[llvm] r205086 - CodeGenPrep: wrangle IR to exploit AArch64 tbz/tbnz inst.
Tim Northover
tnorthover at apple.com
Sat Mar 29 01:22:29 PDT 2014
Author: tnorthover
Date: Sat Mar 29 03:22:29 2014
New Revision: 205086
URL: http://llvm.org/viewvc/llvm-project?rev=205086&view=rev
Log:
CodeGenPrep: wrangle IR to exploit AArch64 tbz/tbnz inst.
Given IR like:
%bit = and %val, #imm-with-1-bit-set
%tst = icmp %bit, 0
br i1 %tst, label %true, label %false
some targets can emit just a single instruction (tbz/tbnz in the
AArch64 case). However, with ISel acting at the basic-block level, all
three instructions need to be together for this to be possible.
This adds another transformation to CodeGenPrep to expose these
opportunities, if targets opt in via the hook.
Modified:
llvm/trunk/include/llvm/Target/TargetLowering.h
llvm/trunk/lib/CodeGen/CodeGenPrepare.cpp
llvm/trunk/lib/CodeGen/TargetLoweringBase.cpp
Modified: llvm/trunk/include/llvm/Target/TargetLowering.h
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/Target/TargetLowering.h?rev=205086&r1=205085&r2=205086&view=diff
==============================================================================
--- llvm/trunk/include/llvm/Target/TargetLowering.h (original)
+++ llvm/trunk/include/llvm/Target/TargetLowering.h Sat Mar 29 03:22:29 2014
@@ -222,6 +222,21 @@ public:
return true;
}
+ /// \brief Return if the target supports combining a
+ /// chain like:
+ /// \code
+ /// %andResult = and %val1, #imm-with-one-bit-set;
+ /// %icmpResult = icmp %andResult, 0
+ /// br i1 %icmpResult, label %dest1, label %dest2
+ /// \endcode
+ /// into a single machine instruction of a form like:
+ /// \code
+ /// brOnBitSet %register, #bitNumber, dest
+ /// \endcode
+ bool isMaskAndBranchFoldingLegal() const {
+ return MaskAndBranchFoldingIsLegal;
+ }
+
/// Return the ValueType of the result of SETCC operations. Also used to
/// obtain the target's preferred type for the condition operand of SELECT and
/// BRCOND nodes. In the case of BRCOND the argument passed is MVT::Other
@@ -1724,6 +1739,10 @@ protected:
/// the branch is usually predicted right.
bool PredictableSelectIsExpensive;
+ /// MaskAndBranchFoldingIsLegal - Indicates if the target supports folding
+ /// a mask of a single bit, a compare, and a branch into a single instruction.
+ bool MaskAndBranchFoldingIsLegal;
+
protected:
/// Return true if the value types that can be represented by the specified
/// register class are all legal.
Modified: llvm/trunk/lib/CodeGen/CodeGenPrepare.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/CodeGenPrepare.cpp?rev=205086&r1=205085&r2=205086&view=diff
==============================================================================
--- llvm/trunk/lib/CodeGen/CodeGenPrepare.cpp (original)
+++ llvm/trunk/lib/CodeGen/CodeGenPrepare.cpp Sat Mar 29 03:22:29 2014
@@ -60,6 +60,7 @@ STATISTIC(NumExtUses, "Number of uses
STATISTIC(NumRetsDup, "Number of return instructions duplicated");
STATISTIC(NumDbgValueMoved, "Number of debug value instructions moved");
STATISTIC(NumSelectsExpanded, "Number of selects turned into branches");
+STATISTIC(NumAndCmpsMoved, "Number of and/cmp's pushed into branches");
static cl::opt<bool> DisableBranchOpts(
"disable-cgp-branch-opts", cl::Hidden, cl::init(false),
@@ -69,6 +70,10 @@ static cl::opt<bool> DisableSelectToBran
"disable-cgp-select2branch", cl::Hidden, cl::init(false),
cl::desc("Disable select to branch conversion."));
+static cl::opt<bool> EnableAndCmpSinking(
+ "enable-andcmp-sinking", cl::Hidden, cl::init(true),
+ cl::desc("Enable sinkinig and/cmp into branches."));
+
namespace {
typedef SmallPtrSet<Instruction *, 16> SetOfInstrs;
typedef DenseMap<Instruction *, Type *> InstrToOrigTy;
@@ -135,6 +140,7 @@ typedef DenseMap<Instruction *, Type *>
bool OptimizeShuffleVectorInst(ShuffleVectorInst *SI);
bool DupRetToEnableTailCallOpts(BasicBlock *BB);
bool PlaceDbgValues(Function &F);
+ bool sinkAndCmp(Function &F);
};
}
@@ -190,6 +196,13 @@ bool CodeGenPrepare::runOnFunction(Funct
// find a node corresponding to the value.
EverMadeChange |= PlaceDbgValues(F);
+ // If there is a mask, compare against zero, and branch that can be combined
+ // into a single target instruction, push the mask and compare into branch
+ // users. Do this before OptimizeBlock -> OptimizeInst ->
+ // OptimizeCmpExpression, which perturbs the pattern being searched for.
+ if (!DisableBranchOpts)
+ EverMadeChange |= sinkAndCmp(F);
+
bool MadeChange = true;
while (MadeChange) {
MadeChange = false;
@@ -2925,4 +2938,71 @@ bool CodeGenPrepare::PlaceDbgValues(Func
}
}
return MadeChange;
+}
+
+// If there is a sequence that branches based on comparing a single bit
+// against zero that can be combined into a single instruction, and the
+// target supports folding these into a single instruction, sink the
+// mask and compare into the branch uses. Do this before OptimizeBlock ->
+// OptimizeInst -> OptimizeCmpExpression, which perturbs the pattern being
+// searched for.
+bool CodeGenPrepare::sinkAndCmp(Function &F) {
+ if (!EnableAndCmpSinking)
+ return false;
+ if (!TLI || !TLI->isMaskAndBranchFoldingLegal())
+ return false;
+ bool MadeChange = false;
+ for (Function::iterator I = F.begin(), E = F.end(); I != E; ) {
+ BasicBlock *BB = I++;
+
+ // Does this BB end with the following?
+ // %andVal = and %val, #single-bit-set
+ // %icmpVal = icmp %andResult, 0
+ // br i1 %cmpVal label %dest1, label %dest2"
+ BranchInst *Brcc = dyn_cast<BranchInst>(BB->getTerminator());
+ if (!Brcc || !Brcc->isConditional())
+ continue;
+ ICmpInst *Cmp = dyn_cast<ICmpInst>(Brcc->getOperand(0));
+ if (!Cmp || Cmp->getParent() != BB)
+ continue;
+ ConstantInt *Zero = dyn_cast<ConstantInt>(Cmp->getOperand(1));
+ if (!Zero || !Zero->isZero())
+ continue;
+ Instruction *And = dyn_cast<Instruction>(Cmp->getOperand(0));
+ if (!And || And->getOpcode() != Instruction::And || And->getParent() != BB)
+ continue;
+ ConstantInt* Mask = dyn_cast<ConstantInt>(And->getOperand(1));
+ if (!Mask || !Mask->getUniqueInteger().isPowerOf2())
+ continue;
+ DEBUG(dbgs() << "found and; icmp ?,0; brcc\n"); DEBUG(BB->dump());
+
+ // Push the "and; icmp" for any users that are conditional branches.
+ // Since there can only be one branch use per BB, we don't need to keep
+ // track of which BBs we insert into.
+ for (Value::use_iterator UI = Cmp->use_begin(), E = Cmp->use_end();
+ UI != E; ) {
+ Use &TheUse = *UI;
+ // Find brcc use.
+ BranchInst *BrccUser = dyn_cast<BranchInst>(*UI);
+ ++UI;
+ if (!BrccUser || !BrccUser->isConditional())
+ continue;
+ BasicBlock *UserBB = BrccUser->getParent();
+ if (UserBB == BB) continue;
+ DEBUG(dbgs() << "found Brcc use\n");
+
+ // Sink the "and; icmp" to use.
+ MadeChange = true;
+ BinaryOperator *NewAnd =
+ BinaryOperator::CreateAnd(And->getOperand(0), And->getOperand(1), "",
+ BrccUser);
+ CmpInst *NewCmp =
+ CmpInst::Create(Cmp->getOpcode(), Cmp->getPredicate(), NewAnd, Zero,
+ "", BrccUser);
+ TheUse = NewCmp;
+ ++NumAndCmpsMoved;
+ DEBUG(BrccUser->getParent()->dump());
+ }
+ }
+ return MadeChange;
}
Modified: llvm/trunk/lib/CodeGen/TargetLoweringBase.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/TargetLoweringBase.cpp?rev=205086&r1=205085&r2=205086&view=diff
==============================================================================
--- llvm/trunk/lib/CodeGen/TargetLoweringBase.cpp (original)
+++ llvm/trunk/lib/CodeGen/TargetLoweringBase.cpp Sat Mar 29 03:22:29 2014
@@ -679,6 +679,7 @@ TargetLoweringBase::TargetLoweringBase(c
Pow2DivIsCheap = false;
JumpIsExpensive = false;
PredictableSelectIsExpensive = false;
+ MaskAndBranchFoldingIsLegal = false;
StackPointerRegisterToSaveRestore = 0;
ExceptionPointerRegister = 0;
ExceptionSelectorRegister = 0;
More information about the llvm-commits
mailing list