Add an AlignmentFromAssumptions Pass

This adds a ScalarEvolution-powered transformation that updates load, store and
memory intrinsic pointer alignments based on invariant((a+q) & b == 0)
expressions. Many of the simple cases we can get with ValueTracking, but we
still need something like this for the more complicated cases (such as those
with an offset) that require some algebra. Note that gcc's
__builtin_assume_aligned's optional third argument provides exactly for this
kind of 'misalignment' offset for which this kind of logic is necessary.

The primary motivation is to fixup alignments for vector loads/stores after
vectorization (and unrolling). This pass is added to the optimization pipeline
just after the SLP vectorizer runs (which, admittedly, does not preserve SE,
although I imagine it could).  Regardless, I actually don't think that the
preservation matters too much in this case: SE computes lazily, and this pass
won't issue any SE queries unless there are any assume intrinsics, so there
should be no real additional cost in the common case (SLP does preserve DT and
LoopInfo).

llvm-svn: 217344

include/llvm-c/Transforms/Scalar.h

@@ -35,6 +35,9 @@ extern "C" {
 /** See llvm::createAggressiveDCEPass function. */
 void LLVMAddAggressiveDCEPass(LLVMPassManagerRef PM);
 
+/** See llvm::createAlignmentFromAssumptionsPass function. */
+void LLVMAddAlignmentFromAssumptionsPass(LLVMPassManagerRef PM);
+
 /** See llvm::createCFGSimplificationPass function. */
 void LLVMAddCFGSimplificationPass(LLVMPassManagerRef PM);
 

include/llvm/InitializePasses.h

@@ -73,6 +73,7 @@ void initializeAlwaysInlinerPass(PassRegistry&);
 void initializeArgPromotionPass(PassRegistry&);
 void initializeAtomicExpandPass(PassRegistry&);
 void initializeSampleProfileLoaderPass(PassRegistry&);
+void initializeAlignmentFromAssumptionsPass(PassRegistry&);
 void initializeBarrierNoopPass(PassRegistry&);
 void initializeBasicAliasAnalysisPass(PassRegistry&);
 void initializeCallGraphWrapperPassPass(PassRegistry &);

include/llvm/LinkAllPasses.h

@@ -52,6 +52,7 @@ namespace {
       (void) llvm::createAliasAnalysisCounterPass();
       (void) llvm::createAliasDebugger();
       (void) llvm::createArgumentPromotionPass();
+      (void) llvm::createAlignmentFromAssumptionsPass();
       (void) llvm::createBasicAliasAnalysisPass();
       (void) llvm::createLibCallAliasAnalysisPass(nullptr);
       (void) llvm::createScalarEvolutionAliasAnalysisPass();

include/llvm/Transforms/Scalar.h

@@ -34,6 +34,13 @@ class TargetMachine;
 //
 FunctionPass *createConstantPropagationPass();
 
+//===----------------------------------------------------------------------===//
+//
+// AlignmentFromAssumptions - Use assume intrinsics to set load/store
+// alignments.
+//
+FunctionPass *createAlignmentFromAssumptionsPass();
+
 //===----------------------------------------------------------------------===//
 //
 // SCCP - Sparse conditional constant propagation.

lib/Transforms/IPO/PassManagerBuilder.cpp

@@ -310,6 +310,10 @@ void PassManagerBuilder::populateModulePassManager(PassManagerBase &MPM) {
   if (!DisableUnrollLoops)
     MPM.add(createLoopUnrollPass());    // Unroll small loops
 
+  // After vectorization and unrolling, assume intrinsics may tell us more
+  // about pointer alignments.
+  MPM.add(createAlignmentFromAssumptionsPass());
+
   if (!DisableUnitAtATime) {
     // FIXME: We shouldn't bother with this anymore.
     MPM.add(createStripDeadPrototypesPass()); // Get rid of dead prototypes
@@ -399,6 +403,10 @@ void PassManagerBuilder::addLTOOptimizationPasses(PassManagerBase &PM) {
   // More scalar chains could be vectorized due to more alias information
   PM.add(createSLPVectorizerPass()); // Vectorize parallel scalar chains.
 
+  // After vectorization, assume intrinsics may tell us more about pointer
+  // alignments.
+  PM.add(createAlignmentFromAssumptionsPass());
+
   if (LoadCombine)
     PM.add(createLoadCombinePass());
 

lib/Transforms/Scalar/AlignmentFromAssumptions.cpp

@@ -0,0 +1,420 @@
+//===----------------------- AlignmentFromAssumptions.cpp -----------------===//
+//                  Set Load/Store Alignments From Assumptions
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file implements a ScalarEvolution-based transformation to set
+// the alignments of load, stores and memory intrinsics based on the truth
+// expressions of assume intrinsics. The primary motivation is to handle
+// complex alignment assumptions that apply to vector loads and stores that
+// appear after vectorization and unrolling.
+//
+//===----------------------------------------------------------------------===//
+
+#define AA_NAME "alignment-from-assumptions"
+#define DEBUG_TYPE AA_NAME
+#include "llvm/Transforms/Scalar.h"
+#include "llvm/ADT/SmallPtrSet.h"
+#include "llvm/ADT/Statistic.h"
+#include "llvm/Analysis/AssumptionTracker.h"
+#include "llvm/Analysis/LoopInfo.h"
+#include "llvm/Analysis/ValueTracking.h"
+#include "llvm/Analysis/ScalarEvolution.h"
+#include "llvm/Analysis/ScalarEvolutionExpressions.h"
+#include "llvm/IR/Constant.h"
+#include "llvm/IR/Dominators.h"
+#include "llvm/IR/Instruction.h"
+#include "llvm/IR/IntrinsicInst.h"
+#include "llvm/IR/Intrinsics.h"
+#include "llvm/IR/DataLayout.h"
+#include "llvm/Support/Debug.h"
+#include "llvm/Support/raw_ostream.h"
+using namespace llvm;
+
+STATISTIC(NumLoadAlignChanged,
+  "Number of loads changed by alignment assumptions");
+STATISTIC(NumStoreAlignChanged,
+  "Number of stores changed by alignment assumptions");
+STATISTIC(NumMemIntAlignChanged,
+  "Number of memory intrinsics changed by alignment assumptions");
+
+namespace {
+struct AlignmentFromAssumptions : public FunctionPass {
+  static char ID; // Pass identification, replacement for typeid
+  AlignmentFromAssumptions() : FunctionPass(ID) {
+    initializeAlignmentFromAssumptionsPass(*PassRegistry::getPassRegistry());
+  }
+
+  bool runOnFunction(Function &F);
+
+  virtual void getAnalysisUsage(AnalysisUsage &AU) const {
+    AU.addRequired<AssumptionTracker>();
+    AU.addRequired<ScalarEvolution>();
+    AU.addRequired<DominatorTreeWrapperPass>();
+
+    AU.setPreservesCFG();
+    AU.addPreserved<LoopInfo>();
+    AU.addPreserved<DominatorTreeWrapperPass>();
+    AU.addPreserved<ScalarEvolution>();
+  }
+
+  // For memory transfers, we need a common alignment for both the source and
+  // destination. If we have a new alignment for only one operand of a transfer
+  // instruction, save it in these maps.  If we reach the other operand through
+  // another assumption later, then we may change the alignment at that point.
+  DenseMap<MemTransferInst *, unsigned> NewDestAlignments, NewSrcAlignments;
+
+  AssumptionTracker *AT;
+  ScalarEvolution *SE;
+  DominatorTree *DT;
+  const DataLayout *DL;
+
+  bool extractAlignmentInfo(CallInst *I, Value *&AAPtr, const SCEV *&AlignSCEV,
+                            const SCEV *&OffSCEV);
+  bool processAssumption(CallInst *I);
+};
+}
+
+char AlignmentFromAssumptions::ID = 0;
+static const char aip_name[] = "Alignment from assumptions";
+INITIALIZE_PASS_BEGIN(AlignmentFromAssumptions, AA_NAME,
+                      aip_name, false, false)
+INITIALIZE_PASS_DEPENDENCY(AssumptionTracker)
+INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
+INITIALIZE_PASS_DEPENDENCY(ScalarEvolution)
+INITIALIZE_PASS_END(AlignmentFromAssumptions, AA_NAME,
+                    aip_name, false, false)
+
+FunctionPass *llvm::createAlignmentFromAssumptionsPass() {
+  return new AlignmentFromAssumptions();
+}
+
+// Given an expression for the (constant) alignment, AlignSCEV, and an
+// expression for the displacement between a pointer and the aligned address,
+// DiffSCEV, compute the alignment of the displaced pointer if it can be
+// reduced to a constant.
+static unsigned getNewAlignmentDiff(const SCEV *DiffSCEV,
+                                    const SCEV *AlignSCEV,
+                                    ScalarEvolution *SE) {
+  // DiffUnits = Diff % int64_t(Alignment)
+  const SCEV *DiffAlignDiv = SE->getUDivExpr(DiffSCEV, AlignSCEV);
+  const SCEV *DiffAlign = SE->getMulExpr(DiffAlignDiv, AlignSCEV);
+  const SCEV *DiffUnitsSCEV = SE->getMinusSCEV(DiffAlign, DiffSCEV);
+
+  DEBUG(dbgs() << "\talignment relative to " << *AlignSCEV << " is " <<
+                  *DiffUnitsSCEV << " (diff: " << *DiffSCEV << ")\n");
+
+  if (const SCEVConstant *ConstDUSCEV =
+      dyn_cast<SCEVConstant>(DiffUnitsSCEV)) {
+    int64_t DiffUnits = ConstDUSCEV->getValue()->getSExtValue();
+
+    // If the displacement is an exact multiple of the alignment, then the
+    // displaced pointer has the same alignment as the aligned pointer, so
+    // return the alignment value.
+    if (!DiffUnits)
+      return (unsigned)
+        cast<SCEVConstant>(AlignSCEV)->getValue()->getSExtValue();
+
+    // If the displacement is not an exact multiple, but the remainder is a
+    // constant, then return this remainder (but only if it is a power of 2).
+    uint64_t DiffUnitsAbs = abs64(DiffUnits);
+    if (isPowerOf2_64(DiffUnitsAbs))
+      return (unsigned) DiffUnitsAbs;
+  }
+
+  return 0;
+}
+
+// There is an address given by an offset OffSCEV from AASCEV which has an
+// alignment AlignSCEV. Use that information, if possible, to compute a new
+// alignment for Ptr.
+static unsigned getNewAlignment(const SCEV *AASCEV, const SCEV *AlignSCEV,
+                                const SCEV *OffSCEV, Value *Ptr,
+                                ScalarEvolution *SE) {
+  const SCEV *PtrSCEV = SE->getSCEV(Ptr);
+  const SCEV *DiffSCEV = SE->getMinusSCEV(PtrSCEV, AASCEV);
+
+  // What we really want to know is the overall offset to the aligned
+  // address. This address is displaced by the provided offset.
+  DiffSCEV = SE->getMinusSCEV(DiffSCEV, OffSCEV);
+
+  DEBUG(dbgs() << "AFI: alignment of " << *Ptr << " relative to " <<
+                  *AlignSCEV << " and offset " << *OffSCEV <<
+                  " using diff " << *DiffSCEV << "\n");
+
+  unsigned NewAlignment = getNewAlignmentDiff(DiffSCEV, AlignSCEV, SE);
+  DEBUG(dbgs() << "\tnew alignment: " << NewAlignment << "\n");
+
+  if (NewAlignment) {
+    return NewAlignment;
+  } else if (const SCEVAddRecExpr *DiffARSCEV =
+             dyn_cast<SCEVAddRecExpr>(DiffSCEV)) {
+    // The relative offset to the alignment assumption did not yield a constant,
+    // but we should try harder: if we assume that a is 32-byte aligned, then in
+    // for (i = 0; i < 1024; i += 4) r += a[i]; not all of the loads from a are
+    // 32-byte aligned, but instead alternate between 32 and 16-byte alignment.
+    // As a result, the new alignment will not be a constant, but can still
+    // be improved over the default (of 4) to 16.
+
+    const SCEV *DiffStartSCEV = DiffARSCEV->getStart();
+    const SCEV *DiffIncSCEV = DiffARSCEV->getStepRecurrence(*SE);
+
+    DEBUG(dbgs() << "\ttrying start/inc alignment using start " <<
+                    *DiffStartSCEV << " and inc " << *DiffIncSCEV << "\n");
+
+    // Now compute the new alignment using the displacement to the value in the
+    // first iteration, and also the alignment using the per-iteration delta.
+    // If these are the same, then use that answer. Otherwise, use the smaller
+    // one, but only if it divides the larger one.
+    NewAlignment = getNewAlignmentDiff(DiffStartSCEV, AlignSCEV, SE);
+    unsigned NewIncAlignment = getNewAlignmentDiff(DiffIncSCEV, AlignSCEV, SE);
+
+    DEBUG(dbgs() << "\tnew start alignment: " << NewAlignment << "\n");
+    DEBUG(dbgs() << "\tnew inc alignment: " << NewIncAlignment << "\n");
+
+    if (NewAlignment > NewIncAlignment) {
+      if (NewAlignment % NewIncAlignment == 0) {
+        DEBUG(dbgs() << "\tnew start/inc alignment: " <<
+                        NewIncAlignment << "\n");
+        return NewIncAlignment;
+      }
+    } else if (NewIncAlignment > NewAlignment) {
+      if (NewIncAlignment % NewAlignment == 0) {
+        DEBUG(dbgs() << "\tnew start/inc alignment: " <<
+                        NewAlignment << "\n");
+        return NewAlignment;
+      }
+    } else if (NewIncAlignment == NewAlignment && NewIncAlignment) {
+      DEBUG(dbgs() << "\tnew start/inc alignment: " <<
+                      NewAlignment << "\n");
+      return NewAlignment;
+    }
+  }
+
+  return 0;
+}
+
+bool AlignmentFromAssumptions::extractAlignmentInfo(CallInst *I,
+                                 Value *&AAPtr, const SCEV *&AlignSCEV,
+                                 const SCEV *&OffSCEV) {
+  // An alignment assume must be a statement about the least-significant
+  // bits of the pointer being zero, possibly with some offset.
+  ICmpInst *ICI = dyn_cast<ICmpInst>(I->getArgOperand(0));
+  if (!ICI)
+    return false;
+
+  // This must be an expression of the form: x & m == 0.
+  if (ICI->getPredicate() != ICmpInst::ICMP_EQ)
+    return false;
+
+  // Swap things around so that the RHS is 0.
+  Value *CmpLHS = ICI->getOperand(0);
+  Value *CmpRHS = ICI->getOperand(1);
+  const SCEV *CmpLHSSCEV = SE->getSCEV(CmpLHS);
+  const SCEV *CmpRHSSCEV = SE->getSCEV(CmpRHS);
+  if (CmpLHSSCEV->isZero())
+    std::swap(CmpLHS, CmpRHS);
+  else if (!CmpRHSSCEV->isZero())
+    return false;
+
+  BinaryOperator *CmpBO = dyn_cast<BinaryOperator>(CmpLHS);
+  if (!CmpBO || CmpBO->getOpcode() != Instruction::And)
+    return false;
+
+  // Swap things around so that the right operand of the and is a constant
+  // (the mask); we cannot deal with variable masks.
+  Value *AndLHS = CmpBO->getOperand(0);
+  Value *AndRHS = CmpBO->getOperand(1);
+  const SCEV *AndLHSSCEV = SE->getSCEV(AndLHS);
+  const SCEV *AndRHSSCEV = SE->getSCEV(AndRHS);
+  if (isa<SCEVConstant>(AndLHSSCEV)) {
+    std::swap(AndLHS, AndRHS);
+    std::swap(AndLHSSCEV, AndRHSSCEV);
+  }
+
+  const SCEVConstant *MaskSCEV = dyn_cast<SCEVConstant>(AndRHSSCEV);
+  if (!MaskSCEV)
+    return false;
+
+  // The mask must have some trailing ones (otherwise the condition is
+  // trivial and tells us nothing about the alignment of the left operand).
+  unsigned TrailingOnes =
+    MaskSCEV->getValue()->getValue().countTrailingOnes();
+  if (!TrailingOnes)
+    return false;
+
+  // Cap the alignment at the maximum with which LLVM can deal (and make sure
+  // we don't overflow the shift).
+  uint64_t Alignment;
+  TrailingOnes = std::min(TrailingOnes,
+    unsigned(sizeof(unsigned) * CHAR_BIT - 1));
+  Alignment = std::min(1u << TrailingOnes, +Value::MaximumAlignment);
+
+  Type *Int64Ty = Type::getInt64Ty(I->getParent()->getParent()->getContext());
+  AlignSCEV = SE->getConstant(Int64Ty, Alignment);
+
+  // The LHS might be a ptrtoint instruction, or it might be the pointer
+  // with an offset.
+  AAPtr = nullptr;
+  OffSCEV = nullptr;
+  if (PtrToIntInst *PToI = dyn_cast<PtrToIntInst>(AndLHS)) {
+    AAPtr = PToI->getPointerOperand();
+    OffSCEV = SE->getConstant(Int64Ty, 0);
+  } else if (const SCEVAddExpr* AndLHSAddSCEV =
+             dyn_cast<SCEVAddExpr>(AndLHSSCEV)) {
+    // Try to find the ptrtoint; subtract it and the rest is the offset.
+    for (SCEVAddExpr::op_iterator J = AndLHSAddSCEV->op_begin(),
+         JE = AndLHSAddSCEV->op_end(); J != JE; ++J)
+      if (const SCEVUnknown *OpUnk = dyn_cast<SCEVUnknown>(*J))
+        if (PtrToIntInst *PToI = dyn_cast<PtrToIntInst>(OpUnk->getValue())) {
+          AAPtr = PToI->getPointerOperand();
+          OffSCEV = SE->getMinusSCEV(AndLHSAddSCEV, *J);
+          break;
+        }
+  }
+
+  if (!AAPtr)
+    return false;
+
+  // Sign extend the offset to 64 bits (so that it is like all of the other
+  // expressions). 
+  unsigned OffSCEVBits = OffSCEV->getType()->getPrimitiveSizeInBits();
+  if (OffSCEVBits < 64)
+    OffSCEV = SE->getSignExtendExpr(OffSCEV, Int64Ty);
+  else if (OffSCEVBits > 64)
+    return false;
+
+  AAPtr = AAPtr->stripPointerCasts();
+  return true;
+}
+
+bool AlignmentFromAssumptions::processAssumption(CallInst *ACall) {
+  Value *AAPtr;
+  const SCEV *AlignSCEV, *OffSCEV;
+  if (!extractAlignmentInfo(ACall, AAPtr, AlignSCEV, OffSCEV))
+    return false;
+
+  const SCEV *AASCEV = SE->getSCEV(AAPtr);
+
+  // Apply the assumption to all other users of the specified pointer.
+  SmallPtrSet<Instruction *, 32> Visited;
+  SmallVector<Instruction*, 16> WorkList;
+  for (User *J : AAPtr->users()) {
+    if (J == ACall)
+      continue;
+
+    if (Instruction *K = dyn_cast<Instruction>(J))
+      if (isValidAssumeForContext(ACall, K, DL, DT))
+        WorkList.push_back(K);
+  }
+
+  while (!WorkList.empty()) {
+    Instruction *J = WorkList.pop_back_val();
+
+    if (LoadInst *LI = dyn_cast<LoadInst>(J)) {
+      unsigned NewAlignment = getNewAlignment(AASCEV, AlignSCEV, OffSCEV,
+        LI->getPointerOperand(), SE);
+
+      if (NewAlignment > LI->getAlignment()) {
+        LI->setAlignment(NewAlignment);
+        ++NumLoadAlignChanged;
+      }
+    } else if (StoreInst *SI = dyn_cast<StoreInst>(J)) {
+      unsigned NewAlignment = getNewAlignment(AASCEV, AlignSCEV, OffSCEV,
+        SI->getPointerOperand(), SE);
+
+      if (NewAlignment > SI->getAlignment()) {
+        SI->setAlignment(NewAlignment);
+        ++NumStoreAlignChanged;
+      }
+    } else if (MemIntrinsic *MI = dyn_cast<MemIntrinsic>(J)) {
+      unsigned NewDestAlignment = getNewAlignment(AASCEV, AlignSCEV, OffSCEV,
+        MI->getDest(), SE);
+
+      // For memory transfers, we need a common alignment for both the
+      // source and destination. If we have a new alignment for this
+      // instruction, but only for one operand, save it. If we reach the
+      // other operand through another assumption later, then we may
+      // change the alignment at that point.
+      if (MemTransferInst *MTI = dyn_cast<MemTransferInst>(MI)) {
+        unsigned NewSrcAlignment = getNewAlignment(AASCEV, AlignSCEV, OffSCEV,
+          MTI->getSource(), SE);
+
+        DenseMap<MemTransferInst *, unsigned>::iterator DI =
+          NewDestAlignments.find(MTI);
+        unsigned AltDestAlignment = (DI == NewDestAlignments.end()) ?
+                                    0 : DI->second;
+
+        DenseMap<MemTransferInst *, unsigned>::iterator SI =
+          NewSrcAlignments.find(MTI);
+        unsigned AltSrcAlignment = (SI == NewSrcAlignments.end()) ?
+                                   0 : SI->second;
+
+        DEBUG(dbgs() << "\tmem trans: " << NewDestAlignment << " " <<
+                        AltDestAlignment << " " << NewSrcAlignment <<
+                        " " << AltSrcAlignment << "\n");
+
+        // Of these four alignments, pick the largest possible...
+        unsigned NewAlignment = 0;
+        if (NewDestAlignment <= std::max(NewSrcAlignment, AltSrcAlignment))
+          NewAlignment = std::max(NewAlignment, NewDestAlignment);
+        if (AltDestAlignment <= std::max(NewSrcAlignment, AltSrcAlignment))
+          NewAlignment = std::max(NewAlignment, AltDestAlignment);
+        if (NewSrcAlignment <= std::max(NewDestAlignment, AltDestAlignment))
+          NewAlignment = std::max(NewAlignment, NewSrcAlignment);
+        if (AltSrcAlignment <= std::max(NewDestAlignment, AltDestAlignment))
+          NewAlignment = std::max(NewAlignment, AltSrcAlignment);
+
+        if (NewAlignment > MI->getAlignment()) {
+          MI->setAlignment(ConstantInt::get(Type::getInt32Ty(
+            MI->getParent()->getContext()), NewAlignment));
+          ++NumMemIntAlignChanged;
+        }
+
+        NewDestAlignments.insert(std::make_pair(MTI, NewDestAlignment));
+        NewSrcAlignments.insert(std::make_pair(MTI, NewSrcAlignment));
+      } else if (NewDestAlignment > MI->getAlignment()) {
+        assert((!isa<MemIntrinsic>(MI) || isa<MemSetInst>(MI)) &&
+               "Unknown memory intrinsic");
+
+        MI->setAlignment(ConstantInt::get(Type::getInt32Ty(
+          MI->getParent()->getContext()), NewDestAlignment));
+        ++NumMemIntAlignChanged;
+      }
+    }
+
+    // Now that we've updated that use of the pointer, look for other uses of
+    // the pointer to update.
+    Visited.insert(J);
+    for (User *UJ : J->users()) {
+      Instruction *K = cast<Instruction>(UJ);
+      if (!Visited.count(K) && isValidAssumeForContext(ACall, K, DL, DT))
+        WorkList.push_back(K);
+    }
+  }
+
+  return true;
+}
+
+bool AlignmentFromAssumptions::runOnFunction(Function &F) {
+  bool Changed = false;
+  AT = &getAnalysis<AssumptionTracker>();
+  SE = &getAnalysis<ScalarEvolution>();
+  DT = &getAnalysis<DominatorTreeWrapperPass>().getDomTree();
+  DataLayoutPass *DLP = getAnalysisIfAvailable<DataLayoutPass>();
+  DL = DLP ? &DLP->getDataLayout() : nullptr;
+
+  NewDestAlignments.clear();
+  NewSrcAlignments.clear();
+
+  for (auto &I : AT->assumptions(&F))
+    Changed |= processAssumption(I);
+
+  return Changed;
+}
+

lib/Transforms/Scalar/CMakeLists.txt

@@ -1,5 +1,6 @@
 add_llvm_library(LLVMScalarOpts
   ADCE.cpp
+  AlignmentFromAssumptions.cpp
   ConstantHoisting.cpp
   ConstantProp.cpp
   CorrelatedValuePropagation.cpp

lib/Transforms/Scalar/Scalar.cpp

@@ -28,6 +28,7 @@ using namespace llvm;
 /// ScalarOpts library.
 void llvm::initializeScalarOpts(PassRegistry &Registry) {
   initializeADCEPass(Registry);
+  initializeAlignmentFromAssumptionsPass(Registry);
   initializeSampleProfileLoaderPass(Registry);
   initializeConstantHoistingPass(Registry);
   initializeConstantPropagationPass(Registry);
@@ -78,6 +79,10 @@ void LLVMAddAggressiveDCEPass(LLVMPassManagerRef PM) {
   unwrap(PM)->add(createAggressiveDCEPass());
 }
 
+void LLVMAddAlignmentFromAssumptionsPass(LLVMPassManagerRef PM) {
+  unwrap(PM)->add(createAlignmentFromAssumptionsPass());
+}
+
 void LLVMAddCFGSimplificationPass(LLVMPassManagerRef PM) {
   unwrap(PM)->add(createCFGSimplificationPass());
 }

test/Transforms/AlignmentFromAssumptions/simple.ll

@@ -0,0 +1,215 @@
+target datalayout = "e-i64:64-f80:128-n8:16:32:64-S128"
+; RUN: opt < %s -alignment-from-assumptions -S | FileCheck %s
+
+define i32 @foo(i32* nocapture %a) nounwind uwtable readonly {
+entry:
+  %ptrint = ptrtoint i32* %a to i64
+  %maskedptr = and i64 %ptrint, 31
+  %maskcond = icmp eq i64 %maskedptr, 0
+  tail call void @llvm.assume(i1 %maskcond)
+  %0 = load i32* %a, align 4
+  ret i32 %0
+
+; CHECK-LABEL: @foo
+; CHECK: load i32* {{[^,]+}}, align 32
+; CHECK: ret i32
+}
+
+define i32 @foo2(i32* nocapture %a) nounwind uwtable readonly {
+entry:
+  %ptrint = ptrtoint i32* %a to i64
+  %offsetptr = add i64 %ptrint, 24
+  %maskedptr = and i64 %offsetptr, 31
+  %maskcond = icmp eq i64 %maskedptr, 0
+  tail call void @llvm.assume(i1 %maskcond)
+  %arrayidx = getelementptr inbounds i32* %a, i64 2
+  %0 = load i32* %arrayidx, align 4
+  ret i32 %0
+
+; CHECK-LABEL: @foo2
+; CHECK: load i32* {{[^,]+}}, align 16
+; CHECK: ret i32
+}
+
+define i32 @foo2a(i32* nocapture %a) nounwind uwtable readonly {
+entry:
+  %ptrint = ptrtoint i32* %a to i64
+  %offsetptr = add i64 %ptrint, 28
+  %maskedptr = and i64 %offsetptr, 31
+  %maskcond = icmp eq i64 %maskedptr, 0
+  tail call void @llvm.assume(i1 %maskcond)
+  %arrayidx = getelementptr inbounds i32* %a, i64 -1
+  %0 = load i32* %arrayidx, align 4
+  ret i32 %0
+
+; CHECK-LABEL: @foo2a
+; CHECK: load i32* {{[^,]+}}, align 32
+; CHECK: ret i32
+}
+
+define i32 @goo(i32* nocapture %a) nounwind uwtable readonly {
+entry:
+  %ptrint = ptrtoint i32* %a to i64
+  %maskedptr = and i64 %ptrint, 31
+  %maskcond = icmp eq i64 %maskedptr, 0
+  tail call void @llvm.assume(i1 %maskcond)
+  %0 = load i32* %a, align 4
+  ret i32 %0
+
+; CHECK-LABEL: @goo
+; CHECK: load i32* {{[^,]+}}, align 32
+; CHECK: ret i32
+}
+
+define i32 @hoo(i32* nocapture %a) nounwind uwtable readonly {
+entry:
+  %ptrint = ptrtoint i32* %a to i64
+  %maskedptr = and i64 %ptrint, 31
+  %maskcond = icmp eq i64 %maskedptr, 0
+  tail call void @llvm.assume(i1 %maskcond)
+  br label %for.body
+
+for.body:                                         ; preds = %entry, %for.body
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %r.06 = phi i32 [ 0, %entry ], [ %add, %for.body ]
+  %arrayidx = getelementptr inbounds i32* %a, i64 %indvars.iv
+  %0 = load i32* %arrayidx, align 4
+  %add = add nsw i32 %0, %r.06
+  %indvars.iv.next = add i64 %indvars.iv, 8
+  %1 = trunc i64 %indvars.iv.next to i32
+  %cmp = icmp slt i32 %1, 2048
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  %add.lcssa = phi i32 [ %add, %for.body ]
+  ret i32 %add.lcssa
+
+; CHECK-LABEL: @hoo
+; CHECK: load i32* %arrayidx, align 32
+; CHECK: ret i32 %add.lcssa
+}
+
+define i32 @joo(i32* nocapture %a) nounwind uwtable readonly {
+entry:
+  %ptrint = ptrtoint i32* %a to i64
+  %maskedptr = and i64 %ptrint, 31
+  %maskcond = icmp eq i64 %maskedptr, 0
+  tail call void @llvm.assume(i1 %maskcond)
+  br label %for.body
+
+for.body:                                         ; preds = %entry, %for.body
+  %indvars.iv = phi i64 [ 4, %entry ], [ %indvars.iv.next, %for.body ]
+  %r.06 = phi i32 [ 0, %entry ], [ %add, %for.body ]
+  %arrayidx = getelementptr inbounds i32* %a, i64 %indvars.iv
+  %0 = load i32* %arrayidx, align 4
+  %add = add nsw i32 %0, %r.06
+  %indvars.iv.next = add i64 %indvars.iv, 8
+  %1 = trunc i64 %indvars.iv.next to i32
+  %cmp = icmp slt i32 %1, 2048
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  %add.lcssa = phi i32 [ %add, %for.body ]
+  ret i32 %add.lcssa
+
+; CHECK-LABEL: @joo
+; CHECK: load i32* %arrayidx, align 16
+; CHECK: ret i32 %add.lcssa
+}
+
+define i32 @koo(i32* nocapture %a) nounwind uwtable readonly {
+entry:
+  %ptrint = ptrtoint i32* %a to i64
+  %maskedptr = and i64 %ptrint, 31
+  %maskcond = icmp eq i64 %maskedptr, 0
+  tail call void @llvm.assume(i1 %maskcond)
+  br label %for.body
+
+for.body:                                         ; preds = %entry, %for.body
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %r.06 = phi i32 [ 0, %entry ], [ %add, %for.body ]
+  %arrayidx = getelementptr inbounds i32* %a, i64 %indvars.iv
+  %0 = load i32* %arrayidx, align 4
+  %add = add nsw i32 %0, %r.06
+  %indvars.iv.next = add i64 %indvars.iv, 4
+  %1 = trunc i64 %indvars.iv.next to i32
+  %cmp = icmp slt i32 %1, 2048
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  %add.lcssa = phi i32 [ %add, %for.body ]
+  ret i32 %add.lcssa
+
+; CHECK-LABEL: @koo
+; CHECK: load i32* %arrayidx, align 16
+; CHECK: ret i32 %add.lcssa
+}
+
+define i32 @koo2(i32* nocapture %a) nounwind uwtable readonly {
+entry:
+  %ptrint = ptrtoint i32* %a to i64
+  %maskedptr = and i64 %ptrint, 31
+  %maskcond = icmp eq i64 %maskedptr, 0
+  tail call void @llvm.assume(i1 %maskcond)
+  br label %for.body
+
+for.body:                                         ; preds = %entry, %for.body
+  %indvars.iv = phi i64 [ -4, %entry ], [ %indvars.iv.next, %for.body ]
+  %r.06 = phi i32 [ 0, %entry ], [ %add, %for.body ]
+  %arrayidx = getelementptr inbounds i32* %a, i64 %indvars.iv
+  %0 = load i32* %arrayidx, align 4
+  %add = add nsw i32 %0, %r.06
+  %indvars.iv.next = add i64 %indvars.iv, 4
+  %1 = trunc i64 %indvars.iv.next to i32
+  %cmp = icmp slt i32 %1, 2048
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body
+  %add.lcssa = phi i32 [ %add, %for.body ]
+  ret i32 %add.lcssa
+
+; CHECK-LABEL: @koo2
+; CHECK: load i32* %arrayidx, align 16
+; CHECK: ret i32 %add.lcssa
+}
+
+define i32 @moo(i32* nocapture %a) nounwind uwtable {
+entry:
+  %ptrint = ptrtoint i32* %a to i64
+  %maskedptr = and i64 %ptrint, 31
+  %maskcond = icmp eq i64 %maskedptr, 0
+  tail call void @llvm.assume(i1 %maskcond)
+  %0 = bitcast i32* %a to i8*
+  tail call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 64, i32 4, i1 false)
+  ret i32 undef
+
+; CHECK-LABEL: @moo
+; CHECK: @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 64, i32 32, i1 false)
+; CHECK: ret i32 undef
+}
+
+define i32 @moo2(i32* nocapture %a, i32* nocapture %b) nounwind uwtable {
+entry:
+  %ptrint = ptrtoint i32* %a to i64
+  %maskedptr = and i64 %ptrint, 31
+  %maskcond = icmp eq i64 %maskedptr, 0
+  tail call void @llvm.assume(i1 %maskcond)
+  %ptrint1 = ptrtoint i32* %b to i64
+  %maskedptr3 = and i64 %ptrint1, 127
+  %maskcond4 = icmp eq i64 %maskedptr3, 0
+  tail call void @llvm.assume(i1 %maskcond4)
+  %0 = bitcast i32* %a to i8*
+  %1 = bitcast i32* %b to i8*
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* %1, i64 64, i32 4, i1 false)
+  ret i32 undef
+
+; CHECK-LABEL: @moo2
+; CHECK: @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* %1, i64 64, i32 32, i1 false)
+; CHECK: ret i32 undef
+}
+
+declare void @llvm.assume(i1) nounwind
+
+declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind
+