[SimplifyCFG] don't sink common insts too soon (PR34603)

This should solve:
https://bugs.llvm.org/show_bug.cgi?id=34603
...by preventing SimplifyCFG from altering redundant instructions before early-cse has a chance to run.
It changes the default (canonical-forming) behavior of SimplifyCFG, so we're only doing the
sinking transform later in the optimization pipeline.

Differential Revision: https://reviews.llvm.org/D38566

llvm-svn: 320749

llvm/include/llvm/Transforms/Scalar.h

@@ -267,7 +267,7 @@ FunctionPass *createJumpThreadingPass(int Threshold = -1);
 //
 FunctionPass *createCFGSimplificationPass(
     unsigned Threshold = 1, bool ForwardSwitchCond = false,
-    bool ConvertSwitch = false, bool KeepLoops = true,
+    bool ConvertSwitch = false, bool KeepLoops = true, bool SinkCommon = false,
     std::function<bool(const Function &)> Ftor = nullptr);
 
 //===----------------------------------------------------------------------===//

llvm/include/llvm/Transforms/Scalar/SimplifyCFG.h

@@ -39,7 +39,8 @@ public:
       : SimplifyCFGPass(SimplifyCFGOptions()
                             .forwardSwitchCondToPhi(false)
                             .convertSwitchToLookupTable(false)
-                            .needCanonicalLoops(true)) {}
+                            .needCanonicalLoops(true)
+                            .sinkCommonInsts(false)) {}
 
 
   /// Construct a pass with optional optimizations.

llvm/include/llvm/Transforms/Utils/Local.h

@@ -63,16 +63,20 @@ struct SimplifyCFGOptions {
   bool ForwardSwitchCondToPhi;
   bool ConvertSwitchToLookupTable;
   bool NeedCanonicalLoop;
+  bool SinkCommonInsts;
   AssumptionCache *AC;
 
   SimplifyCFGOptions(unsigned BonusThreshold = 1,
                      bool ForwardSwitchCond = false,
                      bool SwitchToLookup = false, bool CanonicalLoops = true,
+                     bool SinkCommon = false,
                      AssumptionCache *AssumpCache = nullptr)
       : BonusInstThreshold(BonusThreshold),
         ForwardSwitchCondToPhi(ForwardSwitchCond),
         ConvertSwitchToLookupTable(SwitchToLookup),
-        NeedCanonicalLoop(CanonicalLoops), AC(AssumpCache) {}
+        NeedCanonicalLoop(CanonicalLoops),
+        SinkCommonInsts(SinkCommon),
+        AC(AssumpCache) {}
 
   // Support 'builder' pattern to set members by name at construction time.
   SimplifyCFGOptions &bonusInstThreshold(int I) {
@@ -91,6 +95,10 @@ struct SimplifyCFGOptions {
     NeedCanonicalLoop = B;
     return *this;
   }
+  SimplifyCFGOptions &sinkCommonInsts(bool B) {
+    SinkCommonInsts = B;
+    return *this;
+  }
   SimplifyCFGOptions &setAssumptionCache(AssumptionCache *Cache) {
     AC = Cache;
     return *this;

llvm/lib/Passes/PassBuilder.cpp

@@ -747,21 +747,24 @@ PassBuilder::buildModuleOptimizationPipeline(OptimizationLevel Level,
   // Cleanup after the loop optimization passes.
   OptimizePM.addPass(InstCombinePass());
 
-
   // Now that we've formed fast to execute loop structures, we do further
   // optimizations. These are run afterward as they might block doing complex
   // analyses and transforms such as what are needed for loop vectorization.
 
-  // Optimize parallel scalar instruction chains into SIMD instructions.
+  // Cleanup after loop vectorization, etc. Simplification passes like CVP and
-  OptimizePM.addPass(SLPVectorizerPass());
-
-  // Cleanup after all of the vectorizers. Simplification passes like CVP and
   // GVN, loop transforms, and others have already run, so it's now better to
   // convert to more optimized IR using more aggressive simplify CFG options.
+  // The extra sinking transform can create larger basic blocks, so do this
+  // before SLP vectorization.
   OptimizePM.addPass(SimplifyCFGPass(SimplifyCFGOptions().
                                      forwardSwitchCondToPhi(true).
                                      convertSwitchToLookupTable(true).
-                                         needCanonicalLoops(false)));
+                                     needCanonicalLoops(false).
+                                     sinkCommonInsts(true)));
+
+  // Optimize parallel scalar instruction chains into SIMD instructions.
+  OptimizePM.addPass(SLPVectorizerPass());
+
   OptimizePM.addPass(InstCombinePass());
 
   // Unroll small loops to hide loop backedge latency and saturate any parallel

llvm/lib/Target/AArch64/AArch64TargetMachine.cpp

@@ -365,7 +365,7 @@ void AArch64PassConfig::addIRPasses() {
   // determine whether it succeeded. We can exploit existing control-flow in
   // ldrex/strex loops to simplify this, but it needs tidying up.
   if (TM->getOptLevel() != CodeGenOpt::None && EnableAtomicTidy)
-    addPass(createCFGSimplificationPass(1, true, true, false));
+    addPass(createCFGSimplificationPass(1, true, true, false, true));
 
   // Run LoopDataPrefetch
   //

llvm/lib/Target/ARM/ARMTargetMachine.cpp

@@ -385,7 +385,7 @@ void ARMPassConfig::addIRPasses() {
   // ldrex/strex loops to simplify this, but it needs tidying up.
   if (TM->getOptLevel() != CodeGenOpt::None && EnableAtomicTidy)
     addPass(createCFGSimplificationPass(
-        1, false, false, true, [this](const Function &F) {
+        1, false, false, true, true, [this](const Function &F) {
           const auto &ST = this->TM->getSubtarget<ARMSubtarget>(F);
           return ST.hasAnyDataBarrier() && !ST.isThumb1Only();
         }));

llvm/lib/Transforms/IPO/PassManagerBuilder.cpp

@@ -630,6 +630,13 @@ void PassManagerBuilder::populateModulePassManager(
     addInstructionCombiningPass(MPM);
   }
 
+  // Cleanup after loop vectorization, etc. Simplification passes like CVP and
+  // GVN, loop transforms, and others have already run, so it's now better to
+  // convert to more optimized IR using more aggressive simplify CFG options.
+  // The extra sinking transform can create larger basic blocks, so do this
+  // before SLP vectorization.
+  MPM.add(createCFGSimplificationPass(1, true, true, false, true));
+
   if (RunSLPAfterLoopVectorization && SLPVectorize) {
     MPM.add(createSLPVectorizerPass()); // Vectorize parallel scalar chains.
     if (OptLevel > 1 && ExtraVectorizerPasses) {
@@ -638,9 +645,6 @@ void PassManagerBuilder::populateModulePassManager(
   }
 
   addExtensionsToPM(EP_Peephole, MPM);
-  // Switches to lookup tables and other transforms that may not be considered
-  // canonical by other IR passes.
-  MPM.add(createCFGSimplificationPass(1, true, true, false));
   addInstructionCombiningPass(MPM);
 
   if (!DisableUnrollLoops) {

llvm/lib/Transforms/Scalar/SimplifyCFGPass.cpp

@@ -61,6 +61,11 @@ static cl::opt<bool> UserForwardSwitchCond(
     "forward-switch-cond", cl::Hidden, cl::init(false),
     cl::desc("Forward switch condition to phi ops (default = false)"));
 
+static cl::opt<bool> UserSinkCommonInsts(
+    "sink-common-insts", cl::Hidden, cl::init(false),
+    cl::desc("Sink common instructions (default = false)"));
+
+
 STATISTIC(NumSimpl, "Number of blocks simplified");
 
 /// If we have more than one empty (other than phi node) return blocks,
@@ -205,6 +210,9 @@ SimplifyCFGPass::SimplifyCFGPass(const SimplifyCFGOptions &Opts) {
   Options.NeedCanonicalLoop = UserKeepLoops.getNumOccurrences()
                                   ? UserKeepLoops
                                   : Opts.NeedCanonicalLoop;
+  Options.SinkCommonInsts = UserSinkCommonInsts.getNumOccurrences()
+                                ? UserSinkCommonInsts
+                                : Opts.SinkCommonInsts;
 }
 
 PreservedAnalyses SimplifyCFGPass::run(Function &F,
@@ -226,6 +234,7 @@ struct CFGSimplifyPass : public FunctionPass {
 
   CFGSimplifyPass(unsigned Threshold = 1, bool ForwardSwitchCond = false,
                   bool ConvertSwitch = false, bool KeepLoops = true,
+                  bool SinkCommon = false,
                   std::function<bool(const Function &)> Ftor = nullptr)
       : FunctionPass(ID), PredicateFtor(std::move(Ftor)) {
 
@@ -246,6 +255,10 @@ struct CFGSimplifyPass : public FunctionPass {
 
     Options.NeedCanonicalLoop =
         UserKeepLoops.getNumOccurrences() ? UserKeepLoops : KeepLoops;
+
+    Options.SinkCommonInsts = UserSinkCommonInsts.getNumOccurrences()
+                                  ? UserSinkCommonInsts
+                                  : SinkCommon;
   }
 
   bool runOnFunction(Function &F) override {
@@ -276,7 +289,8 @@ INITIALIZE_PASS_END(CFGSimplifyPass, "simplifycfg", "Simplify the CFG", false,
 FunctionPass *
 llvm::createCFGSimplificationPass(unsigned Threshold, bool ForwardSwitchCond,
                                   bool ConvertSwitch, bool KeepLoops,
+                                  bool SinkCommon,
                                   std::function<bool(const Function &)> Ftor) {
   return new CFGSimplifyPass(Threshold, ForwardSwitchCond, ConvertSwitch,
-                             KeepLoops, std::move(Ftor));
+                             KeepLoops, SinkCommon, std::move(Ftor));
 }

llvm/lib/Transforms/Utils/SimplifyCFG.cpp

@@ -5728,7 +5728,7 @@ bool SimplifyCFGOpt::SimplifyUncondBranch(BranchInst *BI,
   BasicBlock *BB = BI->getParent();
   BasicBlock *Succ = BI->getSuccessor(0);
 
-  if (SinkCommon && SinkThenElseCodeToEnd(BI))
+  if (SinkCommon && Options.SinkCommonInsts && SinkThenElseCodeToEnd(BI))
     return true;
 
   // If the Terminator is the only non-phi instruction, simplify the block.

llvm/test/DebugInfo/Generic/simplifycfg_sink_last_inst.ll

@@ -1,4 +1,4 @@
-; RUN: opt -simplifycfg -S < %s | FileCheck %s
+; RUN: opt -simplifycfg -sink-common-insts -S < %s | FileCheck %s
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"

llvm/test/Other/new-pm-defaults.ll

@@ -197,8 +197,8 @@
 ; CHECK-O-NEXT: Running pass: LoopLoadEliminationPass
 ; CHECK-O-NEXT: Running analysis: LoopAccessAnalysis
 ; CHECK-O-NEXT: Running pass: InstCombinePass
-; CHECK-O-NEXT: Running pass: SLPVectorizerPass
 ; CHECK-O-NEXT: Running pass: SimplifyCFGPass
+; CHECK-O-NEXT: Running pass: SLPVectorizerPass
 ; CHECK-O-NEXT: Running pass: InstCombinePass
 ; CHECK-O-NEXT: Running pass: LoopUnrollPass
 ; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy

llvm/test/Other/new-pm-thinlto-defaults.ll

@@ -185,8 +185,8 @@
 ; CHECK-POSTLINK-O-NEXT: Running pass: LoopLoadEliminationPass
 ; CHECK-POSTLINK-O-NEXT: Running analysis: LoopAccessAnalysis
 ; CHECK-POSTLINK-O-NEXT: Running pass: InstCombinePass
-; CHECK-POSTLINK-O-NEXT: Running pass: SLPVectorizerPass
 ; CHECK-POSTLINK-O-NEXT: Running pass: SimplifyCFGPass
+; CHECK-POSTLINK-O-NEXT: Running pass: SLPVectorizerPass
 ; CHECK-POSTLINK-O-NEXT: Running pass: InstCombinePass
 ; CHECK-POSTLINK-O-NEXT: Running pass: LoopUnrollPass
 ; CHECK-POSTLINK-O-NEXT: Running analysis: OuterAnalysisManagerProxy

llvm/test/Transforms/PhaseOrdering/simplifycfg-options.ll

@@ -76,10 +76,8 @@ define double @max_of_loads(double* %x, double* %y, i64 %i) {
 ; ALL-NEXT:    [[XI:%.*]] = load double, double* [[XI_PTR]], align 8
 ; ALL-NEXT:    [[YI:%.*]] = load double, double* [[YI_PTR]], align 8
 ; ALL-NEXT:    [[CMP:%.*]] = fcmp ogt double [[XI]], [[YI]]
-; ALL-NEXT:    [[Y_SINK:%.*]] = select i1 [[CMP]], double* [[X]], double* [[Y]]
+; ALL-NEXT:    [[XI_YI:%.*]] = select i1 [[CMP]], double [[XI]], double [[YI]]
-; ALL-NEXT:    [[YI_PTR_AGAIN:%.*]] = getelementptr double, double* [[Y_SINK]], i64 [[I]]
+; ALL-NEXT:    ret double [[XI_YI]]
-; ALL-NEXT:    [[YI_AGAIN:%.*]] = load double, double* [[YI_PTR_AGAIN]], align 8
-; ALL-NEXT:    ret double [[YI_AGAIN]]
 ;
 entry:
   %xi_ptr = getelementptr double, double* %x, i64 %i

llvm/test/Transforms/SimplifyCFG/no-md-sink.ll

@@ -1,4 +1,4 @@
-; RUN: opt < %s -simplifycfg -S | FileCheck %s
+; RUN: opt < %s -simplifycfg -sink-common-insts -S | FileCheck %s
 
 define i1 @test1(i1 zeroext %flag, i8* %y) #0 {
 entry:

llvm/test/Transforms/SimplifyCFG/sink-common-code.ll

@@ -1,4 +1,4 @@
-; RUN: opt < %s -simplifycfg -S | FileCheck -enable-var-scope %s
+; RUN: opt < %s -simplifycfg -sink-common-insts -S | FileCheck -enable-var-scope %s
 
 define zeroext i1 @test1(i1 zeroext %flag, i32 %blksA, i32 %blksB, i32 %nblks) {
 entry: