2 files changed, 57 insertions, 4 deletions
diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index 9ae4a928fb5..a7ecfc2e586 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -3065,10 +3065,9 @@ bool X86TTIImpl::areInlineCompatible(const Function *Caller,
   const FeatureBitset &CalleeBits =
       TM.getSubtargetImpl(*Callee)->getFeatureBits();
 
-  // FIXME: This is likely too limiting as it will include subtarget features
-  // that we might not care about for inlining, but it is conservatively
-  // correct.
-  return (CallerBits & CalleeBits) == CalleeBits;
+  FeatureBitset RealCallerBits = CallerBits & ~InlineFeatureIgnoreList;
+  FeatureBitset RealCalleeBits = CalleeBits & ~InlineFeatureIgnoreList;
+  return (RealCallerBits & RealCalleeBits) == RealCalleeBits;
 }
 
 const X86TTIImpl::TTI::MemCmpExpansionOptions *
diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.h b/llvm/lib/Target/X86/X86TargetTransformInfo.h
index b2e3e05cbe3..5035818fde9 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.h
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.h
@@ -35,6 +35,60 @@ class X86TTIImpl : public BasicTTIImplBase<X86TTIImpl> {
   const X86Subtarget *getST() const { return ST; }
   const X86TargetLowering *getTLI() const { return TLI; }
 
+  const FeatureBitset InlineFeatureIgnoreList = {
+    // This indicates the CPU is 64 bit capable not that we are in 64-bit mode.
+    X86::Feature64Bit,
+
+    // These features don't have any intrinsics or ABI effect.
+    X86::FeatureNOPL,
+    X86::FeatureCMPXCHG16B,
+    X86::FeatureLAHFSAHF,
+
+    // Codegen control options.
+    X86::FeatureFast11ByteNOP,
+    X86::FeatureFast15ByteNOP,
+    X86::FeatureFastBEXTR,
+    X86::FeatureFastHorizontalOps,
+    X86::FeatureFastLZCNT,
+    X86::FeatureFastPartialYMMorZMMWrite,
+    X86::FeatureFastScalarFSQRT,
+    X86::FeatureFastSHLDRotate,
+    X86::FeatureFastVariableShuffle,
+    X86::FeatureFastVectorFSQRT,
+    X86::FeatureLEAForSP,
+    X86::FeatureLEAUsesAG,
+    X86::FeatureLZCNTFalseDeps,
+    X86::FeatureMacroFusion,
+    X86::FeatureMergeToThreeWayBranch,
+    X86::FeaturePadShortFunctions,
+    X86::FeaturePOPCNTFalseDeps,
+    X86::FeatureSSEUnalignedMem,
+    X86::FeatureSlow3OpsLEA,
+    X86::FeatureSlowDivide32,
+    X86::FeatureSlowDivide64,
+    X86::FeatureSlowIncDec,
+    X86::FeatureSlowLEA,
+    X86::FeatureSlowPMADDWD,
+    X86::FeatureSlowPMULLD,
+    X86::FeatureSlowSHLD,
+    X86::FeatureSlowTwoMemOps,
+    X86::FeatureSlowUAMem16,
+
+    // Perf-tuning flags.
+    X86::FeatureHasFastGather,
+    X86::FeatureSlowUAMem32,
+
+    // Based on whether user set the -mprefer-vector-width command line.
+    X86::FeaturePrefer256Bit,
+
+    // CPU name enums. These just follow CPU string.
+    X86::ProcIntelAtom,
+    X86::ProcIntelGLM,
+    X86::ProcIntelGLP,
+    X86::ProcIntelSLM,
+    X86::ProcIntelTRM,
+  };
+
 public:
   explicit X86TTIImpl(const X86TargetMachine *TM, const Function &F)
       : BaseT(TM, F.getParent()->getDataLayout()), ST(TM->getSubtargetImpl(F)),