Commit ead81592 authored by Kazu Hirata's avatar Kazu Hirata
Browse files

[JumpThreading] Thread jumps through two basic blocks 

Summary:
This patch teaches JumpThreading.cpp to thread through two basic
blocks like:

  bb3:
    %var = phi i32* [ null, %bb1 ], [ @a, %bb2 ]
    %tobool = icmp eq i32 %cond, 0
    br i1 %tobool, label %bb4, label ...

  bb4:
    %cmp = icmp eq i32* %var, null
    br i1 %cmp, label bb5, label bb6

by duplicating basic blocks like bb3 above.  Once we duplicate bb3 as
bb3.dup and redirect edge bb2->bb3 to bb2->bb3.dup, we have:

  bb3:
    %var = phi i32* [ @a, %bb2 ]
    %tobool = icmp eq i32 %cond, 0
    br i1 %tobool, label %bb4, label ...

  bb3.dup:
    %var = phi i32* [ null, %bb1 ]
    %tobool = icmp eq i32 %cond, 0
    br i1 %tobool, label %bb4, label ...

  bb4:
    %cmp = icmp eq i32* %var, null
    br i1 %cmp, label bb5, label bb6

Then the existing code in JumpThreading.cpp can thread edge
bb3.dup->bb4 through bb4 and eventually create bb3.dup->bb5.

Reviewers: wmi

Subscribers: hiraditya, jfb, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D70247
parent dac7b23c

llvm/include/llvm/Transforms/Scalar/JumpThreading.h

+5 −0
Original line number Diff line number Diff line
@@ -139,6 +139,11 @@ public: 
                                               RecursionSet, CxtI);

  }



  Constant *EvaluateOnPredecessorEdge(BasicBlock *BB, BasicBlock *PredPredBB,

                                      Value *cond);

  bool MaybeThreadThroughTwoBasicBlocks(BasicBlock *BB, Value *Cond);

  void ThreadThroughTwoBasicBlocks(BasicBlock *PredPredBB, BasicBlock *PredBB,

                                   BasicBlock *BB, BasicBlock *SuccBB);

  bool ProcessThreadableEdges(Value *Cond, BasicBlock *BB,

                              jumpthreading::ConstantPreference Preference,

                              Instruction *CxtI = nullptr);

llvm/lib/Transforms/Scalar/JumpThreading.cpp

+228 −2
Original line number Diff line number Diff line
@@ -1548,6 +1548,52 @@ FindMostPopularDest(BasicBlock *BB, 
  return MostPopularDest;

}



// Try to evaluate the value of V when the control flows from PredPredBB to

// BB->getSinglePredecessor() and then on to BB.

Constant *JumpThreadingPass::EvaluateOnPredecessorEdge(BasicBlock *BB,

                                                       BasicBlock *PredPredBB,

                                                       Value *V) {

  BasicBlock *PredBB = BB->getSinglePredecessor();

  assert(PredBB && "Expected a single predecessor");



  if (Constant *Cst = dyn_cast<Constant>(V)) {

    return Cst;

  }



  // Consult LVI if V is not an instruction in BB or PredBB.

  Instruction *I = dyn_cast<Instruction>(V);

  if (!I || (I->getParent() != BB && I->getParent() != PredBB)) {

    if (DTU->hasPendingDomTreeUpdates())

      LVI->disableDT();

    else

      LVI->enableDT();

    return LVI->getConstantOnEdge(V, PredPredBB, PredBB, nullptr);

  }



  // Look into a PHI argument.

  if (PHINode *PHI = dyn_cast<PHINode>(V)) {

    if (PHI->getParent() == PredBB)

      return dyn_cast<Constant>(PHI->getIncomingValueForBlock(PredPredBB));

    return nullptr;

  }



  // If we have a CmpInst, try to fold it for each incoming edge into PredBB.

  if (CmpInst *CondCmp = dyn_cast<CmpInst>(V)) {

    if (CondCmp->getParent() == BB) {

      Constant *Op0 =

          EvaluateOnPredecessorEdge(BB, PredPredBB, CondCmp->getOperand(0));

      Constant *Op1 =

          EvaluateOnPredecessorEdge(BB, PredPredBB, CondCmp->getOperand(1));

      if (Op0 && Op1) {

        return ConstantExpr::getCompare(CondCmp->getPredicate(), Op0, Op1);

      }

    }

    return nullptr;

  }



  return nullptr;

}



bool JumpThreadingPass::ProcessThreadableEdges(Value *Cond, BasicBlock *BB,

                                               ConstantPreference Preference,

                                               Instruction *CxtI) {
@@ -1557,8 +1603,12 @@ bool JumpThreadingPass::ProcessThreadableEdges(Value *Cond, BasicBlock *BB, 
    return false;



  PredValueInfoTy PredValues;

  if (!ComputeValueKnownInPredecessors(Cond, BB, PredValues, Preference, CxtI))

    return false;

  if (!ComputeValueKnownInPredecessors(Cond, BB, PredValues, Preference,

                                       CxtI)) {

    // We don't have known values in predecessors.  See if we can thread through

    // BB and its sole predecessor.

    return MaybeThreadThroughTwoBasicBlocks(BB, Cond);

  }



  assert(!PredValues.empty() &&

         "ComputeValueKnownInPredecessors returned true with no values");
@@ -2015,6 +2065,182 @@ JumpThreadingPass::CloneInstructions(BasicBlock::iterator BI, 
  return ValueMapping;

}



/// Attempt to thread through two successive basic blocks.

bool JumpThreadingPass::MaybeThreadThroughTwoBasicBlocks(BasicBlock *BB,

                                                         Value *Cond) {

  // Consider:

  //

  // PredBB:

  //   %var = phi i32* [ null, %bb1 ], [ @a, %bb2 ]

  //   %tobool = icmp eq i32 %cond, 0

  //   br i1 %tobool, label %BB, label ...

  //

  // BB:

  //   %cmp = icmp eq i32* %var, null

  //   br i1 %cmp, label ..., label ...

  //

  // We don't know the value of %var at BB even if we know which incoming edge

  // we take to BB.  However, once we duplicate PredBB for each of its incoming

  // edges (say, PredBB1 and PredBB2), we know the value of %var in each copy of

  // PredBB.  Then we can thread edges PredBB1->BB and PredBB2->BB through BB.



  // Require that BB end with a Branch for simplicity.

  BranchInst *CondBr = dyn_cast<BranchInst>(BB->getTerminator());

  if (!CondBr)

    return false;



  // BB must have exactly one predecessor.

  BasicBlock *PredBB = BB->getSinglePredecessor();

  if (!PredBB)

    return false;



  // Require that PredBB end with a Branch.  If PredBB ends with an

  // unconditional branch, we should be merging PredBB and BB instead.  For

  // simplicity, we don't deal with a switch.

  BranchInst *PredBBBranch = dyn_cast<BranchInst>(PredBB->getTerminator());

  if (!PredBBBranch)

    return false;



  // If PredBB has exactly one incoming edge, we don't gain anything by copying

  // PredBB.

  if (PredBB->getSinglePredecessor())

    return false;



  // Don't thread across a loop header.

  if (LoopHeaders.count(PredBB))

    return false;



  // Find a predecessor that we can thread.  For simplicity, we only consider a

  // successor edge out of BB to which we thread exactly one incoming edge into

  // PredBB.

  unsigned ZeroCount = 0;

  unsigned OneCount = 0;

  BasicBlock *ZeroPred = nullptr;

  BasicBlock *OnePred = nullptr;

  for (BasicBlock *P : predecessors(PredBB)) {

    if (Constant *Cst = EvaluateOnPredecessorEdge(BB, P, Cond)) {

      if (Cst->isZeroValue()) {

        ZeroCount++;

        ZeroPred = P;

      } else {

        OneCount++;

        OnePred = P;

      }

    }

  }



  // Disregard complicated cases where we have to thread multiple edges.

  BasicBlock *PredPredBB;

  if (ZeroCount == 1) {

    PredPredBB = ZeroPred;

  } else if (OneCount == 1) {

    PredPredBB = OnePred;

  } else {

    return false;

  }



  BasicBlock *SuccBB = CondBr->getSuccessor(PredPredBB == ZeroPred);



  // If threading to the same block as we come from, we would infinite loop.

  if (SuccBB == BB) {

    LLVM_DEBUG(dbgs() << "  Not threading across BB '" << BB->getName()

                      << "' - would thread to self!\n");

    return false;

  }



  // If threading this would thread across a loop header, don't thread the edge.

  // See the comments above FindLoopHeaders for justifications and caveats.

  if (LoopHeaders.count(BB) || LoopHeaders.count(SuccBB)) {

    LLVM_DEBUG({

      bool BBIsHeader = LoopHeaders.count(BB);

      bool SuccIsHeader = LoopHeaders.count(SuccBB);

      dbgs() << "  Not threading across "

             << (BBIsHeader ? "loop header BB '" : "block BB '")

             << BB->getName() << "' to dest "

             << (SuccIsHeader ? "loop header BB '" : "block BB '")

             << SuccBB->getName()

             << "' - it might create an irreducible loop!\n";

    });

    return false;

  }



  // Check the cost of duplicating BB and PredBB.

  unsigned JumpThreadCost =

      getJumpThreadDuplicationCost(BB, BB->getTerminator(), BBDupThreshold);

  JumpThreadCost += getJumpThreadDuplicationCost(

      PredBB, PredBB->getTerminator(), BBDupThreshold);

  if (JumpThreadCost > BBDupThreshold) {

    LLVM_DEBUG(dbgs() << "  Not threading BB '" << BB->getName()

                      << "' - Cost is too high: " << JumpThreadCost << "\n");

    return false;

  }



  // Now we are ready to duplicate PredBB.

  ThreadThroughTwoBasicBlocks(PredPredBB, PredBB, BB, SuccBB);

  return true;

}



void JumpThreadingPass::ThreadThroughTwoBasicBlocks(BasicBlock *PredPredBB,

                                                    BasicBlock *PredBB,

                                                    BasicBlock *BB,

                                                    BasicBlock *SuccBB) {

  LLVM_DEBUG(dbgs() << "  Threading through '" << PredBB->getName() << "' and '"

                    << BB->getName() << "'\n");



  BranchInst *CondBr = cast<BranchInst>(BB->getTerminator());

  BranchInst *PredBBBranch = cast<BranchInst>(PredBB->getTerminator());



  BasicBlock *NewBB =

      BasicBlock::Create(PredBB->getContext(), PredBB->getName() + ".thread",

                         PredBB->getParent(), PredBB);

  NewBB->moveAfter(PredBB);



  // Set the block frequency of NewBB.

  if (HasProfileData) {

    auto NewBBFreq = BFI->getBlockFreq(PredPredBB) *

                     BPI->getEdgeProbability(PredPredBB, PredBB);

    BFI->setBlockFreq(NewBB, NewBBFreq.getFrequency());

  }



  // We are going to have to map operands from the original BB block to the new

  // copy of the block 'NewBB'.  If there are PHI nodes in PredBB, evaluate them

  // to account for entry from PredPredBB.

  DenseMap<Instruction *, Value *> ValueMapping =

      CloneInstructions(PredBB->begin(), PredBB->end(), NewBB, PredPredBB);



  // Update the terminator of PredPredBB to jump to NewBB instead of PredBB.

  // This eliminates predecessors from PredPredBB, which requires us to simplify

  // any PHI nodes in PredBB.

  Instruction *PredPredTerm = PredPredBB->getTerminator();

  for (unsigned i = 0, e = PredPredTerm->getNumSuccessors(); i != e; ++i)

    if (PredPredTerm->getSuccessor(i) == PredBB) {

      PredBB->removePredecessor(PredPredBB, true);

      PredPredTerm->setSuccessor(i, NewBB);

    }



  AddPHINodeEntriesForMappedBlock(PredBBBranch->getSuccessor(0), PredBB, NewBB,

                                  ValueMapping);

  AddPHINodeEntriesForMappedBlock(PredBBBranch->getSuccessor(1), PredBB, NewBB,

                                  ValueMapping);



  DTU->applyUpdatesPermissive(

      {{DominatorTree::Insert, NewBB, CondBr->getSuccessor(0)},

       {DominatorTree::Insert, NewBB, CondBr->getSuccessor(1)},

       {DominatorTree::Insert, PredPredBB, NewBB},

       {DominatorTree::Delete, PredPredBB, PredBB}});



  UpdateSSA(PredBB, NewBB, ValueMapping);



  // Clean up things like PHI nodes with single operands, dead instructions,

  // etc.

  SimplifyInstructionsInBlock(NewBB, TLI);

  SimplifyInstructionsInBlock(PredBB, TLI);



  SmallVector<BasicBlock *, 1> PredsToFactor;

  PredsToFactor.push_back(NewBB);

  ThreadEdge(BB, PredsToFactor, SuccBB);

}



/// TryThreadEdge - Thread an edge if it's safe and profitable to do so.

bool JumpThreadingPass::TryThreadEdge(

    BasicBlock *BB, const SmallVectorImpl<BasicBlock *> &PredBBs,

llvm/test/Transforms/JumpThreading/thread-two-bbs1.ll

0 → 100644
+59 −0
Original line number Diff line number Diff line 
; RUN: opt < %s -jump-threading -S -verify | FileCheck %s



target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"

target triple = "x86_64-unknown-linux-gnu"



@a = global i32 0, align 4



define void @foo(i32 %cond1, i32 %cond2) {

; CHECK-LABEL: @foo

; CHECK-LABEL: entry

entry:

  %tobool = icmp eq i32 %cond1, 0

  br i1 %tobool, label %bb.cond2, label %bb.f1



bb.f1:

  call void @f1()

  br label %bb.cond2

; Verify that we branch on cond2 without checking ptr.

; CHECK:      call void @f1()

; CHECK-NEXT: icmp eq i32 %cond2, 0

; CHECK-NEXT: label %bb.f4, label %bb.f2



bb.cond2:

  %ptr = phi i32* [ null, %bb.f1 ], [ @a, %entry ]

  %tobool1 = icmp eq i32 %cond2, 0

  br i1 %tobool1, label %bb.file, label %bb.f2

; Verify that we branch on cond2 without checking ptr.

; CHECK:      icmp eq i32 %cond2, 0

; CHECK-NEXT: label %bb.f3, label %bb.f2



bb.f2:

  call void @f2()

  br label %exit



; Verify that we eliminate this basic block.

; CHECK-NOT: bb.file:

bb.file:

  %cmp = icmp eq i32* %ptr, null

  br i1 %cmp, label %bb.f4, label %bb.f3



bb.f3:

  call void @f3()

  br label %exit



bb.f4:

  call void @f4()

  br label %exit



exit:

  ret void

}



declare void @f1()



declare void @f2()



declare void @f3()



declare void @f4()

llvm/test/Transforms/JumpThreading/thread-two-bbs2.ll

0 → 100644
+56 −0
Original line number Diff line number Diff line 
; RUN: opt < %s -jump-threading -S -verify | FileCheck %s



target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"

target triple = "x86_64-unknown-linux-gnu"



define void @foo(i32 %cond1, i32 %cond2) {

; CHECK-LABEL: @foo

; CHECK-LABEL: entry

entry:

  %tobool = icmp ne i32 %cond1, 0

  br i1 %tobool, label %bb.f1, label %bb.f2



bb.f1:

  call void @f1()

  br label %bb.cond2

; Verify that we branch on cond2 without checking tobool again.

; CHECK:      call void @f1()

; CHECK-NEXT: icmp eq i32 %cond2, 0

; CHECK-NEXT: label %exit, label %bb.f3



bb.f2:

  call void @f2()

  br label %bb.cond2

; Verify that we branch on cond2 without checking tobool again.

; CHECK:      call void @f2()

; CHECK-NEXT: icmp eq i32 %cond2, 0

; CHECK-NEXT: label %exit, label %bb.f4



bb.cond2:

  %tobool1 = icmp eq i32 %cond2, 0

  br i1 %tobool1, label %exit, label %bb.cond1again



; Verify that we eliminate this basic block.

; CHECK-NOT: bb.cond1again:

bb.cond1again:

  br i1 %tobool, label %bb.f3, label %bb.f4



bb.f3:

  call void @f3()

  br label %exit



bb.f4:

  call void @f4()

  br label %exit



exit:

  ret void

}



declare void @f1() local_unnamed_addr



declare void @f2() local_unnamed_addr



declare void @f3() local_unnamed_addr



declare void @f4() local_unnamed_addr