[NewPM] Port -separate-const-offset-from-gep

llvm/include/llvm/InitializePasses.h

 void initializeSafepointIRVerifierPass(PassRegistry&);
 void initializeSampleProfileLoaderLegacyPassPass(PassRegistry&);
 void initializeModuleSanitizerCoverageLegacyPassPass(PassRegistry &);
 void initializeScalarEvolutionWrapperPassPass(PassRegistry&);
 void initializeScalarizeMaskedMemIntrinPass(PassRegistry&);
 void initializeScalarizerLegacyPassPass(PassRegistry&);
 void initializeScavengerTestPass(PassRegistry&);
 void initializeScopedNoAliasAAWrapperPassPass(PassRegistry&);
-void initializeSeparateConstOffsetFromGEPPass(PassRegistry&);
+void initializeSeparateConstOffsetFromGEPLegacyPassPass(PassRegistry &);
 void initializeShadowStackGCLoweringPass(PassRegistry&);
 void initializeShrinkWrapPass(PassRegistry&);
 void initializeSimpleInlinerPass(PassRegistry&);
 void initializeSimpleLoopUnswitchLegacyPassPass(PassRegistry&);
 void initializeSingleLoopExtractorPass(PassRegistry&);
 void initializeSinkingLegacyPassPass(PassRegistry&);
 void initializeSjLjEHPreparePass(PassRegistry&);
 void initializeSlotIndexesPass(PassRegistry&);

llvm/include/llvm/Transforms/Scalar/SeparateConstOffsetFromGEP.h

+//===- SeparateConstOffsetFromGEP.h ---------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_TRANSFORMS_SCALAR_SEPARATECONSTOFFSETFROMGEP_H
+#define LLVM_TRANSFORMS_SCALAR_SEPARATECONSTOFFSETFROMGEP_H
+
+#include "llvm/IR/PassManager.h"
+
+namespace llvm {
+
+class SeparateConstOffsetFromGEPPass
+    : public PassInfoMixin<SeparateConstOffsetFromGEPPass> {
+  bool LowerGEP;
+
+public:
+  SeparateConstOffsetFromGEPPass(bool LowerGEP = false) : LowerGEP(LowerGEP) {}
+  PreservedAnalyses run(Function &F, FunctionAnalysisManager &);
+};
+
+} // end namespace llvm
+
+#endif // LLVM_TRANSFORMS_SCALAR_SEPARATECONSTOFFSETFROMGEP_H

llvm/lib/Passes/PassBuilder.cpp

 #include "llvm/Transforms/Scalar/NewGVN.h"
 #include "llvm/Transforms/Scalar/PartiallyInlineLibCalls.h"
 #include "llvm/Transforms/Scalar/Reassociate.h"
 #include "llvm/Transforms/Scalar/Reg2Mem.h"
 #include "llvm/Transforms/Scalar/RewriteStatepointsForGC.h"
 #include "llvm/Transforms/Scalar/SCCP.h"
 #include "llvm/Transforms/Scalar/SROA.h"
 #include "llvm/Transforms/Scalar/Scalarizer.h"
+#include "llvm/Transforms/Scalar/SeparateConstOffsetFromGEP.h"
 #include "llvm/Transforms/Scalar/SimpleLoopUnswitch.h"
 #include "llvm/Transforms/Scalar/SimplifyCFG.h"
 #include "llvm/Transforms/Scalar/Sink.h"
 #include "llvm/Transforms/Scalar/SpeculateAroundPHIs.h"
 #include "llvm/Transforms/Scalar/SpeculativeExecution.h"
 #include "llvm/Transforms/Scalar/StraightLineStrengthReduce.h"
 #include "llvm/Transforms/Scalar/StructurizeCFG.h"
 #include "llvm/Transforms/Scalar/TailRecursionElimination.h"

llvm/lib/Passes/PassRegistry.def

 FUNCTION_PASS("print<stack-safety-local>", StackSafetyPrinterPass(dbgs()))
 // TODO: rename to print<foo> after NPM switch
 FUNCTION_PASS("print-alias-sets", AliasSetsPrinterPass(dbgs()))
 FUNCTION_PASS("print-predicateinfo", PredicateInfoPrinterPass(dbgs()))
 FUNCTION_PASS("print-mustexecute", MustExecutePrinterPass(dbgs()))
 FUNCTION_PASS("reassociate", ReassociatePass())
 FUNCTION_PASS("reg2mem", RegToMemPass())
 FUNCTION_PASS("scalarizer", ScalarizerPass())
+FUNCTION_PASS("separate-const-offset-from-gep", SeparateConstOffsetFromGEPPass())
 FUNCTION_PASS("sccp", SCCPPass())
 FUNCTION_PASS("simplifycfg", SimplifyCFGPass())
 FUNCTION_PASS("sink", SinkingPass())
 FUNCTION_PASS("slp-vectorizer", SLPVectorizerPass())
 FUNCTION_PASS("slsr", StraightLineStrengthReducePass())
 FUNCTION_PASS("speculative-execution", SpeculativeExecutionPass())
 FUNCTION_PASS("spec-phis", SpeculateAroundPHIsPass())
 FUNCTION_PASS("sroa", SROA())

llvm/lib/Transforms/Scalar/Scalar.cpp

void llvm::initializeScalarOpts(PassRegistry &Registry) {
   initializeRewriteStatepointsForGCLegacyPassPass(Registry);
   initializeSCCPLegacyPassPass(Registry);
   initializeSROALegacyPassPass(Registry);
   initializeCFGSimplifyPassPass(Registry);
   initializeStructurizeCFGLegacyPassPass(Registry);
   initializeSimpleLoopUnswitchLegacyPassPass(Registry);
   initializeSinkingLegacyPassPass(Registry);
   initializeTailCallElimPass(Registry);
-  initializeSeparateConstOffsetFromGEPPass(Registry);
+  initializeSeparateConstOffsetFromGEPLegacyPassPass(Registry);
   initializeSpeculativeExecutionLegacyPassPass(Registry);
   initializeStraightLineStrengthReduceLegacyPassPass(Registry);
   initializePlaceBackedgeSafepointsImplPass(Registry);
   initializePlaceSafepointsPass(Registry);
   initializeFloat2IntLegacyPassPass(Registry);
   initializeLoopDistributeLegacyPass(Registry);
   initializeLoopLoadEliminationPass(Registry);
   initializeLoopSimplifyCFGLegacyPassPass(Registry);

llvm/lib/Transforms/Scalar/SeparateConstOffsetFromGEP.cpp

 // parts and variant parts, LICM can hoist/sink those invariant parts.
 // CGP (CodeGen Prepare) tries to sink address calculations that match the
 // target's addressing modes. A GEP with multiple indices may not match and will
 // not be sunk. If we lower such GEP into smaller parts, CGP may sink some of
 // them. So we end up with a better addressing mode.
 //
 //===----------------------------------------------------------------------===//
 
+#include "llvm/Transforms/Scalar/SeparateConstOffsetFromGEP.h"
 #include "llvm/ADT/APInt.h"
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/DepthFirstIterator.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/Analysis/LoopInfo.h"
 #include "llvm/Analysis/MemoryBuiltins.h"
 #include "llvm/Analysis/ScalarEvolution.h"
 #include "llvm/Analysis/TargetLibraryInfo.h"
 #include "llvm/Analysis/TargetTransformInfo.h"
 #include "llvm/Analysis/ValueTracking.h"
 #include "llvm/IR/BasicBlock.h"
 #include "llvm/IR/Constant.h"
 #include "llvm/IR/Constants.h"
 #include "llvm/IR/DataLayout.h"
 #include "llvm/IR/DerivedTypes.h"
 #include "llvm/IR/Dominators.h"
 #include "llvm/IR/Function.h"
 #include "llvm/IR/GetElementPtrTypeIterator.h"
 #include "llvm/IR/IRBuilder.h"
 #include "llvm/IR/Instruction.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/Module.h"
+#include "llvm/IR/PassManager.h"
 #include "llvm/IR/PatternMatch.h"
 #include "llvm/IR/Type.h"
 #include "llvm/IR/User.h"
 #include "llvm/IR/Value.h"
 #include "llvm/InitializePasses.h"
 #include "llvm/Pass.h"
 #include "llvm/Support/Casting.h"
 #include "llvm/Support/CommandLine.h"
private:
 
   const DataLayout &DL;
   const DominatorTree *DT;
 };
 
 /// A pass that tries to split every GEP in the function into a variadic
 /// base and a constant offset. It is a FunctionPass because searching for the
 /// constant offset may inspect other basic blocks.
-class SeparateConstOffsetFromGEP : public FunctionPass {
+class SeparateConstOffsetFromGEPLegacyPass : public FunctionPass {
 public:
   static char ID;
 
-  SeparateConstOffsetFromGEP(bool LowerGEP = false)
+  SeparateConstOffsetFromGEPLegacyPass(bool LowerGEP = false)
       : FunctionPass(ID), LowerGEP(LowerGEP) {
-    initializeSeparateConstOffsetFromGEPPass(*PassRegistry::getPassRegistry());
+    initializeSeparateConstOffsetFromGEPLegacyPassPass(
+        *PassRegistry::getPassRegistry());
   }
 
   void getAnalysisUsage(AnalysisUsage &AU) const override {
     AU.addRequired<DominatorTreeWrapperPass>();
     AU.addRequired<ScalarEvolutionWrapperPass>();
     AU.addRequired<TargetTransformInfoWrapperPass>();
     AU.addRequired<LoopInfoWrapperPass>();
     AU.setPreservesCFG();
     AU.addRequired<TargetLibraryInfoWrapperPass>();
   }
 
-  bool doInitialization(Module &M) override {
-    DL = &M.getDataLayout();
-    return false;
-  }
-
   bool runOnFunction(Function &F) override;
 
 private:
+  bool LowerGEP;
+};
+
+/// A pass that tries to split every GEP in the function into a variadic
+/// base and a constant offset. It is a FunctionPass because searching for the
+/// constant offset may inspect other basic blocks.
+class SeparateConstOffsetFromGEP {
+public:
+  SeparateConstOffsetFromGEP(
+      DominatorTree *DT, ScalarEvolution *SE, LoopInfo *LI,
+      TargetLibraryInfo *TLI,
+      function_ref<TargetTransformInfo &(Function &)> GetTTI, bool LowerGEP)
+      : DT(DT), SE(SE), LI(LI), TLI(TLI), GetTTI(GetTTI), LowerGEP(LowerGEP) {}
+
+  bool run(Function &F);
+
+private:
   /// Tries to split the given GEP into a variadic base and a constant offset,
   /// and returns true if the splitting succeeds.
   bool splitGEP(GetElementPtrInst *GEP);
 
   /// Lower a GEP with multiple indices into multiple GEPs with a single index.
   /// Function splitGEP already split the original GEP into a variadic part and
   /// a constant offset (i.e., AccumulativeByteOffset). This function lowers the
   /// variadic part into a set of GEPs with a single index and applies
private:
 
   // Check if it is safe to swap operand of two GEP.
   bool isLegalToSwapOperand(GetElementPtrInst *First, GetElementPtrInst *Second,
                             Loop *CurLoop);
 
   const DataLayout *DL = nullptr;
   DominatorTree *DT = nullptr;
   ScalarEvolution *SE;
-
   LoopInfo *LI;
   TargetLibraryInfo *TLI;
+  // Retrieved lazily since not always used.
+  function_ref<TargetTransformInfo &(Function &)> GetTTI;
 
   /// Whether to lower a GEP with multiple indices into arithmetic operations or
   /// multiple GEPs with a single index.
   bool LowerGEP;
 
   DenseMap<const SCEV *, SmallVector<Instruction *, 2>> DominatingAdds;
   DenseMap<const SCEV *, SmallVector<Instruction *, 2>> DominatingSubs;
 };
 
 } // end anonymous namespace
 
-char SeparateConstOffsetFromGEP::ID = 0;
+char SeparateConstOffsetFromGEPLegacyPass::ID = 0;
 
 INITIALIZE_PASS_BEGIN(
-    SeparateConstOffsetFromGEP, "separate-const-offset-from-gep",
+    SeparateConstOffsetFromGEPLegacyPass, "separate-const-offset-from-gep",
     "Split GEPs to a variadic base and a constant offset for better CSE", false,
     false)
 INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
 INITIALIZE_PASS_DEPENDENCY(ScalarEvolutionWrapperPass)
 INITIALIZE_PASS_DEPENDENCY(TargetTransformInfoWrapperPass)
 INITIALIZE_PASS_DEPENDENCY(LoopInfoWrapperPass)
 INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
 INITIALIZE_PASS_END(
-    SeparateConstOffsetFromGEP, "separate-const-offset-from-gep",
+    SeparateConstOffsetFromGEPLegacyPass, "separate-const-offset-from-gep",
     "Split GEPs to a variadic base and a constant offset for better CSE", false,
     false)
 
 FunctionPass *llvm::createSeparateConstOffsetFromGEPPass(bool LowerGEP) {
-  return new SeparateConstOffsetFromGEP(LowerGEP);
+  return new SeparateConstOffsetFromGEPLegacyPass(LowerGEP);
 }
 
 bool ConstantOffsetExtractor::CanTraceInto(bool SignExtended,
                                             bool ZeroExtended,
                                             BinaryOperator *BO,
                                             bool NonNegative) {
   // We only consider ADD, SUB and OR, because a non-zero constant found in
   // expressions composed of these operations can be easily hoisted as a
bool SeparateConstOffsetFromGEP::splitGEP(GetElementPtrInst *GEP) {
   bool Changed = canonicalizeArrayIndicesToPointerSize(GEP);
 
   bool NeedsExtraction;
   int64_t AccumulativeByteOffset = accumulateByteOffset(GEP, NeedsExtraction);
 
   if (!NeedsExtraction)
     return Changed;
 
-  TargetTransformInfo &TTI =
-      getAnalysis<TargetTransformInfoWrapperPass>().getTTI(*GEP->getFunction());
+  TargetTransformInfo &TTI = GetTTI(*GEP->getFunction());
 
   // If LowerGEP is disabled, before really splitting the GEP, check whether the
   // backend supports the addressing mode we are about to produce. If no, this
   // splitting probably won't be beneficial.
   // If LowerGEP is enabled, even the extracted constant offset can not match
   // the addressing mode, we can still do optimizations to other lowered parts
   // of variable indices. Therefore, we don't check for addressing modes in that
   // case.
bool SeparateConstOffsetFromGEP::splitGEP(GetElementPtrInst *GEP) {
   }
 
   GEP->replaceAllUsesWith(NewGEP);
   GEP->eraseFromParent();
 
   return true;
 }
 
-bool SeparateConstOffsetFromGEP::runOnFunction(Function &F) {
+bool SeparateConstOffsetFromGEPLegacyPass::runOnFunction(Function &F) {
   if (skipFunction(F))
     return false;
+  auto *DT = &getAnalysis<DominatorTreeWrapperPass>().getDomTree();
+  auto *SE = &getAnalysis<ScalarEvolutionWrapperPass>().getSE();
+  auto *LI = &getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
+  auto *TLI = &getAnalysis<TargetLibraryInfoWrapperPass>().getTLI(F);
+  auto GetTTI = [this](Function &F) -> TargetTransformInfo & {
+    return this->getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
+  };
+  SeparateConstOffsetFromGEP Impl(DT, SE, LI, TLI, GetTTI, LowerGEP);
+  return Impl.run(F);
+}
 
+bool SeparateConstOffsetFromGEP::run(Function &F) {
   if (DisableSeparateConstOffsetFromGEP)
     return false;
 
-  DT = &getAnalysis<DominatorTreeWrapperPass>().getDomTree();
-  SE = &getAnalysis<ScalarEvolutionWrapperPass>().getSE();
-  LI = &getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
-  TLI = &getAnalysis<TargetLibraryInfoWrapperPass>().getTLI(F);
+  DL = &F.getParent()->getDataLayout();
   bool Changed = false;
   for (BasicBlock &B : F) {
     for (BasicBlock::iterator I = B.begin(), IE = B.end(); I != IE;)
       if (GetElementPtrInst *GEP = dyn_cast<GetElementPtrInst>(I++))
         Changed |= splitGEP(GEP);
     // No need to split GEP ConstantExprs because all its indices are constant
     // already.
   }
void SeparateConstOffsetFromGEP::swapGEPOperand(GetElementPtrInst *First,
   uint64_t ObjectSize;
   if (!getObjectSize(NewBase, ObjectSize, DAL, TLI) ||
      Offset.ugt(ObjectSize)) {
     First->setIsInBounds(false);
     Second->setIsInBounds(false);
   } else
     First->setIsInBounds(true);
 }
+
+PreservedAnalyses
+SeparateConstOffsetFromGEPPass::run(Function &F, FunctionAnalysisManager &AM) {
+  auto *DT = &AM.getResult<DominatorTreeAnalysis>(F);
+  auto *SE = &AM.getResult<ScalarEvolutionAnalysis>(F);
+  auto *LI = &AM.getResult<LoopAnalysis>(F);
+  auto *TLI = &AM.getResult<TargetLibraryAnalysis>(F);
+  auto GetTTI = [&AM](Function &F) -> TargetTransformInfo & {
+    return AM.getResult<TargetIRAnalysis>(F);
+  };
+  SeparateConstOffsetFromGEP Impl(DT, SE, LI, TLI, GetTTI, LowerGEP);
+  if (!Impl.run(F))
+    return PreservedAnalyses::all();
+  PreservedAnalyses PA;
+  PA.preserveSet<CFGAnalyses>();
+  return PA;
+}

llvm/test/Transforms/SeparateConstOffsetFromGEP/test-add-sub-separation.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -S -separate-const-offset-from-gep < %s | FileCheck %s
+; RUN: opt -S -passes=separate-const-offset-from-gep < %s | FileCheck %s
 
 define void @matchingExtensions(i32* %ap, i32* %bp, i64* %result) {
 ; CHECK-LABEL: @matchingExtensions(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[A:%.*]] = load i32, i32* [[AP:%.*]], align 4
 ; CHECK-NEXT:    [[B:%.*]] = load i32, i32* [[BP:%.*]], align 4
 ; CHECK-NEXT:    [[EB:%.*]] = sext i32 [[B]] to i64
 ; CHECK-NEXT:    [[SUBAB:%.*]] = sub nsw i32 [[A]], [[B]]