Merge the OptimizeExts and OptimizeCmps passes into one PeepholeOptimizer

pass. This pass should expand with all of the small, fine-grained optimization
passes to reduce compile time and increase happiment.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@110627 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/CodeGen/Passes.h

@@ -172,18 +172,14 @@ namespace llvm {
   /// instructions.
   FunctionPass *createMachineSinkingPass();
 
-  /// createOptimizeExtsPass - This pass performs sign / zero extension
+  /// createPeepholeOptimizerPass - This pass performs peephole optimizations -
-  /// optimization by increasing uses of extended values.
+  /// like extension and comparison eliminations.
-  FunctionPass *createOptimizeExtsPass();
+  FunctionPass *createPeepholeOptimizerPass();
 
   /// createOptimizePHIsPass - This pass optimizes machine instruction PHIs
   /// to take advantage of opportunities created during DAG legalization.
   FunctionPass *createOptimizePHIsPass();
 
-  /// createOptimizeCmpsPass - This pass performs redundant comparison removal
-  /// optimization.
-  FunctionPass *createOptimizeCmpsPass();
-
   /// createStackSlotColoringPass - This pass performs stack slot coloring.
   FunctionPass *createStackSlotColoringPass(bool);
 

lib/CodeGen/LLVMTargetMachine.cpp

@@ -353,8 +353,7 @@ bool LLVMTargetMachine::addCommonCodeGenPasses(PassManagerBase &PM,
     PM.add(createDeadMachineInstructionElimPass());
     printAndVerify(PM, "After codegen DCE pass");
 
-    PM.add(createOptimizeExtsPass());
+    PM.add(createPeepholeOptimizerPass());
-    PM.add(createOptimizeCmpsPass());
     if (!DisableMachineLICM)
       PM.add(createMachineLICMPass());
     PM.add(createMachineCSEPass());

lib/CodeGen/OptimizeCmps.cpp

@@ -1,112 +0,0 @@
-//===-- OptimizeCmps.cpp - Optimize comparison instrs ---------------------===//
-//
-//                     The LLVM Compiler Infrastructure
-//
-// This file is distributed under the University of Illinois Open Source
-// License. See LICENSE.TXT for details.
-//
-//===----------------------------------------------------------------------===//
-//
-// This pass performs optimization of comparison instructions. For instance, in
-// this code:
-//
-//     sub r1, 1
-//     cmp r1, 0
-//     bz  L1
-//
-// If the "sub" instruction all ready sets (or could be modified to set) the
-// same flag that the "cmp" instruction sets and that "bz" uses, then we can
-// eliminate the "cmp" instruction.
-//
-//===----------------------------------------------------------------------===//
-
-#define DEBUG_TYPE "opt-compares"
-#include "llvm/CodeGen/Passes.h"
-#include "llvm/CodeGen/MachineFunctionPass.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
-#include "llvm/Target/TargetInstrInfo.h"
-#include "llvm/Target/TargetRegisterInfo.h"
-#include "llvm/Support/CommandLine.h"
-#include "llvm/ADT/Statistic.h"
-using namespace llvm;
-
-STATISTIC(NumEliminated, "Number of compares eliminated");
-
-static cl::opt<bool>
-EnableOptCmps("enable-optimize-cmps", cl::init(false), cl::Hidden);
-
-namespace {
-  class OptimizeCmps : public MachineFunctionPass {
-    const TargetMachine   *TM;
-    const TargetInstrInfo *TII;
-    MachineRegisterInfo   *MRI;
-
-    bool OptimizeCmpInstr(MachineInstr *MI, MachineBasicBlock *MBB);
-
-  public:
-    static char ID; // Pass identification
-    OptimizeCmps() : MachineFunctionPass(ID) {}
-
-    virtual bool runOnMachineFunction(MachineFunction &MF);
-
-    virtual void getAnalysisUsage(AnalysisUsage &AU) const {
-      AU.setPreservesCFG();
-      MachineFunctionPass::getAnalysisUsage(AU);
-    }
-  };
-}
-
-char OptimizeCmps::ID = 0;
-INITIALIZE_PASS(OptimizeCmps, "opt-cmps",
-                "Optimize comparison instrs", false, false);
-
-FunctionPass *llvm::createOptimizeCmpsPass() { return new OptimizeCmps(); }
-
-/// OptimizeCmpInstr - If the instruction is a compare and the previous
-/// instruction it's comparing against all ready sets (or could be modified to
-/// set) the same flag as the compare, then we can remove the comparison and use
-/// the flag from the previous instruction.
-bool OptimizeCmps::OptimizeCmpInstr(MachineInstr *MI, MachineBasicBlock *MBB) {
-  // If this instruction is a comparison against zero and isn't comparing a
-  // physical register, we can try to optimize it.
-  unsigned SrcReg;
-  int CmpValue;
-  if (!TII->AnalyzeCompare(MI, SrcReg, CmpValue) ||
-      TargetRegisterInfo::isPhysicalRegister(SrcReg) || CmpValue != 0)
-    return false;
-
-  MachineRegisterInfo::def_iterator DI = MRI->def_begin(SrcReg);
-  if (llvm::next(DI) != MRI->def_end())
-    // Only support one definition.
-    return false;
-
-  // Attempt to convert the defining instruction to set the "zero" flag.
-  if (TII->ConvertToSetZeroFlag(&*DI, MI)) {
-    ++NumEliminated;
-    return true;
-  }
-
-  return false;
-}
-
-bool OptimizeCmps::runOnMachineFunction(MachineFunction &MF) {
-  TM = &MF.getTarget();
-  TII = TM->getInstrInfo();
-  MRI = &MF.getRegInfo();
-
-  if (!EnableOptCmps) return false;
-
-  bool Changed = false;
-  for (MachineFunction::iterator I = MF.begin(), E = MF.end(); I != E; ++I) {
-    MachineBasicBlock *MBB = &*I;
-    for (MachineBasicBlock::iterator
-           MII = MBB->begin(), ME = MBB->end(); MII != ME; ) {
-      MachineInstr *MI = &*MII++;
-      if (MI->getDesc().isCompare())
-        Changed |= OptimizeCmpInstr(MI, MBB);
-    }
-  }
-
-  return Changed;
-}

lib/CodeGen/PeepholeOptimizer.cpp

@@ -1,4 +1,4 @@
-//===-- OptimizeExts.cpp - Optimize sign / zero extension instrs -----===//
+//===-- PeepholeOptimizer.cpp - Peephole Optimizations --------------------===//
 //
 //                     The LLVM Compiler Infrastructure
 //
@@ -7,17 +7,33 @@
 //
 //===----------------------------------------------------------------------===//
 //
-// This pass performs optimization of sign / zero extension instructions. It
+// Perform peephole optimizations on the machine code:
-// may be extended to handle other instructions of similar property.
 //
-// On some targets, some instructions, e.g. X86 sign / zero extension, may
+// - Optimize Extensions
-// leave the source value in the lower part of the result. This pass will
-// replace (some) uses of the pre-extension value with uses of the sub-register
-// of the results.
 //
+//     Optimization of sign / zero extension instructions. It may be extended to
+//     handle other instructions with similar properties.
+//
+//     On some targets, some instructions, e.g. X86 sign / zero extension, may
+//     leave the source value in the lower part of the result. This optimization
+//     will replace some uses of the pre-extension value with uses of the
+//     sub-register of the results.
+//
+// - Optimize Comparisons
+//
+//     Optimization of comparison instructions. For instance, in this code:
+//
+//       sub r1, 1
+//       cmp r1, 0
+//       bz  L1
+//
+//     If the "sub" instruction all ready sets (or could be modified to set) the
+//     same flag that the "cmp" instruction sets and that "bz" uses, then we can
+//     eliminate the "cmp" instruction.
+// 
 //===----------------------------------------------------------------------===//
 
-#define DEBUG_TYPE "ext-opt"
+#define DEBUG_TYPE "peephole-opt"
 #include "llvm/CodeGen/Passes.h"
 #include "llvm/CodeGen/MachineDominators.h"
 #include "llvm/CodeGen/MachineInstrBuilder.h"
@@ -29,21 +45,29 @@
 #include "llvm/ADT/Statistic.h"
 using namespace llvm;
 
-static cl::opt<bool> Aggressive("aggressive-ext-opt", cl::Hidden,
+// Optimize Extensions
-                                cl::desc("Aggressive extension optimization"));
+static cl::opt<bool>
+Aggressive("aggressive-ext-opt", cl::Hidden,
+           cl::desc("Aggressive extension optimization"));
 
 STATISTIC(NumReuse, "Number of extension results reused");
 
+// Optimize Comparisons
+static cl::opt<bool>
+EnableOptCmps("enable-optimize-cmps", cl::init(false), cl::Hidden);
+
+STATISTIC(NumEliminated, "Number of compares eliminated");
+
 namespace {
-  class OptimizeExts : public MachineFunctionPass {
+  class PeepholeOptimizer : public MachineFunctionPass {
     const TargetMachine   *TM;
     const TargetInstrInfo *TII;
-    MachineRegisterInfo *MRI;
+    MachineRegisterInfo   *MRI;
-    MachineDominatorTree *DT;   // Machine dominator tree
+    MachineDominatorTree  *DT;  // Machine dominator tree
 
   public:
     static char ID; // Pass identification
-    OptimizeExts() : MachineFunctionPass(ID) {}
+    PeepholeOptimizer() : MachineFunctionPass(ID) {}
 
     virtual bool runOnMachineFunction(MachineFunction &MF);
 
@@ -57,27 +81,32 @@ namespace {
     }
 
   private:
-    bool OptimizeInstr(MachineInstr *MI, MachineBasicBlock *MBB,
+    bool OptimizeCmpInstr(MachineInstr *MI, MachineBasicBlock *MBB);
-                       SmallPtrSet<MachineInstr*, 8> &LocalMIs);
+    bool OptimizeExtInstr(MachineInstr *MI, MachineBasicBlock *MBB,
+                          SmallPtrSet<MachineInstr*, 8> &LocalMIs);
   };
 }
 
-char OptimizeExts::ID = 0;
+char PeepholeOptimizer::ID = 0;
-INITIALIZE_PASS(OptimizeExts, "opt-exts",
+INITIALIZE_PASS(PeepholeOptimizer, "peephole-opts",
-                "Optimize sign / zero extensions", false, false);
+                "Peephole Optimizations", false, false);
 
-FunctionPass *llvm::createOptimizeExtsPass() { return new OptimizeExts(); }
+FunctionPass *llvm::createPeepholeOptimizerPass() {
+  return new PeepholeOptimizer();
+}
 
-/// OptimizeInstr - If instruction is a copy-like instruction, i.e. it reads
+/// OptimizeExtInstr - If instruction is a copy-like instruction, i.e. it reads
-/// a single register and writes a single register and it does not modify
+/// a single register and writes a single register and it does not modify the
-/// the source, and if the source value is preserved as a sub-register of
+/// source, and if the source value is preserved as a sub-register of the
-/// the result, then replace all reachable uses of the source with the subreg
+/// result, then replace all reachable uses of the source with the subreg of the
-/// of the result.
+/// result.
-/// Do not generate an EXTRACT that is used only in a debug use, as this
+/// 
-/// changes the code.  Since this code does not currently share EXTRACTs, just
+/// Do not generate an EXTRACT that is used only in a debug use, as this changes
-/// ignore all debug uses.
+/// the code. Since this code does not currently share EXTRACTs, just ignore all
-bool OptimizeExts::OptimizeInstr(MachineInstr *MI, MachineBasicBlock *MBB,
+/// debug uses.
-                                 SmallPtrSet<MachineInstr*, 8> &LocalMIs) {
+bool PeepholeOptimizer::
+OptimizeExtInstr(MachineInstr *MI, MachineBasicBlock *MBB,
+                 SmallPtrSet<MachineInstr*, 8> &LocalMIs) {
   LocalMIs.insert(MI);
 
   unsigned SrcReg, DstReg, SubIdx;
@@ -93,20 +122,21 @@ bool OptimizeExts::OptimizeInstr(MachineInstr *MI, MachineBasicBlock *MBB,
     // No other uses.
     return false;
 
-  // Ok, the source has other uses. See if we can replace the other uses
+  // The source has other uses. See if we can replace the other uses with use of
-  // with use of the result of the extension.
+  // the result of the extension.
   SmallPtrSet<MachineBasicBlock*, 4> ReachedBBs;
   UI = MRI->use_nodbg_begin(DstReg);
   for (MachineRegisterInfo::use_nodbg_iterator UE = MRI->use_nodbg_end();
        UI != UE; ++UI)
     ReachedBBs.insert(UI->getParent());
 
-  bool ExtendLife = true;
   // Uses that are in the same BB of uses of the result of the instruction.
   SmallVector<MachineOperand*, 8> Uses;
+
   // Uses that the result of the instruction can reach.
   SmallVector<MachineOperand*, 8> ExtendedUses;
 
+  bool ExtendLife = true;
   UI = MRI->use_nodbg_begin(SrcReg);
   for (MachineRegisterInfo::use_nodbg_iterator UE = MRI->use_nodbg_end();
        UI != UE; ++UI) {
@@ -114,6 +144,7 @@ bool OptimizeExts::OptimizeInstr(MachineInstr *MI, MachineBasicBlock *MBB,
     MachineInstr *UseMI = &*UI;
     if (UseMI == MI)
       continue;
+
     if (UseMI->isPHI()) {
       ExtendLife = false;
       continue;
@@ -144,15 +175,15 @@ bool OptimizeExts::OptimizeInstr(MachineInstr *MI, MachineBasicBlock *MBB,
       // Local uses that come after the extension.
       if (!LocalMIs.count(UseMI))
         Uses.push_back(&UseMO);
-    } else if (ReachedBBs.count(UseMBB))
+    } else if (ReachedBBs.count(UseMBB)) {
-      // Non-local uses where the result of extension is used. Always replace
+      // Non-local uses where the result of the extension is used. Always
-      // these unless it's a PHI.
+      // replace these unless it's a PHI.
       Uses.push_back(&UseMO);
-    else if (Aggressive && DT->dominates(MBB, UseMBB))
+    } else if (Aggressive && DT->dominates(MBB, UseMBB)) {
-      // We may want to extend live range of the extension result in order to
+      // We may want to extend the live range of the extension result in order
-      // replace these uses.
+      // to replace these uses.
       ExtendedUses.push_back(&UseMO);
-    else {
+    } else {
       // Both will be live out of the def MBB anyway. Don't extend live range of
       // the extension result.
       ExtendLife = false;
@@ -161,7 +192,7 @@ bool OptimizeExts::OptimizeInstr(MachineInstr *MI, MachineBasicBlock *MBB,
   }
 
   if (ExtendLife && !ExtendedUses.empty())
-    // Ok, we'll extend the liveness of the extension result.
+    // Extend the liveness of the extension result.
     std::copy(ExtendedUses.begin(), ExtendedUses.end(),
               std::back_inserter(Uses));
 
@@ -169,12 +200,13 @@ bool OptimizeExts::OptimizeInstr(MachineInstr *MI, MachineBasicBlock *MBB,
   bool Changed = false;
   if (!Uses.empty()) {
     SmallPtrSet<MachineBasicBlock*, 4> PHIBBs;
+
     // Look for PHI uses of the extended result, we don't want to extend the
     // liveness of a PHI input. It breaks all kinds of assumptions down
     // stream. A PHI use is expected to be the kill of its source values.
     UI = MRI->use_nodbg_begin(DstReg);
-    for (MachineRegisterInfo::use_nodbg_iterator UE = MRI->use_nodbg_end();
+    for (MachineRegisterInfo::use_nodbg_iterator
-         UI != UE; ++UI)
+           UE = MRI->use_nodbg_end(); UI != UE; ++UI)
       if (UI->isPHI())
         PHIBBs.insert(UI->getParent());
 
@@ -185,10 +217,12 @@ bool OptimizeExts::OptimizeInstr(MachineInstr *MI, MachineBasicBlock *MBB,
       MachineBasicBlock *UseMBB = UseMI->getParent();
       if (PHIBBs.count(UseMBB))
         continue;
+
       unsigned NewVR = MRI->createVirtualRegister(RC);
       BuildMI(*UseMBB, UseMI, UseMI->getDebugLoc(),
               TII->get(TargetOpcode::COPY), NewVR)
         .addReg(DstReg, 0, SubIdx);
+
       UseMO->setReg(NewVR);
       ++NumReuse;
       Changed = true;
@@ -198,11 +232,41 @@ bool OptimizeExts::OptimizeInstr(MachineInstr *MI, MachineBasicBlock *MBB,
   return Changed;
 }
 
-bool OptimizeExts::runOnMachineFunction(MachineFunction &MF) {
+/// OptimizeCmpInstr - If the instruction is a compare and the previous
-  TM = &MF.getTarget();
+/// instruction it's comparing against all ready sets (or could be modified to
+/// set) the same flag as the compare, then we can remove the comparison and use
+/// the flag from the previous instruction.
+bool PeepholeOptimizer::OptimizeCmpInstr(MachineInstr *MI,
+                                         MachineBasicBlock *MBB) {
+  if (!EnableOptCmps) return false;
+
+  // If this instruction is a comparison against zero and isn't comparing a
+  // physical register, we can try to optimize it.
+  unsigned SrcReg;
+  int CmpValue;
+  if (!TII->AnalyzeCompare(MI, SrcReg, CmpValue) ||
+      TargetRegisterInfo::isPhysicalRegister(SrcReg) || CmpValue != 0)
+    return false;
+
+  MachineRegisterInfo::def_iterator DI = MRI->def_begin(SrcReg);
+  if (llvm::next(DI) != MRI->def_end())
+    // Only support one definition.
+    return false;
+
+  // Attempt to convert the defining instruction to set the "zero" flag.
+  if (TII->ConvertToSetZeroFlag(&*DI, MI)) {
+    ++NumEliminated;
+    return true;
+  }
+
+  return false;
+}
+
+bool PeepholeOptimizer::runOnMachineFunction(MachineFunction &MF) {
+  TM  = &MF.getTarget();
   TII = TM->getInstrInfo();
   MRI = &MF.getRegInfo();
-  DT = Aggressive ? &getAnalysis<MachineDominatorTree>() : 0;
+  DT  = Aggressive ? &getAnalysis<MachineDominatorTree>() : 0;
 
   bool Changed = false;
 
@@ -210,10 +274,18 @@ bool OptimizeExts::runOnMachineFunction(MachineFunction &MF) {
   for (MachineFunction::iterator I = MF.begin(), E = MF.end(); I != E; ++I) {
     MachineBasicBlock *MBB = &*I;
     LocalMIs.clear();
-    for (MachineBasicBlock::iterator MII = I->begin(), ME = I->end(); MII != ME;
+
-         ++MII) {
+    for (MachineBasicBlock::iterator
+           MII = I->begin(), ME = I->end(); MII != ME; ) {
       MachineInstr *MI = &*MII;
-      Changed |= OptimizeInstr(MI, MBB, LocalMIs);
+
+      if (MI->getDesc().isCompare()) {
+        ++MII; // The iterator may become invalid if the compare is deleted.
+        Changed |= OptimizeCmpInstr(MI, MBB);
+      } else {
+        Changed |= OptimizeExtInstr(MI, MBB, LocalMIs);
+        ++MII;
+      }
     }
   }