[PowerPC] exclude ICmpZero in LSR if icmp can be replaced in later hardware loop.

  
Differential Revision: https://reviews.llvm.org/D63477

llvm-svn: 364993

4 files changed, 58 insertions, 7 deletions

diff --git a/llvm/lib/Analysis/TargetTransformInfo.cpp b/llvm/lib/Analysis/TargetTransformInfo.cpp
index 6dbdaeeae5f..50c5ae9c19f 100644
--- a/llvm/lib/Analysis/TargetTransformInfo.cpp
+++ b/llvm/lib/Analysis/TargetTransformInfo.cpp
@@ -264,6 +264,13 @@ bool TargetTransformInfo::canMacroFuseCmp() const {
   return TTIImpl->canMacroFuseCmp();
 }
 
+bool TargetTransformInfo::canSaveCmp(Loop *L, BranchInst **BI,
+                                     ScalarEvolution *SE, LoopInfo *LI,
+                                     DominatorTree *DT, AssumptionCache *AC,
+                                     TargetLibraryInfo *LibInfo) const {
+  return TTIImpl->canSaveCmp(L, BI, SE, LI, DT, AC, LibInfo);
+}
+
 bool TargetTransformInfo::shouldFavorPostInc() const {
   return TTIImpl->shouldFavorPostInc();
 }
diff --git a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
index 5d791a76610..ff3dfbfaca0 100644
--- a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
+++ b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
@@ -875,3 +875,25 @@ int PPCTTIImpl::getInterleavedMemoryOpCost(unsigned Opcode, Type *VecTy,
   return Cost;
 }
 
+bool PPCTTIImpl::canSaveCmp(Loop *L, BranchInst **BI, ScalarEvolution *SE,
+                            LoopInfo *LI, DominatorTree *DT,
+                            AssumptionCache *AC, TargetLibraryInfo *LibInfo) {
+  // Process nested loops first.
+  for (Loop::iterator I = L->begin(), E = L->end(); I != E; ++I)
+    if (canSaveCmp(*I, BI, SE, LI, DT, AC, LibInfo))
+      return false; // Stop search.
+
+  HardwareLoopInfo HWLoopInfo(L);
+
+  if (!HWLoopInfo.canAnalyze(*LI))
+    return false;
+
+  if (!isHardwareLoopProfitable(L, *SE, *AC, LibInfo, HWLoopInfo))
+    return false;
+
+  if (!HWLoopInfo.isHardwareLoopCandidate(*SE, *LI, *DT))
+    return false;
+
+  *BI = HWLoopInfo.ExitBranch;
+  return true;
+}
diff --git a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.h b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.h
index 047f2e34e85..5d76ee418b6 100644
--- a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.h
+++ b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.h
@@ -57,6 +57,9 @@ public:
                                 AssumptionCache &AC,
                                 TargetLibraryInfo *LibInfo,
                                 HardwareLoopInfo &HWLoopInfo);
+  bool canSaveCmp(Loop *L, BranchInst **BI, ScalarEvolution *SE, LoopInfo *LI,
+                  DominatorTree *DT, AssumptionCache *AC,
+                  TargetLibraryInfo *LibInfo);
   void getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
                                TTI::UnrollingPreferences &UP);
 
diff --git a/llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp b/llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp
index 768860140e6..987d5a0f30c 100644
--- a/llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp
+++ b/llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp
@@ -1909,6 +1909,8 @@ class LSRInstance {
   ScalarEvolution &SE;
   DominatorTree &DT;
   LoopInfo &LI;
+  AssumptionCache ∾
+  TargetLibraryInfo &LibInfo;
   const TargetTransformInfo &TTI;
   Loop *const L;
   bool FavorBackedgeIndex = false;
@@ -2047,7 +2049,8 @@ class LSRInstance {
 
 public:
   LSRInstance(Loop *L, IVUsers &IU, ScalarEvolution &SE, DominatorTree &DT,
-              LoopInfo &LI, const TargetTransformInfo &TTI);
+              LoopInfo &LI, const TargetTransformInfo &TTI, AssumptionCache &AC,
+              TargetLibraryInfo &LibInfo);
 
   bool getChanged() const { return Changed; }
 
@@ -3232,6 +3235,9 @@ void LSRInstance::GenerateIVChain(const IVChain &Chain, SCEVExpander &Rewriter,
 }
 
 void LSRInstance::CollectFixupsAndInitialFormulae() {
+  BranchInst *ExitBranch = nullptr;
+  bool SaveCmp = TTI.canSaveCmp(L, &ExitBranch, &SE, &LI, &DT, &AC, &LibInfo);
+
   for (const IVStrideUse &U : IU) {
     Instruction *UserInst = U.getUser();
     // Skip IV users that are part of profitable IV Chains.
@@ -3261,6 +3267,10 @@ void LSRInstance::CollectFixupsAndInitialFormulae() {
     // equality icmps, thanks to IndVarSimplify.
     if (ICmpInst *CI = dyn_cast<ICmpInst>(UserInst))
       if (CI->isEquality()) {
+        // If CI can be saved in some target, like replaced inside hardware loop
+        // in PowerPC, no need to generate initial formulae for it.
+        if (SaveCmp && CI == cast<ICmpInst>(ExitBranch->getCondition()))
+          continue;
         // Swap the operands if needed to put the OperandValToReplace on the
         // left, for consistency.
         Value *NV = CI->getOperand(1);
@@ -5479,8 +5489,9 @@ void LSRInstance::ImplementSolution(
 
 LSRInstance::LSRInstance(Loop *L, IVUsers &IU, ScalarEvolution &SE,
                          DominatorTree &DT, LoopInfo &LI,
-                         const TargetTransformInfo &TTI)
-    : IU(IU), SE(SE), DT(DT), LI(LI), TTI(TTI), L(L),
+                         const TargetTransformInfo &TTI, AssumptionCache &AC,
+                         TargetLibraryInfo &LibInfo)
+    : IU(IU), SE(SE), DT(DT), LI(LI), AC(AC), LibInfo(LibInfo), TTI(TTI), L(L),
       FavorBackedgeIndex(EnableBackedgeIndexing &&
                          TTI.shouldFavorBackedgeIndex(L)) {
   // If LoopSimplify form is not available, stay out of trouble.
@@ -5677,6 +5688,8 @@ void LoopStrengthReduce::getAnalysisUsage(AnalysisUsage &AU) const {
   AU.addPreserved<DominatorTreeWrapperPass>();
   AU.addRequired<ScalarEvolutionWrapperPass>();
   AU.addPreserved<ScalarEvolutionWrapperPass>();
+  AU.addRequired<AssumptionCacheTracker>();
+  AU.addRequired<TargetLibraryInfoWrapperPass>();
   // Requiring LoopSimplify a second time here prevents IVUsers from running
   // twice, since LoopSimplify was invalidated by running ScalarEvolution.
   AU.addRequiredID(LoopSimplifyID);
@@ -5687,11 +5700,14 @@ void LoopStrengthReduce::getAnalysisUsage(AnalysisUsage &AU) const {
 
 static bool ReduceLoopStrength(Loop *L, IVUsers &IU, ScalarEvolution &SE,
                                DominatorTree &DT, LoopInfo &LI,
-                               const TargetTransformInfo &TTI) {
+                               const TargetTransformInfo &TTI,
+                               AssumptionCache &AC,
+                               TargetLibraryInfo &LibInfo) {
+
   bool Changed = false;
 
   // Run the main LSR transformation.
-  Changed |= LSRInstance(L, IU, SE, DT, LI, TTI).getChanged();
+  Changed |= LSRInstance(L, IU, SE, DT, LI, TTI, AC, LibInfo).getChanged();
 
   // Remove any extra phis created by processing inner loops.
   Changed |= DeleteDeadPHIs(L->getHeader());
@@ -5722,14 +5738,17 @@ bool LoopStrengthReduce::runOnLoop(Loop *L, LPPassManager & /*LPM*/) {
   auto &LI = getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
   const auto &TTI = getAnalysis<TargetTransformInfoWrapperPass>().getTTI(
       *L->getHeader()->getParent());
-  return ReduceLoopStrength(L, IU, SE, DT, LI, TTI);
+  auto &AC = getAnalysis<AssumptionCacheTracker>().getAssumptionCache(
+      *L->getHeader()->getParent());
+  auto &LibInfo = getAnalysis<TargetLibraryInfoWrapperPass>().getTLI();
+  return ReduceLoopStrength(L, IU, SE, DT, LI, TTI, AC, LibInfo);
 }
 
 PreservedAnalyses LoopStrengthReducePass::run(Loop &L, LoopAnalysisManager &AM,
                                               LoopStandardAnalysisResults &AR,
                                               LPMUpdater &) {
   if (!ReduceLoopStrength(&L, AM.getResult<IVUsersAnalysis>(L, AR), AR.SE,
-                          AR.DT, AR.LI, AR.TTI))
+                          AR.DT, AR.LI, AR.TTI, AR.AC, AR.TLI))
     return PreservedAnalyses::all();
 
   return getLoopPassPreservedAnalyses();