[llvm] [profcheck] Add unknown branch weights to expanded cmpxchg loop. (PR #165841)

[Jin Huang via llvm-commits]

https://github.com/jinhuang1102 updated https://github.com/llvm/llvm-project/pull/165841

>From 0366285a1c85c914e48f6f58cc73da0f68436fa7 Mon Sep 17 00:00:00 2001
From: Jin Huang <jingold at google.com>
Date: Fri, 31 Oct 2025 08:41:49 +0000
Subject: [PATCH] [profcheck] Add unknown branch weights to expanded cmpxchg
 loop.

---
 llvm/lib/CodeGen/AtomicExpandPass.cpp              |  8 +++++++-
 .../AtomicExpand/AArch64/atomicrmw-fp.ll           | 14 +++++++++++---
 2 files changed, 18 insertions(+), 4 deletions(-)

diff --git a/llvm/lib/CodeGen/AtomicExpandPass.cpp b/llvm/lib/CodeGen/AtomicExpandPass.cpp
index 53f1cfe24a68d..58724d4031eb4 100644
--- a/llvm/lib/CodeGen/AtomicExpandPass.cpp
+++ b/llvm/lib/CodeGen/AtomicExpandPass.cpp
@@ -38,6 +38,7 @@
 #include "llvm/IR/MDBuilder.h"
 #include "llvm/IR/MemoryModelRelaxationAnnotations.h"
 #include "llvm/IR/Module.h"
+#include "llvm/IR/ProfDataUtils.h"
 #include "llvm/IR/Type.h"
 #include "llvm/IR/User.h"
 #include "llvm/IR/Value.h"
@@ -1680,7 +1681,12 @@ Value *AtomicExpandImpl::insertRMWCmpXchgLoop(
 
   Loaded->addIncoming(NewLoaded, LoopBB);
 
-  Builder.CreateCondBr(Success, ExitBB, LoopBB);
+  Instruction *CondBr = Builder.CreateCondBr(Success, ExitBB, LoopBB);
+
+  // Atomic RMW expands to a cmpxchg loop, Since precise branch weights
+  // cannot be easily determined here, we mark the branch as "unknown" (50/50)
+  // to prevent misleading optimizations.
+  setExplicitlyUnknownBranchWeightsIfProfiled(*CondBr, *F, DEBUG_TYPE);
 
   Builder.SetInsertPoint(ExitBB, ExitBB->begin());
   return NewLoaded;
diff --git a/llvm/test/Transforms/AtomicExpand/AArch64/atomicrmw-fp.ll b/llvm/test/Transforms/AtomicExpand/AArch64/atomicrmw-fp.ll
index 8ffacb9bdd5f6..c11d5593f6833 100644
--- a/llvm/test/Transforms/AtomicExpand/AArch64/atomicrmw-fp.ll
+++ b/llvm/test/Transforms/AtomicExpand/AArch64/atomicrmw-fp.ll
@@ -1,7 +1,7 @@
-; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals
 ; RUN: opt -S -mtriple=aarch64-linux-gnu -passes=atomic-expand %s | FileCheck %s
 
-define float @test_atomicrmw_fadd_f32(ptr %ptr, float %value) {
+define float @test_atomicrmw_fadd_f32(ptr %ptr, float %value) !prof !0 {
 ; CHECK-LABEL: @test_atomicrmw_fadd_f32(
 ; CHECK-NEXT:    [[TMP1:%.*]] = load float, ptr [[PTR:%.*]], align 4
 ; CHECK-NEXT:    br label [[ATOMICRMW_START:%.*]]
@@ -14,7 +14,7 @@ define float @test_atomicrmw_fadd_f32(ptr %ptr, float %value) {
 ; CHECK-NEXT:    [[SUCCESS:%.*]] = extractvalue { i32, i1 } [[TMP4]], 1
 ; CHECK-NEXT:    [[NEWLOADED:%.*]] = extractvalue { i32, i1 } [[TMP4]], 0
 ; CHECK-NEXT:    [[TMP5]] = bitcast i32 [[NEWLOADED]] to float
-; CHECK-NEXT:    br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
+; CHECK-NEXT:    br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]], !prof [[PROF1:![0-9]+]]
 ; CHECK:       atomicrmw.end:
 ; CHECK-NEXT:    ret float [[TMP5]]
 ;
@@ -336,3 +336,11 @@ define <2 x half> @atomicrmw_fminimum_2_x_half(ptr %ptr, <2 x half> %val) {
   %res = atomicrmw fminimum ptr %ptr, <2 x half> %val seq_cst
   ret <2 x half> %res
 }
+
+!0 = !{!"function_entry_count", i64 1000}
+;.
+; CHECK: attributes #[[ATTR0:[0-9]+]] = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
+;.
+; CHECK: [[META0:![0-9]+]] = !{!"function_entry_count", i64 1000}
+; CHECK: [[PROF1]] = !{!"unknown", !"atomic-expand"}
+;.