[Flang][Driver] Emit module summary for Full LTO (llvm#164302)

This PR enables module summary for Full LTO. Module summaries are
enabled by default for Full LTO in clang, this change makes the flang
behaviour consistent. Reference PR: https://reviews.llvm.org/D34156

Author: anchuraj

flang/lib/Frontend/FrontendActions.cpp

@@ -1019,24 +1019,40 @@ void CodeGenAction::runOptimizationPipeline(llvm::raw_pwrite_stream &os) {
 
   // Create the pass manager.
   llvm::ModulePassManager mpm;
-  if (opts.PrepareForFatLTO) {
-    // The module summary should be emitted by default for regular LTO
-    // except for ld64 targets.
-    bool emitSummary = opts.PrepareForThinLTO || opts.PrepareForFullLTO ||
-                       triple.getVendor() != llvm::Triple::Apple;
+  // The module summary should be emitted by default for regular LTO
+  // except for ld64 targets.
+  bool emitSummary =
+      opts.PrepareForFullLTO && (triple.getVendor() != llvm::Triple::Apple);
+  if (opts.PrepareForFatLTO)
     mpm = pb.buildFatLTODefaultPipeline(level, opts.PrepareForThinLTO,
                                         emitSummary);
-  } else if (opts.PrepareForFullLTO)
+  else if (opts.PrepareForFullLTO)
     mpm = pb.buildLTOPreLinkDefaultPipeline(level);
   else if (opts.PrepareForThinLTO)
     mpm = pb.buildThinLTOPreLinkDefaultPipeline(level);
   else
     mpm = pb.buildPerModuleDefaultPipeline(level);
 
-  if (action == BackendActionTy::Backend_EmitBC)
-    mpm.addPass(llvm::BitcodeWriterPass(os));
-  else if (action == BackendActionTy::Backend_EmitLL)
-    mpm.addPass(llvm::PrintModulePass(os));
+  if (action == BackendActionTy::Backend_EmitBC ||
+      action == BackendActionTy::Backend_EmitLL || opts.PrepareForFatLTO) {
+    if (opts.PrepareForThinLTO) {
+      // TODO: ThinLTO module summary support is yet to be enabled.
+      if (action == BackendActionTy::Backend_EmitBC)
+        mpm.addPass(llvm::BitcodeWriterPass(os));
+      else if (action == BackendActionTy::Backend_EmitLL)
+        mpm.addPass(llvm::PrintModulePass(os));
+    } else {
+      if (emitSummary && !llvmModule->getModuleFlag("ThinLTO"))
+        llvmModule->addModuleFlag(llvm::Module::Error, "ThinLTO", uint32_t(0));
+      if (action == BackendActionTy::Backend_EmitBC)
+        mpm.addPass(llvm::BitcodeWriterPass(
+            os, /*ShouldPreserveUseListOrder=*/false, emitSummary));
+      else if (action == BackendActionTy::Backend_EmitLL)
+        mpm.addPass(llvm::PrintModulePass(os, /*Banner=*/"",
+                                          /*ShouldPreserveUseListOrder=*/false,
+                                          emitSummary));
+    }
+  }
 
   // FIXME: This should eventually be replaced by a first-class driver option.
   // This should be done for both flang and clang simultaneously.

flang/test/CMakeLists.txt

@@ -72,6 +72,7 @@ if (NOT FLANG_STANDALONE_BUILD)
     FileCheck
     count
     not
+    llvm-bcanalyzer
     llvm-dis
     llvm-objcopy
     llvm-objdump

flang/test/Driver/lto-bc.f90

@@ -1,21 +1,35 @@
 ! Test that the output is LLVM bitcode for LTO and not a native objectfile by
-! disassembling it to LLVM IR.
-! Right now there is nothing special about it and it is similar to non-lto IR,
-! more work is needed to add things like module summaries.
+! disassembling it to LLVM IR. Also tests that module summaries are emitted for LTO
 
 ! RUN: %flang %s -c -o - | not llvm-dis -o %t
 ! RUN: %flang_fc1 %s -emit-llvm-bc -o - | llvm-dis -o - | FileCheck %s
-
-! RUN: %flang -flto %s -c -o - | llvm-dis -o - | FileCheck %s
-! RUN: %flang -flto=thin %s -c -o - | llvm-dis -o - | FileCheck %s
-
 ! CHECK: define void @_QQmain()
 ! CHECK-NEXT:  ret void
 ! CHECK-NEXT: }
+! CHECK-NOT: !{{.*}} = !{i32 1, !"ThinLTO", i32 0}
+! CHECK-NOT: ^{{.*}} = module:
+! CHECK-NOT: ^{{.*}} = gv: (name:
+! CHECK-NOT: ^{{.*}} = blockcount:
+
+! RUN: %flang -flto=thin %s -c -o - | llvm-dis -o - | FileCheck %s --check-prefix=THIN
+! THIN: define void @_QQmain()
+! THIN-NEXT:  ret void
+! THIN-NEXT: }
+! THIN-NOT: !{{.*}} = !{i32 1, !"ThinLTO", i32 0}
+! THIN-NOT: ^{{.*}} = module:
+! THIN-NOT: ^{{.*}} = gv: (name:
+! THIN-NOT: ^{{.*}} = blockcount:
 
-! CHECK-NOT: ^0 = module:
-! CHECK-NOT: ^1 = gv: (name:
-! CHECK-NOT: ^2 = flags:
-! CHECK-NOT: ^3 = blockcount:
+! RUN: %flang -flto %s -c -o - | llvm-dis -o - | FileCheck %s --check-prefix=FULL
+! FULL: define void @_QQmain()
+! FULL-NEXT:  ret void
+! FULL-NEXT: }
+! FULL: !{{.*}} = !{i32 1, !"ThinLTO", i32 0}
+! FULL: ^{{.*}} = module:
+! FULL: ^{{.*}} = gv: (name:
+! FULL: ^{{.*}} = blockcount:
 
+! RUN: %flang_fc1 -flto -emit-llvm-bc %s -o - | llvm-bcanalyzer -dump| FileCheck --check-prefix=MOD-SUMM %s
+! MOD-SUMM: FULL_LTO_GLOBALVAL_SUMMARY_BLOCK
+program main
 end program