[SampleFDO] Skip profile reading when flattened profile used in ThinLTO postlink

If the sample profile has no inlining hierachy information included, we call
the sample profile is flattened. For flattened profile, in ThinLTO postlink
phase, SampleProfileLoader's hot function inlining and profile annotation will
do nothing, so it is better to save the effort to read in the profile and run
the sample profile loader pass. It is helpful for reducing compile time when
the flattened profile is huge.

Differential Revision: https://reviews.llvm.org/D54819

llvm-svn: 351476

4 files changed, 65 insertions, 5 deletions

diff --git a/llvm/lib/Passes/PassBuilder.cpp b/llvm/lib/Passes/PassBuilder.cpp
index 5ec94ea6f40..e56c2d4c8fb 100644
--- a/llvm/lib/Passes/PassBuilder.cpp
+++ b/llvm/lib/Passes/PassBuilder.cpp
@@ -211,6 +211,8 @@ static cl::opt<bool>
 
 extern cl::opt<bool> EnableHotColdSplit;
 
+extern cl::opt<bool> FlattenedProfileUsed;
+
 static bool isOptimizingForSize(PassBuilder::OptimizationLevel Level) {
   switch (Level) {
   case PassBuilder::O0:
@@ -615,9 +617,13 @@ PassBuilder::buildModuleSimplificationPipeline(OptimizationLevel Level,
   if (PGOOpt && !PGOOpt->SampleProfileFile.empty()) {
     // Annotate sample profile right after early FPM to ensure freshness of
     // the debug info.
-    MPM.addPass(SampleProfileLoaderPass(PGOOpt->SampleProfileFile,
-                                        PGOOpt->ProfileRemappingFile,
-                                        Phase == ThinLTOPhase::PreLink));
+    // In ThinLTO mode, when flattened profile is used, all the available
+    // profile information will be annotated in PreLink phase so there is
+    // no need to load the profile again in PostLink.
+    if (!(FlattenedProfileUsed && Phase == ThinLTOPhase::PostLink))
+      MPM.addPass(SampleProfileLoaderPass(PGOOpt->SampleProfileFile,
+                                          PGOOpt->ProfileRemappingFile,
+                                          Phase == ThinLTOPhase::PreLink));
     // Do not invoke ICP in the ThinLTOPrelink phase as it makes it hard
     // for the profile annotation to be accurate in the ThinLTO backend.
     if (Phase != ThinLTOPhase::PreLink)
diff --git a/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp b/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
index b92d3ba4f48..1dd07fa026a 100644
--- a/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
+++ b/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
@@ -104,6 +104,10 @@ static cl::opt<bool>
     EnablePrepareForThinLTO("prepare-for-thinlto", cl::init(false), cl::Hidden,
                             cl::desc("Enable preparation for ThinLTO."));
 
+static cl::opt<bool>
+    EnablePerformThinLTO("perform-thinlto", cl::init(false), cl::Hidden,
+                         cl::desc("Enable performing ThinLTO."));
+
 cl::opt<bool> EnableHotColdSplit("hot-cold-split", cl::init(false), cl::Hidden,
     cl::desc("Enable hot-cold splitting pass"));
 
@@ -146,6 +150,11 @@ static cl::opt<bool>
     EnableCHR("enable-chr", cl::init(true), cl::Hidden,
               cl::desc("Enable control height reduction optimization (CHR)"));
 
+cl::opt<bool> FlattenedProfileUsed(
+    "flattened-profile-used", cl::init(false), cl::Hidden,
+    cl::desc("Indicate the sample profile being used is flattened, i.e., "
+             "no inline hierachy exists in the profile. "));
+
 PassManagerBuilder::PassManagerBuilder() {
     OptLevel = 2;
     SizeLevel = 0;
@@ -166,7 +175,7 @@ PassManagerBuilder::PassManagerBuilder() {
     PGOInstrUse = "";
     PGOSampleUse = "";
     PrepareForThinLTO = EnablePrepareForThinLTO;
-    PerformThinLTO = false;
+    PerformThinLTO = EnablePerformThinLTO;
     DivergentTarget = false;
 }
 
@@ -414,7 +423,11 @@ void PassManagerBuilder::populateModulePassManager(
     legacy::PassManagerBase &MPM) {
   if (!PGOSampleUse.empty()) {
     MPM.add(createPruneEHPass());
-    MPM.add(createSampleProfileLoaderPass(PGOSampleUse));
+    // In ThinLTO mode, when flattened profile is used, all the available
+    // profile information will be annotated in PreLink phase so there is
+    // no need to load the profile again in PostLink.
+    if (!(FlattenedProfileUsed && PerformThinLTO))
+      MPM.add(createSampleProfileLoaderPass(PGOSampleUse));
   }
 
   // Allow forcing function attributes as a debugging and tuning aid.
diff --git a/llvm/test/Transforms/SampleProfile/Inputs/flattened.prof b/llvm/test/Transforms/SampleProfile/Inputs/flattened.prof
new file mode 100644
index 00000000000..962bc6e58e5
--- /dev/null
+++ b/llvm/test/Transforms/SampleProfile/Inputs/flattened.prof
@@ -0,0 +1,2 @@
+foo:100:100
+ 1: 100
diff --git a/llvm/test/Transforms/SampleProfile/flattened.ll b/llvm/test/Transforms/SampleProfile/flattened.ll
new file mode 100644
index 00000000000..7a1e53b966c
--- /dev/null
+++ b/llvm/test/Transforms/SampleProfile/flattened.ll
@@ -0,0 +1,39 @@
+; Check flattened profile will not be read in thinlto postlink.
+; RUN: opt < %s -O2 -flattened-profile-used -pgo-kind=pgo-sample-use-pipeline -profile-file=%S/Inputs/flattened.prof -enable-chr=false -perform-thinlto=true -S | FileCheck %s
+; RUN: opt < %s -passes='thinlto<O2>' -pgo-kind=pgo-sample-use-pipeline -profile-file=%S/Inputs/flattened.prof -flattened-profile-used -S | FileCheck %s
+;
+; Check flattened profile will be read in thinlto prelink.
+; RUN: opt < %s -O2 -flattened-profile-used -pgo-kind=pgo-sample-use-pipeline -profile-file=%S/Inputs/flattened.prof -enable-chr=false -prepare-for-thinlto=true -S | FileCheck %s --check-prefix=PRELINK
+; RUN: opt < %s -passes='thinlto-pre-link<O2>' -pgo-kind=pgo-sample-use-pipeline -profile-file=%S/Inputs/flattened.prof -flattened-profile-used -S | FileCheck %s --check-prefix=PRELINK
+;
+; Check flattened profile will be read in non-thinlto mode.
+; RUN: opt < %s -O2 -flattened-profile-used -pgo-kind=pgo-sample-use-pipeline -profile-file=%S/Inputs/flattened.prof -enable-chr=false -S | FileCheck %s --check-prefix=NOTHINLTO
+; RUN: opt < %s -passes='default<O2>' -pgo-kind=pgo-sample-use-pipeline -profile-file=%S/Inputs/flattened.prof -flattened-profile-used -S | FileCheck %s --check-prefix=NOTHINLTO
+;
+; CHECK-NOT: !{!"ProfileFormat", !"SampleProfile"}
+; PRELINK:   !{!"ProfileFormat", !"SampleProfile"}
+; NOTHINLTO: !{!"ProfileFormat", !"SampleProfile"}
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+; Function Attrs: norecurse nounwind readnone uwtable
+define dso_local i32 @foo() local_unnamed_addr !dbg !7 {
+entry:
+  ret i32 -1, !dbg !9
+}
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!3, !4, !5}
+!llvm.ident = !{!6}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C99, file: !1, producer: "clang version 8.0.0 (trunk 345241)", isOptimized: true, runtimeVersion: 0, emissionKind: LineTablesOnly, enums: !2, nameTableKind: None)
+!1 = !DIFile(filename: "a.c", directory: "")
+!2 = !{}
+!3 = !{i32 2, !"Dwarf Version", i32 4}
+!4 = !{i32 2, !"Debug Info Version", i32 3}
+!5 = !{i32 1, !"wchar_size", i32 4}
+!6 = !{!"clang version 8.0.0 (trunk 345241)"}
+!7 = distinct !DISubprogram(name: "foo", scope: !1, file: !1, line: 1, type: !8, isLocal: false, isDefinition: true, scopeLine: 1, isOptimized: true, unit: !0, retainedNodes: !2)
+!8 = !DISubroutineType(types: !2)
+!9 = !DILocation(line: 2, column: 3, scope: !7)