case X86::TEST8rm:
+ case X86::TEST16rm:
+ case X86::TEST32rm:
+ case X86::TEST64rm:
+ case X86::TEST8ri_NOREX:
+ case X86::AND16i16:
+ case X86::AND16ri:
+ case X86::AND16ri8:
+ case X86::AND16rm:
+ case X86::AND16rr:
+ case X86::AND32i32:
+ case X86::AND32ri:
+ case X86::AND32ri8:
+ case X86::AND32rm:
+ case X86::AND32rr:
+ case X86::AND64i32:
+ case X86::AND64ri32:
+ case X86::AND64ri8:
+ case X86::AND64rm:
+ case X86::AND64rr:
+ case X86::AND8i8:
+ case X86::AND8ri:
+ case X86::AND8rm:
+ case X86::AND8rr:
+ return true;
+ case X86::CMP16i16:
+ case X86::CMP16ri:
+ case X86::CMP16ri8:
+ case X86::CMP16rm:
+ case X86::CMP16rr:
+ case X86::CMP32i32:
+ case X86::CMP32ri:
+ case X86::CMP32ri8:
+ case X86::CMP32rm:
+ case X86::CMP32rr:
+ case X86::CMP64i32:
+ case X86::CMP64ri32:
+ case X86::CMP64ri8:
+ case X86::CMP64rm:
+ case X86::CMP64rr:
+ case X86::CMP8i8:
+ case X86::CMP8ri:
+ case X86::CMP8rm:
+ case X86::CMP8rr:
+ case X86::ADD16i16:
+ case X86::ADD16ri:
+ case X86::ADD16ri8:
+ case X86::ADD16ri8_DB:
+ case X86::ADD16ri_DB:
+ case X86::ADD16rm:
+ case X86::ADD16rr:
+ case X86::ADD16rr_DB:
+ case X86::ADD32i32:
+ case X86::ADD32ri:
+ case X86::ADD32ri8:
+ case X86::ADD32ri8_DB:
+ case X86::ADD32ri_DB:
+ case X86::ADD32rm:
+ case X86::ADD32rr:
+ case X86::ADD32rr_DB:
+ case X86::ADD64i32:
+ case X86::ADD64ri32:
+ case X86::ADD64ri32_DB:
+ case X86::ADD64ri8:
+ case X86::ADD64ri8_DB:
+ case X86::ADD64rm:
+ case X86::ADD64rr:
+ case X86::ADD64rr_DB:
+ case X86::ADD8i8:
+ case X86::ADD8mi:
+ case X86::ADD8mr:
+ case X86::ADD8ri:
+ case X86::ADD8rm:
+ case X86::ADD8rr:
+ case X86::SUB16i16:
+ case X86::SUB16ri:
+ case X86::SUB16ri8:
+ case X86::SUB16rm:
+ case X86::SUB16rr:
+ case X86::SUB32i32:
+ case X86::SUB32ri:
+ case X86::SUB32ri8:
+ case X86::SUB32rm:
+ case X86::SUB32rr:
+ case X86::SUB64i32:
+ case X86::SUB64ri32:
+ case X86::SUB64ri8:
+ case X86::SUB64rm:
+ case X86::SUB64rr:
+ case X86::SUB8i8:
+ case X86::SUB8ri:
+ case X86::SUB8rm:
+ case X86::SUB8rr:
+ 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;
+ }
+}
bool X86InstrInfo::
ReverseBranchCondition(SmallVectorImpl<MachineOperand> &Cond) const {
/// TODO: Eliminate this and move the code to X86MachineFunctionInfo.
///
unsigned X86InstrInfo::getGlobalBaseReg(MachineFunction *MF) const {
- assert(!TM.getSubtarget<X86Subtarget>().is64Bit() &&
+ assert(!Subtarget.is64Bit() &&
"X86-64 PIC uses RIP relative addressing");
X86MachineFunctionInfo *X86FI = MF->getInfo<X86MachineFunctionInfo>();
{ X86::VINSERTF128rm, X86::VINSERTF128rm, X86::VINSERTI128rm },
{ X86::VINSERTF128rr, X86::VINSERTF128rr, X86::VINSERTI128rr },
{ X86::VPERM2F128rm, X86::VPERM2F128rm, X86::VPERM2I128rm },
- { X86::VPERM2F128rr, X86::VPERM2F128rr, X86::VPERM2I128rr }
+ { X86::VPERM2F128rr, X86::VPERM2F128rr, X86::VPERM2I128rr },
+ { X86::VBROADCASTSSrm, X86::VBROADCASTSSrm, X86::VPBROADCASTDrm},
+ { X86::VBROADCASTSSrr, X86::VBROADCASTSSrr, X86::VPBROADCASTDrr},
+ { X86::VBROADCASTSSYrr, X86::VBROADCASTSSYrr, X86::VPBROADCASTDYrr},
+ { X86::VBROADCASTSSYrm, X86::VBROADCASTSSYrm, X86::VPBROADCASTDYrm},
+ { X86::VBROADCASTSDYrr, X86::VBROADCASTSDYrr, X86::VPBROADCASTQYrr},
+ { X86::VBROADCASTSDYrm, X86::VBROADCASTSDYrm, X86::VPBROADCASTQYrm}
};
// FIXME: Some shuffle and unpack instructions have equivalents in different
for (unsigned i = 0, e = array_lengthof(ReplaceableInstrs); i != e; ++i)
if (ReplaceableInstrs[i][domain-1] == opcode)
return ReplaceableInstrs[i];
- return 0;
+ return nullptr;
}
static const uint16_t *lookupAVX2(unsigned opcode, unsigned domain) {
for (unsigned i = 0, e = array_lengthof(ReplaceableInstrsAVX2); i != e; ++i)
if (ReplaceableInstrsAVX2[i][domain-1] == opcode)
return ReplaceableInstrsAVX2[i];
- return 0;
+ return nullptr;
}
std::pair<uint16_t, uint16_t>
X86InstrInfo::getExecutionDomain(const MachineInstr *MI) const {
uint16_t domain = (MI->getDesc().TSFlags >> X86II::SSEDomainShift) & 3;
- bool hasAVX2 = TM.getSubtarget<X86Subtarget>().hasAVX2();
+ bool hasAVX2 = Subtarget.hasAVX2();
uint16_t validDomains = 0;
if (domain && lookup(MI->getOpcode(), domain))
validDomains = 0xe;
assert(dom && "Not an SSE instruction");
const uint16_t *table = lookup(MI->getOpcode(), dom);
if (!table) { // try the other table
- assert((TM.getSubtarget<X86Subtarget>().hasAVX2() || Domain < 3) &&
+ assert((Subtarget.hasAVX2() || Domain < 3) &&
"256-bit vector operations only available in AVX2");
table = lookupAVX2(MI->getOpcode(), dom);
}
NopInst.setOpcode(X86::NOOP);
}
+void X86InstrInfo::getUnconditionalBranch(
+ MCInst &Branch, const MCSymbolRefExpr *BranchTarget) const {
+ Branch.setOpcode(X86::JMP_4);
+ Branch.addOperand(MCOperand::CreateExpr(BranchTarget));
+}
+
+void X86InstrInfo::getTrap(MCInst &MI) const {
+ MI.setOpcode(X86::TRAP);
+}
+
bool X86InstrInfo::isHighLatencyDef(int opc) const {
switch (opc) {
default: return false;
case X86::DIVSSrr:
case X86::DIVSSrr_Int:
case X86::SQRTPDm:
- case X86::SQRTPDm_Int:
case X86::SQRTPDr:
- case X86::SQRTPDr_Int:
case X86::SQRTPSm:
- case X86::SQRTPSm_Int:
case X86::SQRTPSr:
- case X86::SQRTPSr_Int:
case X86::SQRTSDm:
case X86::SQRTSDm_Int:
case X86::SQRTSDr:
case X86::VDIVSSrr:
case X86::VDIVSSrr_Int:
case X86::VSQRTPDm:
- case X86::VSQRTPDm_Int:
case X86::VSQRTPDr:
- case X86::VSQRTPDr_Int:
case X86::VSQRTPSm:
- case X86::VSQRTPSm_Int:
case X86::VSQRTPSr:
- case X86::VSQRTPSr_Int:
case X86::VSQRTSDm:
case X86::VSQRTSDm_Int:
case X86::VSQRTSDr:
case X86::VSQRTSSm:
case X86::VSQRTSSm_Int:
case X86::VSQRTSSr:
+ case X86::VSQRTPDZm:
+ case X86::VSQRTPDZr:
+ case X86::VSQRTPSZm:
+ case X86::VSQRTPSZr:
+ case X86::VSQRTSDZm:
+ case X86::VSQRTSDZm_Int:
+ case X86::VSQRTSDZr:
+ case X86::VSQRTSSZm_Int:
+ case X86::VSQRTSSZr:
+ case X86::VSQRTSSZm:
+ case X86::VDIVSDZrm:
+ case X86::VDIVSDZrr:
+ case X86::VDIVSSZrm:
+ case X86::VDIVSSZrr:
+
+ case X86::VGATHERQPSZrm:
+ case X86::VGATHERQPDZrm:
+ case X86::VGATHERDPDZrm:
+ case X86::VGATHERDPSZrm:
+ case X86::VPGATHERQDZrm:
+ case X86::VPGATHERQQZrm:
+ case X86::VPGATHERDDZrm:
+ case X86::VPGATHERDQZrm:
+ case X86::VSCATTERQPDZmr:
+ case X86::VSCATTERQPSZmr:
+ case X86::VSCATTERDPDZmr:
+ case X86::VSCATTERDPSZmr:
+ case X86::VPSCATTERQDZmr:
+ case X86::VPSCATTERQQZmr:
+ case X86::VPSCATTERDDZmr:
+ case X86::VPSCATTERDQZmr:
return true;
}
}
static char ID;
CGBR() : MachineFunctionPass(ID) {}
- virtual bool runOnMachineFunction(MachineFunction &MF) {
+ bool runOnMachineFunction(MachineFunction &MF) override {
const X86TargetMachine *TM =
static_cast<const X86TargetMachine *>(&MF.getTarget());
- assert(!TM->getSubtarget<X86Subtarget>().is64Bit() &&
- "X86-64 PIC uses RIP relative addressing");
+ // Don't do anything if this is 64-bit as 64-bit PIC
+ // uses RIP relative addressing.
+ if (TM->getSubtarget<X86Subtarget>().is64Bit())
+ return false;
// Only emit a global base reg in PIC mode.
if (TM->getRelocationModel() != Reloc::PIC_)
MachineBasicBlock::iterator MBBI = FirstMBB.begin();
DebugLoc DL = FirstMBB.findDebugLoc(MBBI);
MachineRegisterInfo &RegInfo = MF.getRegInfo();
- const X86InstrInfo *TII = TM->getInstrInfo();
+ const X86InstrInfo *TII = TM->getSubtargetImpl()->getInstrInfo();
unsigned PC;
if (TM->getSubtarget<X86Subtarget>().isPICStyleGOT())
return true;
}
- virtual const char *getPassName() const {
+ const char *getPassName() const override {
return "X86 PIC Global Base Reg Initialization";
}
- virtual void getAnalysisUsage(AnalysisUsage &AU) const {
+ void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.setPreservesCFG();
MachineFunctionPass::getAnalysisUsage(AU);
}
char CGBR::ID = 0;
FunctionPass*
-llvm::createGlobalBaseRegPass() { return new CGBR(); }
+llvm::createX86GlobalBaseRegPass() { return new CGBR(); }
namespace {
struct LDTLSCleanup : public MachineFunctionPass {
static char ID;
LDTLSCleanup() : MachineFunctionPass(ID) {}
- virtual bool runOnMachineFunction(MachineFunction &MF) {
+ bool runOnMachineFunction(MachineFunction &MF) override {
X86MachineFunctionInfo* MFI = MF.getInfo<X86MachineFunctionInfo>();
if (MFI->getNumLocalDynamicTLSAccesses() < 2) {
// No point folding accesses if there isn't at least two.
const X86TargetMachine *TM =
static_cast<const X86TargetMachine *>(&MF->getTarget());
const bool is64Bit = TM->getSubtarget<X86Subtarget>().is64Bit();
- const X86InstrInfo *TII = TM->getInstrInfo();
+ const X86InstrInfo *TII = TM->getSubtargetImpl()->getInstrInfo();
// Insert a Copy from TLSBaseAddrReg to RAX/EAX.
MachineInstr *Copy = BuildMI(*I->getParent(), I, I->getDebugLoc(),
const X86TargetMachine *TM =
static_cast<const X86TargetMachine *>(&MF->getTarget());
const bool is64Bit = TM->getSubtarget<X86Subtarget>().is64Bit();
- const X86InstrInfo *TII = TM->getInstrInfo();
+ const X86InstrInfo *TII = TM->getSubtargetImpl()->getInstrInfo();
// Create a virtual register for the TLS base address.
MachineRegisterInfo &RegInfo = MF->getRegInfo();
return Copy;
}
- virtual const char *getPassName() const {
+ const char *getPassName() const override {
return "Local Dynamic TLS Access Clean-up";
}
- virtual void getAnalysisUsage(AnalysisUsage &AU) const {
+ void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.setPreservesCFG();
AU.addRequired<MachineDominatorTree>();
MachineFunctionPass::getAnalysisUsage(AU);
projects / oota-llvm.git / blobdiff