6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-11-02 07:17:36 +00:00
Code Issues Projects Releases Wiki Activity

Commoning of target specific load/store intrinsics in Early CSE.

Browse Source 
Phabricator revision: http://reviews.llvm.org/D7121
Patch by Sanjin Sijaric <ssijaric@codeaurora.org>!

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@227149 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Chad Rosier
2015-01-26 22:51:15 +00:00
parent f96362358f
commit 13faabb6c5
6 changed files with 486 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

91
lib/Target/AArch64/AArch64TargetTransformInfo.cpp
View File

@@ -44,6 +44,12 @@ class AArch64TTI final : public ImmutablePass, public TargetTransformInfo {
/// are set if the result needs to be inserted and/or extracted from vectors.
unsigned getScalarizationOverhead(Type *Ty, bool Insert, bool Extract) const;
enum MemIntrinsicType {
VECTOR_LDST_TWO_ELEMENTS,
VECTOR_LDST_THREE_ELEMENTS,
VECTOR_LDST_FOUR_ELEMENTS
};
public:
AArch64TTI() : ImmutablePass(ID), TM(nullptr), ST(nullptr), TLI(nullptr) {
llvm_unreachable("This pass cannot be directly constructed");
@@ -131,6 +137,11 @@ public:
void getUnrollingPreferences(const Function *F, Loop *L,
UnrollingPreferences &UP) const override;
Value *getOrCreateResultFromMemIntrinsic(IntrinsicInst *Inst,
Type *ExpectedType) const override;
bool getTgtMemIntrinsic(IntrinsicInst *Inst,
MemIntrinsicInfo &Info) const override;
/// @}
};
@@ -554,3 +565,83 @@ void AArch64TTI::getUnrollingPreferences(const Function *F, Loop *L,
// Disable partial & runtime unrolling on -Os.
UP.PartialOptSizeThreshold = 0;
}
Value *AArch64TTI::getOrCreateResultFromMemIntrinsic(IntrinsicInst *Inst,
Type *ExpectedType) const {
switch (Inst->getIntrinsicID()) {
default:
return nullptr;
case Intrinsic::aarch64_neon_st2:
case Intrinsic::aarch64_neon_st3:
case Intrinsic::aarch64_neon_st4: {
// Create a struct type
StructType *ST = dyn_cast<StructType>(ExpectedType);
if (!ST)
return nullptr;
unsigned NumElts = Inst->getNumArgOperands() - 1;
if (ST->getNumElements() != NumElts)
return nullptr;
for (unsigned i = 0, e = NumElts; i != e; ++i) {
if (Inst->getArgOperand(i)->getType() != ST->getElementType(i))
return nullptr;
}
Value *Res = UndefValue::get(ExpectedType);
IRBuilder<> Builder(Inst);
for (unsigned i = 0, e = NumElts; i != e; ++i) {
Value *L = Inst->getArgOperand(i);
Res = Builder.CreateInsertValue(Res, L, i);
}
return Res;
}
case Intrinsic::aarch64_neon_ld2:
case Intrinsic::aarch64_neon_ld3:
case Intrinsic::aarch64_neon_ld4:
if (Inst->getType() == ExpectedType)
return Inst;
return nullptr;
}
}
bool AArch64TTI::getTgtMemIntrinsic(IntrinsicInst *Inst,
MemIntrinsicInfo &Info) const {
switch (Inst->getIntrinsicID()) {
default:
break;
case Intrinsic::aarch64_neon_ld2:
case Intrinsic::aarch64_neon_ld3:
case Intrinsic::aarch64_neon_ld4:
Info.ReadMem = true;
Info.WriteMem = false;
Info.Vol = false;
Info.NumMemRefs = 1;
Info.PtrVal = Inst->getArgOperand(0);
break;
case Intrinsic::aarch64_neon_st2:
case Intrinsic::aarch64_neon_st3:
case Intrinsic::aarch64_neon_st4:
Info.ReadMem = false;
Info.WriteMem = true;
Info.Vol = false;
Info.NumMemRefs = 1;
Info.PtrVal = Inst->getArgOperand(Inst->getNumArgOperands() - 1);
break;
}
switch (Inst->getIntrinsicID()) {
default:
return false;
case Intrinsic::aarch64_neon_ld2:
case Intrinsic::aarch64_neon_st2:
Info.MatchingId = VECTOR_LDST_TWO_ELEMENTS;
break;
case Intrinsic::aarch64_neon_ld3:
case Intrinsic::aarch64_neon_st3:
Info.MatchingId = VECTOR_LDST_THREE_ELEMENTS;
break;
case Intrinsic::aarch64_neon_ld4:
case Intrinsic::aarch64_neon_st4:
Info.MatchingId = VECTOR_LDST_FOUR_ELEMENTS;
break;
}
return true;
}