[Metadata] Preserve MD_prof when merging instructions when one is missing.

snehasish · snehasish · commit 5b2f87db7ec7 · 2025-03-21T17:43:16.000Z
Preserve branch weight metadata when merging instructions if one of the
instructions is missing metadata. This is similar in behaviour to what
we do today for other types of metadata such as mmra, memprof and
callsite metadata.
diff --git a/llvm/lib/Transforms/Utils/Local.cpp b/llvm/lib/Transforms/Utils/Local.cpp
@@ -3355,9 +3355,10 @@ static void combineMetadata(Instruction *K, const Instruction *J,
       case LLVMContext::MD_invariant_group:
         // Preserve !invariant.group in K.
         break;
-      // Keep empty cases for mmra, memprof, and callsite to prevent them from
-      // being removed as unknown metadata. The actual merging is handled
+      // Keep empty cases for prof, mmra, memprof, and callsite to prevent them
+      // from being removed as unknown metadata. The actual merging is handled
       // separately below.
+      case LLVMContext::MD_prof:
       case LLVMContext::MD_mmra:
       case LLVMContext::MD_memprof:
       case LLVMContext::MD_callsite:
@@ -3386,10 +3387,6 @@ static void combineMetadata(Instruction *K, const Instruction *J,
         if (!AAOnly)
           K->setMetadata(Kind, JMD);
         break;
-      case LLVMContext::MD_prof:
-        if (!AAOnly && DoesKMove)
-          K->setMetadata(Kind, MDNode::getMergedProfMetadata(KMD, JMD, K, J));
-        break;
       case LLVMContext::MD_noalias_addrspace:
         if (DoesKMove)
           K->setMetadata(Kind,
@@ -3436,6 +3433,16 @@ static void combineMetadata(Instruction *K, const Instruction *J,
     K->setMetadata(LLVMContext::MD_callsite,
                    MDNode::getMergedCallsiteMetadata(KCallSite, JCallSite));
   }
+
+  // Merge prof metadata.
+  // Handle separately to support cases where only one instruction has the
+  // metadata.
+  auto JProf = J->getMetadata(LLVMContext::MD_prof);
+  auto KProf = K->getMetadata(LLVMContext::MD_prof);
+  if (!AAOnly && (JProf || KProf)) {
+    K->setMetadata(LLVMContext::MD_prof,
+                   MDNode::getMergedProfMetadata(KProf, JProf, K, J));
+  }
 }
 
 void llvm::combineMetadataForCSE(Instruction *K, const Instruction *J,
diff --git a/llvm/test/Transforms/SimplifyCFG/merge-direct-call-branch-weights-preserve-hoist.ll b/llvm/test/Transforms/SimplifyCFG/merge-direct-call-branch-weights-preserve-hoist.ll
@@ -0,0 +1,62 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals --version 2
+; RUN: opt < %s -passes='simplifycfg<no-sink-common-insts;hoist-common-insts>' -simplifycfg-require-and-preserve-domtree=1 -S | FileCheck %s --check-prefix=HOIST
+
+; Test case based on C++ code with manualy annotated !prof metadata.
+; This is to test that when calls to 'func1' from 'if.then' block
+; and 'if.else' block are hoisted, the branch_weights are merged and
+; attached to merged call rather than dropped.
+;
+; int func1(int a, int b) ;
+; int func2(int a, int b) ;
+
+; int func(int a, int b, bool c) {
+;    int sum= 0;
+;    if(c) {
+;        sum += func1(a, b);
+;    } else {
+;        sum += func1(a, b);
+;        sum -= func2(a, b);
+;    }
+;    return sum;
+; }
+define i32 @_Z4funciib(i32 %a, i32 %b, i1 %c) {
+; HOIST-LABEL: define i32 @_Z4funciib
+; HOIST-SAME: (i32 [[A:%.*]], i32 [[B:%.*]], i1 [[C:%.*]]) {
+; HOIST-NEXT:  entry:
+; HOIST-NEXT:    [[CALL:%.*]] = tail call i32 @_Z5func1ii(i32 [[A]], i32 [[B]]), !prof [[PROF0:![0-9]+]]
+; HOIST-NEXT:    br i1 [[C]], label [[IF_END:%.*]], label [[IF_ELSE:%.*]]
+; HOIST:       if.else:
+; HOIST-NEXT:    [[CALL3:%.*]] = tail call i32 @_Z5func2ii(i32 [[A]], i32 [[B]])
+; HOIST-NEXT:    [[SUB:%.*]] = sub i32 [[CALL]], [[CALL3]]
+; HOIST-NEXT:    br label [[IF_END]]
+; HOIST:       if.end:
+; HOIST-NEXT:    [[SUM_0:%.*]] = phi i32 [ [[SUB]], [[IF_ELSE]] ], [ [[CALL]], [[ENTRY:%.*]] ]
+; HOIST-NEXT:    ret i32 [[SUM_0]]
+;
+entry:
+  br i1 %c, label %if.then, label %if.else
+
+if.then:                                          ; preds = %entry
+  %call = tail call i32 @_Z5func1ii(i32 %a, i32 %b), !prof !0
+  br label %if.end
+
+if.else:                                          ; preds = %entry
+  %call1 = tail call i32 @_Z5func1ii(i32 %a, i32 %b)
+  %call3 = tail call i32 @_Z5func2ii(i32 %a, i32 %b)
+  %sub = sub i32 %call1, %call3
+  br label %if.end
+
+if.end:                                           ; preds = %if.else, %if.then
+  %sum.0 = phi i32 [ %call, %if.then ], [ %sub, %if.else ]
+  ret i32 %sum.0
+}
+
+declare i32 @_Z5func1ii(i32, i32)
+
+declare i32 @_Z5func2ii(i32, i32)
+
+!0 = !{!"branch_weights", i32 10}
+!1 = !{!"branch_weights", i32 90}
+;.
+; HOIST: [[PROF0]] = !{!"branch_weights", i32 10}
+;.
diff --git a/llvm/test/Transforms/SimplifyCFG/merge-direct-call-branch-weights-preserve-sink.ll b/llvm/test/Transforms/SimplifyCFG/merge-direct-call-branch-weights-preserve-sink.ll
@@ -0,0 +1,62 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals --version 2
+; RUN: opt < %s -passes='simplifycfg<sink-common-insts;no-hoist-common-insts>' -simplifycfg-require-and-preserve-domtree=1 -S | FileCheck %s --check-prefix=SINK
+
+
+; Test case based on the following C++ code with manualy annotated !prof metadata.
+; This is to test that when calls to 'func1' from 'if.then' and 'if.else' are
+; sinked, the branch weights are merged and attached to sinked call.
+;
+; int func1(int a, int b) ;
+; int func2(int a, int b) ;
+
+; int func(int a, int b, bool c) {
+;    int sum = 0;
+;    if (c) {
+;        sum += func1(a,b);
+;    } else {
+;        b -= func2(a,b);
+;        sum += func1(a,b);
+;    }
+;    return sum;
+; }
+
+define i32 @_Z4funciib(i32 %a, i32 %b, i1 %c) {
+; SINK-LABEL: define i32 @_Z4funciib
+; SINK-SAME: (i32 [[A:%.*]], i32 [[B:%.*]], i1 [[C:%.*]]) {
+; SINK-NEXT:  entry:
+; SINK-NEXT:    br i1 [[C]], label [[IF_END:%.*]], label [[IF_ELSE:%.*]]
+; SINK:       if.else:
+; SINK-NEXT:    [[CALL1:%.*]] = tail call i32 @_Z5func2ii(i32 [[A]], i32 [[B]])
+; SINK-NEXT:    [[SUB:%.*]] = sub i32 [[B]], [[CALL1]]
+; SINK-NEXT:    br label [[IF_END]]
+; SINK:       if.end:
+; SINK-NEXT:    [[SUB_SINK:%.*]] = phi i32 [ [[SUB]], [[IF_ELSE]] ], [ [[B]], [[ENTRY:%.*]] ]
+; SINK-NEXT:    [[CALL2:%.*]] = tail call i32 @_Z5func1ii(i32 [[A]], i32 [[SUB_SINK]]), !prof [[PROF0:![0-9]+]]
+; SINK-NEXT:    ret i32 [[CALL2]]
+;
+entry:
+  br i1 %c, label %if.then, label %if.else
+
+if.then:                                          ; preds = %entry
+  %call = tail call i32 @_Z5func1ii(i32 %a, i32 %b)
+  br label %if.end
+
+if.else:                                          ; preds = %entry
+  %call1 = tail call i32 @_Z5func2ii(i32 %a, i32 %b)
+  %sub = sub i32 %b, %call1
+  %call2 = tail call i32 @_Z5func1ii(i32 %a, i32 %sub), !prof !0
+  br label %if.end
+
+if.end:                                           ; preds = %if.else, %if.then
+  %sum.0 = phi i32 [ %call, %if.then ], [ %call2, %if.else ]
+  ret i32 %sum.0
+}
+
+declare i32 @_Z5func1ii(i32, i32)
+
+declare i32 @_Z5func2ii(i32, i32)
+
+!0 = !{!"branch_weights", i32 10}
+;.
+; SINK: [[PROF0]] = !{!"branch_weights", i32 10}
+;.
