[LTOs] Allow generation of hotness information

[anemet]

Summary

The flag is passed by the clang driver.

[mehdi_amini]

LGTM, thanks.

lib/LTO/LTOCodeGenerator.cpp

#else
     cl::init(false),
 #endif
     cl::Hidden);
 
 cl::opt<std::string>
     LTORemarksFilename("lto-pass-remarks-output",
                        cl::desc("Output filename for pass remarks"),
                        cl::value_desc("filename"));
+
+cl::opt<bool> LTOPassRemarksWithHotness(
+    "lto-pass-remarks-with-hotness",
+    cl::desc("With PGO, include profile count in optimization remarks"),
+    cl::Hidden);
 }
 
 LTOCodeGenerator::LTOCodeGenerator(LLVMContext &Context)
     : Context(Context), MergedModule(new Module("ld-temp.o", Context)),
       TheLinker(new Linker(*MergedModule)) {
   Context.setDiscardValueNames(LTODiscardValueNames);
   Context.enableDebugTypeODRUniquing();
   initializeLTOPasses();
DiagnosticOutputFile = llvm::make_unique<tool_output_file>(
         LTORemarksFilename, EC, sys::fs::F_None);
     if (EC) {
       emitError(EC.message());
       return false;
     }
     Context.setDiagnosticsOutputFile(
         llvm::make_unique<yaml::Output>(DiagnosticOutputFile->os()));
   }
+
+  if (LTOPassRemarksWithHotness)
+    Context.setDiagnosticHotnessRequested(true);
+
   return true;
 }
 
 void LTOCodeGenerator::finishOptimizationRemarks() {
   if (DiagnosticOutputFile) {
     DiagnosticOutputFile->keep();
     // FIXME: LTOCodeGenerator dtor is not invoked on Darwin
     DiagnosticOutputFile->os().flush();

lib/LTO/ThinLTOCodeGenerator.cpp

 using namespace llvm;
 
 #define DEBUG_TYPE "thinlto"
 
 namespace llvm {
 // Flags -discard-value-names, defined in LTOCodeGenerator.cpp
 extern cl::opt<bool> LTODiscardValueNames;
 extern cl::opt<std::string> LTORemarksFilename;
+extern cl::opt<bool> LTOPassRemarksWithHotness;
 }
 
 namespace {
 
 static cl::opt<int>
     ThreadCount("threads", cl::init(llvm::heavyweight_hardware_concurrency()));
 
 Expected<std::unique_ptr<tool_output_file>>
 setupOptimizationRemarks(LLVMContext &Ctx, int Count) {
+  if (LTOPassRemarksWithHotness)
+    Ctx.setDiagnosticHotnessRequested(true);
+
   if (LTORemarksFilename.empty())
     return nullptr;
 
   std::string FileName =
       LTORemarksFilename + ".thin." + llvm::utostr(Count) + ".yaml";
   std::error_code EC;
   auto DiagnosticOutputFile =
       llvm::make_unique<tool_output_file>(FileName, EC, sys::fs::F_None);

test/LTO/X86/diagnostic-handler-remarks-with-hotness.ll

+; Check that the hotness attribute is included in the optimization record file
+; with -lto-pass-remarks-with-hotness.
+
+; RUN: llvm-as < %s >%t.bc
+; RUN: llvm-lto -lto-pass-remarks-output=%t.yaml \
+; RUN:          -lto-pass-remarks-with-hotness \
+; RUN:          -exported-symbol _func2 \
+; RUN:          -exported-symbol _main -o %t.o %t.bc
+; RUN: cat %t.yaml | FileCheck -check-prefix=YAML %s
+
+; YAML:      --- !Passed
+; YAML-NEXT: Pass:            inline
+; YAML-NEXT: Name:            Inlined
+; YAML-NEXT: Function:        main
+; YAML-NEXT: Hotness:         300
+; YAML-NEXT: Args:
+; YAML-NEXT:   - Callee:          foo
+; YAML-NEXT:   - String:          ' inlined into '
+; YAML-NEXT:   - Caller:          main
+; YAML-NEXT: ...
+
+target triple = "x86_64-apple-darwin"
+
+declare i32 @bar()
+
+define i32 @foo() {
+  %a = call i32 @bar()
+  ret i32 %a
+}
+
+define i32 @main() !prof !0 {
+  %i = call i32 @foo()
+  ret i32 %i
+}
+
+define i32 @func2(i32* %out, i32* %out2, i32* %A, i32* %B, i32* %C, i32* %D, i32* %E, i32* %F) {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.037 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %arrayidx = getelementptr inbounds i32, i32* %A, i64 %i.037
+  %0 = load i32, i32* %arrayidx, align 4
+  %arrayidx1 = getelementptr inbounds i32, i32* %B, i64 %i.037
+  %1 = load i32, i32* %arrayidx1, align 4
+  %add = add nsw i32 %1, %0
+  %arrayidx2 = getelementptr inbounds i32, i32* %C, i64 %i.037
+  %2 = load i32, i32* %arrayidx2, align 4
+  %add3 = add nsw i32 %add, %2
+  %arrayidx4 = getelementptr inbounds i32, i32* %E, i64 %i.037
+  %3 = load i32, i32* %arrayidx4, align 4
+  %add5 = add nsw i32 %add3, %3
+  %arrayidx6 = getelementptr inbounds i32, i32* %F, i64 %i.037
+  %4 = load i32, i32* %arrayidx6, align 4
+  %add7 = add nsw i32 %add5, %4
+  %arrayidx8 = getelementptr inbounds i32, i32* %out, i64 %i.037
+  store i32 %add7, i32* %arrayidx8, align 4
+  %5 = load i32, i32* %arrayidx, align 4
+  %6 = load i32, i32* %arrayidx1, align 4
+  %add11 = add nsw i32 %6, %5
+  %7 = load i32, i32* %arrayidx2, align 4
+  %add13 = add nsw i32 %add11, %7
+  %8 = load i32, i32* %arrayidx4, align 4
+  %add15 = add nsw i32 %add13, %8
+  %9 = load i32, i32* %arrayidx6, align 4
+  %add17 = add nsw i32 %add15, %9
+  %arrayidx18 = getelementptr inbounds i32, i32* %out2, i64 %i.037
+  store i32 %add17, i32* %arrayidx18, align 4
+  %inc = add i64 %i.037, 1
+  %exitcond = icmp eq i64 %inc, 256
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret i32 undef
+}
+
+!0 = !{!"function_entry_count", i64 300}

test/ThinLTO/X86/diagnostic-handler-remarks-with-hotness.ll

+; RUN: opt -module-summary %s -o %t1.bc
+; RUN: opt -module-summary %p/Inputs/diagnostic-handler-remarks.ll -o %t2.bc
+
+; Check that the hotness attribute is included in the optimization record file
+; with -lto-pass-remarks-with-hotness.
+
+; RUN: llvm-lto -thinlto-action=run \
+; RUN:          -lto-pass-remarks-output=%t.yaml \
+; RUN:          -lto-pass-remarks-with-hotness \
+; RUN:          -exported-symbol _func2 \
+; RUN:          -exported-symbol _main %t1.bc %t2.bc 2>&1 | \
+; RUN:     FileCheck %s -allow-empty
+; CHECK-NOT: remark:
+; CHECK-NOT: llvm-lto:
+
+
+; Verify that bar is imported and inlined into foo
+; RUN: cat %t.yaml.thin.0.yaml | FileCheck %s -check-prefix=YAML1
+; YAML1:      --- !Passed
+; YAML1-NEXT: Pass:            inline
+; YAML1-NEXT: Name:            Inlined
+; YAML1-NEXT: Function:        main
+; YAML1-NEXT: Hotness:         50
+; YAML1-NEXT: Args:
+; YAML1-NEXT:   - Callee:          foo
+; YAML1-NEXT:   - String:          ' inlined into '
+; YAML1-NEXT:   - Caller:          main
+; YAML1-NEXT: ...
+
+
+; Verify that bar is imported and inlined into foo
+; RUN: cat %t.yaml.thin.1.yaml | FileCheck %s -check-prefix=YAML2
+; YAML2:      --- !Passed
+; YAML2-NEXT: Pass:            inline
+; YAML2-NEXT: Name:            Inlined
+; YAML2-NEXT: Function:        foo
+; YAML2-NEXT: Args:
+; YAML2-NEXT:   - Callee:          bar
+; YAML2-NEXT:   - String:          ' inlined into '
+; YAML2-NEXT:   - Caller:          foo
+; YAML2-NEXT: ...
+
+
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.11.0"
+
+define i32 @bar() {
+  ret i32 42
+}
+declare i32 @foo()
+define i32 @main() !prof !0 {
+  %i = call i32 @foo()
+  ret i32 %i
+}
+
+!0 = !{!"function_entry_count", i64 50}