This is an archive of the discontinued LLVM Phabricator instance.

Differential D32487

[X86] Relocate code of replacement of subtarget unsupported masked memory intrinsics to run also on -O0 option
ClosedPublic

Authored by aymanmus on Apr 25 2017, 7:19 AM.

Details

Reviewers
zvi
igorb
delena
mkuper
Commits
rGc5490e5a295b: [X86] Relocate code of replacement of subtarget unsupported masked memory…
rL303050: [X86] Relocate code of replacement of subtarget unsupported masked memory…
Summary

Currently, when masked load, store, gather or scatter intrinsics are used, we check in CodeGenPrepare pass if the subtarget support these intrinsics, if not we replace them with scalar code - this is a functional transformation not an optimization (not optional).

CodeGenPrepare pass does not run when the optimization level is set to CodeGenOpt::None (-O0).

Functional transformation should run with all optimization levels, so here I created a new pass which runs on all optimization levels and does no more than this transformation.

Diff Detail

Repository
rL LLVM

Event Timeline

aymanmus created this revision.Apr 25 2017, 7:19 AM
Herald added a subscriber: mgorny. · View Herald TranscriptApr 25 2017, 7:19 AM
zvi added inline comments.Apr 26 2017, 1:18 PM
lib/CodeGen/TargetPassConfig.cpp
494 ↗(On Diff #96553)

Do we want this pass added for all targets unconditionally?

aymanmus added inline comments.Apr 27 2017, 12:08 AM
lib/CodeGen/TargetPassConfig.cpp
494 ↗(On Diff #96553)

Yes, all targets (except for X86) define these intrinsics as illegal by inheriting the target hooks isLegalMasked{Load/Store/Gather/Scatter} (From TargetTransformInfo) which are set to return false by default.

The pass' transformations are completely controlled by target hooks so it's safe to run it on all targets (it's even a functional demand).

aymanmus added a comment.May 3 2017, 5:32 AM

Ping.

zvi added inline comments.May 9 2017, 8:14 AM
test/CodeGen/X86/replace_unsupported_masked_mem_intrin.ll
3 ↗(On Diff #96553)

Can you please open a bug report with a description of the issue that causes this test to crash, and a the pr# as reference in this test?

aymanmus updated this revision to Diff 98596.May 11 2017, 1:36 AM
aymanmus marked an inline comment as done.
aymanmus added a comment.May 15 2017, 3:47 AM

Ping.

delena accepted this revision.May 15 2017, 3:52 AM
This revision is now accepted and ready to land.May 15 2017, 3:52 AM
Closed by commit rL303050: [X86] Relocate code of replacement of subtarget unsupported masked memory… (authored by aymanmus). · Explain WhyMay 15 2017, 4:44 AM
This revision was automatically updated to reflect the committed changes.

Revision Contents

PathSize
llvm/
trunk/
include/
llvm/
CodeGen/
4 lines
1 line
1 line
lib/
CodeGen/
1 line
1 line
546 lines
660 lines
5 lines
test/
CodeGen/
X86/
1 line
2 lines
37 lines
tools/
llc/
1 line
opt/
1 line

Diff 98981

llvm/trunk/include/llvm/CodeGen/Passes.h

Show First 20 Lines • Show All 62 Lines • ▼ Show 20 Linesnamespace llvm {
/// If AbortOnFailedISel is true, abort compilation instead of resetting. /// If AbortOnFailedISel is true, abort compilation instead of resetting.
MachineFunctionPass *createResetMachineFunctionPass(bool EmitFallbackDiag, MachineFunctionPass *createResetMachineFunctionPass(bool EmitFallbackDiag,
bool AbortOnFailedISel); bool AbortOnFailedISel);
/// createCodeGenPreparePass - Transform the code to expose more pattern /// createCodeGenPreparePass - Transform the code to expose more pattern
/// matching during instruction selection. /// matching during instruction selection.
FunctionPass *createCodeGenPreparePass(const TargetMachine *TM = nullptr); FunctionPass *createCodeGenPreparePass(const TargetMachine *TM = nullptr);
/// createScalarizeMaskedMemIntrinPass - Replace masked load, store, gather
/// and scatter intrinsics with scalar code when target doesn't support them.
FunctionPass *createScalarizeMaskedMemIntrinPass();
/// AtomicExpandID -- Lowers atomic operations in terms of either cmpxchg /// AtomicExpandID -- Lowers atomic operations in terms of either cmpxchg
/// load-linked/store-conditional loops. /// load-linked/store-conditional loops.
extern char &AtomicExpandID; extern char &AtomicExpandID;
/// MachineLoopInfo - This pass is a loop analysis pass. /// MachineLoopInfo - This pass is a loop analysis pass.
extern char &MachineLoopInfoID; extern char &MachineLoopInfoID;
/// MachineDominators - This pass is a machine dominators analysis pass. /// MachineDominators - This pass is a machine dominators analysis pass.
▲ Show 20 Lines • Show All 369 Lines • Show Last 20 Lines

llvm/trunk/include/llvm/InitializePasses.h

Show First 20 Lines • Show All 320 Lines • ▼ Show 20 Lines
void initializeSCEVAAWrapperPassPass(PassRegistry&); void initializeSCEVAAWrapperPassPass(PassRegistry&);
void initializeSLPVectorizerPass(PassRegistry&); void initializeSLPVectorizerPass(PassRegistry&);
void initializeSROALegacyPassPass(PassRegistry&); void initializeSROALegacyPassPass(PassRegistry&);
void initializeSafeStackLegacyPassPass(PassRegistry&); void initializeSafeStackLegacyPassPass(PassRegistry&);
void initializeSampleProfileLoaderLegacyPassPass(PassRegistry&); void initializeSampleProfileLoaderLegacyPassPass(PassRegistry&);
void initializeSanitizerCoverageModulePass(PassRegistry&); void initializeSanitizerCoverageModulePass(PassRegistry&);
void initializeScalarEvolutionWrapperPassPass(PassRegistry&); void initializeScalarEvolutionWrapperPassPass(PassRegistry&);
void initializeScalarizerPass(PassRegistry&); void initializeScalarizerPass(PassRegistry&);
void initializeScalarizeMaskedMemIntrinPass(PassRegistry&);
void initializeScopedNoAliasAAWrapperPassPass(PassRegistry&); void initializeScopedNoAliasAAWrapperPassPass(PassRegistry&);
void initializeSeparateConstOffsetFromGEPPass(PassRegistry&); void initializeSeparateConstOffsetFromGEPPass(PassRegistry&);
void initializeShadowStackGCLoweringPass(PassRegistry&); void initializeShadowStackGCLoweringPass(PassRegistry&);
void initializeShrinkWrapPass(PassRegistry&); void initializeShrinkWrapPass(PassRegistry&);
void initializeSimpleInlinerPass(PassRegistry&); void initializeSimpleInlinerPass(PassRegistry&);
void initializeSimpleLoopUnswitchLegacyPassPass(PassRegistry&); void initializeSimpleLoopUnswitchLegacyPassPass(PassRegistry&);
void initializeSingleLoopExtractorPass(PassRegistry&); void initializeSingleLoopExtractorPass(PassRegistry&);
void initializeSinkingLegacyPassPass(PassRegistry&); void initializeSinkingLegacyPassPass(PassRegistry&);
Show All 40 Lines

llvm/trunk/include/llvm/LinkAllPasses.h

Show First 20 Lines • Show All 200 Lines • ▼ Show 20 Lines ForcePassLinking() {
(void) llvm::createSeparateConstOffsetFromGEPPass(); (void) llvm::createSeparateConstOffsetFromGEPPass();
(void) llvm::createSpeculativeExecutionPass(); (void) llvm::createSpeculativeExecutionPass();
(void) llvm::createSpeculativeExecutionIfHasBranchDivergencePass(); (void) llvm::createSpeculativeExecutionIfHasBranchDivergencePass();
(void) llvm::createRewriteSymbolsPass(); (void) llvm::createRewriteSymbolsPass();
(void) llvm::createStraightLineStrengthReducePass(); (void) llvm::createStraightLineStrengthReducePass();
(void) llvm::createMemDerefPrinter(); (void) llvm::createMemDerefPrinter();
(void) llvm::createFloat2IntPass(); (void) llvm::createFloat2IntPass();
(void) llvm::createEliminateAvailableExternallyPass(); (void) llvm::createEliminateAvailableExternallyPass();
(void) llvm::createScalarizeMaskedMemIntrinPass();
(void)new llvm::IntervalPartition(); (void)new llvm::IntervalPartition();
(void)new llvm::ScalarEvolutionWrapperPass(); (void)new llvm::ScalarEvolutionWrapperPass();
llvm::Function::Create(nullptr, llvm::GlobalValue::ExternalLinkage)->viewCFGOnly(); llvm::Function::Create(nullptr, llvm::GlobalValue::ExternalLinkage)->viewCFGOnly();
llvm::RGPassManager RGM; llvm::RGPassManager RGM;
llvm::TargetLibraryInfoImpl TLII; llvm::TargetLibraryInfoImpl TLII;
llvm::TargetLibraryInfo TLI(TLII); llvm::TargetLibraryInfo TLI(TLII);
llvm::AliasAnalysis AA(TLI); llvm::AliasAnalysis AA(TLI);
Show All 9 Lines

llvm/trunk/lib/CodeGen/CMakeLists.txt

Show First 20 Lines • Show All 114 Lines • ▼ Show 20 Linesadd_llvm_library(LLVMCodeGen
RenameIndependentSubregs.cpp RenameIndependentSubregs.cpp
RegisterUsageInfo.cpp RegisterUsageInfo.cpp
RegUsageInfoCollector.cpp RegUsageInfoCollector.cpp
RegUsageInfoPropagate.cpp RegUsageInfoPropagate.cpp
ResetMachineFunctionPass.cpp ResetMachineFunctionPass.cpp
SafeStack.cpp SafeStack.cpp
SafeStackColoring.cpp SafeStackColoring.cpp
SafeStackLayout.cpp SafeStackLayout.cpp
ScalarizeMaskedMemIntrin.cpp
ScheduleDAG.cpp ScheduleDAG.cpp
ScheduleDAGInstrs.cpp ScheduleDAGInstrs.cpp
ScheduleDAGPrinter.cpp ScheduleDAGPrinter.cpp
ScoreboardHazardRecognizer.cpp ScoreboardHazardRecognizer.cpp
ShadowStackGCLowering.cpp ShadowStackGCLowering.cpp
ShrinkWrap.cpp ShrinkWrap.cpp
SjLjEHPrepare.cpp SjLjEHPrepare.cpp
SlotIndexes.cpp SlotIndexes.cpp
Show All 38 Lines

llvm/trunk/lib/CodeGen/CodeGen.cpp

Show First 20 Lines • Show All 75 Lines • ▼ Show 20 Linesvoid llvm::initializeCodeGen(PassRegistry &Registry) {
initializePostRAHazardRecognizerPass(Registry); initializePostRAHazardRecognizerPass(Registry);
initializePostRASchedulerPass(Registry); initializePostRASchedulerPass(Registry);
initializePreISelIntrinsicLoweringLegacyPassPass(Registry); initializePreISelIntrinsicLoweringLegacyPassPass(Registry);
initializeProcessImplicitDefsPass(Registry); initializeProcessImplicitDefsPass(Registry);
initializeRAGreedyPass(Registry); initializeRAGreedyPass(Registry);
initializeRegisterCoalescerPass(Registry); initializeRegisterCoalescerPass(Registry);
initializeRenameIndependentSubregsPass(Registry); initializeRenameIndependentSubregsPass(Registry);
initializeSafeStackLegacyPassPass(Registry); initializeSafeStackLegacyPassPass(Registry);
initializeScalarizeMaskedMemIntrinPass(Registry);
initializeShrinkWrapPass(Registry); initializeShrinkWrapPass(Registry);
initializeSlotIndexesPass(Registry); initializeSlotIndexesPass(Registry);
initializeStackColoringPass(Registry); initializeStackColoringPass(Registry);
initializeStackMapLivenessPass(Registry); initializeStackMapLivenessPass(Registry);
initializeStackProtectorPass(Registry); initializeStackProtectorPass(Registry);
initializeStackSlotColoringPass(Registry); initializeStackSlotColoringPass(Registry);
initializeTailDuplicatePassPass(Registry); initializeTailDuplicatePassPass(Registry);
initializeTargetPassConfigPass(Registry); initializeTargetPassConfigPass(Registry);
Show All 13 Lines

llvm/trunk/lib/CodeGen/CodeGenPrepare.cpp

Show First 20 Lines • Show All 1,543 Lines • ▼ Show 20 Linesstatic bool OptimizeExtractBits(BinaryOperator *ShiftI, ConstantInt *CI,
// If we removed all uses, nuke the shift. // If we removed all uses, nuke the shift.
if (ShiftI->use_empty()) if (ShiftI->use_empty())
ShiftI->eraseFromParent(); ShiftI->eraseFromParent();
return MadeChange; return MadeChange;
} }
// Translate a masked load intrinsic like
// <16 x i32 > @llvm.masked.load( <16 x i32>* %addr, i32 align,
// <16 x i1> %mask, <16 x i32> %passthru)
// to a chain of basic blocks, with loading element one-by-one if
// the appropriate mask bit is set
//
// %1 = bitcast i8* %addr to i32*
// %2 = extractelement <16 x i1> %mask, i32 0
// %3 = icmp eq i1 %2, true
// br i1 %3, label %cond.load, label %else
//
//cond.load: ; preds = %0
// %4 = getelementptr i32* %1, i32 0
// %5 = load i32* %4
// %6 = insertelement <16 x i32> undef, i32 %5, i32 0
// br label %else
//
//else: ; preds = %0, %cond.load
// %res.phi.else = phi <16 x i32> [ %6, %cond.load ], [ undef, %0 ]
// %7 = extractelement <16 x i1> %mask, i32 1
// %8 = icmp eq i1 %7, true
// br i1 %8, label %cond.load1, label %else2
//
//cond.load1: ; preds = %else
// %9 = getelementptr i32* %1, i32 1
// %10 = load i32* %9
// %11 = insertelement <16 x i32> %res.phi.else, i32 %10, i32 1
// br label %else2
//
//else2: ; preds = %else, %cond.load1
// %res.phi.else3 = phi <16 x i32> [ %11, %cond.load1 ], [ %res.phi.else, %else ]
// %12 = extractelement <16 x i1> %mask, i32 2
// %13 = icmp eq i1 %12, true
// br i1 %13, label %cond.load4, label %else5
//
static void scalarizeMaskedLoad(CallInst *CI) {
Value *Ptr = CI->getArgOperand(0);
Value *Alignment = CI->getArgOperand(1);
Value *Mask = CI->getArgOperand(2);
Value *Src0 = CI->getArgOperand(3);
unsigned AlignVal = cast<ConstantInt>(Alignment)->getZExtValue();
VectorType *VecType = dyn_cast<VectorType>(CI->getType());
assert(VecType && "Unexpected return type of masked load intrinsic");
Type *EltTy = CI->getType()->getVectorElementType();
IRBuilder<> Builder(CI->getContext());
Instruction *InsertPt = CI;
BasicBlock *IfBlock = CI->getParent();
BasicBlock *CondBlock = nullptr;
BasicBlock *PrevIfBlock = CI->getParent();
Builder.SetInsertPoint(InsertPt);
Builder.SetCurrentDebugLocation(CI->getDebugLoc());
// Short-cut if the mask is all-true.
bool IsAllOnesMask = isa<Constant>(Mask) &&
cast<Constant>(Mask)->isAllOnesValue();
if (IsAllOnesMask) {
Value *NewI = Builder.CreateAlignedLoad(Ptr, AlignVal);
CI->replaceAllUsesWith(NewI);
CI->eraseFromParent();
return;
}
// Adjust alignment for the scalar instruction.
AlignVal = std::min(AlignVal, VecType->getScalarSizeInBits()/8);
// Bitcast %addr fron i8* to EltTy*
Type *NewPtrType =
EltTy->getPointerTo(cast<PointerType>(Ptr->getType())->getAddressSpace());
Value *FirstEltPtr = Builder.CreateBitCast(Ptr, NewPtrType);
unsigned VectorWidth = VecType->getNumElements();
Value *UndefVal = UndefValue::get(VecType);
// The result vector
Value *VResult = UndefVal;
if (isa<ConstantVector>(Mask)) {
for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
if (cast<ConstantVector>(Mask)->getOperand(Idx)->isNullValue())
continue;
Value *Gep =
Builder.CreateInBoundsGEP(EltTy, FirstEltPtr, Builder.getInt32(Idx));
LoadInst* Load = Builder.CreateAlignedLoad(Gep, AlignVal);
VResult = Builder.CreateInsertElement(VResult, Load,
Builder.getInt32(Idx));
}
Value *NewI = Builder.CreateSelect(Mask, VResult, Src0);
CI->replaceAllUsesWith(NewI);
CI->eraseFromParent();
return;
}
PHINode *Phi = nullptr;
Value *PrevPhi = UndefVal;
for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
// Fill the "else" block, created in the previous iteration
//
// %res.phi.else3 = phi <16 x i32> [ %11, %cond.load1 ], [ %res.phi.else, %else ]
// %mask_1 = extractelement <16 x i1> %mask, i32 Idx
// %to_load = icmp eq i1 %mask_1, true
// br i1 %to_load, label %cond.load, label %else
//
if (Idx > 0) {
Phi = Builder.CreatePHI(VecType, 2, "res.phi.else");
Phi->addIncoming(VResult, CondBlock);
Phi->addIncoming(PrevPhi, PrevIfBlock);
PrevPhi = Phi;
VResult = Phi;
}
Value *Predicate = Builder.CreateExtractElement(Mask, Builder.getInt32(Idx));
Value *Cmp = Builder.CreateICmp(ICmpInst::ICMP_EQ, Predicate,
ConstantInt::get(Predicate->getType(), 1));
// Create "cond" block
//
// %EltAddr = getelementptr i32* %1, i32 0
// %Elt = load i32* %EltAddr
// VResult = insertelement <16 x i32> VResult, i32 %Elt, i32 Idx
//
CondBlock = IfBlock->splitBasicBlock(InsertPt->getIterator(), "cond.load");
Builder.SetInsertPoint(InsertPt);
Value *Gep =
Builder.CreateInBoundsGEP(EltTy, FirstEltPtr, Builder.getInt32(Idx));
LoadInst *Load = Builder.CreateAlignedLoad(Gep, AlignVal);
VResult = Builder.CreateInsertElement(VResult, Load, Builder.getInt32(Idx));
// Create "else" block, fill it in the next iteration
BasicBlock *NewIfBlock =
CondBlock->splitBasicBlock(InsertPt->getIterator(), "else");
Builder.SetInsertPoint(InsertPt);
Instruction *OldBr = IfBlock->getTerminator();
BranchInst::Create(CondBlock, NewIfBlock, Cmp, OldBr);
OldBr->eraseFromParent();
PrevIfBlock = IfBlock;
IfBlock = NewIfBlock;
}
Phi = Builder.CreatePHI(VecType, 2, "res.phi.select");
Phi->addIncoming(VResult, CondBlock);
Phi->addIncoming(PrevPhi, PrevIfBlock);
Value *NewI = Builder.CreateSelect(Mask, Phi, Src0);
CI->replaceAllUsesWith(NewI);
CI->eraseFromParent();
}
// Translate a masked store intrinsic, like
// void @llvm.masked.store(<16 x i32> %src, <16 x i32>* %addr, i32 align,
// <16 x i1> %mask)
// to a chain of basic blocks, that stores element one-by-one if
// the appropriate mask bit is set
//
// %1 = bitcast i8* %addr to i32*
// %2 = extractelement <16 x i1> %mask, i32 0
// %3 = icmp eq i1 %2, true
// br i1 %3, label %cond.store, label %else
//
// cond.store: ; preds = %0
// %4 = extractelement <16 x i32> %val, i32 0
// %5 = getelementptr i32* %1, i32 0
// store i32 %4, i32* %5
// br label %else
//
// else: ; preds = %0, %cond.store
// %6 = extractelement <16 x i1> %mask, i32 1
// %7 = icmp eq i1 %6, true
// br i1 %7, label %cond.store1, label %else2
//
// cond.store1: ; preds = %else
// %8 = extractelement <16 x i32> %val, i32 1
// %9 = getelementptr i32* %1, i32 1
// store i32 %8, i32* %9
// br label %else2
// . . .
static void scalarizeMaskedStore(CallInst *CI) {
Value *Src = CI->getArgOperand(0);
Value *Ptr = CI->getArgOperand(1);
Value *Alignment = CI->getArgOperand(2);
Value *Mask = CI->getArgOperand(3);
unsigned AlignVal = cast<ConstantInt>(Alignment)->getZExtValue();
VectorType *VecType = dyn_cast<VectorType>(Src->getType());
assert(VecType && "Unexpected data type in masked store intrinsic");
Type *EltTy = VecType->getElementType();
IRBuilder<> Builder(CI->getContext());
Instruction *InsertPt = CI;
BasicBlock *IfBlock = CI->getParent();
Builder.SetInsertPoint(InsertPt);
Builder.SetCurrentDebugLocation(CI->getDebugLoc());
// Short-cut if the mask is all-true.
bool IsAllOnesMask = isa<Constant>(Mask) &&
cast<Constant>(Mask)->isAllOnesValue();
if (IsAllOnesMask) {
Builder.CreateAlignedStore(Src, Ptr, AlignVal);
CI->eraseFromParent();
return;
}
// Adjust alignment for the scalar instruction.
AlignVal = std::max(AlignVal, VecType->getScalarSizeInBits()/8);
// Bitcast %addr fron i8* to EltTy*
Type *NewPtrType =
EltTy->getPointerTo(cast<PointerType>(Ptr->getType())->getAddressSpace());
Value *FirstEltPtr = Builder.CreateBitCast(Ptr, NewPtrType);
unsigned VectorWidth = VecType->getNumElements();
if (isa<ConstantVector>(Mask)) {
for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
if (cast<ConstantVector>(Mask)->getOperand(Idx)->isNullValue())
continue;
Value *OneElt = Builder.CreateExtractElement(Src, Builder.getInt32(Idx));
Value *Gep =
Builder.CreateInBoundsGEP(EltTy, FirstEltPtr, Builder.getInt32(Idx));
Builder.CreateAlignedStore(OneElt, Gep, AlignVal);
}
CI->eraseFromParent();
return;
}
for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
// Fill the "else" block, created in the previous iteration
//
// %mask_1 = extractelement <16 x i1> %mask, i32 Idx
// %to_store = icmp eq i1 %mask_1, true
// br i1 %to_store, label %cond.store, label %else
//
Value *Predicate = Builder.CreateExtractElement(Mask, Builder.getInt32(Idx));
Value *Cmp = Builder.CreateICmp(ICmpInst::ICMP_EQ, Predicate,
ConstantInt::get(Predicate->getType(), 1));
// Create "cond" block
//
// %OneElt = extractelement <16 x i32> %Src, i32 Idx
// %EltAddr = getelementptr i32* %1, i32 0
// %store i32 %OneElt, i32* %EltAddr
//
BasicBlock *CondBlock =
IfBlock->splitBasicBlock(InsertPt->getIterator(), "cond.store");
Builder.SetInsertPoint(InsertPt);
Value *OneElt = Builder.CreateExtractElement(Src, Builder.getInt32(Idx));
Value *Gep =
Builder.CreateInBoundsGEP(EltTy, FirstEltPtr, Builder.getInt32(Idx));
Builder.CreateAlignedStore(OneElt, Gep, AlignVal);
// Create "else" block, fill it in the next iteration
BasicBlock *NewIfBlock =
CondBlock->splitBasicBlock(InsertPt->getIterator(), "else");
Builder.SetInsertPoint(InsertPt);
Instruction *OldBr = IfBlock->getTerminator();
BranchInst::Create(CondBlock, NewIfBlock, Cmp, OldBr);
OldBr->eraseFromParent();
IfBlock = NewIfBlock;
}
CI->eraseFromParent();
}
// Translate a masked gather intrinsic like
// <16 x i32 > @llvm.masked.gather.v16i32( <16 x i32*> %Ptrs, i32 4,
// <16 x i1> %Mask, <16 x i32> %Src)
// to a chain of basic blocks, with loading element one-by-one if
// the appropriate mask bit is set
//
// % Ptrs = getelementptr i32, i32* %base, <16 x i64> %ind
// % Mask0 = extractelement <16 x i1> %Mask, i32 0
// % ToLoad0 = icmp eq i1 % Mask0, true
// br i1 % ToLoad0, label %cond.load, label %else
//
// cond.load:
// % Ptr0 = extractelement <16 x i32*> %Ptrs, i32 0
// % Load0 = load i32, i32* % Ptr0, align 4
// % Res0 = insertelement <16 x i32> undef, i32 % Load0, i32 0
// br label %else
//
// else:
// %res.phi.else = phi <16 x i32>[% Res0, %cond.load], [undef, % 0]
// % Mask1 = extractelement <16 x i1> %Mask, i32 1
// % ToLoad1 = icmp eq i1 % Mask1, true
// br i1 % ToLoad1, label %cond.load1, label %else2
//
// cond.load1:
// % Ptr1 = extractelement <16 x i32*> %Ptrs, i32 1
// % Load1 = load i32, i32* % Ptr1, align 4
// % Res1 = insertelement <16 x i32> %res.phi.else, i32 % Load1, i32 1
// br label %else2
// . . .
// % Result = select <16 x i1> %Mask, <16 x i32> %res.phi.select, <16 x i32> %Src
// ret <16 x i32> %Result
static void scalarizeMaskedGather(CallInst *CI) {
Value *Ptrs = CI->getArgOperand(0);
Value *Alignment = CI->getArgOperand(1);
Value *Mask = CI->getArgOperand(2);
Value *Src0 = CI->getArgOperand(3);
VectorType *VecType = dyn_cast<VectorType>(CI->getType());
assert(VecType && "Unexpected return type of masked load intrinsic");
IRBuilder<> Builder(CI->getContext());
Instruction *InsertPt = CI;
BasicBlock *IfBlock = CI->getParent();
BasicBlock *CondBlock = nullptr;
BasicBlock *PrevIfBlock = CI->getParent();
Builder.SetInsertPoint(InsertPt);
unsigned AlignVal = cast<ConstantInt>(Alignment)->getZExtValue();
Builder.SetCurrentDebugLocation(CI->getDebugLoc());
Value *UndefVal = UndefValue::get(VecType);
// The result vector
Value *VResult = UndefVal;
unsigned VectorWidth = VecType->getNumElements();
// Shorten the way if the mask is a vector of constants.
bool IsConstMask = isa<ConstantVector>(Mask);
if (IsConstMask) {
for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
if (cast<ConstantVector>(Mask)->getOperand(Idx)->isNullValue())
continue;
Value *Ptr = Builder.CreateExtractElement(Ptrs, Builder.getInt32(Idx),
"Ptr" + Twine(Idx));
LoadInst *Load = Builder.CreateAlignedLoad(Ptr, AlignVal,
"Load" + Twine(Idx));
VResult = Builder.CreateInsertElement(VResult, Load,
Builder.getInt32(Idx),
"Res" + Twine(Idx));
}
Value *NewI = Builder.CreateSelect(Mask, VResult, Src0);
CI->replaceAllUsesWith(NewI);
CI->eraseFromParent();
return;
}
PHINode *Phi = nullptr;
Value *PrevPhi = UndefVal;
for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
// Fill the "else" block, created in the previous iteration
//
// %Mask1 = extractelement <16 x i1> %Mask, i32 1
// %ToLoad1 = icmp eq i1 %Mask1, true
// br i1 %ToLoad1, label %cond.load, label %else
//
if (Idx > 0) {
Phi = Builder.CreatePHI(VecType, 2, "res.phi.else");
Phi->addIncoming(VResult, CondBlock);
Phi->addIncoming(PrevPhi, PrevIfBlock);
PrevPhi = Phi;
VResult = Phi;
}
Value *Predicate = Builder.CreateExtractElement(Mask,
Builder.getInt32(Idx),
"Mask" + Twine(Idx));
Value *Cmp = Builder.CreateICmp(ICmpInst::ICMP_EQ, Predicate,
ConstantInt::get(Predicate->getType(), 1),
"ToLoad" + Twine(Idx));
// Create "cond" block
//
// %EltAddr = getelementptr i32* %1, i32 0
// %Elt = load i32* %EltAddr
// VResult = insertelement <16 x i32> VResult, i32 %Elt, i32 Idx
//
CondBlock = IfBlock->splitBasicBlock(InsertPt, "cond.load");
Builder.SetInsertPoint(InsertPt);
Value *Ptr = Builder.CreateExtractElement(Ptrs, Builder.getInt32(Idx),
"Ptr" + Twine(Idx));
LoadInst *Load = Builder.CreateAlignedLoad(Ptr, AlignVal,
"Load" + Twine(Idx));
VResult = Builder.CreateInsertElement(VResult, Load, Builder.getInt32(Idx),
"Res" + Twine(Idx));
// Create "else" block, fill it in the next iteration
BasicBlock *NewIfBlock = CondBlock->splitBasicBlock(InsertPt, "else");
Builder.SetInsertPoint(InsertPt);
Instruction *OldBr = IfBlock->getTerminator();
BranchInst::Create(CondBlock, NewIfBlock, Cmp, OldBr);
OldBr->eraseFromParent();
PrevIfBlock = IfBlock;
IfBlock = NewIfBlock;
}
Phi = Builder.CreatePHI(VecType, 2, "res.phi.select");
Phi->addIncoming(VResult, CondBlock);
Phi->addIncoming(PrevPhi, PrevIfBlock);
Value *NewI = Builder.CreateSelect(Mask, Phi, Src0);
CI->replaceAllUsesWith(NewI);
CI->eraseFromParent();
}
// Translate a masked scatter intrinsic, like
// void @llvm.masked.scatter.v16i32(<16 x i32> %Src, <16 x i32*>* %Ptrs, i32 4,
// <16 x i1> %Mask)
// to a chain of basic blocks, that stores element one-by-one if
// the appropriate mask bit is set.
//
// % Ptrs = getelementptr i32, i32* %ptr, <16 x i64> %ind
// % Mask0 = extractelement <16 x i1> % Mask, i32 0
// % ToStore0 = icmp eq i1 % Mask0, true
// br i1 %ToStore0, label %cond.store, label %else
//
// cond.store:
// % Elt0 = extractelement <16 x i32> %Src, i32 0
// % Ptr0 = extractelement <16 x i32*> %Ptrs, i32 0
// store i32 %Elt0, i32* % Ptr0, align 4
// br label %else
//
// else:
// % Mask1 = extractelement <16 x i1> % Mask, i32 1
// % ToStore1 = icmp eq i1 % Mask1, true
// br i1 % ToStore1, label %cond.store1, label %else2
//
// cond.store1:
// % Elt1 = extractelement <16 x i32> %Src, i32 1
// % Ptr1 = extractelement <16 x i32*> %Ptrs, i32 1
// store i32 % Elt1, i32* % Ptr1, align 4
// br label %else2
// . . .
static void scalarizeMaskedScatter(CallInst *CI) {
Value *Src = CI->getArgOperand(0);
Value *Ptrs = CI->getArgOperand(1);
Value *Alignment = CI->getArgOperand(2);
Value *Mask = CI->getArgOperand(3);
assert(isa<VectorType>(Src->getType()) &&
"Unexpected data type in masked scatter intrinsic");
assert(isa<VectorType>(Ptrs->getType()) &&
isa<PointerType>(Ptrs->getType()->getVectorElementType()) &&
"Vector of pointers is expected in masked scatter intrinsic");
IRBuilder<> Builder(CI->getContext());
Instruction *InsertPt = CI;
BasicBlock *IfBlock = CI->getParent();
Builder.SetInsertPoint(InsertPt);
Builder.SetCurrentDebugLocation(CI->getDebugLoc());
unsigned AlignVal = cast<ConstantInt>(Alignment)->getZExtValue();
unsigned VectorWidth = Src->getType()->getVectorNumElements();
// Shorten the way if the mask is a vector of constants.
bool IsConstMask = isa<ConstantVector>(Mask);
if (IsConstMask) {
for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
if (cast<ConstantVector>(Mask)->getOperand(Idx)->isNullValue())
continue;
Value *OneElt = Builder.CreateExtractElement(Src, Builder.getInt32(Idx),
"Elt" + Twine(Idx));
Value *Ptr = Builder.CreateExtractElement(Ptrs, Builder.getInt32(Idx),
"Ptr" + Twine(Idx));
Builder.CreateAlignedStore(OneElt, Ptr, AlignVal);
}
CI->eraseFromParent();
return;
}
for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
// Fill the "else" block, created in the previous iteration
//
// % Mask1 = extractelement <16 x i1> % Mask, i32 Idx
// % ToStore = icmp eq i1 % Mask1, true
// br i1 % ToStore, label %cond.store, label %else
//
Value *Predicate = Builder.CreateExtractElement(Mask,
Builder.getInt32(Idx),
"Mask" + Twine(Idx));
Value *Cmp =
Builder.CreateICmp(ICmpInst::ICMP_EQ, Predicate,
ConstantInt::get(Predicate->getType(), 1),
"ToStore" + Twine(Idx));
// Create "cond" block
//
// % Elt1 = extractelement <16 x i32> %Src, i32 1
// % Ptr1 = extractelement <16 x i32*> %Ptrs, i32 1
// %store i32 % Elt1, i32* % Ptr1
//
BasicBlock *CondBlock = IfBlock->splitBasicBlock(InsertPt, "cond.store");
Builder.SetInsertPoint(InsertPt);
Value *OneElt = Builder.CreateExtractElement(Src, Builder.getInt32(Idx),
"Elt" + Twine(Idx));
Value *Ptr = Builder.CreateExtractElement(Ptrs, Builder.getInt32(Idx),
"Ptr" + Twine(Idx));
Builder.CreateAlignedStore(OneElt, Ptr, AlignVal);
// Create "else" block, fill it in the next iteration
BasicBlock *NewIfBlock = CondBlock->splitBasicBlock(InsertPt, "else");
Builder.SetInsertPoint(InsertPt);
Instruction *OldBr = IfBlock->getTerminator();
BranchInst::Create(CondBlock, NewIfBlock, Cmp, OldBr);
OldBr->eraseFromParent();
IfBlock = NewIfBlock;
}
CI->eraseFromParent();
}
/// If counting leading or trailing zeros is an expensive operation and a zero /// If counting leading or trailing zeros is an expensive operation and a zero
/// input is defined, add a check for zero to avoid calling the intrinsic. /// input is defined, add a check for zero to avoid calling the intrinsic.
/// ///
/// We want to transform: /// We want to transform:
/// %z = call i64 @llvm.cttz.i64(i64 %A, i1 false) /// %z = call i64 @llvm.cttz.i64(i64 %A, i1 false)
/// ///
/// into: /// into:
/// entry: /// entry:
▲ Show 20 Lines • Show All 164 Lines • ▼ Show 20 Lines case Intrinsic::objectsize: {
// If the iterator instruction was recursively deleted, start over at the // If the iterator instruction was recursively deleted, start over at the
// start of the block. // start of the block.
if (IterHandle != CurValue) { if (IterHandle != CurValue) {
CurInstIterator = BB->begin(); CurInstIterator = BB->begin();
SunkAddrs.clear(); SunkAddrs.clear();
} }
return true; return true;
} }
case Intrinsic::masked_load: {
// Scalarize unsupported vector masked load
if (!TTI->isLegalMaskedLoad(CI->getType())) {
scalarizeMaskedLoad(CI);
ModifiedDT = true;
return true;
}
return false;
}
case Intrinsic::masked_store: {
if (!TTI->isLegalMaskedStore(CI->getArgOperand(0)->getType())) {
scalarizeMaskedStore(CI);
ModifiedDT = true;
return true;
}
return false;
}
case Intrinsic::masked_gather: {
if (!TTI->isLegalMaskedGather(CI->getType())) {
scalarizeMaskedGather(CI);
ModifiedDT = true;
return true;
}
return false;
}
case Intrinsic::masked_scatter: {
if (!TTI->isLegalMaskedScatter(CI->getArgOperand(0)->getType())) {
scalarizeMaskedScatter(CI);
ModifiedDT = true;
return true;
}
return false;
}
case Intrinsic::aarch64_stlxr: case Intrinsic::aarch64_stlxr:
case Intrinsic::aarch64_stxr: { case Intrinsic::aarch64_stxr: {
ZExtInst *ExtVal = dyn_cast<ZExtInst>(CI->getArgOperand(0)); ZExtInst *ExtVal = dyn_cast<ZExtInst>(CI->getArgOperand(0));
if (!ExtVal || !ExtVal->hasOneUse() || if (!ExtVal || !ExtVal->hasOneUse() ||
ExtVal->getParent() == CI->getParent()) ExtVal->getParent() == CI->getParent())
return false; return false;
// Sink a zext feeding stlxr/stxr before it, so it can be folded into it. // Sink a zext feeding stlxr/stxr before it, so it can be folded into it.
ExtVal->moveBefore(CI); ExtVal->moveBefore(CI);
▲ Show 20 Lines • Show All 4,093 Lines • Show Last 20 Lines

llvm/trunk/lib/CodeGen/ScalarizeMaskedMemIntrin.cpp

PropertyOld ValueNew Value
svn:eol-stylenullnative
svn:keywordsnullAuthor Date Id Rev URL
svn:mime-typenulltext/plain
//=== ScalarizeMaskedMemIntrin.cpp - Scalarize unsupported masked mem ===//
//=== instrinsics ===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This pass replaces masked memory intrinsics - when unsupported by the target
// - with a chain of basic blocks, that deal with the elements one-by-one if the
// appropriate mask bit is set.
//
//===----------------------------------------------------------------------===//
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/Target/TargetSubtargetInfo.h"
using namespace llvm;
#define DEBUG_TYPE "scalarize-masked-mem-intrin"
namespace {
class ScalarizeMaskedMemIntrin : public FunctionPass {
const TargetTransformInfo *TTI;
public:
static char ID; // Pass identification, replacement for typeid
explicit ScalarizeMaskedMemIntrin() : FunctionPass(ID), TTI(nullptr) {
initializeScalarizeMaskedMemIntrinPass(*PassRegistry::getPassRegistry());
}
bool runOnFunction(Function &F) override;
StringRef getPassName() const override {
return "Scalarize Masked Memory Intrinsics";
}
void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.addRequired<TargetTransformInfoWrapperPass>();
}
private:
bool optimizeBlock(BasicBlock &BB, bool &ModifiedDT);
bool optimizeCallInst(CallInst *CI, bool &ModifiedDT);
};
} // namespace
char ScalarizeMaskedMemIntrin::ID = 0;
INITIALIZE_PASS_BEGIN(ScalarizeMaskedMemIntrin, "scalarize-masked-mem-intrin",
"Scalarize unsupported masked memory intrinsics", false,
false)
INITIALIZE_PASS_END(ScalarizeMaskedMemIntrin, "scalarize-masked-mem-intrin",
"Scalarize unsupported masked memory intrinsics", false,
false)
FunctionPass *llvm::createScalarizeMaskedMemIntrinPass() {
return new ScalarizeMaskedMemIntrin();
}
// Translate a masked load intrinsic like
// <16 x i32 > @llvm.masked.load( <16 x i32>* %addr, i32 align,
// <16 x i1> %mask, <16 x i32> %passthru)
// to a chain of basic blocks, with loading element one-by-one if
// the appropriate mask bit is set
//
// %1 = bitcast i8* %addr to i32*
// %2 = extractelement <16 x i1> %mask, i32 0
// %3 = icmp eq i1 %2, true
// br i1 %3, label %cond.load, label %else
//
// cond.load: ; preds = %0
// %4 = getelementptr i32* %1, i32 0
// %5 = load i32* %4
// %6 = insertelement <16 x i32> undef, i32 %5, i32 0
// br label %else
//
// else: ; preds = %0, %cond.load
// %res.phi.else = phi <16 x i32> [ %6, %cond.load ], [ undef, %0 ]
// %7 = extractelement <16 x i1> %mask, i32 1
// %8 = icmp eq i1 %7, true
// br i1 %8, label %cond.load1, label %else2
//
// cond.load1: ; preds = %else
// %9 = getelementptr i32* %1, i32 1
// %10 = load i32* %9
// %11 = insertelement <16 x i32> %res.phi.else, i32 %10, i32 1
// br label %else2
//
// else2: ; preds = %else, %cond.load1
// %res.phi.else3 = phi <16 x i32> [ %11, %cond.load1 ], [ %res.phi.else, %else ]
// %12 = extractelement <16 x i1> %mask, i32 2
// %13 = icmp eq i1 %12, true
// br i1 %13, label %cond.load4, label %else5
//
static void scalarizeMaskedLoad(CallInst *CI) {
Value *Ptr = CI->getArgOperand(0);
Value *Alignment = CI->getArgOperand(1);
Value *Mask = CI->getArgOperand(2);
Value *Src0 = CI->getArgOperand(3);
unsigned AlignVal = cast<ConstantInt>(Alignment)->getZExtValue();
VectorType *VecType = dyn_cast<VectorType>(CI->getType());
assert(VecType && "Unexpected return type of masked load intrinsic");
Type *EltTy = CI->getType()->getVectorElementType();
IRBuilder<> Builder(CI->getContext());
Instruction *InsertPt = CI;
BasicBlock *IfBlock = CI->getParent();
BasicBlock *CondBlock = nullptr;
BasicBlock *PrevIfBlock = CI->getParent();
Builder.SetInsertPoint(InsertPt);
Builder.SetCurrentDebugLocation(CI->getDebugLoc());
// Short-cut if the mask is all-true.
bool IsAllOnesMask =
isa<Constant>(Mask) && cast<Constant>(Mask)->isAllOnesValue();
if (IsAllOnesMask) {
Value *NewI = Builder.CreateAlignedLoad(Ptr, AlignVal);
CI->replaceAllUsesWith(NewI);
CI->eraseFromParent();
return;
}
// Adjust alignment for the scalar instruction.
AlignVal = std::min(AlignVal, VecType->getScalarSizeInBits() / 8);
// Bitcast %addr fron i8* to EltTy*
Type *NewPtrType =
EltTy->getPointerTo(cast<PointerType>(Ptr->getType())->getAddressSpace());
Value *FirstEltPtr = Builder.CreateBitCast(Ptr, NewPtrType);
unsigned VectorWidth = VecType->getNumElements();
Value *UndefVal = UndefValue::get(VecType);
// The result vector
Value *VResult = UndefVal;
if (isa<ConstantVector>(Mask)) {
for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
if (cast<ConstantVector>(Mask)->getOperand(Idx)->isNullValue())
continue;
Value *Gep =
Builder.CreateInBoundsGEP(EltTy, FirstEltPtr, Builder.getInt32(Idx));
LoadInst *Load = Builder.CreateAlignedLoad(Gep, AlignVal);
VResult =
Builder.CreateInsertElement(VResult, Load, Builder.getInt32(Idx));
}
Value *NewI = Builder.CreateSelect(Mask, VResult, Src0);
CI->replaceAllUsesWith(NewI);
CI->eraseFromParent();
return;
}
PHINode *Phi = nullptr;
Value *PrevPhi = UndefVal;
for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
// Fill the "else" block, created in the previous iteration
//
// %res.phi.else3 = phi <16 x i32> [ %11, %cond.load1 ], [ %res.phi.else, %else ]
// %mask_1 = extractelement <16 x i1> %mask, i32 Idx
// %to_load = icmp eq i1 %mask_1, true
// br i1 %to_load, label %cond.load, label %else
//
if (Idx > 0) {
Phi = Builder.CreatePHI(VecType, 2, "res.phi.else");
Phi->addIncoming(VResult, CondBlock);
Phi->addIncoming(PrevPhi, PrevIfBlock);
PrevPhi = Phi;
VResult = Phi;
}
Value *Predicate =
Builder.CreateExtractElement(Mask, Builder.getInt32(Idx));
Value *Cmp = Builder.CreateICmp(ICmpInst::ICMP_EQ, Predicate,
ConstantInt::get(Predicate->getType(), 1));
// Create "cond" block
//
// %EltAddr = getelementptr i32* %1, i32 0
// %Elt = load i32* %EltAddr
// VResult = insertelement <16 x i32> VResult, i32 %Elt, i32 Idx
//
CondBlock = IfBlock->splitBasicBlock(InsertPt->getIterator(), "cond.load");
Builder.SetInsertPoint(InsertPt);
Value *Gep =
Builder.CreateInBoundsGEP(EltTy, FirstEltPtr, Builder.getInt32(Idx));
LoadInst *Load = Builder.CreateAlignedLoad(Gep, AlignVal);
VResult = Builder.CreateInsertElement(VResult, Load, Builder.getInt32(Idx));
// Create "else" block, fill it in the next iteration
BasicBlock *NewIfBlock =
CondBlock->splitBasicBlock(InsertPt->getIterator(), "else");
Builder.SetInsertPoint(InsertPt);
Instruction *OldBr = IfBlock->getTerminator();
BranchInst::Create(CondBlock, NewIfBlock, Cmp, OldBr);
OldBr->eraseFromParent();
PrevIfBlock = IfBlock;
IfBlock = NewIfBlock;
}
Phi = Builder.CreatePHI(VecType, 2, "res.phi.select");
Phi->addIncoming(VResult, CondBlock);
Phi->addIncoming(PrevPhi, PrevIfBlock);
Value *NewI = Builder.CreateSelect(Mask, Phi, Src0);
CI->replaceAllUsesWith(NewI);
CI->eraseFromParent();
}
// Translate a masked store intrinsic, like
// void @llvm.masked.store(<16 x i32> %src, <16 x i32>* %addr, i32 align,
// <16 x i1> %mask)
// to a chain of basic blocks, that stores element one-by-one if
// the appropriate mask bit is set
//
// %1 = bitcast i8* %addr to i32*
// %2 = extractelement <16 x i1> %mask, i32 0
// %3 = icmp eq i1 %2, true
// br i1 %3, label %cond.store, label %else
//
// cond.store: ; preds = %0
// %4 = extractelement <16 x i32> %val, i32 0
// %5 = getelementptr i32* %1, i32 0
// store i32 %4, i32* %5
// br label %else
//
// else: ; preds = %0, %cond.store
// %6 = extractelement <16 x i1> %mask, i32 1
// %7 = icmp eq i1 %6, true
// br i1 %7, label %cond.store1, label %else2
//
// cond.store1: ; preds = %else
// %8 = extractelement <16 x i32> %val, i32 1
// %9 = getelementptr i32* %1, i32 1
// store i32 %8, i32* %9
// br label %else2
// . . .
static void scalarizeMaskedStore(CallInst *CI) {
Value *Src = CI->getArgOperand(0);
Value *Ptr = CI->getArgOperand(1);
Value *Alignment = CI->getArgOperand(2);
Value *Mask = CI->getArgOperand(3);
unsigned AlignVal = cast<ConstantInt>(Alignment)->getZExtValue();
VectorType *VecType = dyn_cast<VectorType>(Src->getType());
assert(VecType && "Unexpected data type in masked store intrinsic");
Type *EltTy = VecType->getElementType();
IRBuilder<> Builder(CI->getContext());
Instruction *InsertPt = CI;
BasicBlock *IfBlock = CI->getParent();
Builder.SetInsertPoint(InsertPt);
Builder.SetCurrentDebugLocation(CI->getDebugLoc());
// Short-cut if the mask is all-true.
bool IsAllOnesMask =
isa<Constant>(Mask) && cast<Constant>(Mask)->isAllOnesValue();
if (IsAllOnesMask) {
Builder.CreateAlignedStore(Src, Ptr, AlignVal);
CI->eraseFromParent();
return;
}
// Adjust alignment for the scalar instruction.
AlignVal = std::max(AlignVal, VecType->getScalarSizeInBits() / 8);
// Bitcast %addr fron i8* to EltTy*
Type *NewPtrType =
EltTy->getPointerTo(cast<PointerType>(Ptr->getType())->getAddressSpace());
Value *FirstEltPtr = Builder.CreateBitCast(Ptr, NewPtrType);
unsigned VectorWidth = VecType->getNumElements();
if (isa<ConstantVector>(Mask)) {
for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
if (cast<ConstantVector>(Mask)->getOperand(Idx)->isNullValue())
continue;
Value *OneElt = Builder.CreateExtractElement(Src, Builder.getInt32(Idx));
Value *Gep =
Builder.CreateInBoundsGEP(EltTy, FirstEltPtr, Builder.getInt32(Idx));
Builder.CreateAlignedStore(OneElt, Gep, AlignVal);
}
CI->eraseFromParent();
return;
}
for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
// Fill the "else" block, created in the previous iteration
//
// %mask_1 = extractelement <16 x i1> %mask, i32 Idx
// %to_store = icmp eq i1 %mask_1, true
// br i1 %to_store, label %cond.store, label %else
//
Value *Predicate =
Builder.CreateExtractElement(Mask, Builder.getInt32(Idx));
Value *Cmp = Builder.CreateICmp(ICmpInst::ICMP_EQ, Predicate,
ConstantInt::get(Predicate->getType(), 1));
// Create "cond" block
//
// %OneElt = extractelement <16 x i32> %Src, i32 Idx
// %EltAddr = getelementptr i32* %1, i32 0
// %store i32 %OneElt, i32* %EltAddr
//
BasicBlock *CondBlock =
IfBlock->splitBasicBlock(InsertPt->getIterator(), "cond.store");
Builder.SetInsertPoint(InsertPt);
Value *OneElt = Builder.CreateExtractElement(Src, Builder.getInt32(Idx));
Value *Gep =
Builder.CreateInBoundsGEP(EltTy, FirstEltPtr, Builder.getInt32(Idx));
Builder.CreateAlignedStore(OneElt, Gep, AlignVal);
// Create "else" block, fill it in the next iteration
BasicBlock *NewIfBlock =
CondBlock->splitBasicBlock(InsertPt->getIterator(), "else");
Builder.SetInsertPoint(InsertPt);
Instruction *OldBr = IfBlock->getTerminator();
BranchInst::Create(CondBlock, NewIfBlock, Cmp, OldBr);
OldBr->eraseFromParent();
IfBlock = NewIfBlock;
}
CI->eraseFromParent();
}
// Translate a masked gather intrinsic like
// <16 x i32 > @llvm.masked.gather.v16i32( <16 x i32*> %Ptrs, i32 4,
// <16 x i1> %Mask, <16 x i32> %Src)
// to a chain of basic blocks, with loading element one-by-one if
// the appropriate mask bit is set
//
// % Ptrs = getelementptr i32, i32* %base, <16 x i64> %ind
// % Mask0 = extractelement <16 x i1> %Mask, i32 0
// % ToLoad0 = icmp eq i1 % Mask0, true
// br i1 % ToLoad0, label %cond.load, label %else
//
// cond.load:
// % Ptr0 = extractelement <16 x i32*> %Ptrs, i32 0
// % Load0 = load i32, i32* % Ptr0, align 4
// % Res0 = insertelement <16 x i32> undef, i32 % Load0, i32 0
// br label %else
//
// else:
// %res.phi.else = phi <16 x i32>[% Res0, %cond.load], [undef, % 0]
// % Mask1 = extractelement <16 x i1> %Mask, i32 1
// % ToLoad1 = icmp eq i1 % Mask1, true
// br i1 % ToLoad1, label %cond.load1, label %else2
//
// cond.load1:
// % Ptr1 = extractelement <16 x i32*> %Ptrs, i32 1
// % Load1 = load i32, i32* % Ptr1, align 4
// % Res1 = insertelement <16 x i32> %res.phi.else, i32 % Load1, i32 1
// br label %else2
// . . .
// % Result = select <16 x i1> %Mask, <16 x i32> %res.phi.select, <16 x i32> %Src
// ret <16 x i32> %Result
static void scalarizeMaskedGather(CallInst *CI) {
Value *Ptrs = CI->getArgOperand(0);
Value *Alignment = CI->getArgOperand(1);
Value *Mask = CI->getArgOperand(2);
Value *Src0 = CI->getArgOperand(3);
VectorType *VecType = dyn_cast<VectorType>(CI->getType());
assert(VecType && "Unexpected return type of masked load intrinsic");
IRBuilder<> Builder(CI->getContext());
Instruction *InsertPt = CI;
BasicBlock *IfBlock = CI->getParent();
BasicBlock *CondBlock = nullptr;
BasicBlock *PrevIfBlock = CI->getParent();
Builder.SetInsertPoint(InsertPt);
unsigned AlignVal = cast<ConstantInt>(Alignment)->getZExtValue();
Builder.SetCurrentDebugLocation(CI->getDebugLoc());
Value *UndefVal = UndefValue::get(VecType);
// The result vector
Value *VResult = UndefVal;
unsigned VectorWidth = VecType->getNumElements();
// Shorten the way if the mask is a vector of constants.
bool IsConstMask = isa<ConstantVector>(Mask);
if (IsConstMask) {
for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
if (cast<ConstantVector>(Mask)->getOperand(Idx)->isNullValue())
continue;
Value *Ptr = Builder.CreateExtractElement(Ptrs, Builder.getInt32(Idx),
"Ptr" + Twine(Idx));
LoadInst *Load =
Builder.CreateAlignedLoad(Ptr, AlignVal, "Load" + Twine(Idx));
VResult = Builder.CreateInsertElement(
VResult, Load, Builder.getInt32(Idx), "Res" + Twine(Idx));
}
Value *NewI = Builder.CreateSelect(Mask, VResult, Src0);
CI->replaceAllUsesWith(NewI);
CI->eraseFromParent();
return;
}
PHINode *Phi = nullptr;
Value *PrevPhi = UndefVal;
for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
// Fill the "else" block, created in the previous iteration
//
// %Mask1 = extractelement <16 x i1> %Mask, i32 1
// %ToLoad1 = icmp eq i1 %Mask1, true
// br i1 %ToLoad1, label %cond.load, label %else
//
if (Idx > 0) {
Phi = Builder.CreatePHI(VecType, 2, "res.phi.else");
Phi->addIncoming(VResult, CondBlock);
Phi->addIncoming(PrevPhi, PrevIfBlock);
PrevPhi = Phi;
VResult = Phi;
}
Value *Predicate = Builder.CreateExtractElement(Mask, Builder.getInt32(Idx),
"Mask" + Twine(Idx));
Value *Cmp = Builder.CreateICmp(ICmpInst::ICMP_EQ, Predicate,
ConstantInt::get(Predicate->getType(), 1),
"ToLoad" + Twine(Idx));
// Create "cond" block
//
// %EltAddr = getelementptr i32* %1, i32 0
// %Elt = load i32* %EltAddr
// VResult = insertelement <16 x i32> VResult, i32 %Elt, i32 Idx
//
CondBlock = IfBlock->splitBasicBlock(InsertPt, "cond.load");
Builder.SetInsertPoint(InsertPt);
Value *Ptr = Builder.CreateExtractElement(Ptrs, Builder.getInt32(Idx),
"Ptr" + Twine(Idx));
LoadInst *Load =
Builder.CreateAlignedLoad(Ptr, AlignVal, "Load" + Twine(Idx));
VResult = Builder.CreateInsertElement(VResult, Load, Builder.getInt32(Idx),
"Res" + Twine(Idx));
// Create "else" block, fill it in the next iteration
BasicBlock *NewIfBlock = CondBlock->splitBasicBlock(InsertPt, "else");
Builder.SetInsertPoint(InsertPt);
Instruction *OldBr = IfBlock->getTerminator();
BranchInst::Create(CondBlock, NewIfBlock, Cmp, OldBr);
OldBr->eraseFromParent();
PrevIfBlock = IfBlock;
IfBlock = NewIfBlock;
}
Phi = Builder.CreatePHI(VecType, 2, "res.phi.select");
Phi->addIncoming(VResult, CondBlock);
Phi->addIncoming(PrevPhi, PrevIfBlock);
Value *NewI = Builder.CreateSelect(Mask, Phi, Src0);
CI->replaceAllUsesWith(NewI);
CI->eraseFromParent();
}
// Translate a masked scatter intrinsic, like
// void @llvm.masked.scatter.v16i32(<16 x i32> %Src, <16 x i32*>* %Ptrs, i32 4,
// <16 x i1> %Mask)
// to a chain of basic blocks, that stores element one-by-one if
// the appropriate mask bit is set.
//
// % Ptrs = getelementptr i32, i32* %ptr, <16 x i64> %ind
// % Mask0 = extractelement <16 x i1> % Mask, i32 0
// % ToStore0 = icmp eq i1 % Mask0, true
// br i1 %ToStore0, label %cond.store, label %else
//
// cond.store:
// % Elt0 = extractelement <16 x i32> %Src, i32 0
// % Ptr0 = extractelement <16 x i32*> %Ptrs, i32 0
// store i32 %Elt0, i32* % Ptr0, align 4
// br label %else
//
// else:
// % Mask1 = extractelement <16 x i1> % Mask, i32 1
// % ToStore1 = icmp eq i1 % Mask1, true
// br i1 % ToStore1, label %cond.store1, label %else2
//
// cond.store1:
// % Elt1 = extractelement <16 x i32> %Src, i32 1
// % Ptr1 = extractelement <16 x i32*> %Ptrs, i32 1
// store i32 % Elt1, i32* % Ptr1, align 4
// br label %else2
// . . .
static void scalarizeMaskedScatter(CallInst *CI) {
Value *Src = CI->getArgOperand(0);
Value *Ptrs = CI->getArgOperand(1);
Value *Alignment = CI->getArgOperand(2);
Value *Mask = CI->getArgOperand(3);
assert(isa<VectorType>(Src->getType()) &&
"Unexpected data type in masked scatter intrinsic");
assert(isa<VectorType>(Ptrs->getType()) &&
isa<PointerType>(Ptrs->getType()->getVectorElementType()) &&
"Vector of pointers is expected in masked scatter intrinsic");
IRBuilder<> Builder(CI->getContext());
Instruction *InsertPt = CI;
BasicBlock *IfBlock = CI->getParent();
Builder.SetInsertPoint(InsertPt);
Builder.SetCurrentDebugLocation(CI->getDebugLoc());
unsigned AlignVal = cast<ConstantInt>(Alignment)->getZExtValue();
unsigned VectorWidth = Src->getType()->getVectorNumElements();
// Shorten the way if the mask is a vector of constants.
bool IsConstMask = isa<ConstantVector>(Mask);
if (IsConstMask) {
for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
if (cast<ConstantVector>(Mask)->getOperand(Idx)->isNullValue())
continue;
Value *OneElt = Builder.CreateExtractElement(Src, Builder.getInt32(Idx),
"Elt" + Twine(Idx));
Value *Ptr = Builder.CreateExtractElement(Ptrs, Builder.getInt32(Idx),
"Ptr" + Twine(Idx));
Builder.CreateAlignedStore(OneElt, Ptr, AlignVal);
}
CI->eraseFromParent();
return;
}
for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
// Fill the "else" block, created in the previous iteration
//
// % Mask1 = extractelement <16 x i1> % Mask, i32 Idx
// % ToStore = icmp eq i1 % Mask1, true
// br i1 % ToStore, label %cond.store, label %else
//
Value *Predicate = Builder.CreateExtractElement(Mask, Builder.getInt32(Idx),
"Mask" + Twine(Idx));
Value *Cmp = Builder.CreateICmp(ICmpInst::ICMP_EQ, Predicate,
ConstantInt::get(Predicate->getType(), 1),
"ToStore" + Twine(Idx));
// Create "cond" block
//
// % Elt1 = extractelement <16 x i32> %Src, i32 1
// % Ptr1 = extractelement <16 x i32*> %Ptrs, i32 1
// %store i32 % Elt1, i32* % Ptr1
//
BasicBlock *CondBlock = IfBlock->splitBasicBlock(InsertPt, "cond.store");
Builder.SetInsertPoint(InsertPt);
Value *OneElt = Builder.CreateExtractElement(Src, Builder.getInt32(Idx),
"Elt" + Twine(Idx));
Value *Ptr = Builder.CreateExtractElement(Ptrs, Builder.getInt32(Idx),
"Ptr" + Twine(Idx));
Builder.CreateAlignedStore(OneElt, Ptr, AlignVal);
// Create "else" block, fill it in the next iteration
BasicBlock *NewIfBlock = CondBlock->splitBasicBlock(InsertPt, "else");
Builder.SetInsertPoint(InsertPt);
Instruction *OldBr = IfBlock->getTerminator();
BranchInst::Create(CondBlock, NewIfBlock, Cmp, OldBr);
OldBr->eraseFromParent();
IfBlock = NewIfBlock;
}
CI->eraseFromParent();
}
bool ScalarizeMaskedMemIntrin::runOnFunction(Function &F) {
if (skipFunction(F))
return false;
bool EverMadeChange = false;
TTI = &getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
bool MadeChange = true;
while (MadeChange) {
MadeChange = false;
for (Function::iterator I = F.begin(); I != F.end();) {
BasicBlock *BB = &*I++;
bool ModifiedDTOnIteration = false;
MadeChange |= optimizeBlock(*BB, ModifiedDTOnIteration);
// Restart BB iteration if the dominator tree of the Function was changed
if (ModifiedDTOnIteration)
break;
}
EverMadeChange |= MadeChange;
}
return EverMadeChange;
}
bool ScalarizeMaskedMemIntrin::optimizeBlock(BasicBlock &BB, bool &ModifiedDT) {
bool MadeChange = false;
BasicBlock::iterator CurInstIterator = BB.begin();
while (CurInstIterator != BB.end()) {
if (CallInst *CI = dyn_cast<CallInst>(&*CurInstIterator++))
MadeChange |= optimizeCallInst(CI, ModifiedDT);
if (ModifiedDT)
return true;
}
return MadeChange;
}
bool ScalarizeMaskedMemIntrin::optimizeCallInst(CallInst *CI,
bool &ModifiedDT) {
IntrinsicInst *II = dyn_cast<IntrinsicInst>(CI);
if (II) {
switch (II->getIntrinsicID()) {
default:
break;
case Intrinsic::masked_load: {
// Scalarize unsupported vector masked load
if (!TTI->isLegalMaskedLoad(CI->getType())) {
scalarizeMaskedLoad(CI);
ModifiedDT = true;
return true;
}
return false;
}
case Intrinsic::masked_store: {
if (!TTI->isLegalMaskedStore(CI->getArgOperand(0)->getType())) {
scalarizeMaskedStore(CI);
ModifiedDT = true;
return true;
}
return false;
}
case Intrinsic::masked_gather: {
if (!TTI->isLegalMaskedGather(CI->getType())) {
scalarizeMaskedGather(CI);
ModifiedDT = true;
return true;
}
return false;
}
case Intrinsic::masked_scatter: {
if (!TTI->isLegalMaskedScatter(CI->getArgOperand(0)->getType())) {
scalarizeMaskedScatter(CI);
ModifiedDT = true;
return true;
}
return false;
}
}
}
return false;
}

llvm/trunk/lib/CodeGen/TargetPassConfig.cpp

Show First 20 Lines • Show All 482 Lines • ▼ Show 20 Lines if (getOptLevel() != CodeGenOpt::None && !DisableConstantHoisting)
addPass(createConstantHoistingPass()); addPass(createConstantHoistingPass());
if (getOptLevel() != CodeGenOpt::None && !DisablePartialLibcallInlining) if (getOptLevel() != CodeGenOpt::None && !DisablePartialLibcallInlining)
addPass(createPartiallyInlineLibCallsPass()); addPass(createPartiallyInlineLibCallsPass());
// Insert calls to mcount-like functions. // Insert calls to mcount-like functions.
addPass(createCountingFunctionInserterPass()); addPass(createCountingFunctionInserterPass());
// Add scalarization of target's unsupported masked memory intrinsics pass.
// the unsupported intrinsic will be replaced with a chain of basic blocks,
// that stores/loads element one-by-one if the appropriate mask bit is set.
addPass(createScalarizeMaskedMemIntrinPass());
// Expand reduction intrinsics into shuffle sequences if the target wants to. // Expand reduction intrinsics into shuffle sequences if the target wants to.
addPass(createExpandReductionsPass()); addPass(createExpandReductionsPass());
} }
/// Turn exception handling constructs into something the code generators can /// Turn exception handling constructs into something the code generators can
/// handle. /// handle.
void TargetPassConfig::addPassesToHandleExceptions() { void TargetPassConfig::addPassesToHandleExceptions() {
const MCAsmInfo *MCAI = TM->getMCAsmInfo(); const MCAsmInfo *MCAI = TM->getMCAsmInfo();
▲ Show 20 Lines • Show All 442 Lines • Show Last 20 Lines

llvm/trunk/test/CodeGen/X86/O0-pipeline.ll

Show All 17 Lines
; CHECK-NEXT: Expand Atomic instructions ; CHECK-NEXT: Expand Atomic instructions
; CHECK-NEXT: Dominator Tree Construction ; CHECK-NEXT: Dominator Tree Construction
; CHECK-NEXT: Basic Alias Analysis (stateless AA impl) ; CHECK-NEXT: Basic Alias Analysis (stateless AA impl)
; CHECK-NEXT: Module Verifier ; CHECK-NEXT: Module Verifier
; CHECK-NEXT: Lower Garbage Collection Instructions ; CHECK-NEXT: Lower Garbage Collection Instructions
; CHECK-NEXT: Shadow Stack GC Lowering ; CHECK-NEXT: Shadow Stack GC Lowering
; CHECK-NEXT: Remove unreachable blocks from the CFG ; CHECK-NEXT: Remove unreachable blocks from the CFG
; CHECK-NEXT: Inserts calls to mcount-like functions ; CHECK-NEXT: Inserts calls to mcount-like functions
; CHECK-NEXT: Scalarize Masked Memory Intrinsics
; CHECK-NEXT: Expand reduction intrinsics ; CHECK-NEXT: Expand reduction intrinsics
; CHECK-NEXT: Rewrite Symbols ; CHECK-NEXT: Rewrite Symbols
; CHECK-NEXT: FunctionPass Manager ; CHECK-NEXT: FunctionPass Manager
; CHECK-NEXT: Dominator Tree Construction ; CHECK-NEXT: Dominator Tree Construction
; CHECK-NEXT: Exception handling preparation ; CHECK-NEXT: Exception handling preparation
; CHECK-NEXT: Safe Stack instrumentation pass ; CHECK-NEXT: Safe Stack instrumentation pass
; CHECK-NEXT: Insert stack protectors ; CHECK-NEXT: Insert stack protectors
; CHECK-NEXT: Module Verifier ; CHECK-NEXT: Module Verifier
Show All 33 Lines

llvm/trunk/test/CodeGen/X86/masked_gather_scatter.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=x86_64-unknown-linux-gnu -mattr=+avx512f < %s | FileCheck %s --check-prefix=ALL --check-prefix=KNL_64 ; RUN: llc -mtriple=x86_64-unknown-linux-gnu -mattr=+avx512f < %s | FileCheck %s --check-prefix=ALL --check-prefix=KNL_64
; RUN: llc -mtriple=i386-unknown-linux-gnu -mattr=+avx512f < %s | FileCheck %s --check-prefix=ALL --check-prefix=KNL_32 ; RUN: llc -mtriple=i386-unknown-linux-gnu -mattr=+avx512f < %s | FileCheck %s --check-prefix=ALL --check-prefix=KNL_32
; RUN: llc -mtriple=x86_64-unknown-linux-gnu -mattr=+avx512vl -mattr=+avx512dq < %s | FileCheck %s --check-prefix=ALL --check-prefix=SKX ; RUN: llc -mtriple=x86_64-unknown-linux-gnu -mattr=+avx512vl -mattr=+avx512dq < %s | FileCheck %s --check-prefix=ALL --check-prefix=SKX
; RUN: llc -mtriple=i386-unknown-linux-gnu -mattr=+avx512vl -mattr=+avx512dq < %s | FileCheck %s --check-prefix=ALL --check-prefix=SKX_32 ; RUN: llc -mtriple=i386-unknown-linux-gnu -mattr=+avx512vl -mattr=+avx512dq < %s | FileCheck %s --check-prefix=ALL --check-prefix=SKX_32
; RUN: opt -mtriple=x86_64-apple-darwin -codegenprepare -mcpu=corei7-avx -S < %s | FileCheck %s -check-prefix=SCALAR ; RUN: opt -mtriple=x86_64-apple-darwin -scalarize-masked-mem-intrin -mcpu=corei7-avx -S < %s | FileCheck %s -check-prefix=SCALAR
; RUN: llc -O0 -mtriple=x86_64-unknown-linux-gnu -mcpu=skx < %s -o /dev/null ; RUN: llc -O0 -mtriple=x86_64-unknown-linux-gnu -mcpu=skx < %s -o /dev/null
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128" target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu" target triple = "x86_64-unknown-linux-gnu"
; SCALAR-LABEL: test1 ; SCALAR-LABEL: test1
; SCALAR: extractelement <16 x float*> ; SCALAR: extractelement <16 x float*>
▲ Show 20 Lines • Show All 2,189 Lines • Show Last 20 Lines

llvm/trunk/test/CodeGen/X86/replace_unsupported_masked_mem_intrin.ll

; RUN: llc -O0 -mtriple=x86_64-unknown-linux-gnu -mattr=+sse,+sse2 < %s -o /dev/null
; pr33001 - Check that llc doesn't crash when running with O0 option.
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
define <4 x i32> @test_masked_load(<4 x i32>* %base, <4 x i1> %mask) {
%res = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %base, i32 4, <4 x i1> %mask, <4 x i32> zeroinitializer)
ret <4 x i32> %res
}
declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32, <4 x i1>, <4 x i32>)
define void @test_masked_store(<4 x i32>* %base, <4 x i32> %value, <4 x i1> %mask) {
call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %value, <4 x i32>* %base, i32 4, <4 x i1> %mask)
ret void
}
declare void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>, <4 x i32>*, i32, <4 x i1>)
define <4 x i32> @llvm_masked_gather(<4 x i32*> %ptrs, <4 x i1> %mask) {
%res = call <4 x i32> @llvm.masked.gather.v4i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> undef)
ret <4 x i32> %res
}
declare <4 x i32> @llvm.masked.gather.v4i32(<4 x i32*>, i32, <4 x i1>, <4 x i32>)
define void @llvm_masked_scatter(<4 x i32*> %ptrs, <4 x i32> %value, <4 x i1> %mask) {
call void @llvm.masked.scatter.v4i32(<4 x i32> %value, <4 x i32*> %ptrs, i32 4, <4 x i1> %mask)
ret void
}
declare void @llvm.masked.scatter.v4i32(<4 x i32>, <4 x i32*>, i32, <4 x i1>)

llvm/trunk/tools/llc/llc.cpp

Show First 20 Lines • Show All 295 Lines • ▼ Show 20 Linesint main(int argc, char **argv) {
initializeCodeGen(*Registry); initializeCodeGen(*Registry);
initializeLoopStrengthReducePass(*Registry); initializeLoopStrengthReducePass(*Registry);
initializeLowerIntrinsicsPass(*Registry); initializeLowerIntrinsicsPass(*Registry);
initializeCountingFunctionInserterPass(*Registry); initializeCountingFunctionInserterPass(*Registry);
initializeUnreachableBlockElimLegacyPassPass(*Registry); initializeUnreachableBlockElimLegacyPassPass(*Registry);
initializeConstantHoistingLegacyPassPass(*Registry); initializeConstantHoistingLegacyPassPass(*Registry);
initializeScalarOpts(*Registry); initializeScalarOpts(*Registry);
initializeVectorization(*Registry); initializeVectorization(*Registry);
initializeScalarizeMaskedMemIntrinPass(*Registry);
initializeExpandReductionsPass(*Registry); initializeExpandReductionsPass(*Registry);
// Register the target printer for --version. // Register the target printer for --version.
cl::AddExtraVersionPrinter(TargetRegistry::printRegisteredTargetsForVersion); cl::AddExtraVersionPrinter(TargetRegistry::printRegisteredTargetsForVersion);
cl::ParseCommandLineOptions(argc, argv, "llvm system compiler\n"); cl::ParseCommandLineOptions(argc, argv, "llvm system compiler\n");
Context.setDiscardValueNames(DiscardValueNames); Context.setDiscardValueNames(DiscardValueNames);
▲ Show 20 Lines • Show All 304 Lines • Show Last 20 Lines

llvm/trunk/tools/opt/opt.cpp

Show First 20 Lines • Show All 379 Lines • ▼ Show 20 Linesint main(int argc, char **argv) {
initializeIPO(Registry); initializeIPO(Registry);
initializeAnalysis(Registry); initializeAnalysis(Registry);
initializeTransformUtils(Registry); initializeTransformUtils(Registry);
initializeInstCombine(Registry); initializeInstCombine(Registry);
initializeInstrumentation(Registry); initializeInstrumentation(Registry);
initializeTarget(Registry); initializeTarget(Registry);
// For codegen passes, only passes that do IR to IR transformation are // For codegen passes, only passes that do IR to IR transformation are
// supported. // supported.
initializeScalarizeMaskedMemIntrinPass(Registry);
initializeCodeGenPreparePass(Registry); initializeCodeGenPreparePass(Registry);
initializeAtomicExpandPass(Registry); initializeAtomicExpandPass(Registry);
initializeRewriteSymbolsLegacyPassPass(Registry); initializeRewriteSymbolsLegacyPassPass(Registry);
initializeWinEHPreparePass(Registry); initializeWinEHPreparePass(Registry);
initializeDwarfEHPreparePass(Registry); initializeDwarfEHPreparePass(Registry);
initializeSafeStackLegacyPassPass(Registry); initializeSafeStackLegacyPassPass(Registry);
initializeSjLjEHPreparePass(Registry); initializeSjLjEHPreparePass(Registry);
initializePreISelIntrinsicLoweringLegacyPassPass(Registry); initializePreISelIntrinsicLoweringLegacyPassPass(Registry);
▲ Show 20 Lines • Show All 376 Lines • Show Last 20 Lines