[llvm] r246243 - Constant propagation after hiting llvm.assume

Philip Reames via llvm-commits llvm-commits at lists.llvm.org
Fri Aug 28 09:54:21 PDT 2015


Piotr,

I'm a bit confused by the need for the ReplaceWithConstMap variable in 
this patch.  Wouldn't simply calling replaceDominatedUsesWith be 
sufficient?  Is there a reason to prefer the BB local variable?

Philip


On 08/27/2015 06:01 PM, Piotr Padlewski via llvm-commits wrote:
> Author: prazek
> Date: Thu Aug 27 20:01:57 2015
> New Revision: 246243
>
> URL: http://llvm.org/viewvc/llvm-project?rev=246243&view=rev
> Log:
> Constant propagation after hiting llvm.assume
>
> After hitting @llvm.assume(X) we can:
> - propagate equality that X == true
> - if X is icmp/fcmp (with eq operation), and one of operand
>    is constant we can change all variables with constants in the same BasicBlock
>
> http://reviews.llvm.org/D11918
>
> Added:
>      llvm/trunk/test/Transforms/GVN/assume-equal.ll
> Modified:
>      llvm/trunk/lib/Transforms/Scalar/GVN.cpp
>
> Modified: llvm/trunk/lib/Transforms/Scalar/GVN.cpp
> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Transforms/Scalar/GVN.cpp?rev=246243&r1=246242&r2=246243&view=diff
> ==============================================================================
> --- llvm/trunk/lib/Transforms/Scalar/GVN.cpp (original)
> +++ llvm/trunk/lib/Transforms/Scalar/GVN.cpp Thu Aug 27 20:01:57 2015
> @@ -608,6 +608,10 @@ namespace {
>       DenseMap<uint32_t, LeaderTableEntry> LeaderTable;
>       BumpPtrAllocator TableAllocator;
>   
> +    // Block-local map of equivalent values to their leader, does not
> +    // propagate to any successors. Entries added mid-block are applied
> +    // to the remaining instructions in the block.
> +    SmallMapVector<llvm::Value *, llvm::Constant *, 4> ReplaceWithConstMap;
>       SmallVector<Instruction*, 8> InstrsToErase;
>   
>       typedef SmallVector<NonLocalDepResult, 64> LoadDepVect;
> @@ -699,6 +703,7 @@ namespace {
>       // Helper functions of redundant load elimination
>       bool processLoad(LoadInst *L);
>       bool processNonLocalLoad(LoadInst *L);
> +    bool processAssumeIntrinsic(IntrinsicInst *II);
>       void AnalyzeLoadAvailability(LoadInst *LI, LoadDepVect &Deps,
>                                    AvailValInBlkVect &ValuesPerBlock,
>                                    UnavailBlkVect &UnavailableBlocks);
> @@ -719,6 +724,7 @@ namespace {
>       void verifyRemoved(const Instruction *I) const;
>       bool splitCriticalEdges();
>       BasicBlock *splitCriticalEdges(BasicBlock *Pred, BasicBlock *Succ);
> +    bool replaceOperandsWithConsts(Instruction *I) const;
>       bool propagateEquality(Value *LHS, Value *RHS, const BasicBlockEdge &Root);
>       bool processFoldableCondBr(BranchInst *BI);
>       void addDeadBlock(BasicBlock *BB);
> @@ -1760,6 +1766,38 @@ bool GVN::processNonLocalLoad(LoadInst *
>     return PerformLoadPRE(LI, ValuesPerBlock, UnavailableBlocks);
>   }
>   
> +bool GVN::processAssumeIntrinsic(IntrinsicInst *IntrinsicI) {
> +  assert(IntrinsicI->getIntrinsicID() == Intrinsic::assume &&
> +         "This function can only be called with llvm.assume intrinsic");
> +  Value *V = IntrinsicI->getArgOperand(0);
> +  Constant *True = ConstantInt::getTrue(V->getContext());
> +  bool Changed = false;
> +  for (BasicBlock *Successor : successors(IntrinsicI->getParent())) {
> +    BasicBlockEdge Edge(IntrinsicI->getParent(), Successor);
> +
> +    // This property is only true in dominated successors, propagateEquality
> +    // will check dominance for us.
> +    Changed |= propagateEquality(V, True, Edge);
> +  }
> +
> +  if (auto *CmpI = dyn_cast<CmpInst>(V)) {
> +    if (CmpI->getPredicate() == CmpInst::Predicate::ICMP_EQ ||
> +        CmpI->getPredicate() == CmpInst::Predicate::FCMP_OEQ ||
> +        (CmpI->getPredicate() == CmpInst::Predicate::FCMP_UEQ &&
> +         CmpI->getFastMathFlags().noNaNs())) {
> +      Value *CmpLHS = CmpI->getOperand(0);
> +      Value *CmpRHS = CmpI->getOperand(1);
> +      if (isa<Constant>(CmpLHS))
> +        std::swap(CmpLHS, CmpRHS);
> +      auto *RHSConst = dyn_cast<Constant>(CmpRHS);
> +
> +      // If only one operand is constant.
> +      if (RHSConst != nullptr && !isa<Constant>(CmpLHS))
> +        ReplaceWithConstMap[CmpLHS] = RHSConst;
> +    }
> +  }
> +  return Changed;
> +}
>   
>   static void patchReplacementInstruction(Instruction *I, Value *Repl) {
>     // Patch the replacement so that it is not more restrictive than the value
> @@ -2032,6 +2070,21 @@ static bool isOnlyReachableViaThisEdge(c
>     return Pred != nullptr;
>   }
>   
> +// Tries to replace instruction with const, using information from
> +// ReplaceWithConstMap.
> +bool GVN::replaceOperandsWithConsts(Instruction *Instr) const {
> +  bool Changed = false;
> +  for (unsigned OpNum = 0; OpNum < Instr->getNumOperands(); ++OpNum) {
> +    Value *Operand = Instr->getOperand(OpNum);
> +    auto it = ReplaceWithConstMap.find(Operand);
> +    if (it != ReplaceWithConstMap.end()) {
> +      Instr->setOperand(OpNum, it->second);
> +      Changed = true;
> +    }
> +  }
> +  return Changed;
> +}
> +
>   /// The given values are known to be equal in every block
>   /// dominated by 'Root'.  Exploit this, for example by replacing 'LHS' with
>   /// 'RHS' everywhere in the scope.  Returns whether a change was made.
> @@ -2048,11 +2101,13 @@ bool GVN::propagateEquality(Value *LHS,
>       std::pair<Value*, Value*> Item = Worklist.pop_back_val();
>       LHS = Item.first; RHS = Item.second;
>   
> -    if (LHS == RHS) continue;
> +    if (LHS == RHS)
> +      continue;
>       assert(LHS->getType() == RHS->getType() && "Equality but unequal types!");
>   
>       // Don't try to propagate equalities between constants.
> -    if (isa<Constant>(LHS) && isa<Constant>(RHS)) continue;
> +    if (isa<Constant>(LHS) && isa<Constant>(RHS))
> +      continue;
>   
>       // Prefer a constant on the right-hand side, or an Argument if no constants.
>       if (isa<Constant>(LHS) || (isa<Argument>(LHS) && !isa<Constant>(RHS)))
> @@ -2203,6 +2258,10 @@ bool GVN::processInstruction(Instruction
>       return true;
>     }
>   
> +  if (IntrinsicInst *IntrinsicI = dyn_cast<IntrinsicInst>(I))
> +    if (IntrinsicI->getIntrinsicID() == Intrinsic::assume)
> +      return processAssumeIntrinsic(IntrinsicI);
> +
>     if (LoadInst *LI = dyn_cast<LoadInst>(I)) {
>       if (processLoad(LI))
>         return true;
> @@ -2267,7 +2326,8 @@ bool GVN::processInstruction(Instruction
>   
>     // Instructions with void type don't return a value, so there's
>     // no point in trying to find redundancies in them.
> -  if (I->getType()->isVoidTy()) return false;
> +  if (I->getType()->isVoidTy())
> +    return false;
>   
>     uint32_t NextNum = VN.getNextUnusedValueNumber();
>     unsigned Num = VN.lookup_or_add(I);
> @@ -2374,10 +2434,15 @@ bool GVN::processBlock(BasicBlock *BB) {
>     if (DeadBlocks.count(BB))
>       return false;
>   
> +  // Clearing map before every BB because it can be used only for single BB.
> +  ReplaceWithConstMap.clear();
>     bool ChangedFunction = false;
>   
>     for (BasicBlock::iterator BI = BB->begin(), BE = BB->end();
>          BI != BE;) {
> +    if (!ReplaceWithConstMap.empty())
> +      ChangedFunction |= replaceOperandsWithConsts(BI);
> +
>       ChangedFunction |= processInstruction(BI);
>       if (InstrsToErase.empty()) {
>         ++BI;
>
> Added: llvm/trunk/test/Transforms/GVN/assume-equal.ll
> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/GVN/assume-equal.ll?rev=246243&view=auto
> ==============================================================================
> --- llvm/trunk/test/Transforms/GVN/assume-equal.ll (added)
> +++ llvm/trunk/test/Transforms/GVN/assume-equal.ll Thu Aug 27 20:01:57 2015
> @@ -0,0 +1,122 @@
> +; RUN: opt < %s -gvn -S | FileCheck %s
> +
> +%struct.A = type { i32 (...)** }
> + at _ZTV1A = available_externally unnamed_addr constant [4 x i8*] [i8* null, i8* bitcast (i8** @_ZTI1A to i8*), i8* bitcast (i32 (%struct.A*)* @_ZN1A3fooEv to i8*), i8* bitcast (i32 (%struct.A*)* @_ZN1A3barEv to i8*)], align 8
> + at _ZTI1A = external constant i8*
> +
> +; Checks if indirect calls can be replaced with direct
> +; assuming that %vtable == @_ZTV1A (with alignment).
> +; Checking const propagation across other BBs
> +; CHECK-LABEL: define void @_Z1gb(
> +
> +define void @_Z1gb(i1 zeroext %p) {
> +entry:
> +  %call = tail call noalias i8* @_Znwm(i64 8) #4
> +  %0 = bitcast i8* %call to %struct.A*
> +  tail call void @_ZN1AC1Ev(%struct.A* %0) #1
> +  %1 = bitcast i8* %call to i8***
> +  %vtable = load i8**, i8*** %1, align 8
> +  %cmp.vtables = icmp eq i8** %vtable, getelementptr inbounds ([4 x i8*], [4 x i8*]* @_ZTV1A, i64 0, i64 2)
> +  tail call void @llvm.assume(i1 %cmp.vtables)
> +  br i1 %p, label %if.then, label %if.else
> +
> +if.then:                                          ; preds = %entry
> +  %vtable1.cast = bitcast i8** %vtable to i32 (%struct.A*)**
> +  %2 = load i32 (%struct.A*)*, i32 (%struct.A*)** %vtable1.cast, align 8
> +
> +  ; CHECK: call i32 @_ZN1A3fooEv(
> +  %call2 = tail call i32 %2(%struct.A* %0) #1
> +
> +  br label %if.end
> +
> +if.else:                                          ; preds = %entry
> +  %vfn47 = getelementptr inbounds i8*, i8** %vtable, i64 1
> +  %vfn4 = bitcast i8** %vfn47 to i32 (%struct.A*)**
> +
> +  ; CHECK: call i32 @_ZN1A3barEv(
> +  %3 = load i32 (%struct.A*)*, i32 (%struct.A*)** %vfn4, align 8
> +
> +  %call5 = tail call i32 %3(%struct.A* %0) #1
> +  br label %if.end
> +
> +if.end:                                           ; preds = %if.else, %if.then
> +  ret void
> +}
> +
> +; Checking const propagation in the same BB
> +; CHECK-LABEL: define i32 @main()
> +
> +define i32 @main() {
> +entry:
> +  %call = tail call noalias i8* @_Znwm(i64 8)
> +  %0 = bitcast i8* %call to %struct.A*
> +  tail call void @_ZN1AC1Ev(%struct.A* %0)
> +  %1 = bitcast i8* %call to i8***
> +  %vtable = load i8**, i8*** %1, align 8
> +  %cmp.vtables = icmp eq i8** %vtable, getelementptr inbounds ([4 x i8*], [4 x i8*]* @_ZTV1A, i64 0, i64 2)
> +  tail call void @llvm.assume(i1 %cmp.vtables)
> +  %vtable1.cast = bitcast i8** %vtable to i32 (%struct.A*)**
> +
> +  ; CHECK: call i32 @_ZN1A3fooEv(
> +  %2 = load i32 (%struct.A*)*, i32 (%struct.A*)** %vtable1.cast, align 8
> +
> +  %call2 = tail call i32 %2(%struct.A* %0)
> +  ret i32 0
> +}
> +
> +; This tests checks const propatation with fcmp instruction.
> +; CHECK-LABEL: define float @_Z1gf(float %p)
> +
> +define float @_Z1gf(float %p) {
> +entry:
> +  %p.addr = alloca float, align 4
> +  %f = alloca float, align 4
> +  store float %p, float* %p.addr, align 4
> +
> +  store float 3.000000e+00, float* %f, align 4
> +  %0 = load float, float* %p.addr, align 4
> +  %1 = load float, float* %f, align 4
> +  %cmp = fcmp oeq float %1, %0 ; note const on lhs
> +  call void @llvm.assume(i1 %cmp)
> +
> +  ; CHECK: ret float 3.000000e+00
> +  ret float %0
> +}
> +
> +; CHECK-LABEL: define float @_Z1hf(float %p)
> +
> +define float @_Z1hf(float %p) {
> +entry:
> +  %p.addr = alloca float, align 4
> +  store float %p, float* %p.addr, align 4
> +
> +  %0 = load float, float* %p.addr, align 4
> +  %cmp = fcmp nnan ueq float %0, 3.000000e+00
> +  call void @llvm.assume(i1 %cmp)
> +
> +  ; CHECK: ret float 3.000000e+00
> +  ret float %0
> +}
> +
> +; CHECK-LABEL: define float @_Z1if(float %p)
> +
> +
> +define float @_Z1if(float %p) {
> +entry:
> +  %p.addr = alloca float, align 4
> +  store float %p, float* %p.addr, align 4
> +
> +  %0 = load float, float* %p.addr, align 4
> +  %cmp = fcmp ueq float %0, 3.000000e+00 ; no nnan flag - can't propagate
> +  call void @llvm.assume(i1 %cmp)
> +
> +  ; CHECK-NOT: ret float 3.000000e+00
> +  ret float %0
> +}
> +
> +declare noalias i8* @_Znwm(i64)
> +declare void @_ZN1AC1Ev(%struct.A*)
> +declare void @llvm.assume(i1)
> +declare i32 @_ZN1A3fooEv(%struct.A*)
> +declare i32 @_ZN1A3barEv(%struct.A*)
> +
>
>
> _______________________________________________
> llvm-commits mailing list
> llvm-commits at lists.llvm.org
> http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-commits



More information about the llvm-commits mailing list