[MemDep] Use PhiValuesAnalysis to improve alias analysis results

[john.brawn]

Summary

This is being done in order to make GVN able to better optimize certain inputs. MemDep doesn't use PhiValues directly, but does need to notifiy it when things get invalidated.

[john.brawn]

Rebase on top of latest patch for D44564.

[sebpop]

Looks good to me. Thanks!

include/llvm/Analysis/MemoryDependenceAnalysis.h

 class AssumptionCache;
 class CallSite;
 class DominatorTree;
 class Function;
 class Instruction;
 class LoadInst;
 class PHITransAddr;
 class TargetLibraryInfo;
+class PhiValues;
 class Value;
 
 /// A memory dependence query can return one of three different answers.
 class MemDepResult {
   enum DepType {
     /// Clients of MemDep never see this.
     ///
     /// Entries with this marker occur in a LocalDeps map or NonLocalDeps map
private:
   // A reverse mapping from dependencies to the non-local dependees.
   ReverseDepMapType ReverseNonLocalDeps;
 
   /// Current AA implementation, just a cache.
   AliasAnalysis &AA;
   AssumptionCache ∾
   const TargetLibraryInfo &TLI;
   DominatorTree &DT;
+  PhiValues &PV;
   PredIteratorCache PredCache;
 
 public:
   MemoryDependenceResults(AliasAnalysis &AA, AssumptionCache &AC,
                           const TargetLibraryInfo &TLI,
-                          DominatorTree &DT)
-      : AA(AA), AC(AC), TLI(TLI), DT(DT) {}
+                          DominatorTree &DT, PhiValues &PV)
+      : AA(AA), AC(AC), TLI(TLI), DT(DT), PV(PV) {}
 
   /// Handle invalidation in the new PM.
   bool invalidate(Function &F, const PreservedAnalyses &PA,
                   FunctionAnalysisManager::Invalidator &Inv);
 
   /// Some methods limit the number of instructions they will examine.
   /// The return value of this method is the default limit that will be
   /// used if no limit is explicitly passed in.

lib/Analysis/MemoryDependenceAnalysis.cpp

 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/Statistic.h"
 #include "llvm/Analysis/AliasAnalysis.h"
 #include "llvm/Analysis/AssumptionCache.h"
 #include "llvm/Analysis/MemoryBuiltins.h"
 #include "llvm/Analysis/MemoryLocation.h"
 #include "llvm/Analysis/OrderedBasicBlock.h"
 #include "llvm/Analysis/PHITransAddr.h"
+#include "llvm/Analysis/PhiValues.h"
 #include "llvm/Analysis/TargetLibraryInfo.h"
 #include "llvm/Analysis/ValueTracking.h"
 #include "llvm/IR/Attributes.h"
 #include "llvm/IR/BasicBlock.h"
 #include "llvm/IR/CallSite.h"
 #include "llvm/IR/Constants.h"
 #include "llvm/IR/DataLayout.h"
 #include "llvm/IR/DerivedTypes.h"

 void MemoryDependenceResults::invalidateCachedPointerInfo(Value *Ptr) {
   // If Ptr isn't really a pointer, just ignore it.
   if (!Ptr->getType()->isPointerTy())
     return;
   // Flush store info for the pointer.
   RemoveCachedNonLocalPointerDependencies(ValueIsLoadPair(Ptr, false));
   // Flush load info for the pointer.
   RemoveCachedNonLocalPointerDependencies(ValueIsLoadPair(Ptr, true));
+  // Invalidate phis that use the pointer.
+  PV.invalidateValue(Ptr);
 }
 
 void MemoryDependenceResults::invalidateCachedPredecessors() {
   PredCache.clear();
 }
 
 void MemoryDependenceResults::removeInstruction(Instruction *RemInst) {
   // Walk through the Non-local dependencies, removing this one as the value
if (ReversePtrDepIt != ReverseNonLocalPtrDeps.end()) {
 
     while (!ReversePtrDepsToAdd.empty()) {
       ReverseNonLocalPtrDeps[ReversePtrDepsToAdd.back().first].insert(
           ReversePtrDepsToAdd.back().second);
       ReversePtrDepsToAdd.pop_back();
     }
   }
 
+  // Invalidate phis that use the removed instruction.
+  PV.invalidateValue(RemInst);
+
   assert(!NonLocalDeps.count(RemInst) && "RemInst got reinserted?");
   LLVM_DEBUG(verifyRemoved(RemInst));
 }
 
 /// Verify that the specified instruction does not occur in our internal data
 /// structures.
 ///
 /// This function verifies by asserting in debug builds.

 AnalysisKey MemoryDependenceAnalysis::Key;
 
 MemoryDependenceResults
 MemoryDependenceAnalysis::run(Function &F, FunctionAnalysisManager &AM) {
   auto &AA = AM.getResult<AAManager>(F);
   auto &AC = AM.getResult<AssumptionAnalysis>(F);
   auto &TLI = AM.getResult<TargetLibraryAnalysis>(F);
   auto &DT = AM.getResult<DominatorTreeAnalysis>(F);
-  return MemoryDependenceResults(AA, AC, TLI, DT);
+  auto &PV = AM.getResult<PhiValuesAnalysis>(F);
+  return MemoryDependenceResults(AA, AC, TLI, DT, PV);
 }
 
 char MemoryDependenceWrapperPass::ID = 0;
 
 INITIALIZE_PASS_BEGIN(MemoryDependenceWrapperPass, "memdep",
                       "Memory Dependence Analysis", false, true)
 INITIALIZE_PASS_DEPENDENCY(AssumptionCacheTracker)
 INITIALIZE_PASS_DEPENDENCY(AAResultsWrapperPass)
 INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
 INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
+INITIALIZE_PASS_DEPENDENCY(PhiValuesWrapperPass)
 INITIALIZE_PASS_END(MemoryDependenceWrapperPass, "memdep",
                     "Memory Dependence Analysis", false, true)
 
 MemoryDependenceWrapperPass::MemoryDependenceWrapperPass() : FunctionPass(ID) {
   initializeMemoryDependenceWrapperPassPass(*PassRegistry::getPassRegistry());
 }
 
 MemoryDependenceWrapperPass::~MemoryDependenceWrapperPass() = default;
 
 void MemoryDependenceWrapperPass::releaseMemory() {
   MemDep.reset();
 }
 
 void MemoryDependenceWrapperPass::getAnalysisUsage(AnalysisUsage &AU) const {
   AU.setPreservesAll();
   AU.addRequired<AssumptionCacheTracker>();
   AU.addRequired<DominatorTreeWrapperPass>();
+  AU.addRequired<PhiValuesWrapperPass>();
   AU.addRequiredTransitive<AAResultsWrapperPass>();
   AU.addRequiredTransitive<TargetLibraryInfoWrapperPass>();
 }
 
 bool MemoryDependenceResults::invalidate(Function &F, const PreservedAnalyses &PA,
                                FunctionAnalysisManager::Invalidator &Inv) {
   // Check whether our analysis is preserved.
   auto PAC = PA.getChecker<MemoryDependenceAnalysis>();
   if (!PAC.preserved() && !PAC.preservedSet<AllAnalysesOn<Function>>())
     // If not, give up now.
     return true;
 
   // Check whether the analyses we depend on became invalid for any reason.
   if (Inv.invalidate<AAManager>(F, PA) ||
       Inv.invalidate<AssumptionAnalysis>(F, PA) ||
-      Inv.invalidate<DominatorTreeAnalysis>(F, PA))
+      Inv.invalidate<DominatorTreeAnalysis>(F, PA) ||
+      Inv.invalidate<PhiValuesAnalysis>(F, PA))
     return true;
 
   // Otherwise this analysis result remains valid.
   return false;
 }
 
 unsigned MemoryDependenceResults::getDefaultBlockScanLimit() const {
   return BlockScanLimit;
 }
 
 bool MemoryDependenceWrapperPass::runOnFunction(Function &F) {
   auto &AA = getAnalysis<AAResultsWrapperPass>().getAAResults();
   auto &AC = getAnalysis<AssumptionCacheTracker>().getAssumptionCache(F);
   auto &TLI = getAnalysis<TargetLibraryInfoWrapperPass>().getTLI();
   auto &DT = getAnalysis<DominatorTreeWrapperPass>().getDomTree();
-  MemDep.emplace(AA, AC, TLI, DT);
+  auto &PV = getAnalysis<PhiValuesWrapperPass>().getResult();
+  MemDep.emplace(AA, AC, TLI, DT, PV);
   return false;
 }

test/Other/new-pm-defaults.ll

 ; CHECK-EP-LOOP-LATE-NEXT: Running pass: NoOpLoopPass
 ; CHECK-O-NEXT: Running pass: LoopDeletionPass
 ; CHECK-O-NEXT: Running pass: LoopFullUnrollPass
 ; CHECK-EP-LOOP-END-NEXT: Running pass: NoOpLoopPass
 ; CHECK-O-NEXT: Finished Loop pass manager run.
 ; CHECK-Os-NEXT: Running pass: MergedLoadStoreMotionPass
 ; CHECK-Os-NEXT: Running pass: GVN
 ; CHECK-Os-NEXT: Running analysis: MemoryDependenceAnalysis
+; CHECK-Os-NEXT: Running analysis: PhiValuesAnalysis
 ; CHECK-Oz-NEXT: Running pass: MergedLoadStoreMotionPass
 ; CHECK-Oz-NEXT: Running pass: GVN
 ; CHECK-Oz-NEXT: Running analysis: MemoryDependenceAnalysis
+; CHECK-Oz-NEXT: Running analysis: PhiValuesAnalysis
 ; CHECK-O2-NEXT: Running pass: MergedLoadStoreMotionPass
 ; CHECK-O2-NEXT: Running pass: GVN
 ; CHECK-O2-NEXT: Running analysis: MemoryDependenceAnalysis
+; CHECK-O2-NEXT: Running analysis: PhiValuesAnalysis
 ; CHECK-O3-NEXT: Running pass: MergedLoadStoreMotionPass
 ; CHECK-O3-NEXT: Running pass: GVN
 ; CHECK-O3-NEXT: Running analysis: MemoryDependenceAnalysis
+; CHECK-O3-NEXT: Running analysis: PhiValuesAnalysis
 ; CHECK-O-NEXT: Running pass: MemCpyOptPass
 ; CHECK-O1-NEXT: Running analysis: MemoryDependenceAnalysis
+; CHECK-O1-NEXT: Running analysis: PhiValuesAnalysis
 ; CHECK-O-NEXT: Running pass: SCCPPass
 ; CHECK-O-NEXT: Running pass: BDCEPass
 ; CHECK-O-NEXT: Running analysis: DemandedBitsAnalysis
 ; CHECK-O-NEXT: Running pass: InstCombinePass
 ; CHECK-EP-PEEPHOLE-NEXT: Running pass: NoOpFunctionPass
 ; CHECK-O-NEXT: Running pass: JumpThreadingPass
 ; CHECK-O-NEXT: Running pass: CorrelatedValuePropagationPass
 ; CHECK-O-NEXT: Running pass: DSEPass

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

 ; CHECK-EP-Peephole-NEXT: Running pass: NoOpFunctionPass
 ; CHECK-O2-NEXT: Running pass: JumpThreadingPass
 ; CHECK-O2-NEXT: Running analysis: LazyValueAnalysis
 ; CHECK-O2-NEXT: Running pass: SROA on foo
 ; CHECK-O2-NEXT: Finished llvm::Function pass manager run.
 ; CHECK-O2-NEXT: Running pass: ModuleToPostOrderCGSCCPassAdaptor<{{.*}}PostOrderFunctionAttrsPass>
 ; CHECK-O2-NEXT: Running pass: ModuleToFunctionPassAdaptor<{{.*}}PassManager{{.*}}>
 ; CHECK-O2-NEXT: Running analysis: MemoryDependenceAnalysis
+; CHECK-O2-NEXT: Running analysis: PhiValuesAnalysis
 ; CHECK-O2-NEXT: Running analysis: DemandedBitsAnalysis
 ; CHECK-O2-NEXT: Running pass: CrossDSOCFIPass
 ; CHECK-O2-NEXT: Running pass: ModuleToFunctionPassAdaptor<{{.*}}SimplifyCFGPass>
 ; CHECK-O2-NEXT: Running pass: EliminateAvailableExternallyPass
 ; CHECK-O2-NEXT: Running pass: GlobalDCEPass
 ; CHECK-O-NEXT: Finished llvm::Module pass manager run.
 ; CHECK-O-NEXT: Running pass: PrintModulePass
 

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

 ; CHECK-O-NEXT: Running pass: IndVarSimplifyPass
 ; CHECK-O-NEXT: Running pass: LoopIdiomRecognizePass
 ; CHECK-O-NEXT: Running pass: LoopDeletionPass
 ; CHECK-O-NEXT: Running pass: LoopFullUnrollPass
 ; CHECK-O-NEXT: Finished Loop pass manager run.
 ; CHECK-Os-NEXT: Running pass: MergedLoadStoreMotionPass
 ; CHECK-Os-NEXT: Running pass: GVN
 ; CHECK-Os-NEXT: Running analysis: MemoryDependenceAnalysis
+; CHECK-Os-NEXT: Running analysis: PhiValuesAnalysis
 ; CHECK-Oz-NEXT: Running pass: MergedLoadStoreMotionPass
 ; CHECK-Oz-NEXT: Running pass: GVN
 ; CHECK-Oz-NEXT: Running analysis: MemoryDependenceAnalysis
+; CHECK-Oz-NEXT: Running analysis: PhiValuesAnalysis
 ; CHECK-O2-NEXT: Running pass: MergedLoadStoreMotionPass
 ; CHECK-O2-NEXT: Running pass: GVN
 ; CHECK-O2-NEXT: Running analysis: MemoryDependenceAnalysis
+; CHECK-O2-NEXT: Running analysis: PhiValuesAnalysis
 ; CHECK-O3-NEXT: Running pass: MergedLoadStoreMotionPass
 ; CHECK-O3-NEXT: Running pass: GVN
 ; CHECK-O3-NEXT: Running analysis: MemoryDependenceAnalysis
+; CHECK-O3-NEXT: Running analysis: PhiValuesAnalysis
 ; CHECK-O-NEXT: Running pass: MemCpyOptPass
 ; CHECK-O1-NEXT: Running analysis: MemoryDependenceAnalysis
+; CHECK-O1-NEXT: Running analysis: PhiValuesAnalysis
 ; CHECK-O-NEXT: Running pass: SCCPPass
 ; CHECK-O-NEXT: Running pass: BDCEPass
 ; CHECK-O-NEXT: Running analysis: DemandedBitsAnalysis
 ; CHECK-O-NEXT: Running pass: InstCombinePass
 ; CHECK-O-NEXT: Running pass: JumpThreadingPass
 ; CHECK-O-NEXT: Running pass: CorrelatedValuePropagationPass
 ; CHECK-O-NEXT: Running pass: DSEPass
 ; CHECK-O-NEXT: Running pass: FunctionToLoopPassAdaptor<{{.*}}LICMPass{{.*}}>

test/Other/opt-O2-pipeline.ll

 ; CHECK-NEXT:         Loop-Closed SSA Form Pass
 ; CHECK-NEXT:         Scalar Evolution Analysis
 ; CHECK-NEXT:         Loop Pass Manager
 ; CHECK-NEXT:           Induction Variable Simplification
 ; CHECK-NEXT:           Recognize loop idioms
 ; CHECK-NEXT:           Delete dead loops
 ; CHECK-NEXT:           Unroll loops
 ; CHECK-NEXT:         MergedLoadStoreMotion
+; CHECK-NEXT:         Phi Values Analysis
 ; CHECK-NEXT:         Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:         Function Alias Analysis Results
 ; CHECK-NEXT:         Memory Dependence Analysis
 ; CHECK-NEXT:         Lazy Branch Probability Analysis
 ; CHECK-NEXT:         Lazy Block Frequency Analysis
 ; CHECK-NEXT:         Optimization Remark Emitter
 ; CHECK-NEXT:         Global Value Numbering
+; CHECK-NEXT:         Phi Values Analysis
 ; CHECK-NEXT:         Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:         Function Alias Analysis Results
 ; CHECK-NEXT:         Memory Dependence Analysis
 ; CHECK-NEXT:         MemCpy Optimization
 ; CHECK-NEXT:         Sparse Conditional Constant Propagation
 ; CHECK-NEXT:         Demanded bits analysis
 ; CHECK-NEXT:         Bit-Tracking Dead Code Elimination
 ; CHECK-NEXT:         Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:         Function Alias Analysis Results
 ; CHECK-NEXT:         Natural Loop Information
 ; CHECK-NEXT:         Lazy Branch Probability Analysis
 ; CHECK-NEXT:         Lazy Block Frequency Analysis
 ; CHECK-NEXT:         Optimization Remark Emitter
 ; CHECK-NEXT:         Combine redundant instructions
 ; CHECK-NEXT:         Lazy Value Information Analysis
 ; CHECK-NEXT:         Jump Threading
 ; CHECK-NEXT:         Value Propagation
 ; CHECK-NEXT:         Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:         Function Alias Analysis Results
+; CHECK-NEXT:         Phi Values Analysis
 ; CHECK-NEXT:         Memory Dependence Analysis
 ; CHECK-NEXT:         Dead Store Elimination
 ; CHECK-NEXT:         Natural Loop Information
 ; CHECK-NEXT:         Canonicalize natural loops
 ; CHECK-NEXT:         LCSSA Verifier
 ; CHECK-NEXT:         Loop-Closed SSA Form Pass
 ; CHECK-NEXT:         Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:         Function Alias Analysis Results

test/Other/opt-O3-pipeline.ll

 ; CHECK-NEXT:         Loop-Closed SSA Form Pass
 ; CHECK-NEXT:         Scalar Evolution Analysis
 ; CHECK-NEXT:         Loop Pass Manager
 ; CHECK-NEXT:           Induction Variable Simplification
 ; CHECK-NEXT:           Recognize loop idioms
 ; CHECK-NEXT:           Delete dead loops
 ; CHECK-NEXT:           Unroll loops
 ; CHECK-NEXT:         MergedLoadStoreMotion
+; CHECK-NEXT:         Phi Values Analysis
 ; CHECK-NEXT:         Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:         Function Alias Analysis Results
 ; CHECK-NEXT:         Memory Dependence Analysis
 ; CHECK-NEXT:         Lazy Branch Probability Analysis
 ; CHECK-NEXT:         Lazy Block Frequency Analysis
 ; CHECK-NEXT:         Optimization Remark Emitter
 ; CHECK-NEXT:         Global Value Numbering
+; CHECK-NEXT:         Phi Values Analysis
 ; CHECK-NEXT:         Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:         Function Alias Analysis Results
 ; CHECK-NEXT:         Memory Dependence Analysis
 ; CHECK-NEXT:         MemCpy Optimization
 ; CHECK-NEXT:         Sparse Conditional Constant Propagation
 ; CHECK-NEXT:         Demanded bits analysis
 ; CHECK-NEXT:         Bit-Tracking Dead Code Elimination
 ; CHECK-NEXT:         Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:         Function Alias Analysis Results
 ; CHECK-NEXT:         Natural Loop Information
 ; CHECK-NEXT:         Lazy Branch Probability Analysis
 ; CHECK-NEXT:         Lazy Block Frequency Analysis
 ; CHECK-NEXT:         Optimization Remark Emitter
 ; CHECK-NEXT:         Combine redundant instructions
 ; CHECK-NEXT:         Lazy Value Information Analysis
 ; CHECK-NEXT:         Jump Threading
 ; CHECK-NEXT:         Value Propagation
 ; CHECK-NEXT:         Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:         Function Alias Analysis Results
+; CHECK-NEXT:         Phi Values Analysis
 ; CHECK-NEXT:         Memory Dependence Analysis
 ; CHECK-NEXT:         Dead Store Elimination
 ; CHECK-NEXT:         Natural Loop Information
 ; CHECK-NEXT:         Canonicalize natural loops
 ; CHECK-NEXT:         LCSSA Verifier
 ; CHECK-NEXT:         Loop-Closed SSA Form Pass
 ; CHECK-NEXT:         Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:         Function Alias Analysis Results

test/Other/opt-Os-pipeline.ll

 ; CHECK-NEXT:         Loop-Closed SSA Form Pass
 ; CHECK-NEXT:         Scalar Evolution Analysis
 ; CHECK-NEXT:         Loop Pass Manager
 ; CHECK-NEXT:           Induction Variable Simplification
 ; CHECK-NEXT:           Recognize loop idioms
 ; CHECK-NEXT:           Delete dead loops
 ; CHECK-NEXT:           Unroll loops
 ; CHECK-NEXT:         MergedLoadStoreMotion
+; CHECK-NEXT:         Phi Values Analysis
 ; CHECK-NEXT:         Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:         Function Alias Analysis Results
 ; CHECK-NEXT:         Memory Dependence Analysis
 ; CHECK-NEXT:         Lazy Branch Probability Analysis
 ; CHECK-NEXT:         Lazy Block Frequency Analysis
 ; CHECK-NEXT:         Optimization Remark Emitter
 ; CHECK-NEXT:         Global Value Numbering
+; CHECK-NEXT:         Phi Values Analysis
 ; CHECK-NEXT:         Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:         Function Alias Analysis Results
 ; CHECK-NEXT:         Memory Dependence Analysis
 ; CHECK-NEXT:         MemCpy Optimization
 ; CHECK-NEXT:         Sparse Conditional Constant Propagation
 ; CHECK-NEXT:         Demanded bits analysis
 ; CHECK-NEXT:         Bit-Tracking Dead Code Elimination
 ; CHECK-NEXT:         Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:         Function Alias Analysis Results
 ; CHECK-NEXT:         Natural Loop Information
 ; CHECK-NEXT:         Lazy Branch Probability Analysis
 ; CHECK-NEXT:         Lazy Block Frequency Analysis
 ; CHECK-NEXT:         Optimization Remark Emitter
 ; CHECK-NEXT:         Combine redundant instructions
 ; CHECK-NEXT:         Lazy Value Information Analysis
 ; CHECK-NEXT:         Jump Threading
 ; CHECK-NEXT:         Value Propagation
 ; CHECK-NEXT:         Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:         Function Alias Analysis Results
+; CHECK-NEXT:         Phi Values Analysis
 ; CHECK-NEXT:         Memory Dependence Analysis
 ; CHECK-NEXT:         Dead Store Elimination
 ; CHECK-NEXT:         Natural Loop Information
 ; CHECK-NEXT:         Canonicalize natural loops
 ; CHECK-NEXT:         LCSSA Verifier
 ; CHECK-NEXT:         Loop-Closed SSA Form Pass
 ; CHECK-NEXT:         Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:         Function Alias Analysis Results

test/Transforms/GVN/PRE/pre-after-rle.ll

 
 ; CHECK-LABEL: preheader:
 ; CHECK: %s = phi i32* [ %s, %body ], [ %gep, %else ], [ %call.cast, %if ]
 
 preheader:
   %cmp = icmp slt i32 1, %h
   br i1 %cmp, label %body, label %exit
 
-; Alias analysis currently can't figure out %width doesn't alias %s, so just
-; check that the redundant load has been removed.
+; CHECK-LABEL: preheader.body_crit_edge:
+; CHECK: load i32, i32* %width, align 8
+
 ; CHECK-LABEL: body:
 ; CHECK-NOT: load i32*, i32** %start, align 8
+; CHECK-NOT: load i32, i32* %width, align 8
 body:
   %j = phi i32 [ 0, %preheader ], [ %j.next, %body ]
   %s = load i32*, i32** %start, align 8
   %idx = getelementptr inbounds i32, i32* %s, i64 0
   store i32 0, i32* %idx, align 4
   %j.next = add nuw nsw i32 %j, 1
   %w = load i32, i32* %width, align 8
   %cmp3 = icmp slt i32 %j.next, %w
   br i1 %cmp3, label %body, label %preheader
 
 exit:
   ret void
 }