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

[CostModel][X86] Added missing AVX2 arithmetic costs. 

Allows us to correctly fall through to the lower AVX1 costs if look up failed.

llvm-svn: 291353
This commit is contained in:
Simon Pilgrim 2017-01-07 17:27:39 +00:00
parent 100eae1ee0
commit df7de7a87e
1 changed files with 29 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

48
llvm/lib/Target/X86/X86TargetTransformInfo.cpp
View File

@ -322,28 +322,38 @@ int X86TTIImpl::getArithmeticInstrCost(
return LT.first * Entry->Cost;
static const CostTblEntry AVX2CustomCostTable[] = {
{ ISD::SHL, MVT::v32i8, 11 }, // vpblendvb sequence.
{ ISD::SHL, MVT::v16i16, 10 }, // extend/vpsrlvd/pack sequence.
{ ISD::SHL, MVT::v32i8, 11 }, // vpblendvb sequence.
{ ISD::SHL, MVT::v16i16, 10 }, // extend/vpsrlvd/pack sequence.
{ ISD::SRL, MVT::v32i8, 11 }, // vpblendvb sequence.
{ ISD::SRL, MVT::v16i16, 10 }, // extend/vpsrlvd/pack sequence.
{ ISD::SRL, MVT::v32i8, 11 }, // vpblendvb sequence.
{ ISD::SRL, MVT::v16i16, 10 }, // extend/vpsrlvd/pack sequence.
{ ISD::SRA, MVT::v32i8, 24 }, // vpblendvb sequence.
{ ISD::SRA, MVT::v16i16, 10 }, // extend/vpsravd/pack sequence.
{ ISD::SRA, MVT::v2i64, 4 }, // srl/xor/sub sequence.
{ ISD::SRA, MVT::v4i64, 4 }, // srl/xor/sub sequence.
{ ISD::SRA, MVT::v32i8, 24 }, // vpblendvb sequence.
{ ISD::SRA, MVT::v16i16, 10 }, // extend/vpsravd/pack sequence.
{ ISD::SRA, MVT::v2i64, 4 }, // srl/xor/sub sequence.
{ ISD::SRA, MVT::v4i64, 4 }, // srl/xor/sub sequence.
{ ISD::MUL, MVT::v32i8, 17 }, // extend/pmullw/trunc sequence.
{ ISD::MUL, MVT::v16i8, 7 }, // extend/pmullw/trunc sequence.
{ ISD::MUL, MVT::v8i32, 1 }, // pmulld
{ ISD::MUL, MVT::v4i64, 8 }, // 3*pmuludq/3*shift/2*add
{ ISD::SUB, MVT::v32i8, 1 }, // psubb
{ ISD::ADD, MVT::v32i8, 1 }, // paddb
{ ISD::SUB, MVT::v16i16, 1 }, // psubw
{ ISD::ADD, MVT::v16i16, 1 }, // paddw
{ ISD::SUB, MVT::v8i32, 1 }, // psubd
{ ISD::ADD, MVT::v8i32, 1 }, // paddd
{ ISD::SUB, MVT::v4i64, 1 }, // psubq
{ ISD::ADD, MVT::v4i64, 1 }, // paddq
{ ISD::FDIV, MVT::f32, 7 }, // Haswell from http://www.agner.org/
{ ISD::FDIV, MVT::v4f32, 7 }, // Haswell from http://www.agner.org/
{ ISD::FDIV, MVT::v8f32, 14 }, // Haswell from http://www.agner.org/
{ ISD::FDIV, MVT::f64, 14 }, // Haswell from http://www.agner.org/
{ ISD::FDIV, MVT::v2f64, 14 }, // Haswell from http://www.agner.org/
{ ISD::FDIV, MVT::v4f64, 28 }, // Haswell from http://www.agner.org/
{ ISD::MUL, MVT::v32i8, 17 }, // extend/pmullw/trunc sequence.
{ ISD::MUL, MVT::v16i8, 7 }, // extend/pmullw/trunc sequence.
{ ISD::MUL, MVT::v16i16, 1 }, // pmullw
{ ISD::MUL, MVT::v8i32, 1 }, // pmulld
{ ISD::MUL, MVT::v4i64, 8 }, // 3*pmuludq/3*shift/2*add
{ ISD::FDIV, MVT::f32, 7 }, // Haswell from http://www.agner.org/
{ ISD::FDIV, MVT::v4f32, 7 }, // Haswell from http://www.agner.org/
{ ISD::FDIV, MVT::v8f32, 14 }, // Haswell from http://www.agner.org/
{ ISD::FDIV, MVT::f64, 14 }, // Haswell from http://www.agner.org/
{ ISD::FDIV, MVT::v2f64, 14 }, // Haswell from http://www.agner.org/
{ ISD::FDIV, MVT::v4f64, 28 }, // Haswell from http://www.agner.org/
};
// Look for AVX2 lowering tricks for custom cases.
@ -463,7 +473,7 @@ int X86TTIImpl::getArithmeticInstrCost(
{ ISD::MUL, MVT::v4i64, 18 },
};
if (ST->hasAVX() && !ST->hasAVX2())
if (ST->hasAVX())
if (const auto *Entry = CostTableLookup(AVX1CostTable, ISD, LT.second))
return LT.first * Entry->Cost;