Index: llvm/trunk/lib/Target/X86/X86TargetTransformInfo.cpp =================================================================== --- llvm/trunk/lib/Target/X86/X86TargetTransformInfo.cpp +++ llvm/trunk/lib/Target/X86/X86TargetTransformInfo.cpp @@ -857,13 +857,17 @@ int ISD = TLI->InstructionOpcodeToISD(Opcode); assert(ISD && "Invalid opcode"); + static const CostTblEntry SSE2CostTbl[] = { + { ISD::SETCC, MVT::v2i64, 8 }, + { ISD::SETCC, MVT::v4i32, 1 }, + { ISD::SETCC, MVT::v8i16, 1 }, + { ISD::SETCC, MVT::v16i8, 1 }, + }; + static const CostTblEntry SSE42CostTbl[] = { { ISD::SETCC, MVT::v2f64, 1 }, { ISD::SETCC, MVT::v4f32, 1 }, { ISD::SETCC, MVT::v2i64, 1 }, - { ISD::SETCC, MVT::v4i32, 1 }, - { ISD::SETCC, MVT::v8i16, 1 }, - { ISD::SETCC, MVT::v16i8, 1 }, }; static const CostTblEntry AVX1CostTbl[] = { @@ -906,6 +910,10 @@ if (const auto *Entry = CostTableLookup(SSE42CostTbl, ISD, MTy)) return LT.first * Entry->Cost; + if (ST->hasSSE2()) + if (const auto *Entry = CostTableLookup(SSE2CostTbl, ISD, MTy)) + return LT.first * Entry->Cost; + return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy); } Index: llvm/trunk/test/Analysis/CostModel/X86/cmp.ll =================================================================== --- llvm/trunk/test/Analysis/CostModel/X86/cmp.ll +++ llvm/trunk/test/Analysis/CostModel/X86/cmp.ll @@ -87,18 +87,18 @@ ;AVX: cost of 1 {{.*}} icmp %H = icmp eq <4 x i32> undef, undef - ;SSE2: cost of 1 {{.*}} icmp - ;SSE3: cost of 1 {{.*}} icmp - ;SSSE3: cost of 1 {{.*}} icmp - ;SSE41: cost of 1 {{.*}} icmp + ;SSE2: cost of 8 {{.*}} icmp + ;SSE3: cost of 8 {{.*}} icmp + ;SSSE3: cost of 8 {{.*}} icmp + ;SSE41: cost of 8 {{.*}} icmp ;SSE42: cost of 1 {{.*}} icmp ;AVX: cost of 1 {{.*}} icmp %I = icmp eq <2 x i64> undef, undef - ;SSE2: cost of 2 {{.*}} icmp - ;SSE3: cost of 2 {{.*}} icmp - ;SSSE3: cost of 2 {{.*}} icmp - ;SSE41: cost of 2 {{.*}} icmp + ;SSE2: cost of 16 {{.*}} icmp + ;SSE3: cost of 16 {{.*}} icmp + ;SSSE3: cost of 16 {{.*}} icmp + ;SSE41: cost of 16 {{.*}} icmp ;SSE42: cost of 2 {{.*}} icmp ;AVX1: cost of 4 {{.*}} icmp ;AVX2: cost of 1 {{.*}} icmp