From 642c8d35755887b2c06cb589371c0c13b3530ad7 Mon Sep 17 00:00:00 2001
From: Xin Tong <trent.xin.tong@gmail.com>
Date: Thu, 15 Nov 2018 18:06:42 +0000
Subject: [PATCH] [LTO] Load sample profile in LTO link step.

Summary:
Load sample profile in LTO link step.
ThinLTO calls populateModulePassManager to load the profile

Reviewers: tejohnson, davidxl, danielcdh

Subscribers: mehdi_amini, inglorion, steven_wu, dexonsmith, llvm-commits

Differential Revision: https://reviews.llvm.org/D54564

llvm-svn: 346971
---
 llvm/lib/Passes/PassBuilder.cpp                    |  7 ++++
 llvm/lib/Transforms/IPO/PassManagerBuilder.cpp     |  6 +++
 .../LTO/Resolution/X86/load-sample-prof-lto.ll     | 46 ++++++++++++++++++++++
 3 files changed, 59 insertions(+)
 create mode 100644 llvm/test/LTO/Resolution/X86/load-sample-prof-lto.ll

diff --git a/llvm/lib/Passes/PassBuilder.cpp b/llvm/lib/Passes/PassBuilder.cpp
index 33f74cf..d6c6413 100644
--- a/llvm/lib/Passes/PassBuilder.cpp
+++ b/llvm/lib/Passes/PassBuilder.cpp
@@ -1004,6 +1004,13 @@ PassBuilder::buildLTODefaultPipeline(OptimizationLevel Level, bool DebugLogging,
   assert(Level != O0 && "Must request optimizations for the default pipeline!");
   ModulePassManager MPM(DebugLogging);
 
+  if (PGOOpt && !PGOOpt->SampleProfileFile.empty()) {
+    // Load sample profile before running the LTO optimization pipeline.
+    MPM.addPass(SampleProfileLoaderPass(PGOOpt->SampleProfileFile,
+                                        PGOOpt->ProfileRemappingFile,
+                                        false /* ThinLTOPhase::PreLink */));
+  }
+
   // Remove unused virtual tables to improve the quality of code generated by
   // whole-program devirtualization and bitset lowering.
   MPM.addPass(GlobalDCEPass());
diff --git a/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp b/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
index 19ff2a2..4a6b4aa 100644
--- a/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
+++ b/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
@@ -747,6 +747,12 @@ void PassManagerBuilder::populateModulePassManager(
 }
 
 void PassManagerBuilder::addLTOOptimizationPasses(legacy::PassManagerBase &PM) {
+  // Load sample profile before running the LTO optimization pipeline.
+  if (!PGOSampleUse.empty()) {
+    PM.add(createPruneEHPass());
+    PM.add(createSampleProfileLoaderPass(PGOSampleUse));
+  }
+
   // Remove unused virtual tables to improve the quality of code generated by
   // whole-program devirtualization and bitset lowering.
   PM.add(createGlobalDCEPass());
diff --git a/llvm/test/LTO/Resolution/X86/load-sample-prof-lto.ll b/llvm/test/LTO/Resolution/X86/load-sample-prof-lto.ll
new file mode 100644
index 0000000..bdf4f08
--- /dev/null
+++ b/llvm/test/LTO/Resolution/X86/load-sample-prof-lto.ll
@@ -0,0 +1,46 @@
+; Test that LTO pipeline loads profile.
+;
+; RUN: opt < %s -o %t.bc
+
+; Run the old pm LTO pipeline.
+; RUN: llvm-lto2 run -o %t.out %t.bc -save-temps \
+; RUN:   -r %t.bc,foo,px -r %t.bc,bar,x \
+; RUN:   -lto-sample-profile-file=%S/Inputs/load-sample-prof.prof
+; RUN: llvm-dis %t.out.0.4.opt.bc -o - | FileCheck %s
+
+; Run the new pm LTO pipeline.
+; RUN: llvm-lto2 run -o %t.out %t.bc -save-temps -use-new-pm \
+; RUN:   -r %t.bc,foo,px -r %t.bc,bar,x \
+; RUN:   -lto-sample-profile-file=%S/Inputs/load-sample-prof.prof
+; RUN: llvm-dis %t.out.0.4.opt.bc -o - | FileCheck %s
+
+; Make sure profile information is attached.
+; CHECK: !prof
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+define void @foo() local_unnamed_addr !dbg !7 {
+entry:
+  tail call void @bar(), !dbg !10
+  ret void, !dbg !11
+}
+
+declare void @bar() local_unnamed_addr
+
+!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 6.0.0 ", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug, enums: !2)
+!1 = !DIFile(filename: "test.c", directory: "/tmp")
+!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 6.0.0 "}
+!7 = distinct !DISubprogram(name: "foo", scope: !1, file: !1, line: 3, type: !8, isLocal: false, isDefinition: true, scopeLine: 3, isOptimized: true, unit: !0, retainedNodes: !2)
+!8 = !DISubroutineType(types: !9)
+!9 = !{null}
+!10 = !DILocation(line: 4, column: 5, scope: !7)
+!11 = !DILocation(line: 5, column: 1, scope: !7)
-- 
2.7.4