diff --git a/llvm/lib/Target/X86/X86.td b/llvm/lib/Target/X86/X86.td --- a/llvm/lib/Target/X86/X86.td +++ b/llvm/lib/Target/X86/X86.td @@ -1193,6 +1193,7 @@ TuningFastScalarFSQRT, TuningFastVectorFSQRT, TuningFastScalarShiftMasks, + TuningFastVariablePerLaneShuffle, TuningFastMOVBE, TuningSlowSHLD, TuningSBBDepBreaking, @@ -1208,9 +1209,7 @@ FeaturePKU, FeatureVAES, FeatureVPCLMULQDQ]; - list ZN3AdditionalTuning = - [TuningMacroFusion, - TuningFastVariablePerLaneShuffle]; + list ZN3AdditionalTuning = [TuningMacroFusion]; list ZN3Tuning = !listconcat(ZN2Tuning, ZN3AdditionalTuning); list ZN3Features = diff --git a/llvm/test/CodeGen/X86/vector-shuffle-fast-per-lane.ll b/llvm/test/CodeGen/X86/vector-shuffle-fast-per-lane.ll --- a/llvm/test/CodeGen/X86/vector-shuffle-fast-per-lane.ll +++ b/llvm/test/CodeGen/X86/vector-shuffle-fast-per-lane.ll @@ -4,8 +4,8 @@ ; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+avx2,+fast-variable-perlane-shuffle | FileCheck %s --check-prefixes=FAST ; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+avx512f,+fast-variable-perlane-shuffle | FileCheck %s --check-prefixes=FAST ; -; RUN: llc < %s -mtriple=x86_64-unknown -mcpu=znver1 | FileCheck %s --check-prefixes=SLOW -; RUN: llc < %s -mtriple=x86_64-unknown -mcpu=znver2 | FileCheck %s --check-prefixes=SLOW +; RUN: llc < %s -mtriple=x86_64-unknown -mcpu=znver1 | FileCheck %s --check-prefixes=FAST +; RUN: llc < %s -mtriple=x86_64-unknown -mcpu=znver2 | FileCheck %s --check-prefixes=FAST ; RUN: llc < %s -mtriple=x86_64-unknown -mcpu=znver3 | FileCheck %s --check-prefixes=FAST ; RUN: llc < %s -mtriple=x86_64-unknown -mcpu=haswell | FileCheck %s --check-prefixes=FAST ; RUN: llc < %s -mtriple=x86_64-unknown -mcpu=skx | FileCheck %s --check-prefixes=FAST