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

[X86][SSE] Reordered cast vectorization costs. NFCI. 

Reordered the data tables at the top and placed the lookups after. The first stage in the yak shaving necessary to get more accurate costs for a variety of targets given the recent improvements to SINT_TO_FP/UINT_TO_FP/SIGN_EXTEND vector lowering.

llvm-svn: 242643
This commit is contained in:
Simon Pilgrim 2015-07-19 15:36:12 +00:00
parent 5191fe9509
commit e2c244f3b4
1 changed files with 48 additions and 47 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

95
llvm/lib/Target/X86/X86TargetTransformInfo.cpp
View File

@ -467,40 +467,6 @@ unsigned X86TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src) {
int ISD = TLI->InstructionOpcodeToISD(Opcode);
assert(ISD && "Invalid opcode");
std::pair<unsigned, MVT> LTSrc = TLI->getTypeLegalizationCost(DL, Src);
std::pair<unsigned, MVT> LTDest = TLI->getTypeLegalizationCost(DL, Dst);
static const TypeConversionCostTblEntry<MVT::SimpleValueType>
SSE2ConvTbl[] = {
// These are somewhat magic numbers justified by looking at the output of
// Intel's IACA, running some kernels and making sure when we take
// legalization into account the throughput will be overestimated.
{ ISD::UINT_TO_FP, MVT::v2f64, MVT::v2i64, 2*10 },
{ ISD::UINT_TO_FP, MVT::v2f64, MVT::v4i32, 4*10 },
{ ISD::UINT_TO_FP, MVT::v2f64, MVT::v8i16, 8*10 },
{ ISD::UINT_TO_FP, MVT::v2f64, MVT::v16i8, 16*10 },
{ ISD::SINT_TO_FP, MVT::v2f64, MVT::v2i64, 2*10 },
{ ISD::SINT_TO_FP, MVT::v2f64, MVT::v4i32, 4*10 },
{ ISD::SINT_TO_FP, MVT::v2f64, MVT::v8i16, 8*10 },
{ ISD::SINT_TO_FP, MVT::v2f64, MVT::v16i8, 16*10 },
// There are faster sequences for float conversions.
{ ISD::UINT_TO_FP, MVT::v4f32, MVT::v2i64, 15 },
{ ISD::UINT_TO_FP, MVT::v4f32, MVT::v4i32, 8 },
{ ISD::UINT_TO_FP, MVT::v4f32, MVT::v8i16, 15 },
{ ISD::UINT_TO_FP, MVT::v4f32, MVT::v16i8, 8 },
{ ISD::SINT_TO_FP, MVT::v4f32, MVT::v2i64, 15 },
{ ISD::SINT_TO_FP, MVT::v4f32, MVT::v4i32, 15 },
{ ISD::SINT_TO_FP, MVT::v4f32, MVT::v8i16, 15 },
{ ISD::SINT_TO_FP, MVT::v4f32, MVT::v16i8, 8 },
};
if (ST->hasSSE2() && !ST->hasAVX()) {
int Idx =
ConvertCostTableLookup(SSE2ConvTbl, ISD, LTDest.second, LTSrc.second);
if (Idx != -1)
return LTSrc.first * SSE2ConvTbl[Idx].Cost;
}
static const TypeConversionCostTblEntry<MVT::SimpleValueType>
AVX512ConversionTbl[] = {
{ ISD::FP_EXTEND, MVT::v8f64, MVT::v8f32, 1 },
@ -534,19 +500,6 @@ unsigned X86TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src) {
{ ISD::SINT_TO_FP, MVT::v8f64, MVT::v8i32, 1 },
};
if (ST->hasAVX512()) {
int Idx = ConvertCostTableLookup(AVX512ConversionTbl, ISD, LTDest.second,
LTSrc.second);
if (Idx != -1)
return AVX512ConversionTbl[Idx].Cost;
}
EVT SrcTy = TLI->getValueType(DL, Src);
EVT DstTy = TLI->getValueType(DL, Dst);
// The function getSimpleVT only handles simple value types.
if (!SrcTy.isSimple() || !DstTy.isSimple())
return BaseT::getCastInstrCost(Opcode, Dst, Src);
static const TypeConversionCostTblEntry<MVT::SimpleValueType>
AVX2ConversionTbl[] = {
{ ISD::SIGN_EXTEND, MVT::v16i16, MVT::v16i8, 1 },
@ -650,6 +603,54 @@ unsigned X86TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src) {
{ ISD::FP_TO_UINT, MVT::v4i32, MVT::v4f64, 4*4 },
};
static const TypeConversionCostTblEntry<MVT::SimpleValueType>
SSE2ConvTbl[] = {
// These are somewhat magic numbers justified by looking at the output of
// Intel's IACA, running some kernels and making sure when we take
// legalization into account the throughput will be overestimated.
{ ISD::UINT_TO_FP, MVT::v2f64, MVT::v2i64, 2*10 },
{ ISD::UINT_TO_FP, MVT::v2f64, MVT::v4i32, 4*10 },
{ ISD::UINT_TO_FP, MVT::v2f64, MVT::v8i16, 8*10 },
{ ISD::UINT_TO_FP, MVT::v2f64, MVT::v16i8, 16*10 },
{ ISD::SINT_TO_FP, MVT::v2f64, MVT::v2i64, 2*10 },
{ ISD::SINT_TO_FP, MVT::v2f64, MVT::v4i32, 4*10 },
{ ISD::SINT_TO_FP, MVT::v2f64, MVT::v8i16, 8*10 },
{ ISD::SINT_TO_FP, MVT::v2f64, MVT::v16i8, 16*10 },
// There are faster sequences for float conversions.
{ ISD::UINT_TO_FP, MVT::v4f32, MVT::v2i64, 15 },
{ ISD::UINT_TO_FP, MVT::v4f32, MVT::v4i32, 8 },
{ ISD::UINT_TO_FP, MVT::v4f32, MVT::v8i16, 15 },
{ ISD::UINT_TO_FP, MVT::v4f32, MVT::v16i8, 8 },
{ ISD::SINT_TO_FP, MVT::v4f32, MVT::v2i64, 15 },
{ ISD::SINT_TO_FP, MVT::v4f32, MVT::v4i32, 15 },
{ ISD::SINT_TO_FP, MVT::v4f32, MVT::v8i16, 15 },
{ ISD::SINT_TO_FP, MVT::v4f32, MVT::v16i8, 8 },
};
std::pair<unsigned, MVT> LTSrc = TLI->getTypeLegalizationCost(DL, Src);
std::pair<unsigned, MVT> LTDest = TLI->getTypeLegalizationCost(DL, Dst);
if (ST->hasSSE2() && !ST->hasAVX()) {
int Idx =
ConvertCostTableLookup(SSE2ConvTbl, ISD, LTDest.second, LTSrc.second);
if (Idx != -1)
return LTSrc.first * SSE2ConvTbl[Idx].Cost;
}
if (ST->hasAVX512()) {
int Idx = ConvertCostTableLookup(AVX512ConversionTbl, ISD, LTDest.second,
LTSrc.second);
if (Idx != -1)
return AVX512ConversionTbl[Idx].Cost;
}
EVT SrcTy = TLI->getValueType(DL, Src);
EVT DstTy = TLI->getValueType(DL, Dst);
// The function getSimpleVT only handles simple value types.
if (!SrcTy.isSimple() || !DstTy.isSimple())
return BaseT::getCastInstrCost(Opcode, Dst, Src);
if (ST->hasAVX2()) {
int Idx = ConvertCostTableLookup(AVX2ConversionTbl, ISD,
DstTy.getSimpleVT(), SrcTy.getSimpleVT());