[llvm] Implement areInlineCompatible for SystemZ using feature bitset (PR #132976)

[via llvm-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-backend-systemz

Author: Andres Chavarria (chavandres)

<details>
<summary>Changes</summary>

## What?
Implement `areInlineCompatible` for the SystemZ target using FeatureBitset comparison.

## Why?
The default implementation in `TargetTransformInfoImpl.h` makes a string comparison and only inlines when the target-cpu and the target-features for caller and callee are the same. We are missing out on optimizations when the callee has a subset of features of the caller.

## How?
Get the FeatureBitset of the caller and callee and check when callee is a subset or equal to the caller's features. It's a similar implementation to ARM, PowerPC...

## Testing?
Test cases check for when the callee is a subset of the caller, when it's not a subset and when both are equals.

---
Full diff: https://github.com/llvm/llvm-project/pull/132976.diff


4 Files Affected:

- (modified) llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp (+14) 
- (modified) llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.h (+4) 
- (added) llvm/test/Transforms/Inline/SystemZ/inline-target-attr.ll (+50) 
- (added) llvm/test/Transforms/Inline/SystemZ/lit.local.cfg (+2) 


``````````diff
diff --git a/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp b/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp
index 06a0a3a631654..bd0fdb414bedf 100644
--- a/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp
+++ b/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp
@@ -422,6 +422,20 @@ bool SystemZTTIImpl::isLSRCostLess(const TargetTransformInfo::LSRCost &C1,
              C2.ScaleCost, C2.SetupCost);
 }
 
+bool SystemZTTIImpl::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();
+
+  // Check that target features from the callee are subset or
+  // equal to the caller's features.
+  return (CalleeBits == CallerBits) || (CalleeBits < CallerBits);
+}
+
 unsigned SystemZTTIImpl::getNumberOfRegisters(unsigned ClassID) const {
   bool Vector = (ClassID == 1);
   if (!Vector)
diff --git a/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.h b/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.h
index 512fcc854d532..45de346cf97f7 100644
--- a/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.h
+++ b/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.h
@@ -62,6 +62,10 @@ class SystemZTTIImpl : public BasicTTIImplBase<SystemZTTIImpl> {
 
   bool isLSRCostLess(const TargetTransformInfo::LSRCost &C1,
                      const TargetTransformInfo::LSRCost &C2);
+  
+  bool areInlineCompatible(const Function *Caller,
+                          const Function *Callee) const;
+  
   /// @}
 
   /// \name Vector TTI Implementations
diff --git a/llvm/test/Transforms/Inline/SystemZ/inline-target-attr.ll b/llvm/test/Transforms/Inline/SystemZ/inline-target-attr.ll
new file mode 100644
index 0000000000000..1c70962dd18ee
--- /dev/null
+++ b/llvm/test/Transforms/Inline/SystemZ/inline-target-attr.ll
@@ -0,0 +1,50 @@
+; RUN: opt < %s -mtriple=s390x-linux-gnu -S -passes=inline | FileCheck %s
+; RUN: opt < %s -mtriple=s390x-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 @quux() #2 {
+entry:
+  %call = call i32 @bar()
+  ret i32 %call
+; CHECK-LABEL: quux
+; CHECK: call i32 (...) @baz()
+}
+
+define i32 @foobar() #1 {
+entry:
+  %call = call i32 @bar()
+  ret i32 %call
+; CHECK-LABEL: foobar
+; CHECK: call i32 (...) @baz()
+}
+
+
+attributes #0 = { "target-cpu"="generic" "target-features"="+guarded-storage" }
+attributes #1 = { "target-cpu"="generic" "target-features"="+guarded-storage,+enhanced-sort" }
+attributes #2 = { "target-cpu"="generic" "target-features"="+concurrent-functions" }
diff --git a/llvm/test/Transforms/Inline/SystemZ/lit.local.cfg b/llvm/test/Transforms/Inline/SystemZ/lit.local.cfg
new file mode 100644
index 0000000000000..f9dd98a21cc3e
--- /dev/null
+++ b/llvm/test/Transforms/Inline/SystemZ/lit.local.cfg
@@ -0,0 +1,2 @@
+if not "SystemZ" in config.root.targets:
+    config.unsupported = True

``````````

</details>


https://github.com/llvm/llvm-project/pull/132976