forked from OSchip/llvm-project
Update computeArraySize() to use ComputeMultiple() to determine the array size associated with a malloc; also extend PerformHeapAllocSRoA() to check if the optimized malloc's arg had its highest bit set, so that it is safe for ComputeMultiple() to look through sext instructions while determining the optimized malloc's array size
llvm-svn: 86676
This commit is contained in:
parent
4744488e8d
commit
fcc77b1c02
|
@ -44,9 +44,7 @@ CallInst *extractMallocCallFromBitCast(Value *I);
|
|||
/// isArrayMalloc - Returns the corresponding CallInst if the instruction
|
||||
/// is a call to malloc whose array size can be determined and the array size
|
||||
/// is not constant 1. Otherwise, return NULL.
|
||||
CallInst *isArrayMalloc(Value *I, const TargetData *TD);
|
||||
const CallInst *isArrayMalloc(const Value *I,
|
||||
const TargetData *TD);
|
||||
const CallInst *isArrayMalloc(const Value *I, const TargetData *TD);
|
||||
|
||||
/// getMallocType - Returns the PointerType resulting from the malloc call.
|
||||
/// The PointerType depends on the number of bitcast uses of the malloc call:
|
||||
|
@ -67,7 +65,8 @@ const Type *getMallocAllocatedType(const CallInst *CI);
|
|||
/// then return that multiple. For non-array mallocs, the multiple is
|
||||
/// constant 1. Otherwise, return NULL for mallocs whose array size cannot be
|
||||
/// determined.
|
||||
Value *getMallocArraySize(CallInst *CI, const TargetData *TD);
|
||||
Value *getMallocArraySize(CallInst *CI, const TargetData *TD,
|
||||
bool LookThroughSExt = false);
|
||||
|
||||
//===----------------------------------------------------------------------===//
|
||||
// free Call Utility Functions.
|
||||
|
|
|
@ -16,7 +16,7 @@
|
|||
#include "llvm/Constants.h"
|
||||
#include "llvm/Instructions.h"
|
||||
#include "llvm/Module.h"
|
||||
#include "llvm/Analysis/ConstantFolding.h"
|
||||
#include "llvm/Analysis/ValueTracking.h"
|
||||
#include "llvm/Target/TargetData.h"
|
||||
using namespace llvm;
|
||||
|
||||
|
@ -87,12 +87,8 @@ const CallInst *llvm::extractMallocCallFromBitCast(const Value *I) {
|
|||
: NULL;
|
||||
}
|
||||
|
||||
/// isConstantOne - Return true only if val is constant int 1.
|
||||
static bool isConstantOne(Value *val) {
|
||||
return isa<ConstantInt>(val) && cast<ConstantInt>(val)->isOne();
|
||||
}
|
||||
|
||||
static Value *isArrayMallocHelper(const CallInst *CI, const TargetData *TD) {
|
||||
static Value *computeArraySize(const CallInst *CI, const TargetData *TD,
|
||||
bool LookThroughSExt = false) {
|
||||
if (!CI)
|
||||
return NULL;
|
||||
|
||||
|
@ -101,97 +97,28 @@ static Value *isArrayMallocHelper(const CallInst *CI, const TargetData *TD) {
|
|||
if (!T || !T->isSized() || !TD)
|
||||
return NULL;
|
||||
|
||||
Value *MallocArg = CI->getOperand(1);
|
||||
const Type *ArgType = MallocArg->getType();
|
||||
ConstantExpr *CO = dyn_cast<ConstantExpr>(MallocArg);
|
||||
BinaryOperator *BO = dyn_cast<BinaryOperator>(MallocArg);
|
||||
|
||||
unsigned ElementSizeInt = TD->getTypeAllocSize(T);
|
||||
unsigned ElementSize = TD->getTypeAllocSize(T);
|
||||
if (const StructType *ST = dyn_cast<StructType>(T))
|
||||
ElementSizeInt = TD->getStructLayout(ST)->getSizeInBytes();
|
||||
Constant *ElementSize = ConstantInt::get(ArgType, ElementSizeInt);
|
||||
ElementSize = TD->getStructLayout(ST)->getSizeInBytes();
|
||||
|
||||
// First, check if CI is a non-array malloc.
|
||||
if (CO && CO == ElementSize)
|
||||
// Match CreateMalloc's use of constant 1 array-size for non-array mallocs.
|
||||
return ConstantInt::get(ArgType, 1);
|
||||
// If malloc calls' arg can be determined to be a multiple of ElementSize,
|
||||
// return the multiple. Otherwise, return NULL.
|
||||
Value *MallocArg = CI->getOperand(1);
|
||||
Value *Multiple = NULL;
|
||||
APInt Val(TD->getTypeSizeInBits(MallocArg->getType()->getScalarType()), 0);
|
||||
if (ComputeMultiple(MallocArg, ElementSize, Multiple,
|
||||
Val, LookThroughSExt, TD))
|
||||
return Multiple;
|
||||
|
||||
// Second, check if CI is an array malloc whose array size can be determined.
|
||||
if (isConstantOne(ElementSize))
|
||||
return MallocArg;
|
||||
|
||||
if (ConstantInt *CInt = dyn_cast<ConstantInt>(MallocArg))
|
||||
if (CInt->getZExtValue() % ElementSizeInt == 0)
|
||||
return ConstantInt::get(ArgType, CInt->getZExtValue() / ElementSizeInt);
|
||||
|
||||
if (!CO && !BO)
|
||||
return NULL;
|
||||
|
||||
Value *Op0 = NULL;
|
||||
Value *Op1 = NULL;
|
||||
unsigned Opcode = 0;
|
||||
if (CO && ((CO->getOpcode() == Instruction::Mul) ||
|
||||
(CO->getOpcode() == Instruction::Shl))) {
|
||||
Op0 = CO->getOperand(0);
|
||||
Op1 = CO->getOperand(1);
|
||||
Opcode = CO->getOpcode();
|
||||
}
|
||||
if (BO && ((BO->getOpcode() == Instruction::Mul) ||
|
||||
(BO->getOpcode() == Instruction::Shl))) {
|
||||
Op0 = BO->getOperand(0);
|
||||
Op1 = BO->getOperand(1);
|
||||
Opcode = BO->getOpcode();
|
||||
}
|
||||
|
||||
// Determine array size if malloc's argument is the product of a mul or shl.
|
||||
if (Op0) {
|
||||
if (Opcode == Instruction::Mul) {
|
||||
if (Op1 == ElementSize)
|
||||
// ArraySize * ElementSize
|
||||
return Op0;
|
||||
if (Op0 == ElementSize)
|
||||
// ElementSize * ArraySize
|
||||
return Op1;
|
||||
}
|
||||
if (Opcode == Instruction::Shl) {
|
||||
ConstantInt *Op1CI = dyn_cast<ConstantInt>(Op1);
|
||||
if (!Op1CI) return NULL;
|
||||
|
||||
APInt Op1Int = Op1CI->getValue();
|
||||
uint64_t BitToSet = Op1Int.getLimitedValue(Op1Int.getBitWidth() - 1);
|
||||
Value *Op1Pow = ConstantInt::get(Op1CI->getContext(),
|
||||
APInt(Op1Int.getBitWidth(), 0).set(BitToSet));
|
||||
if (Op0 == ElementSize)
|
||||
// ArraySize << log2(ElementSize)
|
||||
return Op1Pow;
|
||||
if (Op1Pow == ElementSize)
|
||||
// ElementSize << log2(ArraySize)
|
||||
return Op0;
|
||||
}
|
||||
}
|
||||
|
||||
// We could not determine the malloc array size from MallocArg.
|
||||
return NULL;
|
||||
}
|
||||
|
||||
/// isArrayMalloc - Returns the corresponding CallInst if the instruction
|
||||
/// is a call to malloc whose array size can be determined and the array size
|
||||
/// is not constant 1. Otherwise, return NULL.
|
||||
CallInst *llvm::isArrayMalloc(Value *I, const TargetData *TD) {
|
||||
CallInst *CI = extractMallocCall(I);
|
||||
Value *ArraySize = isArrayMallocHelper(CI, TD);
|
||||
|
||||
if (ArraySize &&
|
||||
ArraySize != ConstantInt::get(CI->getOperand(1)->getType(), 1))
|
||||
return CI;
|
||||
|
||||
// CI is a non-array malloc or we can't figure out that it is an array malloc.
|
||||
return NULL;
|
||||
}
|
||||
|
||||
const CallInst *llvm::isArrayMalloc(const Value *I, const TargetData *TD) {
|
||||
const CallInst *CI = extractMallocCall(I);
|
||||
Value *ArraySize = isArrayMallocHelper(CI, TD);
|
||||
Value *ArraySize = computeArraySize(CI, TD);
|
||||
|
||||
if (ArraySize &&
|
||||
ArraySize != ConstantInt::get(CI->getOperand(1)->getType(), 1))
|
||||
|
@ -207,7 +134,7 @@ const CallInst *llvm::isArrayMalloc(const Value *I, const TargetData *TD) {
|
|||
/// 1: PointerType is the bitcast's result type.
|
||||
/// >1: Unique PointerType cannot be determined, return NULL.
|
||||
const PointerType *llvm::getMallocType(const CallInst *CI) {
|
||||
assert(isMalloc(CI) && "GetMallocType and not malloc call");
|
||||
assert(isMalloc(CI) && "getMallocType and not malloc call");
|
||||
|
||||
const PointerType *MallocType = NULL;
|
||||
unsigned NumOfBitCastUses = 0;
|
||||
|
@ -247,8 +174,10 @@ const Type *llvm::getMallocAllocatedType(const CallInst *CI) {
|
|||
/// then return that multiple. For non-array mallocs, the multiple is
|
||||
/// constant 1. Otherwise, return NULL for mallocs whose array size cannot be
|
||||
/// determined.
|
||||
Value *llvm::getMallocArraySize(CallInst *CI, const TargetData *TD) {
|
||||
return isArrayMallocHelper(CI, TD);
|
||||
Value *llvm::getMallocArraySize(CallInst *CI, const TargetData *TD,
|
||||
bool LookThroughSExt) {
|
||||
assert(isMalloc(CI) && "getMallocArraySize and not malloc call");
|
||||
return computeArraySize(CI, TD, LookThroughSExt);
|
||||
}
|
||||
|
||||
//===----------------------------------------------------------------------===//
|
||||
|
|
|
@ -1321,15 +1321,15 @@ static GlobalVariable *PerformHeapAllocSRoA(GlobalVariable *GV, CallInst *CI,
|
|||
// if (F1) { free(F1); F1 = 0; }
|
||||
// if (F2) { free(F2); F2 = 0; }
|
||||
// }
|
||||
Value *RunningOr = 0;
|
||||
// The malloc can also fail if its argument is too large.
|
||||
Constant *ConstantZero = ConstantInt::get(CI->getOperand(1)->getType(), 0);
|
||||
Value *RunningOr = new ICmpInst(CI, ICmpInst::ICMP_SLT, CI->getOperand(1),
|
||||
ConstantZero, "isneg");
|
||||
for (unsigned i = 0, e = FieldMallocs.size(); i != e; ++i) {
|
||||
Value *Cond = new ICmpInst(CI, ICmpInst::ICMP_EQ, FieldMallocs[i],
|
||||
Constant::getNullValue(FieldMallocs[i]->getType()),
|
||||
"isnull");
|
||||
if (!RunningOr)
|
||||
RunningOr = Cond; // First seteq
|
||||
else
|
||||
RunningOr = BinaryOperator::CreateOr(RunningOr, Cond, "tmp", CI);
|
||||
RunningOr = BinaryOperator::CreateOr(RunningOr, Cond, "tmp", CI);
|
||||
}
|
||||
|
||||
// Split the basic block at the old malloc.
|
||||
|
@ -1490,7 +1490,7 @@ static bool TryToOptimizeStoreOfMallocToGlobal(GlobalVariable *GV,
|
|||
// This eliminates dynamic allocation, avoids an indirection accessing the
|
||||
// data, and exposes the resultant global to further GlobalOpt.
|
||||
// We cannot optimize the malloc if we cannot determine malloc array size.
|
||||
if (Value *NElems = getMallocArraySize(CI, TD)) {
|
||||
if (Value *NElems = getMallocArraySize(CI, TD, true)) {
|
||||
if (ConstantInt *NElements = dyn_cast<ConstantInt>(NElems))
|
||||
// Restrict this transformation to only working on small allocations
|
||||
// (2048 bytes currently), as we don't want to introduce a 16M global or
|
||||
|
@ -1535,7 +1535,7 @@ static bool TryToOptimizeStoreOfMallocToGlobal(GlobalVariable *GV,
|
|||
extractMallocCallFromBitCast(Malloc) : cast<CallInst>(Malloc);
|
||||
}
|
||||
|
||||
GVI = PerformHeapAllocSRoA(GV, CI, getMallocArraySize(CI, TD), TD);
|
||||
GVI = PerformHeapAllocSRoA(GV, CI, getMallocArraySize(CI, TD, true),TD);
|
||||
return true;
|
||||
}
|
||||
}
|
||||
|
|
|
@ -31,7 +31,6 @@ entry:
|
|||
}
|
||||
|
||||
declare i32 @bar(i8*)
|
||||
declare i32 @bar2(i64*)
|
||||
|
||||
define i32 @foo1(i32 %n) nounwind {
|
||||
entry:
|
||||
|
@ -66,11 +65,6 @@ entry:
|
|||
%call = tail call i8* @malloc(i64 %n) ; <i8*> [#uses=1]
|
||||
; CHECK: %call =
|
||||
; 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]
|
||||
; CHECK: %call2 =
|
||||
; CHECK: ==> 8 elements, 8 bytes allocated
|
||||
|
@ -78,12 +72,10 @@ entry:
|
|||
; CHECK: %call4 =
|
||||
; CHECK: ==> 16 elements, 16 bytes allocated
|
||||
%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]
|
||||
%call10 = tail call i32 @bar(i8* %call4) nounwind ; <i32> [#uses=1]
|
||||
%add = add i32 %call8, %call6 ; <i32> [#uses=1]
|
||||
%add10 = add i32 %add, %call7 ; <i32> [#uses=1]
|
||||
%add11 = add i32 %add10, %call10 ; <i32> [#uses=1]
|
||||
%add11 = add i32 %add, %call10 ; <i32> [#uses=1]
|
||||
ret i32 %add11
|
||||
}
|
||||
|
||||
|
|
Loading…
Reference in New Issue