[DebugInfo] Preserve line and column number when merging debug info.

This patch introduces a new option `-preserve-merged-debug-info` to
preserve an arbitrary version of debug information when DILocations are
merged. This is intended to be used in production environments from
which sample based profiles are derived such as AutoFDO and MemProf.

With this patch we have see a 0.2% improvement on an internal workload
at Google when generating AutoFDO profiles. It also significantly
improves the ability for MemProf by preserving debug info for merged
call instructions used in the contextual profile.

Co-authored-by: Krzysztof Pszeniczny <[email protected]>

Author: Snehasish Kumar

llvm/lib/IR/DebugInfoMetadata.cpp

@@ -21,6 +21,7 @@
 #include "llvm/IR/IntrinsicInst.h"
 #include "llvm/IR/Type.h"
 #include "llvm/IR/Value.h"
+#include "llvm/Support/CommandLine.h"
 
 #include <numeric>
 #include <optional>
@@ -34,6 +35,12 @@ cl::opt<bool> EnableFSDiscriminator(
     cl::desc("Enable adding flow sensitive discriminators"));
 } // namespace llvm
 
+// When true, preserves line and column number by picking one of the merged
+// location info in a deterministic manner to assist sample based PGO.
+static cl::opt<bool> PreserveMergedDebugInfo(
+    "preserve-merged-debug-info", cl::init(false), cl::Hidden,
+    cl::desc("Preserve line and column number when merging locations."));
+
 uint32_t DIType::getAlignInBits() const {
   return (getTag() == dwarf::DW_TAG_LLVM_ptrauth_type ? 0 : SubclassData32);
 }
@@ -125,6 +132,14 @@ DILocation *DILocation::getMergedLocation(DILocation *LocA, DILocation *LocB) {
   if (LocA == LocB)
     return LocA;
 
+  if (PreserveMergedDebugInfo) {
+    auto A = std::make_tuple(LocA->getLine(), LocA->getColumn(),
+                             LocA->getDiscriminator());
+    auto B = std::make_tuple(LocB->getLine(), LocB->getColumn(),
+                             LocB->getDiscriminator());
+    return A < B ? LocA : LocB;
+  }
+
   LLVMContext &C = LocA->getContext();
 
   using LocVec = SmallVector<const DILocation *>;

llvm/test/DebugInfo/preserve-merged-debug-info.ll

@@ -0,0 +1,65 @@
+; RUN: opt %s -passes=simplifycfg -hoist-common-insts -preserve-merged-debug-info -S | FileCheck %s
+; CHECK: tail call i32 @bar{{.*!dbg !}}[[TAG:[0-9]+]]
+; CHECK: ![[TAG]] = !DILocation(line: 9, column: 16, scope: !9) 
+
+; ModuleID = '../llvm/test/DebugInfo/Inputs/debug-info-merge-call.c'
+source_filename = "../llvm/test/DebugInfo/Inputs/debug-info-merge-call.c"
+target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-i128:128-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+; Function Attrs: nounwind uwtable
+define dso_local i32 @test(i32 noundef %n) local_unnamed_addr #0 !dbg !9 {
+entry:
+  %call = tail call i32 @foo(i32 noundef %n) #2, !dbg !12
+  %cmp1 = icmp sgt i32 %n, 100, !dbg !13
+  br i1 %cmp1, label %if.then, label %if.else, !dbg !13
+
+if.then:                                          ; preds = %entry
+  %call2 = tail call i32 @bar(i32 noundef %n) #2, !dbg !14
+  %add = add nsw i32 %call2, %call, !dbg !15
+  br label %if.end, !dbg !16
+
+if.else:                                          ; preds = %entry
+  %call4 = tail call i32 @bar(i32 noundef %n) #2, !dbg !17
+  br label %if.end
+
+if.end:                                           ; preds = %if.else, %if.then
+  %r.0 = phi i32 [ %add, %if.then ], [ %call4, %if.else ], !dbg !18
+  ret i32 %r.0, !dbg !19
+}
+
+declare !dbg !20 i32 @foo(i32 noundef) local_unnamed_addr #1
+
+declare !dbg !21 i32 @bar(i32 noundef) local_unnamed_addr #1
+
+attributes #0 = { nounwind uwtable "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+cmov,+cx8,+fxsr,+mmx,+sse,+sse2,+x87" "tune-cpu"="generic" }
+attributes #1 = { "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+cmov,+cx8,+fxsr,+mmx,+sse,+sse2,+x87" "tune-cpu"="generic" }
+attributes #2 = { nounwind }
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!2, !3, !4, !5, !6, !7}
+!llvm.ident = !{!8}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C11, file: !1, producer: "clang version 21.0.0git ([email protected]:snehasish/llvm-project.git 6ce41db6b0275d060d6e60f88b96a1657024345c)", isOptimized: true, runtimeVersion: 0, emissionKind: LineTablesOnly, splitDebugInlining: false, nameTableKind: None)
+!1 = !DIFile(filename: "../llvm/test/DebugInfo/Inputs/debug-info-merge-call.c", directory: "/usr/local/google/home/snehasishk/working/llvm-project/build-assert", checksumkind: CSK_MD5, checksum: "ac1be6c40dad11691922d600f9d55c55")
+!2 = !{i32 7, !"Dwarf Version", i32 5}
+!3 = !{i32 2, !"Debug Info Version", i32 3}
+!4 = !{i32 1, !"wchar_size", i32 4}
+!5 = !{i32 8, !"PIC Level", i32 2}
+!6 = !{i32 7, !"PIE Level", i32 2}
+!7 = !{i32 7, !"uwtable", i32 2}
+!8 = !{!"clang version 21.0.0git ([email protected]:snehasish/llvm-project.git 6ce41db6b0275d060d6e60f88b96a1657024345c)"}
+!9 = distinct !DISubprogram(name: "test", scope: !1, file: !1, line: 5, type: !10, scopeLine: 5, flags: DIFlagPrototyped | DIFlagAllCallsDescribed, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !0)
+!10 = !DISubroutineType(types: !11)
+!11 = !{}
+!12 = !DILocation(line: 7, column: 13, scope: !9)
+!13 = !DILocation(line: 8, column: 8, scope: !9)
+!14 = !DILocation(line: 9, column: 16, scope: !9)
+!15 = !DILocation(line: 9, column: 14, scope: !9)
+!16 = !DILocation(line: 10, column: 3, scope: !9)
+!17 = !DILocation(line: 11, column: 10, scope: !9)
+!18 = !DILocation(line: 0, scope: !9)
+!19 = !DILocation(line: 13, column: 3, scope: !9)
+!20 = !DISubprogram(name: "foo", scope: !1, file: !1, line: 2, type: !10, flags: DIFlagPrototyped, spFlags: DISPFlagOptimized)
+!21 = !DISubprogram(name: "bar", scope: !1, file: !1, line: 1, type: !10, flags: DIFlagPrototyped, spFlags: DISPFlagOptimized)
+