summaryrefslogtreecommitdiffstats
path: root/lib/Target/X86/X86TargetTransformInfo.cpp
diff options
context:
space:
mode:
authordim <dim@FreeBSD.org>2013-06-10 20:36:52 +0000
committerdim <dim@FreeBSD.org>2013-06-10 20:36:52 +0000
commitaa45f148926e3461a1fd8b10c990f0a51a908cc9 (patch)
tree909310b2e05119d1d6efda049977042abbb58bb1 /lib/Target/X86/X86TargetTransformInfo.cpp
parent169d2bd06003c39970bc94c99669a34b61bb7e45 (diff)
downloadFreeBSD-src-aa45f148926e3461a1fd8b10c990f0a51a908cc9.zip
FreeBSD-src-aa45f148926e3461a1fd8b10c990f0a51a908cc9.tar.gz
Vendor import of llvm tags/RELEASE_33/final r183502 (effectively, 3.3
release): http://llvm.org/svn/llvm-project/llvm/tags/RELEASE_33/final@183502
Diffstat (limited to 'lib/Target/X86/X86TargetTransformInfo.cpp')
-rw-r--r--lib/Target/X86/X86TargetTransformInfo.cpp35
1 files changed, 35 insertions, 0 deletions
diff --git a/lib/Target/X86/X86TargetTransformInfo.cpp b/lib/Target/X86/X86TargetTransformInfo.cpp
index a98c699..eba9d78 100644
--- a/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -334,9 +334,44 @@ unsigned X86TTI::getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src) const {
int ISD = TLI->InstructionOpcodeToISD(Opcode);
assert(ISD && "Invalid opcode");
+ std::pair<unsigned, MVT> LTSrc = TLI->getTypeLegalizationCost(Src);
+ std::pair<unsigned, MVT> LTDest = TLI->getTypeLegalizationCost(Dst);
+
+ static const TypeConversionCostTblEntry<MVT> 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, 15 },
+ { 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<MVT>(SSE2ConvTbl,
+ array_lengthof(SSE2ConvTbl),
+ ISD, LTDest.second, LTSrc.second);
+ if (Idx != -1)
+ return LTSrc.first * SSE2ConvTbl[Idx].Cost;
+ }
+
EVT SrcTy = TLI->getValueType(Src);
EVT DstTy = TLI->getValueType(Dst);
+ // The function getSimpleVT only handles simple value types.
if (!SrcTy.isSimple() || !DstTy.isSimple())
return TargetTransformInfo::getCastInstrCost(Opcode, Dst, Src);
OpenPOWER on IntegriCloud