forked from OSchip/llvm-project
Revert "r214832 - MachineCombiner Pass for selecting faster instruction"
It broke compiling of most Benchmark and internal test, as clang got clashed by segmentation fault or assertion. llvm-svn: 214845
This commit is contained in:
parent
51f5326e25
commit
ec100526e3
|
@ -1351,15 +1351,14 @@ class BaseMulAccum<bit isSub, bits<3> opc, RegisterClass multype,
|
||||||
}
|
}
|
||||||
|
|
||||||
multiclass MulAccum<bit isSub, string asm, SDNode AccNode> {
|
multiclass MulAccum<bit isSub, string asm, SDNode AccNode> {
|
||||||
// MADD/MSUB generation is decided by MachineCombiner.cpp
|
|
||||||
def Wrrr : BaseMulAccum<isSub, 0b000, GPR32, GPR32, asm,
|
def Wrrr : BaseMulAccum<isSub, 0b000, GPR32, GPR32, asm,
|
||||||
[/*(set GPR32:$Rd, (AccNode GPR32:$Ra, (mul GPR32:$Rn, GPR32:$Rm)))*/]>,
|
[(set GPR32:$Rd, (AccNode GPR32:$Ra, (mul GPR32:$Rn, GPR32:$Rm)))]>,
|
||||||
Sched<[WriteIM32, ReadIM, ReadIM, ReadIMA]> {
|
Sched<[WriteIM32, ReadIM, ReadIM, ReadIMA]> {
|
||||||
let Inst{31} = 0;
|
let Inst{31} = 0;
|
||||||
}
|
}
|
||||||
|
|
||||||
def Xrrr : BaseMulAccum<isSub, 0b000, GPR64, GPR64, asm,
|
def Xrrr : BaseMulAccum<isSub, 0b000, GPR64, GPR64, asm,
|
||||||
[/*(set GPR64:$Rd, (AccNode GPR64:$Ra, (mul GPR64:$Rn, GPR64:$Rm)))*/]>,
|
[(set GPR64:$Rd, (AccNode GPR64:$Ra, (mul GPR64:$Rn, GPR64:$Rm)))]>,
|
||||||
Sched<[WriteIM64, ReadIM, ReadIM, ReadIMA]> {
|
Sched<[WriteIM64, ReadIM, ReadIM, ReadIMA]> {
|
||||||
let Inst{31} = 1;
|
let Inst{31} = 1;
|
||||||
}
|
}
|
||||||
|
|
|
@ -14,7 +14,6 @@
|
||||||
#include "AArch64InstrInfo.h"
|
#include "AArch64InstrInfo.h"
|
||||||
#include "AArch64Subtarget.h"
|
#include "AArch64Subtarget.h"
|
||||||
#include "MCTargetDesc/AArch64AddressingModes.h"
|
#include "MCTargetDesc/AArch64AddressingModes.h"
|
||||||
#include "AArch64MachineCombinerPattern.h"
|
|
||||||
#include "llvm/CodeGen/MachineFrameInfo.h"
|
#include "llvm/CodeGen/MachineFrameInfo.h"
|
||||||
#include "llvm/CodeGen/MachineInstrBuilder.h"
|
#include "llvm/CodeGen/MachineInstrBuilder.h"
|
||||||
#include "llvm/CodeGen/MachineMemOperand.h"
|
#include "llvm/CodeGen/MachineMemOperand.h"
|
||||||
|
@ -698,12 +697,17 @@ static bool UpdateOperandRegClass(MachineInstr *Instr) {
|
||||||
return true;
|
return true;
|
||||||
}
|
}
|
||||||
|
|
||||||
/// convertFlagSettingOpcode - return opcode that does not
|
/// optimizeCompareInstr - Convert the instruction supplying the argument to the
|
||||||
/// set flags when possible. The caller is responsible to do
|
/// comparison into one that sets the zero bit in the flags register.
|
||||||
/// the actual substitution and legality checking.
|
bool AArch64InstrInfo::optimizeCompareInstr(
|
||||||
static unsigned convertFlagSettingOpcode(MachineInstr *MI) {
|
MachineInstr *CmpInstr, unsigned SrcReg, unsigned SrcReg2, int CmpMask,
|
||||||
|
int CmpValue, const MachineRegisterInfo *MRI) const {
|
||||||
|
|
||||||
|
// Replace SUBSWrr with SUBWrr if NZCV is not used.
|
||||||
|
int Cmp_NZCV = CmpInstr->findRegisterDefOperandIdx(AArch64::NZCV, true);
|
||||||
|
if (Cmp_NZCV != -1) {
|
||||||
unsigned NewOpc;
|
unsigned NewOpc;
|
||||||
switch (MI->getOpcode()) {
|
switch (CmpInstr->getOpcode()) {
|
||||||
default:
|
default:
|
||||||
return false;
|
return false;
|
||||||
case AArch64::ADDSWrr: NewOpc = AArch64::ADDWrr; break;
|
case AArch64::ADDSWrr: NewOpc = AArch64::ADDWrr; break;
|
||||||
|
@ -723,22 +727,7 @@ static unsigned convertFlagSettingOpcode(MachineInstr *MI) {
|
||||||
case AArch64::SUBSXrs: NewOpc = AArch64::SUBXrs; break;
|
case AArch64::SUBSXrs: NewOpc = AArch64::SUBXrs; break;
|
||||||
case AArch64::SUBSXrx: NewOpc = AArch64::SUBXrx; break;
|
case AArch64::SUBSXrx: NewOpc = AArch64::SUBXrx; break;
|
||||||
}
|
}
|
||||||
return NewOpc;
|
|
||||||
}
|
|
||||||
|
|
||||||
/// optimizeCompareInstr - Convert the instruction supplying the argument to the
|
|
||||||
/// comparison into one that sets the zero bit in the flags register.
|
|
||||||
bool AArch64InstrInfo::optimizeCompareInstr(
|
|
||||||
MachineInstr *CmpInstr, unsigned SrcReg, unsigned SrcReg2, int CmpMask,
|
|
||||||
int CmpValue, const MachineRegisterInfo *MRI) const {
|
|
||||||
|
|
||||||
// Replace SUBSWrr with SUBWrr if NZCV is not used.
|
|
||||||
int Cmp_NZCV = CmpInstr->findRegisterDefOperandIdx(AArch64::NZCV, true);
|
|
||||||
if (Cmp_NZCV != -1) {
|
|
||||||
unsigned Opc = CmpInstr->getOpcode();
|
|
||||||
unsigned NewOpc = convertFlagSettingOpcode(CmpInstr);
|
|
||||||
if (NewOpc == Opc)
|
|
||||||
return false;
|
|
||||||
const MCInstrDesc &MCID = get(NewOpc);
|
const MCInstrDesc &MCID = get(NewOpc);
|
||||||
CmpInstr->setDesc(MCID);
|
CmpInstr->setDesc(MCID);
|
||||||
CmpInstr->RemoveOperand(Cmp_NZCV);
|
CmpInstr->RemoveOperand(Cmp_NZCV);
|
||||||
|
@ -2196,448 +2185,3 @@ void AArch64InstrInfo::getNoopForMachoTarget(MCInst &NopInst) const {
|
||||||
NopInst.setOpcode(AArch64::HINT);
|
NopInst.setOpcode(AArch64::HINT);
|
||||||
NopInst.addOperand(MCOperand::CreateImm(0));
|
NopInst.addOperand(MCOperand::CreateImm(0));
|
||||||
}
|
}
|
||||||
/// useMachineCombiner - return true when a target supports MachineCombiner
|
|
||||||
bool AArch64InstrInfo::useMachineCombiner(void) const {
|
|
||||||
// AArch64 supports the combiner
|
|
||||||
return true;
|
|
||||||
}
|
|
||||||
//
|
|
||||||
// True when Opc sets flag
|
|
||||||
static bool isCombineInstrSettingFlag(unsigned Opc) {
|
|
||||||
switch (Opc) {
|
|
||||||
case AArch64::ADDSWrr:
|
|
||||||
case AArch64::ADDSWri:
|
|
||||||
case AArch64::ADDSXrr:
|
|
||||||
case AArch64::ADDSXri:
|
|
||||||
case AArch64::SUBSWrr:
|
|
||||||
case AArch64::SUBSXrr:
|
|
||||||
// Note: MSUB Wd,Wn,Wm,Wi -> Wd = Wi - WnxWm, not Wd=WnxWm - Wi.
|
|
||||||
case AArch64::SUBSWri:
|
|
||||||
case AArch64::SUBSXri:
|
|
||||||
return true;
|
|
||||||
default:
|
|
||||||
break;
|
|
||||||
}
|
|
||||||
return false;
|
|
||||||
}
|
|
||||||
//
|
|
||||||
// 32b Opcodes that can be combined with a MUL
|
|
||||||
static bool isCombineInstrCandidate32(unsigned Opc) {
|
|
||||||
switch (Opc) {
|
|
||||||
case AArch64::ADDWrr:
|
|
||||||
case AArch64::ADDWri:
|
|
||||||
case AArch64::SUBWrr:
|
|
||||||
case AArch64::ADDSWrr:
|
|
||||||
case AArch64::ADDSWri:
|
|
||||||
case AArch64::SUBSWrr:
|
|
||||||
// Note: MSUB Wd,Wn,Wm,Wi -> Wd = Wi - WnxWm, not Wd=WnxWm - Wi.
|
|
||||||
case AArch64::SUBWri:
|
|
||||||
case AArch64::SUBSWri:
|
|
||||||
return true;
|
|
||||||
default:
|
|
||||||
break;
|
|
||||||
}
|
|
||||||
return false;
|
|
||||||
}
|
|
||||||
//
|
|
||||||
// 64b Opcodes that can be combined with a MUL
|
|
||||||
static bool isCombineInstrCandidate64(unsigned Opc) {
|
|
||||||
switch (Opc) {
|
|
||||||
case AArch64::ADDXrr:
|
|
||||||
case AArch64::ADDXri:
|
|
||||||
case AArch64::SUBXrr:
|
|
||||||
case AArch64::ADDSXrr:
|
|
||||||
case AArch64::ADDSXri:
|
|
||||||
case AArch64::SUBSXrr:
|
|
||||||
// Note: MSUB Wd,Wn,Wm,Wi -> Wd = Wi - WnxWm, not Wd=WnxWm - Wi.
|
|
||||||
case AArch64::SUBXri:
|
|
||||||
case AArch64::SUBSXri:
|
|
||||||
return true;
|
|
||||||
default:
|
|
||||||
break;
|
|
||||||
}
|
|
||||||
return false;
|
|
||||||
}
|
|
||||||
//
|
|
||||||
// Opcodes that can be combined with a MUL
|
|
||||||
static bool isCombineInstrCandidate(unsigned Opc) {
|
|
||||||
return (isCombineInstrCandidate32(Opc) || isCombineInstrCandidate64(Opc));
|
|
||||||
}
|
|
||||||
|
|
||||||
static bool canCombineWithMUL(MachineBasicBlock &MBB, MachineOperand &MO,
|
|
||||||
unsigned MulOpc, unsigned ZeroReg) {
|
|
||||||
MachineRegisterInfo &MRI = MBB.getParent()->getRegInfo();
|
|
||||||
MachineInstr *MI = nullptr;
|
|
||||||
// We need a virtual register definition.
|
|
||||||
if (MO.isReg() && TargetRegisterInfo::isVirtualRegister(MO.getReg()))
|
|
||||||
MI = MRI.getUniqueVRegDef(MO.getReg());
|
|
||||||
// And it needs to be in the trace (otherwise, it won't have a depth).
|
|
||||||
if (!MI || MI->getParent() != &MBB || (unsigned)MI->getOpcode() != MulOpc)
|
|
||||||
return false;
|
|
||||||
|
|
||||||
assert(MI->getNumOperands() >= 4 && MI->getOperand(0).isReg() &&
|
|
||||||
MI->getOperand(1).isReg() && MI->getOperand(2).isReg() &&
|
|
||||||
MI->getOperand(3).isReg() && "MAdd/MSub must have a least 4 regs");
|
|
||||||
|
|
||||||
// The third input reg must be zero.
|
|
||||||
if (MI->getOperand(3).getReg() != ZeroReg)
|
|
||||||
return false;
|
|
||||||
|
|
||||||
// Must only used by the user we combine with.
|
|
||||||
if (!MRI.hasOneNonDBGUse(MI->getOperand(0).getReg()))
|
|
||||||
return false;
|
|
||||||
|
|
||||||
return true;
|
|
||||||
}
|
|
||||||
|
|
||||||
/// hasPattern - return true when there is potentially a faster code sequence
|
|
||||||
/// for an instruction chain ending in \p Root. All potential patterns are
|
|
||||||
/// listed
|
|
||||||
/// in the \p Pattern vector. Pattern should be sorted in priority order since
|
|
||||||
/// the pattern evaluator stops checking as soon as it finds a faster sequence.
|
|
||||||
|
|
||||||
bool AArch64InstrInfo::hasPattern(
|
|
||||||
MachineInstr &Root,
|
|
||||||
SmallVectorImpl<MachineCombinerPattern::MC_PATTERN> &Pattern) const {
|
|
||||||
unsigned Opc = Root.getOpcode();
|
|
||||||
MachineBasicBlock &MBB = *Root.getParent();
|
|
||||||
bool Found = false;
|
|
||||||
|
|
||||||
if (!isCombineInstrCandidate(Opc))
|
|
||||||
return 0;
|
|
||||||
if (isCombineInstrSettingFlag(Opc)) {
|
|
||||||
int Cmp_NZCV = Root.findRegisterDefOperandIdx(AArch64::NZCV, true);
|
|
||||||
// When NZCV is live bail out.
|
|
||||||
if (Cmp_NZCV == -1)
|
|
||||||
return 0;
|
|
||||||
unsigned NewOpc = convertFlagSettingOpcode(&Root);
|
|
||||||
// When opcode can't change bail out.
|
|
||||||
// CHECKME: do we miss any cases for opcode conversion?
|
|
||||||
if (NewOpc == Opc)
|
|
||||||
return 0;
|
|
||||||
Opc = NewOpc;
|
|
||||||
}
|
|
||||||
|
|
||||||
switch (Opc) {
|
|
||||||
default:
|
|
||||||
break;
|
|
||||||
case AArch64::ADDWrr:
|
|
||||||
assert(Root.getOperand(1).isReg() && Root.getOperand(2).isReg() &&
|
|
||||||
"ADDWrr does not have register operands");
|
|
||||||
if (canCombineWithMUL(MBB, Root.getOperand(1), AArch64::MADDWrrr,
|
|
||||||
AArch64::WZR)) {
|
|
||||||
Pattern.push_back(MachineCombinerPattern::MC_MULADDW_OP1);
|
|
||||||
Found = true;
|
|
||||||
}
|
|
||||||
if (canCombineWithMUL(MBB, Root.getOperand(2), AArch64::MADDWrrr,
|
|
||||||
AArch64::WZR)) {
|
|
||||||
Pattern.push_back(MachineCombinerPattern::MC_MULADDW_OP2);
|
|
||||||
Found = true;
|
|
||||||
}
|
|
||||||
break;
|
|
||||||
case AArch64::ADDXrr:
|
|
||||||
if (canCombineWithMUL(MBB, Root.getOperand(1), AArch64::MADDXrrr,
|
|
||||||
AArch64::XZR)) {
|
|
||||||
Pattern.push_back(MachineCombinerPattern::MC_MULADDX_OP1);
|
|
||||||
Found = true;
|
|
||||||
}
|
|
||||||
if (canCombineWithMUL(MBB, Root.getOperand(2), AArch64::MADDXrrr,
|
|
||||||
AArch64::XZR)) {
|
|
||||||
Pattern.push_back(MachineCombinerPattern::MC_MULADDX_OP2);
|
|
||||||
Found = true;
|
|
||||||
}
|
|
||||||
break;
|
|
||||||
case AArch64::SUBWrr:
|
|
||||||
if (canCombineWithMUL(MBB, Root.getOperand(1), AArch64::MADDWrrr,
|
|
||||||
AArch64::WZR)) {
|
|
||||||
Pattern.push_back(MachineCombinerPattern::MC_MULSUBW_OP1);
|
|
||||||
Found = true;
|
|
||||||
}
|
|
||||||
if (canCombineWithMUL(MBB, Root.getOperand(2), AArch64::MADDWrrr,
|
|
||||||
AArch64::WZR)) {
|
|
||||||
Pattern.push_back(MachineCombinerPattern::MC_MULSUBW_OP2);
|
|
||||||
Found = true;
|
|
||||||
}
|
|
||||||
break;
|
|
||||||
case AArch64::SUBXrr:
|
|
||||||
if (canCombineWithMUL(MBB, Root.getOperand(1), AArch64::MADDXrrr,
|
|
||||||
AArch64::XZR)) {
|
|
||||||
Pattern.push_back(MachineCombinerPattern::MC_MULSUBX_OP1);
|
|
||||||
Found = true;
|
|
||||||
}
|
|
||||||
if (canCombineWithMUL(MBB, Root.getOperand(2), AArch64::MADDXrrr,
|
|
||||||
AArch64::XZR)) {
|
|
||||||
Pattern.push_back(MachineCombinerPattern::MC_MULSUBX_OP2);
|
|
||||||
Found = true;
|
|
||||||
}
|
|
||||||
break;
|
|
||||||
case AArch64::ADDWri:
|
|
||||||
if (canCombineWithMUL(MBB, Root.getOperand(1), AArch64::MADDWrrr,
|
|
||||||
AArch64::WZR)) {
|
|
||||||
Pattern.push_back(MachineCombinerPattern::MC_MULADDWI_OP1);
|
|
||||||
Found = true;
|
|
||||||
}
|
|
||||||
break;
|
|
||||||
case AArch64::ADDXri:
|
|
||||||
if (canCombineWithMUL(MBB, Root.getOperand(1), AArch64::MADDXrrr,
|
|
||||||
AArch64::XZR)) {
|
|
||||||
Pattern.push_back(MachineCombinerPattern::MC_MULADDXI_OP1);
|
|
||||||
Found = true;
|
|
||||||
}
|
|
||||||
break;
|
|
||||||
case AArch64::SUBWri:
|
|
||||||
if (canCombineWithMUL(MBB, Root.getOperand(1), AArch64::MADDWrrr,
|
|
||||||
AArch64::WZR)) {
|
|
||||||
Pattern.push_back(MachineCombinerPattern::MC_MULSUBWI_OP1);
|
|
||||||
Found = true;
|
|
||||||
}
|
|
||||||
break;
|
|
||||||
case AArch64::SUBXri:
|
|
||||||
if (canCombineWithMUL(MBB, Root.getOperand(1), AArch64::MADDXrrr,
|
|
||||||
AArch64::XZR)) {
|
|
||||||
Pattern.push_back(MachineCombinerPattern::MC_MULSUBXI_OP1);
|
|
||||||
Found = true;
|
|
||||||
}
|
|
||||||
break;
|
|
||||||
}
|
|
||||||
return Found;
|
|
||||||
}
|
|
||||||
|
|
||||||
/// genMadd - Generate madd instruction and combine mul and add.
|
|
||||||
/// Example:
|
|
||||||
/// MUL I=A,B,0
|
|
||||||
/// ADD R,I,C
|
|
||||||
/// ==> MADD R,A,B,C
|
|
||||||
/// \param Root is the ADD instruction
|
|
||||||
/// \param [out] InsInstr is a vector of machine instructions and will
|
|
||||||
/// contain the generated madd instruction
|
|
||||||
/// \param IdxMulOpd is index of operand in Root that is the result of
|
|
||||||
/// the MUL. In the example above IdxMulOpd is 1.
|
|
||||||
/// \param MaddOpc the opcode fo the madd instruction
|
|
||||||
static MachineInstr *genMadd(MachineFunction &MF, MachineRegisterInfo &MRI,
|
|
||||||
const TargetInstrInfo *TII, MachineInstr &Root,
|
|
||||||
SmallVectorImpl<MachineInstr *> &InsInstrs,
|
|
||||||
unsigned IdxMulOpd, unsigned MaddOpc) {
|
|
||||||
assert(IdxMulOpd == 1 || IdxMulOpd == 2);
|
|
||||||
|
|
||||||
unsigned IdxOtherOpd = IdxMulOpd == 1 ? 2 : 1;
|
|
||||||
MachineInstr *MUL = MRI.getUniqueVRegDef(Root.getOperand(IdxMulOpd).getReg());
|
|
||||||
MachineOperand R = Root.getOperand(0);
|
|
||||||
MachineOperand A = MUL->getOperand(1);
|
|
||||||
MachineOperand B = MUL->getOperand(2);
|
|
||||||
MachineOperand C = Root.getOperand(IdxOtherOpd);
|
|
||||||
MachineInstrBuilder MIB = BuildMI(MF, Root.getDebugLoc(), TII->get(MaddOpc))
|
|
||||||
.addOperand(R)
|
|
||||||
.addOperand(A)
|
|
||||||
.addOperand(B)
|
|
||||||
.addOperand(C);
|
|
||||||
// Insert the MADD
|
|
||||||
InsInstrs.push_back(MIB);
|
|
||||||
return MUL;
|
|
||||||
}
|
|
||||||
|
|
||||||
/// genMaddR - Generate madd instruction and combine mul and add using
|
|
||||||
/// an extra virtual register
|
|
||||||
/// Example - an ADD intermediate needs to be stored in a register:
|
|
||||||
/// MUL I=A,B,0
|
|
||||||
/// ADD R,I,Imm
|
|
||||||
/// ==> ORR V, ZR, Imm
|
|
||||||
/// ==> MADD R,A,B,V
|
|
||||||
/// \param Root is the ADD instruction
|
|
||||||
/// \param [out] InsInstr is a vector of machine instructions and will
|
|
||||||
/// contain the generated madd instruction
|
|
||||||
/// \param IdxMulOpd is index of operand in Root that is the result of
|
|
||||||
/// the MUL. In the example above IdxMulOpd is 1.
|
|
||||||
/// \param MaddOpc the opcode fo the madd instruction
|
|
||||||
/// \param VR is a virtual register that holds the value of an ADD operand
|
|
||||||
/// (V in the example above).
|
|
||||||
static MachineInstr *genMaddR(MachineFunction &MF, MachineRegisterInfo &MRI,
|
|
||||||
const TargetInstrInfo *TII, MachineInstr &Root,
|
|
||||||
SmallVectorImpl<MachineInstr *> &InsInstrs,
|
|
||||||
unsigned IdxMulOpd, unsigned MaddOpc,
|
|
||||||
unsigned VR) {
|
|
||||||
assert(IdxMulOpd == 1 || IdxMulOpd == 2);
|
|
||||||
|
|
||||||
MachineInstr *MUL = MRI.getUniqueVRegDef(Root.getOperand(IdxMulOpd).getReg());
|
|
||||||
MachineOperand R = Root.getOperand(0);
|
|
||||||
MachineOperand A = MUL->getOperand(1);
|
|
||||||
MachineOperand B = MUL->getOperand(2);
|
|
||||||
MachineInstrBuilder MIB = BuildMI(MF, Root.getDebugLoc(), TII->get(MaddOpc))
|
|
||||||
.addOperand(R)
|
|
||||||
.addOperand(A)
|
|
||||||
.addOperand(B)
|
|
||||||
.addReg(VR);
|
|
||||||
// Insert the MADD
|
|
||||||
InsInstrs.push_back(MIB);
|
|
||||||
return MUL;
|
|
||||||
}
|
|
||||||
/// genAlternativeCodeSequence - when hasPattern() finds a pattern
|
|
||||||
/// this function generates the instructions that could replace the
|
|
||||||
/// original code sequence
|
|
||||||
void AArch64InstrInfo::genAlternativeCodeSequence(
|
|
||||||
MachineInstr &Root, MachineCombinerPattern::MC_PATTERN Pattern,
|
|
||||||
SmallVectorImpl<MachineInstr *> &InsInstrs,
|
|
||||||
SmallVectorImpl<MachineInstr *> &DelInstrs,
|
|
||||||
DenseMap<unsigned, unsigned> &InstrIdxForVirtReg) const {
|
|
||||||
MachineBasicBlock &MBB = *Root.getParent();
|
|
||||||
MachineRegisterInfo &MRI = MBB.getParent()->getRegInfo();
|
|
||||||
MachineFunction &MF = *MBB.getParent();
|
|
||||||
const TargetInstrInfo *TII = MF.getTarget().getSubtargetImpl()->getInstrInfo();
|
|
||||||
|
|
||||||
MachineInstr *MUL;
|
|
||||||
unsigned Opc;
|
|
||||||
switch (Pattern) {
|
|
||||||
default:
|
|
||||||
// signal error.
|
|
||||||
break;
|
|
||||||
case MachineCombinerPattern::MC_MULADDW_OP1:
|
|
||||||
case MachineCombinerPattern::MC_MULADDX_OP1:
|
|
||||||
// MUL I=A,B,0
|
|
||||||
// ADD R,I,C
|
|
||||||
// ==> MADD R,A,B,C
|
|
||||||
// --- Create(MADD);
|
|
||||||
Opc = Pattern == MachineCombinerPattern::MC_MULADDW_OP1 ? AArch64::MADDWrrr
|
|
||||||
: AArch64::MADDXrrr;
|
|
||||||
MUL = genMadd(MF, MRI, TII, Root, InsInstrs, 1, Opc);
|
|
||||||
break;
|
|
||||||
case MachineCombinerPattern::MC_MULADDW_OP2:
|
|
||||||
case MachineCombinerPattern::MC_MULADDX_OP2:
|
|
||||||
// MUL I=A,B,0
|
|
||||||
// ADD R,C,I
|
|
||||||
// ==> MADD R,A,B,C
|
|
||||||
// --- Create(MADD);
|
|
||||||
Opc = Pattern == MachineCombinerPattern::MC_MULADDW_OP2 ? AArch64::MADDWrrr
|
|
||||||
: AArch64::MADDXrrr;
|
|
||||||
MUL = genMadd(MF, MRI, TII, Root, InsInstrs, 2, Opc);
|
|
||||||
break;
|
|
||||||
case MachineCombinerPattern::MC_MULADDWI_OP1:
|
|
||||||
case MachineCombinerPattern::MC_MULADDXI_OP1:
|
|
||||||
// MUL I=A,B,0
|
|
||||||
// ADD R,I,Imm
|
|
||||||
// ==> ORR V, ZR, Imm
|
|
||||||
// ==> MADD R,A,B,V
|
|
||||||
// --- Create(MADD);
|
|
||||||
{
|
|
||||||
const TargetRegisterClass *RC =
|
|
||||||
MRI.getRegClass(Root.getOperand(1).getReg());
|
|
||||||
unsigned NewVR = MRI.createVirtualRegister(RC);
|
|
||||||
unsigned BitSize, OrrOpc, ZeroReg;
|
|
||||||
if (Pattern == MachineCombinerPattern::MC_MULADDWI_OP1) {
|
|
||||||
BitSize = 32;
|
|
||||||
OrrOpc = AArch64::ORRWri;
|
|
||||||
ZeroReg = AArch64::WZR;
|
|
||||||
Opc = AArch64::MADDWrrr;
|
|
||||||
} else {
|
|
||||||
OrrOpc = AArch64::ORRXri;
|
|
||||||
BitSize = 64;
|
|
||||||
ZeroReg = AArch64::XZR;
|
|
||||||
Opc = AArch64::MADDXrrr;
|
|
||||||
}
|
|
||||||
uint64_t Imm = Root.getOperand(2).getImm();
|
|
||||||
|
|
||||||
if (Root.getOperand(3).isImm()) {
|
|
||||||
unsigned val = Root.getOperand(3).getImm();
|
|
||||||
Imm = Imm << val;
|
|
||||||
}
|
|
||||||
uint64_t UImm = Imm << (64 - BitSize) >> (64 - BitSize);
|
|
||||||
uint64_t Encoding;
|
|
||||||
|
|
||||||
if (AArch64_AM::processLogicalImmediate(UImm, BitSize, Encoding)) {
|
|
||||||
MachineInstrBuilder MIB1 =
|
|
||||||
BuildMI(MF, Root.getDebugLoc(), TII->get(OrrOpc))
|
|
||||||
.addOperand(MachineOperand::CreateReg(NewVR, RegState::Define))
|
|
||||||
.addReg(ZeroReg)
|
|
||||||
.addImm(Encoding);
|
|
||||||
InsInstrs.push_back(MIB1);
|
|
||||||
InstrIdxForVirtReg.insert(std::make_pair(NewVR, 0));
|
|
||||||
MUL = genMaddR(MF, MRI, TII, Root, InsInstrs, 1, Opc, NewVR);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
break;
|
|
||||||
case MachineCombinerPattern::MC_MULSUBW_OP1:
|
|
||||||
case MachineCombinerPattern::MC_MULSUBX_OP1: {
|
|
||||||
// MUL I=A,B,0
|
|
||||||
// SUB R,I, C
|
|
||||||
// ==> SUB V, 0, C
|
|
||||||
// ==> MADD R,A,B,V // = -C + A*B
|
|
||||||
// --- Create(MADD);
|
|
||||||
const TargetRegisterClass *RC =
|
|
||||||
MRI.getRegClass(Root.getOperand(1).getReg());
|
|
||||||
unsigned NewVR = MRI.createVirtualRegister(RC);
|
|
||||||
unsigned SubOpc, ZeroReg;
|
|
||||||
if (Pattern == MachineCombinerPattern::MC_MULSUBW_OP1) {
|
|
||||||
SubOpc = AArch64::SUBWrr;
|
|
||||||
ZeroReg = AArch64::WZR;
|
|
||||||
Opc = AArch64::MADDWrrr;
|
|
||||||
} else {
|
|
||||||
SubOpc = AArch64::SUBXrr;
|
|
||||||
ZeroReg = AArch64::XZR;
|
|
||||||
Opc = AArch64::MADDXrrr;
|
|
||||||
}
|
|
||||||
// SUB NewVR, 0, C
|
|
||||||
MachineInstrBuilder MIB1 =
|
|
||||||
BuildMI(MF, Root.getDebugLoc(), TII->get(SubOpc))
|
|
||||||
.addOperand(MachineOperand::CreateReg(NewVR, RegState::Define))
|
|
||||||
.addReg(ZeroReg)
|
|
||||||
.addOperand(Root.getOperand(2));
|
|
||||||
InsInstrs.push_back(MIB1);
|
|
||||||
InstrIdxForVirtReg.insert(std::make_pair(NewVR, 0));
|
|
||||||
MUL = genMaddR(MF, MRI, TII, Root, InsInstrs, 1, Opc, NewVR);
|
|
||||||
} break;
|
|
||||||
case MachineCombinerPattern::MC_MULSUBW_OP2:
|
|
||||||
case MachineCombinerPattern::MC_MULSUBX_OP2:
|
|
||||||
// MUL I=A,B,0
|
|
||||||
// SUB R,C,I
|
|
||||||
// ==> MSUB R,A,B,C (computes C - A*B)
|
|
||||||
// --- Create(MSUB);
|
|
||||||
Opc = Pattern == MachineCombinerPattern::MC_MULSUBW_OP2 ? AArch64::MSUBWrrr
|
|
||||||
: AArch64::MSUBXrrr;
|
|
||||||
MUL = genMadd(MF, MRI, TII, Root, InsInstrs, 2, Opc);
|
|
||||||
break;
|
|
||||||
case MachineCombinerPattern::MC_MULSUBWI_OP1:
|
|
||||||
case MachineCombinerPattern::MC_MULSUBXI_OP1: {
|
|
||||||
// MUL I=A,B,0
|
|
||||||
// SUB R,I, Imm
|
|
||||||
// ==> ORR V, ZR, -Imm
|
|
||||||
// ==> MADD R,A,B,V // = -Imm + A*B
|
|
||||||
// --- Create(MADD);
|
|
||||||
const TargetRegisterClass *RC =
|
|
||||||
MRI.getRegClass(Root.getOperand(1).getReg());
|
|
||||||
unsigned NewVR = MRI.createVirtualRegister(RC);
|
|
||||||
unsigned BitSize, OrrOpc, ZeroReg;
|
|
||||||
if (Pattern == MachineCombinerPattern::MC_MULSUBWI_OP1) {
|
|
||||||
BitSize = 32;
|
|
||||||
OrrOpc = AArch64::ORRWri;
|
|
||||||
ZeroReg = AArch64::WZR;
|
|
||||||
Opc = AArch64::MADDWrrr;
|
|
||||||
} else {
|
|
||||||
OrrOpc = AArch64::ORRXri;
|
|
||||||
BitSize = 64;
|
|
||||||
ZeroReg = AArch64::XZR;
|
|
||||||
Opc = AArch64::MADDXrrr;
|
|
||||||
}
|
|
||||||
int Imm = Root.getOperand(2).getImm();
|
|
||||||
if (Root.getOperand(3).isImm()) {
|
|
||||||
unsigned val = Root.getOperand(3).getImm();
|
|
||||||
Imm = Imm << val;
|
|
||||||
}
|
|
||||||
uint64_t UImm = -Imm << (64 - BitSize) >> (64 - BitSize);
|
|
||||||
uint64_t Encoding;
|
|
||||||
if (AArch64_AM::processLogicalImmediate(UImm, BitSize, Encoding)) {
|
|
||||||
MachineInstrBuilder MIB1 =
|
|
||||||
BuildMI(MF, Root.getDebugLoc(), TII->get(OrrOpc))
|
|
||||||
.addOperand(MachineOperand::CreateReg(NewVR, RegState::Define))
|
|
||||||
.addReg(ZeroReg)
|
|
||||||
.addImm(Encoding);
|
|
||||||
InsInstrs.push_back(MIB1);
|
|
||||||
InstrIdxForVirtReg.insert(std::make_pair(NewVR, 0));
|
|
||||||
MUL = genMaddR(MF, MRI, TII, Root, InsInstrs, 1, Opc, NewVR);
|
|
||||||
}
|
|
||||||
} break;
|
|
||||||
}
|
|
||||||
// Record MUL and ADD/SUB for deletion
|
|
||||||
DelInstrs.push_back(MUL);
|
|
||||||
DelInstrs.push_back(&Root);
|
|
||||||
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
|
|
|
@ -17,7 +17,6 @@
|
||||||
#include "AArch64.h"
|
#include "AArch64.h"
|
||||||
#include "AArch64RegisterInfo.h"
|
#include "AArch64RegisterInfo.h"
|
||||||
#include "llvm/Target/TargetInstrInfo.h"
|
#include "llvm/Target/TargetInstrInfo.h"
|
||||||
#include "llvm/CodeGen/MachineCombinerPattern.h"
|
|
||||||
|
|
||||||
#define GET_INSTRINFO_HEADER
|
#define GET_INSTRINFO_HEADER
|
||||||
#include "AArch64GenInstrInfo.inc"
|
#include "AArch64GenInstrInfo.inc"
|
||||||
|
@ -157,26 +156,9 @@ public:
|
||||||
bool optimizeCompareInstr(MachineInstr *CmpInstr, unsigned SrcReg,
|
bool optimizeCompareInstr(MachineInstr *CmpInstr, unsigned SrcReg,
|
||||||
unsigned SrcReg2, int CmpMask, int CmpValue,
|
unsigned SrcReg2, int CmpMask, int CmpValue,
|
||||||
const MachineRegisterInfo *MRI) const override;
|
const MachineRegisterInfo *MRI) const override;
|
||||||
/// hasPattern - return true when there is potentially a faster code sequence
|
|
||||||
/// for an instruction chain ending in <Root>. All potential patterns are
|
|
||||||
/// listed
|
|
||||||
/// in the <Pattern> array.
|
|
||||||
virtual bool hasPattern(
|
|
||||||
MachineInstr &Root,
|
|
||||||
SmallVectorImpl<MachineCombinerPattern::MC_PATTERN> &Pattern) const;
|
|
||||||
|
|
||||||
/// genAlternativeCodeSequence - when hasPattern() finds a pattern
|
|
||||||
/// this function generates the instructions that could replace the
|
|
||||||
/// original code sequence
|
|
||||||
virtual void genAlternativeCodeSequence(
|
|
||||||
MachineInstr &Root, MachineCombinerPattern::MC_PATTERN P,
|
|
||||||
SmallVectorImpl<MachineInstr *> &InsInstrs,
|
|
||||||
SmallVectorImpl<MachineInstr *> &DelInstrs,
|
|
||||||
DenseMap<unsigned, unsigned> &InstrIdxForVirtReg) const;
|
|
||||||
/// useMachineCombiner - AArch64 supports MachineCombiner
|
|
||||||
virtual bool useMachineCombiner(void) const;
|
|
||||||
|
|
||||||
bool expandPostRAPseudo(MachineBasicBlock::iterator MI) const override;
|
bool expandPostRAPseudo(MachineBasicBlock::iterator MI) const override;
|
||||||
|
|
||||||
private:
|
private:
|
||||||
void instantiateCondBranch(MachineBasicBlock &MBB, DebugLoc DL,
|
void instantiateCondBranch(MachineBasicBlock &MBB, DebugLoc DL,
|
||||||
MachineBasicBlock *TBB,
|
MachineBasicBlock *TBB,
|
||||||
|
|
|
@ -1,42 +0,0 @@
|
||||||
//===- AArch64MachineCombinerPattern.h -===//
|
|
||||||
//===- AArch64 instruction pattern supported by combiner -===//
|
|
||||||
//
|
|
||||||
// The LLVM Compiler Infrastructure
|
|
||||||
//
|
|
||||||
// This file is distributed under the University of Illinois Open Source
|
|
||||||
// License. See LICENSE.TXT for details.
|
|
||||||
//
|
|
||||||
//===----------------------------------------------------------------------===//
|
|
||||||
//
|
|
||||||
// This file defines instruction pattern supported by combiner
|
|
||||||
//
|
|
||||||
//===----------------------------------------------------------------------===//
|
|
||||||
|
|
||||||
#ifndef LLVM_TARGET_AArch64MACHINECOMBINERPATTERN_H
|
|
||||||
#define LLVM_TARGET_AArch64MACHINECOMBINERPATTERN_H
|
|
||||||
|
|
||||||
namespace llvm {
|
|
||||||
|
|
||||||
/// Enumeration of instruction pattern supported by machine combiner
|
|
||||||
///
|
|
||||||
///
|
|
||||||
namespace MachineCombinerPattern {
|
|
||||||
enum MC_PATTERN : int {
|
|
||||||
MC_NONE = 0,
|
|
||||||
MC_MULADDW_OP1 = 1,
|
|
||||||
MC_MULADDW_OP2 = 2,
|
|
||||||
MC_MULSUBW_OP1 = 3,
|
|
||||||
MC_MULSUBW_OP2 = 4,
|
|
||||||
MC_MULADDWI_OP1 = 5,
|
|
||||||
MC_MULSUBWI_OP1 = 6,
|
|
||||||
MC_MULADDX_OP1 = 7,
|
|
||||||
MC_MULADDX_OP2 = 8,
|
|
||||||
MC_MULSUBX_OP1 = 9,
|
|
||||||
MC_MULSUBX_OP2 = 10,
|
|
||||||
MC_MULADDXI_OP1 = 11,
|
|
||||||
MC_MULSUBXI_OP1 = 12
|
|
||||||
};
|
|
||||||
} // end namespace MachineCombinerPattern
|
|
||||||
} // end namespace llvm
|
|
||||||
|
|
||||||
#endif
|
|
|
@ -24,10 +24,6 @@ static cl::opt<bool>
|
||||||
EnableCCMP("aarch64-ccmp", cl::desc("Enable the CCMP formation pass"),
|
EnableCCMP("aarch64-ccmp", cl::desc("Enable the CCMP formation pass"),
|
||||||
cl::init(true), cl::Hidden);
|
cl::init(true), cl::Hidden);
|
||||||
|
|
||||||
static cl::opt<bool> EnableMCR("aarch64-mcr",
|
|
||||||
cl::desc("Enable the machine combiner pass"),
|
|
||||||
cl::init(true), cl::Hidden);
|
|
||||||
|
|
||||||
static cl::opt<bool>
|
static cl::opt<bool>
|
||||||
EnableStPairSuppress("aarch64-stp-suppress", cl::desc("Suppress STP for AArch64"),
|
EnableStPairSuppress("aarch64-stp-suppress", cl::desc("Suppress STP for AArch64"),
|
||||||
cl::init(true), cl::Hidden);
|
cl::init(true), cl::Hidden);
|
||||||
|
@ -178,8 +174,6 @@ bool AArch64PassConfig::addInstSelector() {
|
||||||
bool AArch64PassConfig::addILPOpts() {
|
bool AArch64PassConfig::addILPOpts() {
|
||||||
if (EnableCCMP)
|
if (EnableCCMP)
|
||||||
addPass(createAArch64ConditionalCompares());
|
addPass(createAArch64ConditionalCompares());
|
||||||
if (EnableMCR)
|
|
||||||
addPass(&MachineCombinerID);
|
|
||||||
addPass(&EarlyIfConverterID);
|
addPass(&EarlyIfConverterID);
|
||||||
if (EnableStPairSuppress)
|
if (EnableStPairSuppress)
|
||||||
addPass(createAArch64StorePairSuppressPass());
|
addPass(createAArch64StorePairSuppressPass());
|
||||||
|
|
|
@ -1,19 +0,0 @@
|
||||||
; RUN: llc -mtriple=arm64-apple-ios7.0 %s -o - | FileCheck %s
|
|
||||||
; RUN: llc -mtriple=aarch64_be-linux-gnu %s -o - | FileCheck --check-prefix=CHECK-BE %s
|
|
||||||
|
|
||||||
define i128 @test_128bitmul(i128 %lhs, i128 %rhs) {
|
|
||||||
; CHECK-LABEL: test_128bitmul:
|
|
||||||
; CHECK-DAG: umulh [[CARRY:x[0-9]+]], x0, x2
|
|
||||||
; CHECK-DAG: madd [[PART1:x[0-9]+]], x0, x3, [[CARRY]]
|
|
||||||
; CHECK: madd x1, x1, x2, [[PART1]]
|
|
||||||
; CHECK: mul x0, x0, x2
|
|
||||||
|
|
||||||
; CHECK-BE-LABEL: test_128bitmul:
|
|
||||||
; CHECK-BE-DAG: umulh [[CARRY:x[0-9]+]], x1, x3
|
|
||||||
; CHECK-BE-DAG: madd [[PART1:x[0-9]+]], x1, x2, [[CARRY]]
|
|
||||||
; CHECK-BE: madd x0, x0, x3, [[PART1]]
|
|
||||||
; CHECK-BE: mul x1, x1, x3
|
|
||||||
|
|
||||||
%prod = mul i128 %lhs, %rhs
|
|
||||||
ret i128 %prod
|
|
||||||
}
|
|
|
@ -1,16 +1,17 @@
|
||||||
; RUN: llc -mtriple=arm64-apple-ios7.0 -mcpu=cyclone %s -o - | FileCheck %s
|
; RUN: llc -mtriple=arm64-apple-ios7.0 %s -o - | FileCheck %s
|
||||||
; RUN: llc -mtriple=aarch64_be-linux-gnu -mcpu=cyclone %s -o - | FileCheck --check-prefix=CHECK-BE %s
|
; RUN: llc -mtriple=aarch64_be-linux-gnu %s -o - | FileCheck --check-prefix=CHECK-BE %s
|
||||||
|
|
||||||
define i128 @test_128bitmul(i128 %lhs, i128 %rhs) {
|
define i128 @test_128bitmul(i128 %lhs, i128 %rhs) {
|
||||||
; CHECK-LABEL: test_128bitmul:
|
; CHECK-LABEL: test_128bitmul:
|
||||||
; CHECK-DAG: mul [[PART1:x[0-9]+]], x0, x3
|
|
||||||
; CHECK-DAG: umulh [[CARRY:x[0-9]+]], x0, x2
|
; CHECK-DAG: umulh [[CARRY:x[0-9]+]], x0, x2
|
||||||
; CHECK: mul [[PART2:x[0-9]+]], x1, x2
|
; CHECK-DAG: madd [[PART1:x[0-9]+]], x0, x3, [[CARRY]]
|
||||||
|
; CHECK: madd x1, x1, x2, [[PART1]]
|
||||||
; CHECK: mul x0, x0, x2
|
; CHECK: mul x0, x0, x2
|
||||||
|
|
||||||
; CHECK-BE-LABEL: test_128bitmul:
|
; CHECK-BE-LABEL: test_128bitmul:
|
||||||
; CHECK-BE-DAG: mul [[PART1:x[0-9]+]], x1, x2
|
|
||||||
; CHECK-BE-DAG: umulh [[CARRY:x[0-9]+]], x1, x3
|
; CHECK-BE-DAG: umulh [[CARRY:x[0-9]+]], x1, x3
|
||||||
; CHECK-BE: mul [[PART2:x[0-9]+]], x0, x3
|
; CHECK-BE-DAG: madd [[PART1:x[0-9]+]], x1, x2, [[CARRY]]
|
||||||
|
; CHECK-BE: madd x0, x0, x3, [[PART1]]
|
||||||
; CHECK-BE: mul x1, x1, x3
|
; CHECK-BE: mul x1, x1, x3
|
||||||
|
|
||||||
%prod = mul i128 %lhs, %rhs
|
%prod = mul i128 %lhs, %rhs
|
||||||
|
|
Loading…
Reference in New Issue