[SystemZ] TargetTransformInfo cost functions implemented.
getArithmeticInstrCost(), getShuffleCost(), getCastInstrCost(),
getCmpSelInstrCost(), getVectorInstrCost(), getMemoryOpCost(),
getInterleavedMemoryOpCost() implemented.
Interleaved access vectorization enabled.
BasicTTIImpl::getCastInstrCost() improved to check for legal extending loads,
in which case the cost of the z/sext instruction becomes 0.
Review: Ulrich Weigand, Renato Golin.
https://reviews.llvm.org/D29631
llvm-svn: 300052
diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index 531cb97..4d59da0 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -176,7 +176,8 @@
return TTI::PSK_Software;
}
-int AArch64TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src) {
+int AArch64TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,
+ const Instruction *I) {
int ISD = TLI->InstructionOpcodeToISD(Opcode);
assert(ISD && "Invalid opcode");
@@ -436,7 +437,7 @@
}
int AArch64TTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
- Type *CondTy) {
+ Type *CondTy, const Instruction *I) {
int ISD = TLI->InstructionOpcodeToISD(Opcode);
// We don't lower some vector selects well that are wider than the register
@@ -463,11 +464,12 @@
return Entry->Cost;
}
}
- return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy);
+ return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, I);
}
int AArch64TTIImpl::getMemoryOpCost(unsigned Opcode, Type *Ty,
- unsigned Alignment, unsigned AddressSpace) {
+ unsigned Alignment, unsigned AddressSpace,
+ const Instruction *I) {
auto LT = TLI->getTypeLegalizationCost(DL, Ty);
if (ST->isMisaligned128StoreSlow() && Opcode == Instruction::Store &&
diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
index db01725..e37c003 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
@@ -86,7 +86,8 @@
unsigned getMaxInterleaveFactor(unsigned VF);
- int getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src);
+ int getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,
+ const Instruction *I = nullptr);
int getExtractWithExtendCost(unsigned Opcode, Type *Dst, VectorType *VecTy,
unsigned Index);
@@ -103,10 +104,11 @@
int getAddressComputationCost(Type *Ty, ScalarEvolution *SE, const SCEV *Ptr);
- int getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy);
+ int getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
+ const Instruction *I = nullptr);
int getMemoryOpCost(unsigned Opcode, Type *Src, unsigned Alignment,
- unsigned AddressSpace);
+ unsigned AddressSpace, const Instruction *I = nullptr);
int getCostOfKeepingLiveOverCall(ArrayRef<Type *> Tys);