[PATCH] D34698: [AArch64] Inline callee if its target-features are a subset of the caller

[Florian Hahn via Phabricator via llvm-commits]

fhahn created this revision.
Herald added subscribers: eraman, aemerson.

Similar to X86, it should be safe to inline callees if their target-features
are a subset of the caller. This change matches GCC's inlining behavior
with respect to attributes [1].

[1] https://gcc.gnu.org/onlinedocs/gcc/AArch64-Function-Attributes.html#AArch64-Function-Attributes


https://reviews.llvm.org/D34698

Files:
  lib/Target/AArch64/AArch64TargetTransformInfo.cpp
  lib/Target/AArch64/AArch64TargetTransformInfo.h
  test/Transforms/Inline/AArch64/inline-target-attr.ll


Index: test/Transforms/Inline/AArch64/inline-target-attr.ll
===================================================================
--- /dev/null
+++ test/Transforms/Inline/AArch64/inline-target-attr.ll
@@ -0,0 +1,40 @@
+; RUN: opt < %s -mtriple=aarch64-unknown-linux-gnu -S -inline | FileCheck %s
+; RUN: opt < %s -mtriple=aarch64-unknown-linux-gnu -S -passes='cgscc(inline)' | FileCheck %s
+; Check that we only inline when we have compatible target attributes.
+
+define i32 @foo() #0 {
+entry:
+  %call = call i32 (...) @baz()
+  ret i32 %call
+; CHECK-LABEL: foo
+; CHECK: call i32 (...) @baz()
+}
+declare i32 @baz(...) #0
+
+define i32 @bar() #1 {
+entry:
+  %call = call i32 @foo()
+  ret i32 %call
+; CHECK-LABEL: bar
+; CHECK: call i32 (...) @baz()
+}
+
+define i32 @qux() #0 {
+entry:
+  %call = call i32 @bar()
+  ret i32 %call
+; CHECK-LABEL: qux
+; CHECK: call i32 @bar()
+}
+
+define i32 @strict_align() #2 {
+entry:
+  %call = call i32 @foo()
+  ret i32 %call
+; CHECK-LABEL: strict_align
+; CHECK: call i32 (...) @baz()
+}
+
+attributes #0 = { "target-cpu"="generic" "target-features"="+crc,+neon" }
+attributes #1 = { "target-cpu"="generic" "target-features"="+crc,+neon,+crypto" }
+attributes #2 = { "target-cpu"="generic" "target-features"="+crc,+neon,+strict-align" }
Index: lib/Target/AArch64/AArch64TargetTransformInfo.h
===================================================================
--- lib/Target/AArch64/AArch64TargetTransformInfo.h
+++ lib/Target/AArch64/AArch64TargetTransformInfo.h
@@ -51,6 +51,9 @@
       : BaseT(TM, F.getParent()->getDataLayout()), ST(TM->getSubtargetImpl(F)),
         TLI(ST->getTargetLowering()) {}
 
+  bool areInlineCompatible(const Function *Caller,
+                           const Function *Callee) const;
+
   /// \name Scalar TTI Implementations
   /// @{
 
Index: lib/Target/AArch64/AArch64TargetTransformInfo.cpp
===================================================================
--- lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -20,6 +20,20 @@
 
 #define DEBUG_TYPE "aarch64tti"
 
+bool AArch64TTIImpl::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();
+
+  // Inline a callee if its target-features are a subset of the callers
+  // target-features.
+  return (CallerBits & CalleeBits) == CalleeBits;
+}
+
 /// \brief Calculate the cost of materializing a 64-bit value. This helper
 /// method might only calculate a fraction of a larger immediate. Therefore it
 /// is valid to return a cost of ZERO.


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D34698.104198.patch
Type: text/x-patch
Size: 2843 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20170627/4b3dfec2/attachment.bin>