[LoongArch] Add areInlineCompatible

Inline a callee if its target-features are a subset of the callers
target-features.

Author: heiher

llvm/lib/Target/LoongArch/LoongArchTargetTransformInfo.cpp

@@ -19,6 +19,20 @@ using namespace llvm;
 
 #define DEBUG_TYPE "loongarchtti"
 
+bool LoongArchTTIImpl::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;
+}
+
 TypeSize LoongArchTTIImpl::getRegisterBitWidth(
     TargetTransformInfo::RegisterKind K) const {
   TypeSize DefSize = TargetTransformInfoImplBase::getRegisterBitWidth(K);

llvm/lib/Target/LoongArch/LoongArchTargetTransformInfo.h

@@ -40,6 +40,9 @@ class LoongArchTTIImpl : public BasicTTIImplBase<LoongArchTTIImpl> {
       : BaseT(TM, F.getDataLayout()), ST(TM->getSubtargetImpl(F)),
         TLI(ST->getTargetLowering()) {}
 
+  bool areInlineCompatible(const Function *Caller,
+                           const Function *Callee) const;
+
   TypeSize getRegisterBitWidth(TargetTransformInfo::RegisterKind K) const;
   unsigned getNumberOfRegisters(unsigned ClassID) const;
   unsigned getRegisterClassForType(bool Vector, Type *Ty = nullptr) const;

llvm/test/Transforms/Inline/LoongArch/inline-target-features.ll

@@ -0,0 +1,34 @@
+; RUN: opt < %s -mtriple=loongarch64-unknown-linux-gnu -S -passes=inline | FileCheck %s
+; RUN: opt < %s -mtriple=loongarch64-unknown-linux-gnu -S -passes='cgscc(inline)' | FileCheck %s
+; Check that we only inline when we have compatible target attributes.
+
+target datalayout = "e-m:e-p:64:64-i64:64-i128:128-n32:64-S128"
+target triple = "loongarch64-unknown-linux-gnu"
+
+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()
+}
+
+attributes #0 = { "target-cpu"="generic-la64" "target-features"="+f,+d" }
+attributes #1 = { "target-cpu"="generic-la64" "target-features"="+f,+d,+lsx,+lasx" }

llvm/test/Transforms/Inline/LoongArch/lit.local.cfg

@@ -0,0 +1,2 @@
+if not "LoongArch" in config.root.targets:
+    config.unsupported = True