AMDGPU: Use a custom areInlineCompatible

Fixes not inlining OpenCL library functions on AMDGPU,
which don't have an explicitly set target-cpu.

llvm-svn: 310269

1 files changed, 13 insertions, 0 deletions

diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
index 89a03902dc6..fde2132b40b 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
@@ -534,3 +534,16 @@ unsigned AMDGPUTTIImpl::getShuffleCost(TTI::ShuffleKind Kind, Type *Tp, int Inde
 
   return BaseT::getShuffleCost(Kind, Tp, Index, SubTp);
 }
+
+bool AMDGPUTTIImpl::areInlineCompatible(const Function *Caller,
+                                        const Function *Callee) const {
+  const TargetMachine &TM = getTLI()->getTargetMachine();
+  const FeatureBitset &CallerBits =
+    TM.getSubtargetImpl(*Caller)->getFeatureBits();
+  const FeatureBitset &CalleeBits =
+    TM.getSubtargetImpl(*Callee)->getFeatureBits();
+
+  FeatureBitset RealCallerBits = CallerBits & ~InlineFeatureIgnoreList;
+  FeatureBitset RealCalleeBits = CalleeBits & ~InlineFeatureIgnoreList;
+  return ((RealCallerBits & RealCalleeBits) == RealCalleeBits);
+}