[llvm] b969dfe - [NFC][PowerPC] Move the folding RLWINMs from ppc-mi-peephole to PPCInstrInfo.
via llvm-commits
llvm-commits at lists.llvm.org
Mon Nov 2 22:30:17 PST 2020
Author: Esme-Yi
Date: 2020-11-03T06:28:56Z
New Revision: b969dfe26f41ce0373a9e1542ebd4cfb0e6a2c25
URL: https://github.com/llvm/llvm-project/commit/b969dfe26f41ce0373a9e1542ebd4cfb0e6a2c25
DIFF: https://github.com/llvm/llvm-project/commit/b969dfe26f41ce0373a9e1542ebd4cfb0e6a2c25.diff
LOG: [NFC][PowerPC] Move the folding RLWINMs from ppc-mi-peephole to PPCInstrInfo.
Summary: We have the patterns to fold 2 RLWINMs in ppc-mi-peephole, while some RLWINM will be generated after RA, for example D88274. If the RLWINM generated after RA followed by another RLWINM, we expect to perform the optimization after RA, too.
This is a NFC patch to move the folding patterns to PPCInstrInfo, and the follow-up works will be calling it in pre-emit-peephole and expand the patterns to handle more cases.
Reviewed By: shchenz
Differential Revision: https://reviews.llvm.org/D89846
Added:
Modified:
llvm/lib/Target/PowerPC/PPCInstrInfo.cpp
llvm/lib/Target/PowerPC/PPCInstrInfo.h
llvm/lib/Target/PowerPC/PPCMIPeephole.cpp
Removed:
################################################################################
diff --git a/llvm/lib/Target/PowerPC/PPCInstrInfo.cpp b/llvm/lib/Target/PowerPC/PPCInstrInfo.cpp
index 487bf925ac99..e8735b31628c 100644
--- a/llvm/lib/Target/PowerPC/PPCInstrInfo.cpp
+++ b/llvm/lib/Target/PowerPC/PPCInstrInfo.cpp
@@ -3190,6 +3190,143 @@ bool PPCInstrInfo::convertToImmediateForm(MachineInstr &MI,
return false;
}
+bool PPCInstrInfo::combineRLWINM(MachineInstr &MI,
+ MachineInstr **ToErase) const {
+ MachineRegisterInfo *MRI = &MI.getParent()->getParent()->getRegInfo();
+ unsigned FoldingReg = MI.getOperand(1).getReg();
+ if (!Register::isVirtualRegister(FoldingReg))
+ return false;
+ MachineInstr *SrcMI = MRI->getVRegDef(FoldingReg);
+ if (SrcMI->getOpcode() != PPC::RLWINM &&
+ SrcMI->getOpcode() != PPC::RLWINM_rec &&
+ SrcMI->getOpcode() != PPC::RLWINM8 &&
+ SrcMI->getOpcode() != PPC::RLWINM8_rec)
+ return false;
+ assert((MI.getOperand(2).isImm() && MI.getOperand(3).isImm() &&
+ MI.getOperand(4).isImm() && SrcMI->getOperand(2).isImm() &&
+ SrcMI->getOperand(3).isImm() && SrcMI->getOperand(4).isImm()) &&
+ "Invalid PPC::RLWINM Instruction!");
+ uint64_t SHSrc = SrcMI->getOperand(2).getImm();
+ uint64_t SHMI = MI.getOperand(2).getImm();
+ uint64_t MBSrc = SrcMI->getOperand(3).getImm();
+ uint64_t MBMI = MI.getOperand(3).getImm();
+ uint64_t MESrc = SrcMI->getOperand(4).getImm();
+ uint64_t MEMI = MI.getOperand(4).getImm();
+
+ assert((MEMI < 32 && MESrc < 32 && MBMI < 32 && MBSrc < 32) &&
+ "Invalid PPC::RLWINM Instruction!");
+ // If MBMI is bigger than MEMI, we always can not get run of ones.
+ // RotatedSrcMask non-wrap:
+ // 0........31|32........63
+ // RotatedSrcMask: B---E B---E
+ // MaskMI: -----------|--E B------
+ // Result: ----- --- (Bad candidate)
+ //
+ // RotatedSrcMask wrap:
+ // 0........31|32........63
+ // RotatedSrcMask: --E B----|--E B----
+ // MaskMI: -----------|--E B------
+ // Result: --- -----|--- ----- (Bad candidate)
+ //
+ // One special case is RotatedSrcMask is a full set mask.
+ // RotatedSrcMask full:
+ // 0........31|32........63
+ // RotatedSrcMask: ------EB---|-------EB---
+ // MaskMI: -----------|--E B------
+ // Result: -----------|--- ------- (Good candidate)
+
+ // Mark special case.
+ bool SrcMaskFull = (MBSrc - MESrc == 1) || (MBSrc == 0 && MESrc == 31);
+
+ // For other MBMI > MEMI cases, just return.
+ if ((MBMI > MEMI) && !SrcMaskFull)
+ return false;
+
+ // Handle MBMI <= MEMI cases.
+ APInt MaskMI = APInt::getBitsSetWithWrap(32, 32 - MEMI - 1, 32 - MBMI);
+ // In MI, we only need low 32 bits of SrcMI, just consider about low 32
+ // bit of SrcMI mask. Note that in APInt, lowerest bit is at index 0,
+ // while in PowerPC ISA, lowerest bit is at index 63.
+ APInt MaskSrc = APInt::getBitsSetWithWrap(32, 32 - MESrc - 1, 32 - MBSrc);
+
+ APInt RotatedSrcMask = MaskSrc.rotl(SHMI);
+ APInt FinalMask = RotatedSrcMask & MaskMI;
+ uint32_t NewMB, NewME;
+ bool Simplified = false;
+
+ // If final mask is 0, MI result should be 0 too.
+ if (FinalMask.isNullValue()) {
+ bool Is64Bit =
+ (MI.getOpcode() == PPC::RLWINM8 || MI.getOpcode() == PPC::RLWINM8_rec);
+ Simplified = true;
+ LLVM_DEBUG(dbgs() << "Replace Instr: ");
+ LLVM_DEBUG(MI.dump());
+
+ if (MI.getOpcode() == PPC::RLWINM || MI.getOpcode() == PPC::RLWINM8) {
+ // Replace MI with "LI 0"
+ MI.RemoveOperand(4);
+ MI.RemoveOperand(3);
+ MI.RemoveOperand(2);
+ MI.getOperand(1).ChangeToImmediate(0);
+ MI.setDesc(get(Is64Bit ? PPC::LI8 : PPC::LI));
+ } else {
+ // Replace MI with "ANDI_rec reg, 0"
+ MI.RemoveOperand(4);
+ MI.RemoveOperand(3);
+ MI.getOperand(2).setImm(0);
+ MI.setDesc(get(Is64Bit ? PPC::ANDI8_rec : PPC::ANDI_rec));
+ MI.getOperand(1).setReg(SrcMI->getOperand(1).getReg());
+ if (SrcMI->getOperand(1).isKill()) {
+ MI.getOperand(1).setIsKill(true);
+ SrcMI->getOperand(1).setIsKill(false);
+ } else
+ // About to replace MI.getOperand(1), clear its kill flag.
+ MI.getOperand(1).setIsKill(false);
+ }
+
+ LLVM_DEBUG(dbgs() << "With: ");
+ LLVM_DEBUG(MI.dump());
+
+ } else if ((isRunOfOnes((unsigned)(FinalMask.getZExtValue()), NewMB, NewME) &&
+ NewMB <= NewME) ||
+ SrcMaskFull) {
+ // Here we only handle MBMI <= MEMI case, so NewMB must be no bigger
+ // than NewME. Otherwise we get a 64 bit value after folding, but MI
+ // return a 32 bit value.
+ Simplified = true;
+ LLVM_DEBUG(dbgs() << "Converting Instr: ");
+ LLVM_DEBUG(MI.dump());
+
+ uint16_t NewSH = (SHSrc + SHMI) % 32;
+ MI.getOperand(2).setImm(NewSH);
+ // If SrcMI mask is full, no need to update MBMI and MEMI.
+ if (!SrcMaskFull) {
+ MI.getOperand(3).setImm(NewMB);
+ MI.getOperand(4).setImm(NewME);
+ }
+ MI.getOperand(1).setReg(SrcMI->getOperand(1).getReg());
+ if (SrcMI->getOperand(1).isKill()) {
+ MI.getOperand(1).setIsKill(true);
+ SrcMI->getOperand(1).setIsKill(false);
+ } else
+ // About to replace MI.getOperand(1), clear its kill flag.
+ MI.getOperand(1).setIsKill(false);
+
+ LLVM_DEBUG(dbgs() << "To: ");
+ LLVM_DEBUG(MI.dump());
+ }
+ if (Simplified & MRI->use_nodbg_empty(FoldingReg) &&
+ !SrcMI->hasImplicitDef()) {
+ // If FoldingReg has no non-debug use and it has no implicit def (it
+ // is not RLWINMO or RLWINM8o), it's safe to delete its def SrcMI.
+ // Otherwise keep it.
+ *ToErase = SrcMI;
+ LLVM_DEBUG(dbgs() << "Delete dead instruction: ");
+ LLVM_DEBUG(SrcMI->dump());
+ }
+ return Simplified;
+}
+
bool PPCInstrInfo::instrHasImmForm(unsigned Opc, bool IsVFReg,
ImmInstrInfo &III, bool PostRA) const {
// The vast majority of the instructions would need their operand 2 replaced
diff --git a/llvm/lib/Target/PowerPC/PPCInstrInfo.h b/llvm/lib/Target/PowerPC/PPCInstrInfo.h
index 79b7bd4a1d38..f3ada5a0febc 100644
--- a/llvm/lib/Target/PowerPC/PPCInstrInfo.h
+++ b/llvm/lib/Target/PowerPC/PPCInstrInfo.h
@@ -564,6 +564,7 @@ class PPCInstrInfo : public PPCGenInstrInfo {
bool convertToImmediateForm(MachineInstr &MI,
MachineInstr **KilledDef = nullptr) const;
bool foldFrameOffset(MachineInstr &MI) const;
+ bool combineRLWINM(MachineInstr &MI, MachineInstr **ToErase = nullptr) const;
bool isADDIInstrEligibleForFolding(MachineInstr &ADDIMI, int64_t &Imm) const;
bool isADDInstrEligibleForFolding(MachineInstr &ADDMI) const;
bool isImmInstrEligibleForFolding(MachineInstr &MI, unsigned &BaseReg,
diff --git a/llvm/lib/Target/PowerPC/PPCMIPeephole.cpp b/llvm/lib/Target/PowerPC/PPCMIPeephole.cpp
index 227c863685ae..3fd02bc185c9 100644
--- a/llvm/lib/Target/PowerPC/PPCMIPeephole.cpp
+++ b/llvm/lib/Target/PowerPC/PPCMIPeephole.cpp
@@ -848,142 +848,9 @@ bool PPCMIPeephole::simplifyCode(void) {
case PPC::RLWINM_rec:
case PPC::RLWINM8:
case PPC::RLWINM8_rec: {
- unsigned FoldingReg = MI.getOperand(1).getReg();
- if (!Register::isVirtualRegister(FoldingReg))
- break;
-
- MachineInstr *SrcMI = MRI->getVRegDef(FoldingReg);
- if (SrcMI->getOpcode() != PPC::RLWINM &&
- SrcMI->getOpcode() != PPC::RLWINM_rec &&
- SrcMI->getOpcode() != PPC::RLWINM8 &&
- SrcMI->getOpcode() != PPC::RLWINM8_rec)
- break;
- assert((MI.getOperand(2).isImm() && MI.getOperand(3).isImm() &&
- MI.getOperand(4).isImm() && SrcMI->getOperand(2).isImm() &&
- SrcMI->getOperand(3).isImm() && SrcMI->getOperand(4).isImm()) &&
- "Invalid PPC::RLWINM Instruction!");
- uint64_t SHSrc = SrcMI->getOperand(2).getImm();
- uint64_t SHMI = MI.getOperand(2).getImm();
- uint64_t MBSrc = SrcMI->getOperand(3).getImm();
- uint64_t MBMI = MI.getOperand(3).getImm();
- uint64_t MESrc = SrcMI->getOperand(4).getImm();
- uint64_t MEMI = MI.getOperand(4).getImm();
-
- assert((MEMI < 32 && MESrc < 32 && MBMI < 32 && MBSrc < 32) &&
- "Invalid PPC::RLWINM Instruction!");
-
- // If MBMI is bigger than MEMI, we always can not get run of ones.
- // RotatedSrcMask non-wrap:
- // 0........31|32........63
- // RotatedSrcMask: B---E B---E
- // MaskMI: -----------|--E B------
- // Result: ----- --- (Bad candidate)
- //
- // RotatedSrcMask wrap:
- // 0........31|32........63
- // RotatedSrcMask: --E B----|--E B----
- // MaskMI: -----------|--E B------
- // Result: --- -----|--- ----- (Bad candidate)
- //
- // One special case is RotatedSrcMask is a full set mask.
- // RotatedSrcMask full:
- // 0........31|32........63
- // RotatedSrcMask: ------EB---|-------EB---
- // MaskMI: -----------|--E B------
- // Result: -----------|--- ------- (Good candidate)
-
- // Mark special case.
- bool SrcMaskFull = (MBSrc - MESrc == 1) || (MBSrc == 0 && MESrc == 31);
-
- // For other MBMI > MEMI cases, just return.
- if ((MBMI > MEMI) && !SrcMaskFull)
- break;
-
- // Handle MBMI <= MEMI cases.
- APInt MaskMI = APInt::getBitsSetWithWrap(32, 32 - MEMI - 1, 32 - MBMI);
- // In MI, we only need low 32 bits of SrcMI, just consider about low 32
- // bit of SrcMI mask. Note that in APInt, lowerest bit is at index 0,
- // while in PowerPC ISA, lowerest bit is at index 63.
- APInt MaskSrc =
- APInt::getBitsSetWithWrap(32, 32 - MESrc - 1, 32 - MBSrc);
-
- APInt RotatedSrcMask = MaskSrc.rotl(SHMI);
- APInt FinalMask = RotatedSrcMask & MaskMI;
- uint32_t NewMB, NewME;
-
- // If final mask is 0, MI result should be 0 too.
- if (FinalMask.isNullValue()) {
- bool Is64Bit = (MI.getOpcode() == PPC::RLWINM8 ||
- MI.getOpcode() == PPC::RLWINM8_rec);
-
- Simplified = true;
-
- LLVM_DEBUG(dbgs() << "Replace Instr: ");
- LLVM_DEBUG(MI.dump());
-
- if (MI.getOpcode() == PPC::RLWINM || MI.getOpcode() == PPC::RLWINM8) {
- // Replace MI with "LI 0"
- MI.RemoveOperand(4);
- MI.RemoveOperand(3);
- MI.RemoveOperand(2);
- MI.getOperand(1).ChangeToImmediate(0);
- MI.setDesc(TII->get(Is64Bit ? PPC::LI8 : PPC::LI));
- } else {
- // Replace MI with "ANDI_rec reg, 0"
- MI.RemoveOperand(4);
- MI.RemoveOperand(3);
- MI.getOperand(2).setImm(0);
- MI.setDesc(TII->get(Is64Bit ? PPC::ANDI8_rec : PPC::ANDI_rec));
- MI.getOperand(1).setReg(SrcMI->getOperand(1).getReg());
- if (SrcMI->getOperand(1).isKill()) {
- MI.getOperand(1).setIsKill(true);
- SrcMI->getOperand(1).setIsKill(false);
- } else
- // About to replace MI.getOperand(1), clear its kill flag.
- MI.getOperand(1).setIsKill(false);
- }
-
- LLVM_DEBUG(dbgs() << "With: ");
- LLVM_DEBUG(MI.dump());
- } else if ((isRunOfOnes((unsigned)(FinalMask.getZExtValue()), NewMB,
- NewME) && NewMB <= NewME)|| SrcMaskFull) {
- // Here we only handle MBMI <= MEMI case, so NewMB must be no bigger
- // than NewME. Otherwise we get a 64 bit value after folding, but MI
- // return a 32 bit value.
-
- Simplified = true;
- LLVM_DEBUG(dbgs() << "Converting Instr: ");
- LLVM_DEBUG(MI.dump());
-
- uint16_t NewSH = (SHSrc + SHMI) % 32;
- MI.getOperand(2).setImm(NewSH);
- // If SrcMI mask is full, no need to update MBMI and MEMI.
- if (!SrcMaskFull) {
- MI.getOperand(3).setImm(NewMB);
- MI.getOperand(4).setImm(NewME);
- }
- MI.getOperand(1).setReg(SrcMI->getOperand(1).getReg());
- if (SrcMI->getOperand(1).isKill()) {
- MI.getOperand(1).setIsKill(true);
- SrcMI->getOperand(1).setIsKill(false);
- } else
- // About to replace MI.getOperand(1), clear its kill flag.
- MI.getOperand(1).setIsKill(false);
-
- LLVM_DEBUG(dbgs() << "To: ");
- LLVM_DEBUG(MI.dump());
- }
- if (Simplified) {
- // If FoldingReg has no non-debug use and it has no implicit def (it
- // is not RLWINMO or RLWINM8o), it's safe to delete its def SrcMI.
- // Otherwise keep it.
+ Simplified = TII->combineRLWINM(MI, &ToErase);
+ if (Simplified)
++NumRotatesCollapsed;
- if (MRI->use_nodbg_empty(FoldingReg) && !SrcMI->hasImplicitDef()) {
- ToErase = SrcMI;
- LLVM_DEBUG(dbgs() << "Delete dead instruction: ");
- LLVM_DEBUG(SrcMI->dump());
- }
- }
break;
}
}
More information about the llvm-commits
mailing list