[llvm-commits] [llvm] r127981 - in /llvm/trunk: include/llvm/Target/TargetLowering.h lib/Target/ARM/ARMISelLowering.cpp lib/Target/ARM/ARMISelLowering.h lib/Target/X86/X86ISelLowering.cpp lib/Target/X86/X86ISelLowering.h lib/Transforms/Scalar/CodeGenPrepare.cpp
Evan Cheng
evan.cheng at apple.com
Sun Mar 20 18:19:09 PDT 2011
Author: evancheng
Date: Sun Mar 20 20:19:09 2011
New Revision: 127981
URL: http://llvm.org/viewvc/llvm-project?rev=127981&view=rev
Log:
Re-apply r127953 with fixes: eliminate empty return block if it has no predecessors; update dominator tree if cfg is modified.
Modified:
llvm/trunk/include/llvm/Target/TargetLowering.h
llvm/trunk/lib/Target/ARM/ARMISelLowering.cpp
llvm/trunk/lib/Target/ARM/ARMISelLowering.h
llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
llvm/trunk/lib/Target/X86/X86ISelLowering.h
llvm/trunk/lib/Transforms/Scalar/CodeGenPrepare.cpp
Modified: llvm/trunk/include/llvm/Target/TargetLowering.h
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/Target/TargetLowering.h?rev=127981&r1=127980&r2=127981&view=diff
==============================================================================
--- llvm/trunk/include/llvm/Target/TargetLowering.h (original)
+++ llvm/trunk/include/llvm/Target/TargetLowering.h Sun Mar 20 20:19:09 2011
@@ -1287,6 +1287,14 @@
return false;
}
+ /// mayBeEmittedAsTailCall - Return true if the target may be able emit the
+ /// call instruction as a tail call. This is used by optimization passes to
+ /// determine if it's profitable to duplicate return instructions to enable
+ /// tailcall optimization.
+ virtual bool mayBeEmittedAsTailCall(CallInst *CI) const {
+ return false;
+ }
+
/// getTypeForExtArgOrReturn - Return the type that should be used to zero or
/// sign extend a zeroext/signext integer argument or return value.
/// FIXME: Most C calling convention requires the return type to be promoted,
Modified: llvm/trunk/lib/Target/ARM/ARMISelLowering.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/ARM/ARMISelLowering.cpp?rev=127981&r1=127980&r2=127981&view=diff
==============================================================================
--- llvm/trunk/lib/Target/ARM/ARMISelLowering.cpp (original)
+++ llvm/trunk/lib/Target/ARM/ARMISelLowering.cpp Sun Mar 20 20:19:09 2011
@@ -1805,6 +1805,16 @@
return HasRet;
}
+bool ARMTargetLowering::mayBeEmittedAsTailCall(CallInst *CI) const {
+ if (!EnableARMTailCalls)
+ return false;
+
+ if (!CI->isTailCall())
+ return false;
+
+ return !Subtarget->isThumb1Only();
+}
+
// ConstantPool, JumpTable, GlobalAddress, and ExternalSymbol are lowered as
// their target counterpart wrapped in the ARMISD::Wrapper node. Suppose N is
// one of the above mentioned nodes. It has to be wrapped because otherwise
Modified: llvm/trunk/lib/Target/ARM/ARMISelLowering.h
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/ARM/ARMISelLowering.h?rev=127981&r1=127980&r2=127981&view=diff
==============================================================================
--- llvm/trunk/lib/Target/ARM/ARMISelLowering.h (original)
+++ llvm/trunk/lib/Target/ARM/ARMISelLowering.h Sun Mar 20 20:19:09 2011
@@ -457,6 +457,8 @@
virtual bool isUsedByReturnOnly(SDNode *N) const;
+ virtual bool mayBeEmittedAsTailCall(CallInst *CI) const;
+
SDValue getARMCmp(SDValue LHS, SDValue RHS, ISD::CondCode CC,
SDValue &ARMcc, SelectionDAG &DAG, DebugLoc dl) const;
SDValue getVFPCmp(SDValue LHS, SDValue RHS,
Modified: llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86ISelLowering.cpp?rev=127981&r1=127980&r2=127981&view=diff
==============================================================================
--- llvm/trunk/lib/Target/X86/X86ISelLowering.cpp (original)
+++ llvm/trunk/lib/Target/X86/X86ISelLowering.cpp Sun Mar 20 20:19:09 2011
@@ -45,6 +45,7 @@
#include "llvm/ADT/Statistic.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/ADT/VectorExtras.h"
+#include "llvm/Support/CallSite.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/Dwarf.h"
#include "llvm/Support/ErrorHandling.h"
@@ -1595,6 +1596,18 @@
return (CC == CallingConv::Fast || CC == CallingConv::GHC);
}
+bool X86TargetLowering::mayBeEmittedAsTailCall(CallInst *CI) const {
+ if (!CI->isTailCall())
+ return false;
+
+ CallSite CS(CI);
+ CallingConv::ID CalleeCC = CS.getCallingConv();
+ if (!IsTailCallConvention(CalleeCC) && CalleeCC != CallingConv::C)
+ return false;
+
+ return true;
+}
+
/// FuncIsMadeTailCallSafe - Return true if the function is being made into
/// a tailcall target by changing its ABI.
static bool FuncIsMadeTailCallSafe(CallingConv::ID CC) {
Modified: llvm/trunk/lib/Target/X86/X86ISelLowering.h
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86ISelLowering.h?rev=127981&r1=127980&r2=127981&view=diff
==============================================================================
--- llvm/trunk/lib/Target/X86/X86ISelLowering.h (original)
+++ llvm/trunk/lib/Target/X86/X86ISelLowering.h Sun Mar 20 20:19:09 2011
@@ -843,6 +843,8 @@
virtual bool isUsedByReturnOnly(SDNode *N) const;
+ virtual bool mayBeEmittedAsTailCall(CallInst *CI) const;
+
virtual EVT
getTypeForExtArgOrReturn(LLVMContext &Context, EVT VT,
ISD::NodeType ExtendKind) const;
Modified: llvm/trunk/lib/Transforms/Scalar/CodeGenPrepare.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Transforms/Scalar/CodeGenPrepare.cpp?rev=127981&r1=127980&r2=127981&view=diff
==============================================================================
--- llvm/trunk/lib/Transforms/Scalar/CodeGenPrepare.cpp (original)
+++ llvm/trunk/lib/Transforms/Scalar/CodeGenPrepare.cpp Sun Mar 20 20:19:09 2011
@@ -47,16 +47,17 @@
using namespace llvm::PatternMatch;
STATISTIC(NumBlocksElim, "Number of blocks eliminated");
-STATISTIC(NumPHIsElim, "Number of trivial PHIs eliminated");
-STATISTIC(NumGEPsElim, "Number of GEPs converted to casts");
+STATISTIC(NumPHIsElim, "Number of trivial PHIs eliminated");
+STATISTIC(NumGEPsElim, "Number of GEPs converted to casts");
STATISTIC(NumCmpUses, "Number of uses of Cmp expressions replaced with uses of "
"sunken Cmps");
STATISTIC(NumCastUses, "Number of uses of Cast expressions replaced with uses "
"of sunken Casts");
STATISTIC(NumMemoryInsts, "Number of memory instructions whose address "
"computations were sunk");
-STATISTIC(NumExtsMoved, "Number of [s|z]ext instructions combined with loads");
-STATISTIC(NumExtUses, "Number of uses of [s|z]ext instructions optimized");
+STATISTIC(NumExtsMoved, "Number of [s|z]ext instructions combined with loads");
+STATISTIC(NumExtUses, "Number of uses of [s|z]ext instructions optimized");
+STATISTIC(NumRetsDup, "Number of return instructions duplicated");
static cl::opt<bool> DisableBranchOpts(
"disable-cgp-branch-opts", cl::Hidden, cl::init(false),
@@ -75,11 +76,15 @@
/// update it.
BasicBlock::iterator CurInstIterator;
- // Keeps track of non-local addresses that have been sunk into a block. This
- // allows us to avoid inserting duplicate code for blocks with multiple
- // load/stores of the same address.
+ /// Keeps track of non-local addresses that have been sunk into a block.
+ /// This allows us to avoid inserting duplicate code for blocks with
+ /// multiple load/stores of the same address.
DenseMap<Value*, Value*> SunkAddrs;
+ /// UpdateDT - If CFG is modified in anyway, dominator tree may need to
+ /// be updated.
+ bool UpdateDT;
+
public:
static char ID; // Pass identification, replacement for typeid
explicit CodeGenPrepare(const TargetLowering *tli = 0)
@@ -104,6 +109,7 @@
bool OptimizeCallInst(CallInst *CI);
bool MoveExtToFormExtLoad(Instruction *I);
bool OptimizeExtUses(Instruction *I);
+ bool DupRetToEnableTailCallOpts(ReturnInst *RI);
};
}
@@ -118,8 +124,10 @@
bool CodeGenPrepare::runOnFunction(Function &F) {
bool EverMadeChange = false;
+ UpdateDT = false;
DT = getAnalysisIfAvailable<DominatorTree>();
PFI = getAnalysisIfAvailable<ProfileInfo>();
+
// First pass, eliminate blocks that contain only PHI nodes and an
// unconditional branch.
EverMadeChange |= EliminateMostlyEmptyBlocks(F);
@@ -127,8 +135,10 @@
bool MadeChange = true;
while (MadeChange) {
MadeChange = false;
- for (Function::iterator BB = F.begin(), E = F.end(); BB != E; ++BB)
+ for (Function::iterator I = F.begin(), E = F.end(); I != E; ) {
+ BasicBlock *BB = I++;
MadeChange |= OptimizeBlock(*BB);
+ }
EverMadeChange |= MadeChange;
}
@@ -139,11 +149,14 @@
for (Function::iterator BB = F.begin(), E = F.end(); BB != E; ++BB)
MadeChange |= ConstantFoldTerminator(BB);
- if (MadeChange && DT)
- DT->DT->recalculate(F);
+ if (MadeChange)
+ UpdateDT = true;
EverMadeChange |= MadeChange;
}
+ if (UpdateDT && DT)
+ DT->DT->recalculate(F);
+
return EverMadeChange;
}
@@ -547,6 +560,102 @@
return Simplifier.fold(CI, TD);
}
+/// DupRetToEnableTailCallOpts - Look for opportunities to duplicate return
+/// instructions to the predecessor to enable tail call optimizations. The
+/// case it is currently looking for is:
+/// bb0:
+/// %tmp0 = tail call i32 @f0()
+/// br label %return
+/// bb1:
+/// %tmp1 = tail call i32 @f1()
+/// br label %return
+/// bb2:
+/// %tmp2 = tail call i32 @f2()
+/// br label %return
+/// return:
+/// %retval = phi i32 [ %tmp0, %bb0 ], [ %tmp1, %bb1 ], [ %tmp2, %bb2 ]
+/// ret i32 %retval
+///
+/// =>
+///
+/// bb0:
+/// %tmp0 = tail call i32 @f0()
+/// ret i32 %tmp0
+/// bb1:
+/// %tmp1 = tail call i32 @f1()
+/// ret i32 %tmp1
+/// bb2:
+/// %tmp2 = tail call i32 @f2()
+/// ret i32 %tmp2
+///
+bool CodeGenPrepare::DupRetToEnableTailCallOpts(ReturnInst *RI) {
+ Value *V = RI->getReturnValue();
+ if (!V)
+ return false;
+
+ if (PHINode *PN = dyn_cast<PHINode>(V)) {
+ BasicBlock *BB = RI->getParent();
+ if (PN->getParent() != BB)
+ return false;
+
+ // It's not safe to eliminate the sign / zero extension of the return value.
+ // See llvm::isInTailCallPosition().
+ const Function *F = BB->getParent();
+ unsigned CallerRetAttr = F->getAttributes().getRetAttributes();
+ if ((CallerRetAttr & Attribute::ZExt) || (CallerRetAttr & Attribute::SExt))
+ return false;
+
+ // Make sure there are no instructions between PHI and return.
+ BasicBlock::iterator BI = PN;
+ do { ++BI; } while (isa<DbgInfoIntrinsic>(BI));
+ if (&*BI != RI)
+ return false;
+
+ /// Only dup the ReturnInst if the CallInst is likely to be emitted as a
+ /// tail call.
+ SmallVector<CallInst*, 4> TailCalls;
+ for (unsigned I = 0, E = PN->getNumIncomingValues(); I != E; ++I) {
+ CallInst *CI = dyn_cast<CallInst>(PN->getIncomingValue(I));
+ // Make sure the phi value is indeed produced by the tail call.
+ if (CI && CI->hasOneUse() && CI->getParent() == PN->getIncomingBlock(I) &&
+ TLI->mayBeEmittedAsTailCall(CI))
+ TailCalls.push_back(CI);
+ }
+
+ bool Changed = false;
+ for (unsigned i = 0, e = TailCalls.size(); i != e; ++i) {
+ CallInst *CI = TailCalls[i];
+ CallSite CS(CI);
+
+ // Conservatively require the attributes of the call to match those of
+ // the return. Ignore noalias because it doesn't affect the call sequence.
+ unsigned CalleeRetAttr = CS.getAttributes().getRetAttributes();
+ if ((CalleeRetAttr ^ CallerRetAttr) & ~Attribute::NoAlias)
+ continue;
+
+ // Make sure the call instruction is followed by an unconditional branch
+ // to the return block.
+ BasicBlock *CallBB = CI->getParent();
+ BranchInst *BI = dyn_cast<BranchInst>(CallBB->getTerminator());
+ if (!BI || !BI->isUnconditional() || BI->getSuccessor(0) != BB)
+ continue;
+
+ // Duplicate the return into CallBB.
+ (void)FoldReturnIntoUncondBranch(RI, BB, CallBB);
+ UpdateDT = Changed = true;
+ ++NumRetsDup;
+ }
+
+ // If we eliminated all predecessors of the block, delete the block now.
+ if (Changed && pred_begin(BB) == pred_end(BB))
+ BB->eraseFromParent();
+
+ return Changed;
+ }
+
+ return false;
+}
+
//===----------------------------------------------------------------------===//
// Memory Optimization
//===----------------------------------------------------------------------===//
@@ -970,6 +1079,9 @@
if (CallInst *CI = dyn_cast<CallInst>(I))
return OptimizeCallInst(CI);
+ if (ReturnInst *RI = dyn_cast<ReturnInst>(I))
+ return DupRetToEnableTailCallOpts(RI);
+
return false;
}
More information about the llvm-commits
mailing list