maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Re-commit r86077 now that r86290 fixes the 179.art and 175.vpr ARM regressions. 

Here is the original commit message:

This commit updates malloc optimizations to operate on malloc calls that have constant int size arguments.

Update CreateMalloc so that its callers specify the size to allocate:
MallocInst-autoupgrade users use non-TargetData-computed allocation sizes.
Optimization uses use TargetData to compute the allocation size.

Now that malloc calls can have constant sizes, update isArrayMallocHelper() to use TargetData to determine the size of the malloced type and the size of malloced arrays.
Extend getMallocType() to support malloc calls that have non-bitcast uses.

Update OptimizeGlobalAddressOfMalloc() to optimize malloc calls that have non-bitcast uses.  The bitcast use of a malloc call has to be treated specially here because the uses of the bitcast need to be replaced and the bitcast needs to be erased (just like the malloc call) for OptimizeGlobalAddressOfMalloc() to work correctly.

Update PerformHeapAllocSRoA() to optimize malloc calls that have non-bitcast uses.  The bitcast use of the malloc is not handled specially here because ReplaceUsesOfMallocWithGlobal replaces through the bitcast use.

Update OptimizeOnceStoredGlobal() to not care about the malloc calls' bitcast use.

Update all globalopt malloc tests to not rely on autoupgraded-MallocInsts, but instead use explicit malloc calls with correct allocation sizes.

llvm-svn: 86311
This commit is contained in:
Victor Hernandez 2009-11-07 00:16:28 +00:00
parent 79d70e3e65
commit f3db915294
19 changed files with 252 additions and 202 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
llvm/examples/BrainF/BrainF.cpp
View File

@ -81,8 +81,11 @@ void BrainF::header(LLVMContext& C) {
ConstantInt *val_mem = ConstantInt::get(C, APInt(32, memtotal)); ConstantInt *val_mem = ConstantInt::get(C, APInt(32, memtotal));
BasicBlock* BB = builder->GetInsertBlock(); BasicBlock* BB = builder->GetInsertBlock();
const Type* IntPtrTy = IntegerType::getInt32Ty(C); const Type* IntPtrTy = IntegerType::getInt32Ty(C);
ptr_arr = CallInst::CreateMalloc(BB, IntPtrTy, IntegerType::getInt8Ty(C), const Type* Int8Ty = IntegerType::getInt8Ty(C);
val_mem, NULL, "arr"); Constant* allocsize = ConstantExpr::getSizeOf(Int8Ty);
allocsize = ConstantExpr::getTruncOrBitCast(allocsize, IntPtrTy);
ptr_arr = CallInst::CreateMalloc(BB, IntPtrTy, Int8Ty, allocsize, val_mem,
NULL, "arr");
BB->getInstList().push_back(cast<Instruction>(ptr_arr)); BB->getInstList().push_back(cast<Instruction>(ptr_arr));
//call void @llvm.memset.i32(i8 *%arr, i8 0, i32 %d, i32 1) //call void @llvm.memset.i32(i8 *%arr, i8 0, i32 %d, i32 1)

14
llvm/include/llvm/Analysis/MemoryBuiltins.h
View File

@ -49,13 +49,17 @@ const CallInst* isArrayMalloc(const Value *I,
const TargetData *TD); const TargetData *TD);
/// getMallocType - Returns the PointerType resulting from the malloc call. /// getMallocType - Returns the PointerType resulting from the malloc call.
/// This PointerType is the result type of the call's only bitcast use. /// The PointerType depends on the number of bitcast uses of the malloc call:
/// If there is no unique bitcast use, then return NULL. /// 0: PointerType is the malloc calls' return type.
/// 1: PointerType is the bitcast's result type.
/// >1: Unique PointerType cannot be determined, return NULL.
const PointerType *getMallocType(const CallInst *CI); const PointerType *getMallocType(const CallInst *CI);
/// getMallocAllocatedType - Returns the Type allocated by malloc call. This /// getMallocAllocatedType - Returns the Type allocated by malloc call.
/// Type is the result type of the call's only bitcast use. If there is no /// The Type depends on the number of bitcast uses of the malloc call:
/// unique bitcast use, then return NULL. /// 0: PointerType is the malloc calls' return type.
/// 1: PointerType is the bitcast's result type.
/// >1: Unique PointerType cannot be determined, return NULL.
const Type *getMallocAllocatedType(const CallInst *CI); const Type *getMallocAllocatedType(const CallInst *CI);
/// getMallocArraySize - Returns the array size of a malloc call. If the /// getMallocArraySize - Returns the array size of a malloc call. If the

5
llvm/include/llvm/Instructions.h
View File

@ -899,11 +899,12 @@ public:
/// 3. Bitcast the result of the malloc call to the specified type. /// 3. Bitcast the result of the malloc call to the specified type.
static Instruction *CreateMalloc(Instruction *InsertBefore, static Instruction *CreateMalloc(Instruction *InsertBefore,
const Type *IntPtrTy, const Type *AllocTy, const Type *IntPtrTy, const Type *AllocTy,
Value *ArraySize = 0, Value *AllocSize, Value *ArraySize = 0,
const Twine &Name = ""); const Twine &Name = "");
static Instruction *CreateMalloc(BasicBlock *InsertAtEnd, static Instruction *CreateMalloc(BasicBlock *InsertAtEnd,
const Type *IntPtrTy, const Type *AllocTy, const Type *IntPtrTy, const Type *AllocTy,
Value *ArraySize = 0, Function* MallocF = 0, Value *AllocSize, Value *ArraySize = 0,
Function* MallocF = 0,
const Twine &Name = ""); const Twine &Name = "");
/// CreateFree - Generate the IR for a call to the builtin free function. /// CreateFree - Generate the IR for a call to the builtin free function.
static void CreateFree(Value* Source, Instruction *InsertBefore); static void CreateFree(Value* Source, Instruction *InsertBefore);

70
llvm/lib/Analysis/MemoryBuiltins.cpp
View File

@ -17,6 +17,7 @@
#include "llvm/Instructions.h" #include "llvm/Instructions.h"
#include "llvm/Module.h" #include "llvm/Module.h"
#include "llvm/Analysis/ConstantFolding.h" #include "llvm/Analysis/ConstantFolding.h"
#include "llvm/Target/TargetData.h"
using namespace llvm; using namespace llvm;
//===----------------------------------------------------------------------===// //===----------------------------------------------------------------------===//
@ -95,32 +96,34 @@ static Value *isArrayMallocHelper(const CallInst *CI, const TargetData *TD) {
if (!CI) if (!CI)
return NULL; return NULL;
// Type must be known to determine array size. // The size of the malloc's result type must be known to determine array size.
const Type *T = getMallocAllocatedType(CI); const Type *T = getMallocAllocatedType(CI);
if (!T) if (!T || !T->isSized() || !TD)
return NULL; return NULL;
Value *MallocArg = CI->getOperand(1); Value *MallocArg = CI->getOperand(1);
const Type *ArgType = MallocArg->getType();
ConstantExpr *CO = dyn_cast<ConstantExpr>(MallocArg); ConstantExpr *CO = dyn_cast<ConstantExpr>(MallocArg);
BinaryOperator *BO = dyn_cast<BinaryOperator>(MallocArg); BinaryOperator *BO = dyn_cast<BinaryOperator>(MallocArg);
Constant *ElementSize = ConstantExpr::getSizeOf(T); unsigned ElementSizeInt = TD->getTypeAllocSize(T);
ElementSize = ConstantExpr::getTruncOrBitCast(ElementSize, if (const StructType *ST = dyn_cast<StructType>(T))
MallocArg->getType()); ElementSizeInt = TD->getStructLayout(ST)->getSizeInBytes();
Constant *FoldedElementSize = Constant *ElementSize = ConstantInt::get(ArgType, ElementSizeInt);
ConstantFoldConstantExpression(cast<ConstantExpr>(ElementSize), TD);
// First, check if CI is a non-array malloc. // First, check if CI is a non-array malloc.
if (CO && ((CO == ElementSize) || if (CO && CO == ElementSize)
(FoldedElementSize && (CO == FoldedElementSize))))
// Match CreateMalloc's use of constant 1 array-size for non-array mallocs. // Match CreateMalloc's use of constant 1 array-size for non-array mallocs.
return ConstantInt::get(MallocArg->getType(), 1); return ConstantInt::get(ArgType, 1);
// Second, check if CI is an array malloc whose array size can be determined. // Second, check if CI is an array malloc whose array size can be determined.
if (isConstantOne(ElementSize) || if (isConstantOne(ElementSize))
(FoldedElementSize && isConstantOne(FoldedElementSize)))
return MallocArg; return MallocArg;
if (ConstantInt *CInt = dyn_cast<ConstantInt>(MallocArg))
if (CInt->getZExtValue() % ElementSizeInt == 0)
return ConstantInt::get(ArgType, CInt->getZExtValue() / ElementSizeInt);
if (!CO && !BO) if (!CO && !BO)
return NULL; return NULL;
@ -143,12 +146,10 @@ static Value *isArrayMallocHelper(const CallInst *CI, const TargetData *TD) {
// Determine array size if malloc's argument is the product of a mul or shl. // Determine array size if malloc's argument is the product of a mul or shl.
if (Op0) { if (Op0) {
if (Opcode == Instruction::Mul) { if (Opcode == Instruction::Mul) {
if ((Op1 == ElementSize) || if (Op1 == ElementSize)
(FoldedElementSize && (Op1 == FoldedElementSize)))
// ArraySize * ElementSize // ArraySize * ElementSize
return Op0; return Op0;
if ((Op0 == ElementSize) || if (Op0 == ElementSize)
(FoldedElementSize && (Op0 == FoldedElementSize)))
// ElementSize * ArraySize // ElementSize * ArraySize
return Op1; return Op1;
} }
@ -160,11 +161,10 @@ static Value *isArrayMallocHelper(const CallInst *CI, const TargetData *TD) {
uint64_t BitToSet = Op1Int.getLimitedValue(Op1Int.getBitWidth() - 1); uint64_t BitToSet = Op1Int.getLimitedValue(Op1Int.getBitWidth() - 1);
Value *Op1Pow = ConstantInt::get(Op1CI->getContext(), Value *Op1Pow = ConstantInt::get(Op1CI->getContext(),
APInt(Op1Int.getBitWidth(), 0).set(BitToSet)); APInt(Op1Int.getBitWidth(), 0).set(BitToSet));
if (Op0 == ElementSize || (FoldedElementSize && Op0 == FoldedElementSize)) if (Op0 == ElementSize)
// ArraySize << log2(ElementSize) // ArraySize << log2(ElementSize)
return Op1Pow; return Op1Pow;
if (Op1Pow == ElementSize || if (Op1Pow == ElementSize)
(FoldedElementSize && Op1Pow == FoldedElementSize))
// ElementSize << log2(ArraySize) // ElementSize << log2(ArraySize)
return Op0; return Op0;
} }
@ -202,35 +202,41 @@ const CallInst *llvm::isArrayMalloc(const Value *I, const TargetData *TD) {
} }
/// getMallocType - Returns the PointerType resulting from the malloc call. /// getMallocType - Returns the PointerType resulting from the malloc call.
/// This PointerType is the result type of the call's only bitcast use. /// The PointerType depends on the number of bitcast uses of the malloc call:
/// If there is no unique bitcast use, then return NULL. /// 0: PointerType is the calls' return type.
/// 1: PointerType is the bitcast's result type.
/// >1: Unique PointerType cannot be determined, return NULL.
const PointerType *llvm::getMallocType(const CallInst *CI) { const PointerType *llvm::getMallocType(const CallInst *CI) {
assert(isMalloc(CI) && "GetMallocType and not malloc call"); assert(isMalloc(CI) && "GetMallocType and not malloc call");
const BitCastInst *BCI = NULL; const PointerType *MallocType = NULL;
unsigned NumOfBitCastUses = 0;
// Determine if CallInst has a bitcast use. // Determine if CallInst has a bitcast use.
for (Value::use_const_iterator UI = CI->use_begin(), E = CI->use_end(); for (Value::use_const_iterator UI = CI->use_begin(), E = CI->use_end();
UI != E; ) UI != E; )
if ((BCI = dyn_cast<BitCastInst>(cast<Instruction>(*UI++)))) if (const BitCastInst *BCI = dyn_cast<BitCastInst>(*UI++)) {
break; MallocType = cast<PointerType>(BCI->getDestTy());
NumOfBitCastUses++;
}
// Malloc call has 1 bitcast use and no other uses, so type is the bitcast's // Malloc call has 1 bitcast use, so type is the bitcast's destination type.
// destination type. if (NumOfBitCastUses == 1)
if (BCI && CI->hasOneUse()) return MallocType;
return cast<PointerType>(BCI->getDestTy());
// Malloc call was not bitcast, so type is the malloc function's return type. // Malloc call was not bitcast, so type is the malloc function's return type.
if (!BCI) if (NumOfBitCastUses == 0)
return cast<PointerType>(CI->getType()); return cast<PointerType>(CI->getType());
// Type could not be determined. // Type could not be determined.
return NULL; return NULL;
} }
/// getMallocAllocatedType - Returns the Type allocated by malloc call. This /// getMallocAllocatedType - Returns the Type allocated by malloc call.
/// Type is the result type of the call's only bitcast use. If there is no /// The Type depends on the number of bitcast uses of the malloc call:
/// unique bitcast use, then return NULL. /// 0: PointerType is the malloc calls' return type.
/// 1: PointerType is the bitcast's result type.
/// >1: Unique PointerType cannot be determined, return NULL.
const Type *llvm::getMallocAllocatedType(const CallInst *CI) { const Type *llvm::getMallocAllocatedType(const CallInst *CI) {
const PointerType *PT = getMallocType(CI); const PointerType *PT = getMallocType(CI);
return PT ? PT->getElementType() : NULL; return PT ? PT->getElementType() : NULL;

4
llvm/lib/AsmParser/LLParser.cpp
View File

@ -3619,12 +3619,14 @@ bool LLParser::ParseAlloc(Instruction *&Inst, PerFunctionState &PFS,
// Autoupgrade old malloc instruction to malloc call. // Autoupgrade old malloc instruction to malloc call.
// FIXME: Remove in LLVM 3.0. // FIXME: Remove in LLVM 3.0.
const Type *IntPtrTy = Type::getInt32Ty(Context); const Type *IntPtrTy = Type::getInt32Ty(Context);
Constant *AllocSize = ConstantExpr::getSizeOf(Ty);
AllocSize = ConstantExpr::getTruncOrBitCast(AllocSize, IntPtrTy);
if (!MallocF) if (!MallocF)
// Prototype malloc as "void *(int32)". // Prototype malloc as "void *(int32)".
// This function is renamed as "malloc" in ValidateEndOfModule(). // This function is renamed as "malloc" in ValidateEndOfModule().
MallocF = cast<Function>( MallocF = cast<Function>(
M->getOrInsertFunction("", Type::getInt8PtrTy(Context), IntPtrTy, NULL)); M->getOrInsertFunction("", Type::getInt8PtrTy(Context), IntPtrTy, NULL));
Inst = CallInst::CreateMalloc(BB, IntPtrTy, Ty, Size, MallocF); Inst = CallInst::CreateMalloc(BB, IntPtrTy, Ty, AllocSize, Size, MallocF);
return false; return false;
} }

4
llvm/lib/Bitcode/Reader/BitcodeReader.cpp
View File

@ -2101,8 +2101,10 @@ bool BitcodeReader::ParseFunctionBody(Function *F) {
if (!Ty || !Size) return Error("Invalid MALLOC record"); if (!Ty || !Size) return Error("Invalid MALLOC record");
if (!CurBB) return Error("Invalid malloc instruction with no BB"); if (!CurBB) return Error("Invalid malloc instruction with no BB");
const Type *Int32Ty = IntegerType::getInt32Ty(CurBB->getContext()); const Type *Int32Ty = IntegerType::getInt32Ty(CurBB->getContext());
Constant *AllocSize = ConstantExpr::getSizeOf(Ty->getElementType());
AllocSize = ConstantExpr::getTruncOrBitCast(AllocSize, Int32Ty);
I = CallInst::CreateMalloc(CurBB, Int32Ty, Ty->getElementType(), I = CallInst::CreateMalloc(CurBB, Int32Ty, Ty->getElementType(),
Size, NULL); AllocSize, Size, NULL);
InstructionList.push_back(I); InstructionList.push_back(I);
break; break;
} }

131
llvm/lib/Transforms/IPO/GlobalOpt.cpp
View File

@ -812,31 +812,41 @@ static void ConstantPropUsersOf(Value *V) {
/// malloc into a global, and any loads of GV as uses of the new global. /// malloc into a global, and any loads of GV as uses of the new global.
static GlobalVariable *OptimizeGlobalAddressOfMalloc(GlobalVariable *GV, static GlobalVariable *OptimizeGlobalAddressOfMalloc(GlobalVariable *GV,
CallInst *CI, CallInst *CI,
BitCastInst *BCI, const Type *AllocTy,
Value* NElems, Value* NElems,
TargetData* TD) { TargetData* TD) {
DEBUG(errs() << "PROMOTING MALLOC GLOBAL: " << *GV DEBUG(errs() << "PROMOTING GLOBAL: " << *GV << " CALL = " << *CI << '\n');
<< " CALL = " << *CI << " BCI = " << *BCI << '\n');
const Type *IntPtrTy = TD->getIntPtrType(GV->getContext()); const Type *IntPtrTy = TD->getIntPtrType(GV->getContext());
// CI has either 0 or 1 bitcast uses (getMallocType() would otherwise have
// returned NULL and we would not be here).
BitCastInst *BCI = NULL;
for (Value::use_iterator UI = CI->use_begin(), E = CI->use_end(); UI != E; )
if ((BCI = dyn_cast<BitCastInst>(cast<Instruction>(*UI++))))
break;
ConstantInt *NElements = cast<ConstantInt>(NElems); ConstantInt *NElements = cast<ConstantInt>(NElems);
if (NElements->getZExtValue() != 1) { if (NElements->getZExtValue() != 1) {
// If we have an array allocation, transform it to a single element // If we have an array allocation, transform it to a single element
// allocation to make the code below simpler. // allocation to make the code below simpler.
Type *NewTy = ArrayType::get(getMallocAllocatedType(CI), Type *NewTy = ArrayType::get(AllocTy, NElements->getZExtValue());
NElements->getZExtValue()); unsigned TypeSize = TD->getTypeAllocSize(NewTy);
Value* NewM = CallInst::CreateMalloc(CI, IntPtrTy, NewTy); if (const StructType *ST = dyn_cast<StructType>(NewTy))
Instruction* NewMI = cast<Instruction>(NewM); TypeSize = TD->getStructLayout(ST)->getSizeInBytes();
Instruction *NewCI = CallInst::CreateMalloc(CI, IntPtrTy, NewTy,
ConstantInt::get(IntPtrTy, TypeSize));
Value* Indices[2]; Value* Indices[2];
Indices[0] = Indices[1] = Constant::getNullValue(IntPtrTy); Indices[0] = Indices[1] = Constant::getNullValue(IntPtrTy);
Value *NewGEP = GetElementPtrInst::Create(NewMI, Indices, Indices + 2, Value *NewGEP = GetElementPtrInst::Create(NewCI, Indices, Indices + 2,
NewMI->getName()+".el0", CI); NewCI->getName()+".el0", CI);
BCI->replaceAllUsesWith(NewGEP); Value *Cast = new BitCastInst(NewGEP, CI->getType(), "el0", CI);
BCI->eraseFromParent(); if (BCI) BCI->replaceAllUsesWith(NewGEP);
CI->replaceAllUsesWith(Cast);
if (BCI) BCI->eraseFromParent();
CI->eraseFromParent(); CI->eraseFromParent();
BCI = cast<BitCastInst>(NewMI); BCI = dyn_cast<BitCastInst>(NewCI);
CI = extractMallocCallFromBitCast(NewMI); CI = BCI ? extractMallocCallFromBitCast(BCI) : cast<CallInst>(NewCI);
} }
// Create the new global variable. The contents of the malloc'd memory is // Create the new global variable. The contents of the malloc'd memory is
@ -850,8 +860,9 @@ static GlobalVariable *OptimizeGlobalAddressOfMalloc(GlobalVariable *GV,
GV, GV,
GV->isThreadLocal()); GV->isThreadLocal());
// Anything that used the malloc now uses the global directly. // Anything that used the malloc or its bitcast now uses the global directly.
BCI->replaceAllUsesWith(NewGV); if (BCI) BCI->replaceAllUsesWith(NewGV);
CI->replaceAllUsesWith(new BitCastInst(NewGV, CI->getType(), "newgv", CI));
Constant *RepValue = NewGV; Constant *RepValue = NewGV;
if (NewGV->getType() != GV->getType()->getElementType()) if (NewGV->getType() != GV->getType()->getElementType())
@ -919,9 +930,9 @@ static GlobalVariable *OptimizeGlobalAddressOfMalloc(GlobalVariable *GV,
GV->getParent()->getGlobalList().insert(GV, InitBool); GV->getParent()->getGlobalList().insert(GV, InitBool);
// Now the GV is dead, nuke it and the malloc. // Now the GV is dead, nuke it and the malloc (both CI and BCI).
GV->eraseFromParent(); GV->eraseFromParent();
BCI->eraseFromParent(); if (BCI) BCI->eraseFromParent();
CI->eraseFromParent(); CI->eraseFromParent();
// To further other optimizations, loop over all users of NewGV and try to // To further other optimizations, loop over all users of NewGV and try to
@ -1255,12 +1266,9 @@ static void RewriteUsesOfLoadForHeapSRoA(LoadInst *Load,
/// PerformHeapAllocSRoA - CI is an allocation of an array of structures. Break /// PerformHeapAllocSRoA - CI is an allocation of an array of structures. Break
/// it up into multiple allocations of arrays of the fields. /// it up into multiple allocations of arrays of the fields.
static GlobalVariable *PerformHeapAllocSRoA(GlobalVariable *GV, static GlobalVariable *PerformHeapAllocSRoA(GlobalVariable *GV, CallInst *CI,
CallInst *CI, BitCastInst* BCI, Value* NElems, TargetData *TD) {
Value* NElems, DEBUG(errs() << "SROA HEAP ALLOC: " << *GV << " MALLOC = " << *CI << '\n');
TargetData *TD) {
DEBUG(errs() << "SROA HEAP ALLOC: " << *GV << " MALLOC CALL = " << *CI
<< " BITCAST = " << *BCI << '\n');
const Type* MAT = getMallocAllocatedType(CI); const Type* MAT = getMallocAllocatedType(CI);
const StructType *STy = cast<StructType>(MAT); const StructType *STy = cast<StructType>(MAT);
@ -1268,7 +1276,7 @@ static GlobalVariable *PerformHeapAllocSRoA(GlobalVariable *GV,
// it into GV). If there are other uses, change them to be uses of // it into GV). If there are other uses, change them to be uses of
// the global to simplify later code. This also deletes the store // the global to simplify later code. This also deletes the store
// into GV. // into GV.
ReplaceUsesOfMallocWithGlobal(BCI, GV); ReplaceUsesOfMallocWithGlobal(CI, GV);
// Okay, at this point, there are no users of the malloc. Insert N // Okay, at this point, there are no users of the malloc. Insert N
// new mallocs at the same place as CI, and N globals. // new mallocs at the same place as CI, and N globals.
@ -1287,11 +1295,16 @@ static GlobalVariable *PerformHeapAllocSRoA(GlobalVariable *GV,
GV->isThreadLocal()); GV->isThreadLocal());
FieldGlobals.push_back(NGV); FieldGlobals.push_back(NGV);
Value *NMI = CallInst::CreateMalloc(CI, TD->getIntPtrType(CI->getContext()), unsigned TypeSize = TD->getTypeAllocSize(FieldTy);
FieldTy, NElems, if (const StructType* ST = dyn_cast<StructType>(FieldTy))
BCI->getName() + ".f" + Twine(FieldNo)); TypeSize = TD->getStructLayout(ST)->getSizeInBytes();
const Type* IntPtrTy = TD->getIntPtrType(CI->getContext());
Value *NMI = CallInst::CreateMalloc(CI, IntPtrTy, FieldTy,
ConstantInt::get(IntPtrTy, TypeSize),
NElems,
CI->getName() + ".f" + Twine(FieldNo));
FieldMallocs.push_back(NMI); FieldMallocs.push_back(NMI);
new StoreInst(NMI, NGV, BCI); new StoreInst(NMI, NGV, CI);
} }
// The tricky aspect of this transformation is handling the case when malloc // The tricky aspect of this transformation is handling the case when malloc
@ -1308,18 +1321,18 @@ static GlobalVariable *PerformHeapAllocSRoA(GlobalVariable *GV,
// } // }
Value *RunningOr = 0; Value *RunningOr = 0;
for (unsigned i = 0, e = FieldMallocs.size(); i != e; ++i) { for (unsigned i = 0, e = FieldMallocs.size(); i != e; ++i) {
Value *Cond = new ICmpInst(BCI, ICmpInst::ICMP_EQ, FieldMallocs[i], Value *Cond = new ICmpInst(CI, ICmpInst::ICMP_EQ, FieldMallocs[i],
Constant::getNullValue(FieldMallocs[i]->getType()), Constant::getNullValue(FieldMallocs[i]->getType()),
"isnull"); "isnull");
if (!RunningOr) if (!RunningOr)
RunningOr = Cond; // First seteq RunningOr = Cond; // First seteq
else else
RunningOr = BinaryOperator::CreateOr(RunningOr, Cond, "tmp", BCI); RunningOr = BinaryOperator::CreateOr(RunningOr, Cond, "tmp", CI);
} }
// Split the basic block at the old malloc. // Split the basic block at the old malloc.
BasicBlock *OrigBB = BCI->getParent(); BasicBlock *OrigBB = CI->getParent();
BasicBlock *ContBB = OrigBB->splitBasicBlock(BCI, "malloc_cont"); BasicBlock *ContBB = OrigBB->splitBasicBlock(CI, "malloc_cont");
// Create the block to check the first condition. Put all these blocks at the // Create the block to check the first condition. Put all these blocks at the
// end of the function as they are unlikely to be executed. // end of the function as they are unlikely to be executed.
@ -1357,8 +1370,7 @@ static GlobalVariable *PerformHeapAllocSRoA(GlobalVariable *GV,
BranchInst::Create(ContBB, NullPtrBlock); BranchInst::Create(ContBB, NullPtrBlock);
// CI and BCI are no longer needed, remove them. // CI is no longer needed, remove it.
BCI->eraseFromParent();
CI->eraseFromParent(); CI->eraseFromParent();
/// InsertedScalarizedLoads - As we process loads, if we can't immediately /// InsertedScalarizedLoads - As we process loads, if we can't immediately
@ -1444,13 +1456,9 @@ static GlobalVariable *PerformHeapAllocSRoA(GlobalVariable *GV,
/// cast of malloc. /// cast of malloc.
static bool TryToOptimizeStoreOfMallocToGlobal(GlobalVariable *GV, static bool TryToOptimizeStoreOfMallocToGlobal(GlobalVariable *GV,
CallInst *CI, CallInst *CI,
BitCastInst *BCI, const Type *AllocTy,
Module::global_iterator &GVI, Module::global_iterator &GVI,
TargetData *TD) { TargetData *TD) {
// If we can't figure out the type being malloced, then we can't optimize.
const Type *AllocTy = getMallocAllocatedType(CI);
assert(AllocTy);
// If this is a malloc of an abstract type, don't touch it. // If this is a malloc of an abstract type, don't touch it.
if (!AllocTy->isSized()) if (!AllocTy->isSized())
return false; return false;
@ -1471,7 +1479,7 @@ static bool TryToOptimizeStoreOfMallocToGlobal(GlobalVariable *GV,
// for. // for.
{ {
SmallPtrSet<PHINode*, 8> PHIs; SmallPtrSet<PHINode*, 8> PHIs;
if (!ValueIsOnlyUsedLocallyOrStoredToOneGlobal(BCI, GV, PHIs)) if (!ValueIsOnlyUsedLocallyOrStoredToOneGlobal(CI, GV, PHIs))
return false; return false;
} }
@ -1479,16 +1487,15 @@ static bool TryToOptimizeStoreOfMallocToGlobal(GlobalVariable *GV,
// transform the program to use global memory instead of malloc'd memory. // transform the program to use global memory instead of malloc'd memory.
// This eliminates dynamic allocation, avoids an indirection accessing the // This eliminates dynamic allocation, avoids an indirection accessing the
// data, and exposes the resultant global to further GlobalOpt. // data, and exposes the resultant global to further GlobalOpt.
Value *NElems = getMallocArraySize(CI, TD);
// We cannot optimize the malloc if we cannot determine malloc array size. // We cannot optimize the malloc if we cannot determine malloc array size.
if (NElems) { if (Value *NElems = getMallocArraySize(CI, TD)) {
if (ConstantInt *NElements = dyn_cast<ConstantInt>(NElems)) if (ConstantInt *NElements = dyn_cast<ConstantInt>(NElems))
// Restrict this transformation to only working on small allocations // Restrict this transformation to only working on small allocations
// (2048 bytes currently), as we don't want to introduce a 16M global or // (2048 bytes currently), as we don't want to introduce a 16M global or
// something. // something.
if (TD && if (TD &&
NElements->getZExtValue() * TD->getTypeAllocSize(AllocTy) < 2048) { NElements->getZExtValue() * TD->getTypeAllocSize(AllocTy) < 2048) {
GVI = OptimizeGlobalAddressOfMalloc(GV, CI, BCI, NElems, TD); GVI = OptimizeGlobalAddressOfMalloc(GV, CI, AllocTy, NElems, TD);
return true; return true;
} }
@ -1506,28 +1513,28 @@ static bool TryToOptimizeStoreOfMallocToGlobal(GlobalVariable *GV,
// This the structure has an unreasonable number of fields, leave it // This the structure has an unreasonable number of fields, leave it
// alone. // alone.
if (AllocSTy->getNumElements() <= 16 && AllocSTy->getNumElements() != 0 && if (AllocSTy->getNumElements() <= 16 && AllocSTy->getNumElements() != 0 &&
AllGlobalLoadUsesSimpleEnoughForHeapSRA(GV, BCI)) { AllGlobalLoadUsesSimpleEnoughForHeapSRA(GV, CI)) {
// If this is a fixed size array, transform the Malloc to be an alloc of // If this is a fixed size array, transform the Malloc to be an alloc of
// structs. malloc [100 x struct],1 -> malloc struct, 100 // structs. malloc [100 x struct],1 -> malloc struct, 100
if (const ArrayType *AT = if (const ArrayType *AT =
dyn_cast<ArrayType>(getMallocAllocatedType(CI))) { dyn_cast<ArrayType>(getMallocAllocatedType(CI))) {
Value *NumElements = const Type *IntPtrTy = TD->getIntPtrType(CI->getContext());
ConstantInt::get(Type::getInt32Ty(CI->getContext()), unsigned TypeSize = TD->getStructLayout(AllocSTy)->getSizeInBytes();
AT->getNumElements()); Value *AllocSize = ConstantInt::get(IntPtrTy, TypeSize);
Value *NewMI = CallInst::CreateMalloc(CI, Value *NumElements = ConstantInt::get(IntPtrTy, AT->getNumElements());
TD->getIntPtrType(CI->getContext()), Instruction *Malloc = CallInst::CreateMalloc(CI, IntPtrTy, AllocSTy,
AllocSTy, NumElements, AllocSize, NumElements,
BCI->getName()); CI->getName());
Value *Cast = new BitCastInst(NewMI, getMallocType(CI), "tmp", CI); Instruction *Cast = new BitCastInst(Malloc, CI->getType(), "tmp", CI);
BCI->replaceAllUsesWith(Cast); CI->replaceAllUsesWith(Cast);
BCI->eraseFromParent();
CI->eraseFromParent(); CI->eraseFromParent();
BCI = cast<BitCastInst>(NewMI); CI = dyn_cast<BitCastInst>(Malloc) ?
CI = extractMallocCallFromBitCast(NewMI); extractMallocCallFromBitCast(Malloc):
cast<CallInst>(Malloc);
} }
GVI = PerformHeapAllocSRoA(GV, CI, BCI, NElems, TD); GVI = PerformHeapAllocSRoA(GV, CI, getMallocArraySize(CI, TD), TD);
return true; return true;
} }
} }
@ -1559,16 +1566,12 @@ static bool OptimizeOnceStoredGlobal(GlobalVariable *GV, Value *StoredOnceVal,
if (OptimizeAwayTrappingUsesOfLoads(GV, SOVC)) if (OptimizeAwayTrappingUsesOfLoads(GV, SOVC))
return true; return true;
} else if (CallInst *CI = extractMallocCall(StoredOnceVal)) { } else if (CallInst *CI = extractMallocCall(StoredOnceVal)) {
if (getMallocAllocatedType(CI)) { const Type* MallocType = getMallocAllocatedType(CI);
BitCastInst* BCI = NULL; if (MallocType && TryToOptimizeStoreOfMallocToGlobal(GV, CI, MallocType,
for (Value::use_iterator UI = CI->use_begin(), E = CI->use_end(); GVI, TD))
UI != E; )
BCI = dyn_cast<BitCastInst>(cast<Instruction>(*UI++));
if (BCI && TryToOptimizeStoreOfMallocToGlobal(GV, CI, BCI, GVI, TD))
return true; return true;
} }
} }
}
return false; return false;
} }

22
llvm/lib/VMCore/Core.cpp
View File

@ -1699,18 +1699,24 @@ LLVMValueRef LLVMBuildNot(LLVMBuilderRef B, LLVMValueRef V, const char *Name) {
LLVMValueRef LLVMBuildMalloc(LLVMBuilderRef B, LLVMTypeRef Ty, LLVMValueRef LLVMBuildMalloc(LLVMBuilderRef B, LLVMTypeRef Ty,
const char *Name) { const char *Name) {
const Type* IntPtrT = Type::getInt32Ty(unwrap(B)->GetInsertBlock()->getContext()); const Type* ITy = Type::getInt32Ty(unwrap(B)->GetInsertBlock()->getContext());
return wrap(unwrap(B)->Insert(CallInst::CreateMalloc( Constant* AllocSize = ConstantExpr::getSizeOf(unwrap(Ty));
unwrap(B)->GetInsertBlock(), IntPtrT, unwrap(Ty), 0, 0, ""), AllocSize = ConstantExpr::getTruncOrBitCast(AllocSize, ITy);
Twine(Name))); Instruction* Malloc = CallInst::CreateMalloc(unwrap(B)->GetInsertBlock(),
ITy, unwrap(Ty), AllocSize,
0, 0, "");
return wrap(unwrap(B)->Insert(Malloc, Twine(Name)));
} }
LLVMValueRef LLVMBuildArrayMalloc(LLVMBuilderRef B, LLVMTypeRef Ty, LLVMValueRef LLVMBuildArrayMalloc(LLVMBuilderRef B, LLVMTypeRef Ty,
LLVMValueRef Val, const char *Name) { LLVMValueRef Val, const char *Name) {
const Type* IntPtrT = Type::getInt32Ty(unwrap(B)->GetInsertBlock()->getContext()); const Type* ITy = Type::getInt32Ty(unwrap(B)->GetInsertBlock()->getContext());
return wrap(unwrap(B)->Insert(CallInst::CreateMalloc( Constant* AllocSize = ConstantExpr::getSizeOf(unwrap(Ty));
unwrap(B)->GetInsertBlock(), IntPtrT, unwrap(Ty), unwrap(Val), 0, ""), AllocSize = ConstantExpr::getTruncOrBitCast(AllocSize, ITy);
Twine(Name))); Instruction* Malloc = CallInst::CreateMalloc(unwrap(B)->GetInsertBlock(),
ITy, unwrap(Ty), AllocSize,
unwrap(Val), 0, "");
return wrap(unwrap(B)->Insert(Malloc, Twine(Name)));
} }
LLVMValueRef LLVMBuildAlloca(LLVMBuilderRef B, LLVMTypeRef Ty, LLVMValueRef LLVMBuildAlloca(LLVMBuilderRef B, LLVMTypeRef Ty,

45
llvm/lib/VMCore/Instructions.cpp
View File

@ -24,6 +24,7 @@
#include "llvm/Support/CallSite.h" #include "llvm/Support/CallSite.h"
#include "llvm/Support/ConstantRange.h" #include "llvm/Support/ConstantRange.h"
#include "llvm/Support/MathExtras.h" #include "llvm/Support/MathExtras.h"
#include "llvm/Target/TargetData.h"
using namespace llvm; using namespace llvm;
@ -448,22 +449,11 @@ static bool IsConstantOne(Value *val) {
return isa<ConstantInt>(val) && cast<ConstantInt>(val)->isOne(); return isa<ConstantInt>(val) && cast<ConstantInt>(val)->isOne();
} }
static Value *checkArraySize(Value *Amt, const Type *IntPtrTy) {
if (!Amt)
Amt = ConstantInt::get(IntPtrTy, 1);
else {
assert(!isa<BasicBlock>(Amt) &&
"Passed basic block into malloc size parameter! Use other ctor");
assert(Amt->getType() == IntPtrTy &&
"Malloc array size is not an intptr!");
}
return Amt;
}
static Instruction *createMalloc(Instruction *InsertBefore, static Instruction *createMalloc(Instruction *InsertBefore,
BasicBlock *InsertAtEnd, const Type *IntPtrTy, BasicBlock *InsertAtEnd, const Type *IntPtrTy,
const Type *AllocTy, Value *ArraySize, const Type *AllocTy, Value *AllocSize,
Function *MallocF, const Twine &NameStr) { Value *ArraySize, Function *MallocF,
const Twine &Name) {
assert(((!InsertBefore && InsertAtEnd) || (InsertBefore && !InsertAtEnd)) && assert(((!InsertBefore && InsertAtEnd) || (InsertBefore && !InsertAtEnd)) &&
"createMalloc needs either InsertBefore or InsertAtEnd"); "createMalloc needs either InsertBefore or InsertAtEnd");
@ -471,10 +461,14 @@ static Instruction *createMalloc(Instruction *InsertBefore,
// bitcast (i8* malloc(typeSize)) to type* // bitcast (i8* malloc(typeSize)) to type*
// malloc(type, arraySize) becomes: // malloc(type, arraySize) becomes:
// bitcast (i8 *malloc(typeSize*arraySize)) to type* // bitcast (i8 *malloc(typeSize*arraySize)) to type*
Value *AllocSize = ConstantExpr::getSizeOf(AllocTy); if (!ArraySize)
AllocSize = ConstantExpr::getTruncOrBitCast(cast<Constant>(AllocSize), ArraySize = ConstantInt::get(IntPtrTy, 1);
IntPtrTy); else if (ArraySize->getType() != IntPtrTy) {
ArraySize = checkArraySize(ArraySize, IntPtrTy); if (InsertBefore)
ArraySize = CastInst::CreateIntegerCast(ArraySize, IntPtrTy, false, "", InsertBefore);
else
ArraySize = CastInst::CreateIntegerCast(ArraySize, IntPtrTy, false, "", InsertAtEnd);
}
if (!IsConstantOne(ArraySize)) { if (!IsConstantOne(ArraySize)) {
if (IsConstantOne(AllocSize)) { if (IsConstantOne(AllocSize)) {
@ -513,14 +507,14 @@ static Instruction *createMalloc(Instruction *InsertBefore,
Result = MCall; Result = MCall;
if (Result->getType() != AllocPtrType) if (Result->getType() != AllocPtrType)
// Create a cast instruction to convert to the right type... // Create a cast instruction to convert to the right type...
Result = new BitCastInst(MCall, AllocPtrType, NameStr, InsertBefore); Result = new BitCastInst(MCall, AllocPtrType, Name, InsertBefore);
} else { } else {
MCall = CallInst::Create(MallocF, AllocSize, "malloccall"); MCall = CallInst::Create(MallocF, AllocSize, "malloccall");
Result = MCall; Result = MCall;
if (Result->getType() != AllocPtrType) { if (Result->getType() != AllocPtrType) {
InsertAtEnd->getInstList().push_back(MCall); InsertAtEnd->getInstList().push_back(MCall);
// Create a cast instruction to convert to the right type... // Create a cast instruction to convert to the right type...
Result = new BitCastInst(MCall, AllocPtrType, NameStr); Result = new BitCastInst(MCall, AllocPtrType, Name);
} }
} }
MCall->setTailCall(); MCall->setTailCall();
@ -539,8 +533,9 @@ static Instruction *createMalloc(Instruction *InsertBefore,
/// 3. Bitcast the result of the malloc call to the specified type. /// 3. Bitcast the result of the malloc call to the specified type.
Instruction *CallInst::CreateMalloc(Instruction *InsertBefore, Instruction *CallInst::CreateMalloc(Instruction *InsertBefore,
const Type *IntPtrTy, const Type *AllocTy, const Type *IntPtrTy, const Type *AllocTy,
Value *ArraySize, const Twine &Name) { Value *AllocSize, Value *ArraySize,
return createMalloc(InsertBefore, NULL, IntPtrTy, AllocTy, const Twine &Name) {
return createMalloc(InsertBefore, NULL, IntPtrTy, AllocTy, AllocSize,
ArraySize, NULL, Name); ArraySize, NULL, Name);
} }
@ -554,9 +549,9 @@ Instruction *CallInst::CreateMalloc(Instruction *InsertBefore,
/// responsibility of the caller. /// responsibility of the caller.
Instruction *CallInst::CreateMalloc(BasicBlock *InsertAtEnd, Instruction *CallInst::CreateMalloc(BasicBlock *InsertAtEnd,
const Type *IntPtrTy, const Type *AllocTy, const Type *IntPtrTy, const Type *AllocTy,
Value *ArraySize, Function* MallocF, Value *AllocSize, Value *ArraySize,
const Twine &Name) { Function *MallocF, const Twine &Name) {
return createMalloc(NULL, InsertAtEnd, IntPtrTy, AllocTy, return createMalloc(NULL, InsertAtEnd, IntPtrTy, AllocTy, AllocSize,
ArraySize, MallocF, Name); ArraySize, MallocF, Name);
} }

16
llvm/test/Analysis/PointerTracking/sizes.ll
View File

@ -31,6 +31,7 @@ entry:
} }
declare i32 @bar(i8*) declare i32 @bar(i8*)
declare i32 @bar2(i64*)
define i32 @foo1(i32 %n) nounwind { define i32 @foo1(i32 %n) nounwind {
entry: entry:
@ -60,11 +61,16 @@ entry:
ret i32 %add16 ret i32 %add16
} }
define i32 @foo2(i32 %n) nounwind { define i32 @foo2(i64 %n) nounwind {
entry: entry:
%call = malloc i8, i32 %n ; <i8*> [#uses=1] %call = tail call i8* @malloc(i64 %n) ; <i8*> [#uses=1]
; CHECK: %call = ; CHECK: %call =
; CHECK: ==> %n elements, %n bytes allocated ; CHECK: ==> %n elements, %n bytes allocated
%mallocsize = mul i64 %n, 8 ; <i64> [#uses=1]
%malloccall = tail call i8* @malloc(i64 %mallocsize) ; <i8*> [#uses=1]
%call3 = bitcast i8* %malloccall to i64* ; <i64*> [#uses=1]
; CHECK: %malloccall =
; CHECK: ==> (8 * %n) elements, (8 * %n) bytes allocated
%call2 = tail call i8* @calloc(i64 2, i64 4) nounwind ; <i8*> [#uses=1] %call2 = tail call i8* @calloc(i64 2, i64 4) nounwind ; <i8*> [#uses=1]
; CHECK: %call2 = ; CHECK: %call2 =
; CHECK: ==> 8 elements, 8 bytes allocated ; CHECK: ==> 8 elements, 8 bytes allocated
@ -72,13 +78,17 @@ entry:
; CHECK: %call4 = ; CHECK: %call4 =
; CHECK: ==> 16 elements, 16 bytes allocated ; CHECK: ==> 16 elements, 16 bytes allocated
%call6 = tail call i32 @bar(i8* %call) nounwind ; <i32> [#uses=1] %call6 = tail call i32 @bar(i8* %call) nounwind ; <i32> [#uses=1]
%call7 = tail call i32 @bar2(i64* %call3) nounwind ; <i32> [#uses=1]
%call8 = tail call i32 @bar(i8* %call2) nounwind ; <i32> [#uses=1] %call8 = tail call i32 @bar(i8* %call2) nounwind ; <i32> [#uses=1]
%call10 = tail call i32 @bar(i8* %call4) nounwind ; <i32> [#uses=1] %call10 = tail call i32 @bar(i8* %call4) nounwind ; <i32> [#uses=1]
%add = add i32 %call8, %call6 ; <i32> [#uses=1] %add = add i32 %call8, %call6 ; <i32> [#uses=1]
%add11 = add i32 %add, %call10 ; <i32> [#uses=1] %add10 = add i32 %add, %call7 ; <i32> [#uses=1]
%add11 = add i32 %add10, %call10 ; <i32> [#uses=1]
ret i32 %add11 ret i32 %add11
} }
declare noalias i8* @malloc(i64) nounwind
declare noalias i8* @calloc(i64, i64) nounwind declare noalias i8* @calloc(i64, i64) nounwind
declare noalias i8* @realloc(i8* nocapture, i64) nounwind declare noalias i8* @realloc(i8* nocapture, i64) nounwind

7
llvm/test/Transforms/GlobalOpt/2009-06-01-RecursivePHI.ll
View File

@ -1,4 +1,5 @@
; RUN: opt < %s -globalopt ; RUN: opt < %s -globalopt
target datalayout = "E-p:64:64:64-a0:0:8-f32:32:32-f64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-v64:64:64-v128:128:128"
%struct.s_annealing_sched = type { i32, float, float, float, float } %struct.s_annealing_sched = type { i32, float, float, float, float }
%struct.s_bb = type { i32, i32, i32, i32 } %struct.s_bb = type { i32, i32, i32, i32 }
@ -96,7 +97,9 @@ bb.i34: ; preds = %bb
unreachable unreachable
bb1.i38: ; preds = %bb bb1.i38: ; preds = %bb
%0 = malloc %struct.s_net, i32 undef ; <%struct.s_net*> [#uses=1] %mallocsize = mul i64 28, undef ; <i64> [#uses=1]
%malloccall = tail call i8* @malloc(i64 %mallocsize) ; <i8*> [#uses=1]
%0 = bitcast i8* %malloccall to %struct.s_net* ; <%struct.s_net*> [#uses=1]
br i1 undef, label %bb.i1.i39, label %my_malloc.exit2.i br i1 undef, label %bb.i1.i39, label %my_malloc.exit2.i
bb.i1.i39: ; preds = %bb1.i38 bb.i1.i39: ; preds = %bb1.i38
@ -115,3 +118,5 @@ my_malloc.exit8.i: ; preds = %my_malloc.exit2.i
bb7: ; preds = %bb6.preheader bb7: ; preds = %bb6.preheader
unreachable unreachable
} }
declare noalias i8* @malloc(i64)

16
llvm/test/Transforms/GlobalOpt/heap-sra-1.ll
View File

@ -1,18 +1,22 @@
; RUN: opt < %s -globalopt -S | grep {@X.f0} ; RUN: opt < %s -globalopt -S | FileCheck %s
; RUN: opt < %s -globalopt -S | grep {@X.f1} target datalayout = "E-p:64:64:64-a0:0:8-f32:32:32-f64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-v64:64:64-v128:128:128"
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128"
target triple = "i386-apple-darwin7"
%struct.foo = type { i32, i32 } %struct.foo = type { i32, i32 }
@X = internal global %struct.foo* null @X = internal global %struct.foo* null
; CHECK: @X.f0
; CHECK: @X.f1
define void @bar(i32 %Size) nounwind noinline { define void @bar(i64 %Size) nounwind noinline {
entry: entry:
%.sub = malloc %struct.foo, i32 %Size %mallocsize = mul i64 %Size, 8 ; <i64> [#uses=1]
%malloccall = tail call i8* @malloc(i64 %mallocsize) ; <i8*> [#uses=1]
%.sub = bitcast i8* %malloccall to %struct.foo* ; <%struct.foo*> [#uses=1]
store %struct.foo* %.sub, %struct.foo** @X, align 4 store %struct.foo* %.sub, %struct.foo** @X, align 4
ret void ret void
} }
declare noalias i8* @malloc(i64)
define i32 @baz() nounwind readonly noinline { define i32 @baz() nounwind readonly noinline {
bb1.thread: bb1.thread:
%0 = load %struct.foo** @X, align 4 %0 = load %struct.foo** @X, align 4

14
llvm/test/Transforms/GlobalOpt/heap-sra-2.ll
View File

@ -1,20 +1,22 @@
; RUN: opt < %s -globalopt -S | grep {@X.f0} ; RUN: opt < %s -globalopt -S | FileCheck %s
; RUN: opt < %s -globalopt -S | grep {@X.f1} target datalayout = "E-p:64:64:64-a0:0:8-f32:32:32-f64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-v64:64:64-v128:128:128"
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128"
target triple = "i386-apple-darwin7"
%struct.foo = type { i32, i32 } %struct.foo = type { i32, i32 }
@X = internal global %struct.foo* null ; <%struct.foo**> [#uses=2] @X = internal global %struct.foo* null ; <%struct.foo**> [#uses=2]
; CHECK: @X.f0
; CHECK: @X.f1
define void @bar(i32 %Size) nounwind noinline { define void @bar(i32 %Size) nounwind noinline {
entry: entry:
%0 = malloc [1000000 x %struct.foo] %malloccall = tail call i8* @malloc(i64 8000000) ; <i8*> [#uses=1]
;%.sub = bitcast [1000000 x %struct.foo]* %0 to %struct.foo* %0 = bitcast i8* %malloccall to [1000000 x %struct.foo]* ; <[1000000 x %struct.foo]*> [#uses=1]
%.sub = getelementptr [1000000 x %struct.foo]* %0, i32 0, i32 0 ; <%struct.foo*> [#uses=1] %.sub = getelementptr [1000000 x %struct.foo]* %0, i32 0, i32 0 ; <%struct.foo*> [#uses=1]
store %struct.foo* %.sub, %struct.foo** @X, align 4 store %struct.foo* %.sub, %struct.foo** @X, align 4
ret void ret void
} }
declare noalias i8* @malloc(i64)
define i32 @baz() nounwind readonly noinline { define i32 @baz() nounwind readonly noinline {
bb1.thread: bb1.thread:
%0 = load %struct.foo** @X, align 4 ; <%struct.foo*> [#uses=1] %0 = load %struct.foo** @X, align 4 ; <%struct.foo*> [#uses=1]

14
llvm/test/Transforms/GlobalOpt/heap-sra-3.ll
View File

@ -1,24 +1,22 @@
; RUN: opt < %s -globalopt -S | FileCheck %s ; RUN: opt < %s -globalopt -S | FileCheck %s
target datalayout = "E-p:64:64:64-a0:0:8-f32:32:32-f64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-v64:64:64-v128:128:128"
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128"
target triple = "i386-apple-darwin10"
%struct.foo = type { i32, i32 } %struct.foo = type { i32, i32 }
@X = internal global %struct.foo* null @X = internal global %struct.foo* null
; CHECK: @X.f0 ; CHECK: @X.f0
; CHECK: @X.f1 ; CHECK: @X.f1
define void @bar(i32 %Size) nounwind noinline { define void @bar(i64 %Size) nounwind noinline {
entry: entry:
%mallocsize = mul i32 ptrtoint (%struct.foo* getelementptr (%struct.foo* null, i32 1) to i32), %Size, ; <i32> [#uses=1] %mallocsize = mul i64 8, %Size, ; <i64> [#uses=1]
; CHECK: mul i32 %Size ; CHECK: mul i64 %Size, 4
%malloccall = tail call i8* @malloc(i32 %mallocsize) ; <i8*> [#uses=1] %malloccall = tail call i8* @malloc(i64 %mallocsize) ; <i8*> [#uses=1]
%.sub = bitcast i8* %malloccall to %struct.foo* ; <%struct.foo*> [#uses=1] %.sub = bitcast i8* %malloccall to %struct.foo* ; <%struct.foo*> [#uses=1]
store %struct.foo* %.sub, %struct.foo** @X, align 4 store %struct.foo* %.sub, %struct.foo** @X, align 4
ret void ret void
} }
declare noalias i8* @malloc(i32) declare noalias i8* @malloc(i64)
define i32 @baz() nounwind readonly noinline { define i32 @baz() nounwind readonly noinline {
bb1.thread: bb1.thread:

14
llvm/test/Transforms/GlobalOpt/heap-sra-4.ll
View File

@ -1,24 +1,22 @@
; RUN: opt < %s -globalopt -S | FileCheck %s ; RUN: opt < %s -globalopt -S | FileCheck %s
target datalayout = "E-p:64:64:64-a0:0:8-f32:32:32-f64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-v64:64:64-v128:128:128"
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128"
target triple = "i386-apple-darwin7"
%struct.foo = type { i32, i32 } %struct.foo = type { i32, i32 }
@X = internal global %struct.foo* null @X = internal global %struct.foo* null
; CHECK: @X.f0 ; CHECK: @X.f0
; CHECK: @X.f1 ; CHECK: @X.f1
define void @bar(i32 %Size) nounwind noinline { define void @bar(i64 %Size) nounwind noinline {
entry: entry:
%mallocsize = shl i32 ptrtoint (%struct.foo* getelementptr (%struct.foo* null, i32 1) to i32), 9, ; <i32> [#uses=1] %mallocsize = shl i64 %Size, 3 ; <i64> [#uses=1]
%malloccall = tail call i8* @malloc(i32 %mallocsize) ; <i8*> [#uses=1] %malloccall = tail call i8* @malloc(i64 %mallocsize) ; <i8*> [#uses=1]
; CHECK: @malloc(i32 mul (i32 512 ; CHECK: mul i64 %Size, 4
%.sub = bitcast i8* %malloccall to %struct.foo* ; <%struct.foo*> [#uses=1] %.sub = bitcast i8* %malloccall to %struct.foo* ; <%struct.foo*> [#uses=1]
store %struct.foo* %.sub, %struct.foo** @X, align 4 store %struct.foo* %.sub, %struct.foo** @X, align 4
ret void ret void
} }
declare noalias i8* @malloc(i32) declare noalias i8* @malloc(i64)
define i32 @baz() nounwind readonly noinline { define i32 @baz() nounwind readonly noinline {
bb1.thread: bb1.thread:

8
llvm/test/Transforms/GlobalOpt/heap-sra-phi.ll
View File

@ -1,19 +1,21 @@
; RUN: opt < %s -globalopt -S | grep {tmp.f1 = phi i32. } ; RUN: opt < %s -globalopt -S | grep {tmp.f1 = phi i32. }
; RUN: opt < %s -globalopt -S | grep {tmp.f0 = phi i32. } ; RUN: opt < %s -globalopt -S | grep {tmp.f0 = phi i32. }
target datalayout = "E-p:64:64:64-a0:0:8-f32:32:32-f64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-v64:64:64-v128:128:128"
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128"
target triple = "i386-apple-darwin7"
%struct.foo = type { i32, i32 } %struct.foo = type { i32, i32 }
@X = internal global %struct.foo* null ; <%struct.foo**> [#uses=2] @X = internal global %struct.foo* null ; <%struct.foo**> [#uses=2]
define void @bar(i32 %Size) nounwind noinline { define void @bar(i32 %Size) nounwind noinline {
entry: entry:
%tmp = malloc [1000000 x %struct.foo] ; <[1000000 x %struct.foo]*> [#uses=1] %malloccall = tail call i8* @malloc(i64 8000000) ; <i8*> [#uses=1]
%tmp = bitcast i8* %malloccall to [1000000 x %struct.foo]* ; <[1000000 x %struct.foo]*> [#uses=1]
%.sub = getelementptr [1000000 x %struct.foo]* %tmp, i32 0, i32 0 ; <%struct.foo*> [#uses=1] %.sub = getelementptr [1000000 x %struct.foo]* %tmp, i32 0, i32 0 ; <%struct.foo*> [#uses=1]
store %struct.foo* %.sub, %struct.foo** @X, align 4 store %struct.foo* %.sub, %struct.foo** @X, align 4
ret void ret void
} }
declare noalias i8* @malloc(i64)
define i32 @baz() nounwind readonly noinline { define i32 @baz() nounwind readonly noinline {
bb1.thread: bb1.thread:
%tmpLD1 = load %struct.foo** @X, align 4 ; <%struct.foo*> [#uses=1] %tmpLD1 = load %struct.foo** @X, align 4 ; <%struct.foo*> [#uses=1]

9
llvm/test/Transforms/GlobalOpt/malloc-promote-1.ll
View File

@ -1,19 +1,24 @@
; RUN: opt < %s -globalopt -S | not grep global ; RUN: opt < %s -globalopt -S | FileCheck %s
target datalayout = "E-p:64:64:64-a0:0:8-f32:32:32-f64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-v64:64:64-v128:128:128" target datalayout = "E-p:64:64:64-a0:0:8-f32:32:32-f64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-v64:64:64-v128:128:128"
@G = internal global i32* null ; <i32**> [#uses=3] @G = internal global i32* null ; <i32**> [#uses=3]
; CHECK-NOT: global
define void @init() { define void @init() {
%P = malloc i32 ; <i32*> [#uses=1] %malloccall = tail call i8* @malloc(i64 4) ; <i8*> [#uses=1]
%P = bitcast i8* %malloccall to i32* ; <i32*> [#uses=1]
store i32* %P, i32** @G store i32* %P, i32** @G
%GV = load i32** @G ; <i32*> [#uses=1] %GV = load i32** @G ; <i32*> [#uses=1]
store i32 0, i32* %GV store i32 0, i32* %GV
ret void ret void
} }
declare noalias i8* @malloc(i64)
define i32 @get() { define i32 @get() {
%GV = load i32** @G ; <i32*> [#uses=1] %GV = load i32** @G ; <i32*> [#uses=1]
%V = load i32* %GV ; <i32> [#uses=1] %V = load i32* %GV ; <i32> [#uses=1]
ret i32 %V ret i32 %V
; CHECK: ret i32 0
} }

8
llvm/test/Transforms/GlobalOpt/malloc-promote-2.ll
View File

@ -1,11 +1,11 @@
; RUN: opt < %s -globalopt -globaldce -S | not grep malloc ; RUN: opt < %s -globalopt -globaldce -S | not grep malloc
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128" target datalayout = "E-p:64:64:64-a0:0:8-f32:32:32-f64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-v64:64:64-v128:128:128"
target triple = "i686-apple-darwin8"
@G = internal global i32* null ; <i32**> [#uses=3] @G = internal global i32* null ; <i32**> [#uses=3]
define void @init() { define void @init() {
%P = malloc i32, i32 100 ; <i32*> [#uses=1] %malloccall = tail call i8* @malloc(i64 mul (i64 100, i64 4)) ; <i8*> [#uses=1]
%P = bitcast i8* %malloccall to i32* ; <i32*> [#uses=1]
store i32* %P, i32** @G store i32* %P, i32** @G
%GV = load i32** @G ; <i32*> [#uses=1] %GV = load i32** @G ; <i32*> [#uses=1]
%GVe = getelementptr i32* %GV, i32 40 ; <i32*> [#uses=1] %GVe = getelementptr i32* %GV, i32 40 ; <i32*> [#uses=1]
@ -13,6 +13,8 @@ define void @init() {
ret void ret void
} }
declare noalias i8* @malloc(i64)
define i32 @get() { define i32 @get() {
%GV = load i32** @G ; <i32*> [#uses=1] %GV = load i32** @G ; <i32*> [#uses=1]
%GVe = getelementptr i32* %GV, i32 40 ; <i32*> [#uses=1] %GVe = getelementptr i32* %GV, i32 40 ; <i32*> [#uses=1]

8
llvm/test/Transforms/GlobalOpt/malloc-promote-3.ll
View File

@ -1,11 +1,11 @@
; RUN: opt < %s -globalopt -globaldce -S | not grep malloc ; RUN: opt < %s -globalopt -globaldce -S | not grep malloc
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128" target datalayout = "E-p:64:64:64-a0:0:8-f32:32:32-f64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-v64:64:64-v128:128:128"
target triple = "i686-apple-darwin8"
@G = internal global i32* null ; <i32**> [#uses=4] @G = internal global i32* null ; <i32**> [#uses=4]
define void @init() { define void @init() {
%P = malloc i32, i32 100 ; <i32*> [#uses=1] %malloccall = tail call i8* @malloc(i64 mul (i64 100, i64 4)) ; <i8*> [#uses=1]
%P = bitcast i8* %malloccall to i32* ; <i32*> [#uses=1]
store i32* %P, i32** @G store i32* %P, i32** @G
%GV = load i32** @G ; <i32*> [#uses=1] %GV = load i32** @G ; <i32*> [#uses=1]
%GVe = getelementptr i32* %GV, i32 40 ; <i32*> [#uses=1] %GVe = getelementptr i32* %GV, i32 40 ; <i32*> [#uses=1]
@ -13,6 +13,8 @@ define void @init() {
ret void ret void
} }
declare noalias i8* @malloc(i64)
define i32 @get() { define i32 @get() {
%GV = load i32** @G ; <i32*> [#uses=1] %GV = load i32** @G ; <i32*> [#uses=1]
%GVe = getelementptr i32* %GV, i32 40 ; <i32*> [#uses=1] %GVe = getelementptr i32* %GV, i32 40 ; <i32*> [#uses=1]