diff options
| author | Benjamin Kramer <benny.kra@googlemail.com> | 2014-04-26 14:53:05 +0000 |
|---|---|---|
| committer | Benjamin Kramer <benny.kra@googlemail.com> | 2014-04-26 14:53:05 +0000 |
| commit | d9ced7112e85a566999276099aef5f2ddf6735b7 (patch) | |
| tree | 952410994dbcf70b0f42ae18b1b5e934a903ba4b /lib | |
| parent | 9f2c21871ce2bc49e715ea1cf934ac10746ccf70 (diff) | |
| download | llvm-d9ced7112e85a566999276099aef5f2ddf6735b7.tar.gz llvm-d9ced7112e85a566999276099aef5f2ddf6735b7.tar.bz2 llvm-d9ced7112e85a566999276099aef5f2ddf6735b7.tar.xz | |
X86TTI: i16/i32 vector div with a constant (splat) divisor are reasonably cheap now.
Turn vectorization back on.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207320 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'lib')
| -rw-r--r-- | lib/Target/X86/X86TargetTransformInfo.cpp | 19 |
1 files changed, 19 insertions, 0 deletions
diff --git a/lib/Target/X86/X86TargetTransformInfo.cpp b/lib/Target/X86/X86TargetTransformInfo.cpp index 5158004cad..628e9130a1 100644 --- a/lib/Target/X86/X86TargetTransformInfo.cpp +++ b/lib/Target/X86/X86TargetTransformInfo.cpp @@ -284,6 +284,21 @@ unsigned X86TTI::getArithmeticInstrCost(unsigned Opcode, Type *Ty, int ISD = TLI->InstructionOpcodeToISD(Opcode); assert(ISD && "Invalid opcode"); + static const CostTblEntry<MVT::SimpleValueType> + AVX2UniformConstCostTable[] = { + { ISD::SDIV, MVT::v16i16, 6 }, // vpmulhw sequence + { ISD::UDIV, MVT::v16i16, 6 }, // vpmulhuw sequence + { ISD::SDIV, MVT::v8i32, 15 }, // vpmuldq sequence + { ISD::UDIV, MVT::v8i32, 15 }, // vpmuludq sequence + }; + + if (Op2Info == TargetTransformInfo::OK_UniformConstantValue && + ST->hasAVX2()) { + int Idx = CostTableLookup(AVX2UniformConstCostTable, ISD, LT.second); + if (Idx != -1) + return LT.first * AVX2UniformConstCostTable[Idx].Cost; + } + static const CostTblEntry<MVT::SimpleValueType> AVX2CostTable[] = { // Shifts on v4i64/v8i32 on AVX2 is legal even though we declare to // customize them to detect the cases where shift amount is a scalar one. @@ -351,6 +366,10 @@ unsigned X86TTI::getArithmeticInstrCost(unsigned Opcode, Type *Ty, { ISD::SRA, MVT::v16i8, 4 }, // psrlw, pand, pxor, psubb. { ISD::SRA, MVT::v8i16, 1 }, // psraw. { ISD::SRA, MVT::v4i32, 1 }, // psrad. + + { ISD::SDIV, MVT::v8i16, 6 }, // pmulhw sequence + { ISD::UDIV, MVT::v8i16, 6 }, // pmulhuw sequence + { ISD::UDIV, MVT::v4i32, 15 }, // pmuludq sequence }; if (Op2Info == TargetTransformInfo::OK_UniformConstantValue && |