[ThinLTO] Add dump-summary command to llvm-lto2 tool

[ncharlie]

Summary

[ThinLTO] Add dump-summary command to llvm-lto2 tool

Adds command to dump ThinLTO module summaries in YAML to the llvm-lto2 tool.

[tejohnson]

test/tools/llvm-lto2/X86/dump-summary.ll

2

Rather than repeating this command and piping through egrep, you should run once and pipe through FileCheck (see the other tests in this directory for examples). I.e. pipe through "FileCheck %s", then have several lines prefixed by "CHECK: " to look for the expected output. E.g.:

CHECK: NotEligibleToImport: false

[ncharlie]

Use FileCheck rather than egrep

[ncharlie]

test/tools/llvm-lto2/X86/dump-summary.ll

2

Oh, cool - I saw FileCheck before, but assumed that the 'CHECK' lines had to be outputted throughout the pipeline and couldn't be fed into FileCheck like that. I fixed it.

[davide]

Minor comment, LGTM with that (once your other patch goes in).

tools/llvm-lto2/llvm-lto2.cpp

356–367

Add a comment to this function.

[ncharlie]

Added comment.

[davide]

Teresa, any further comments or we can go ahead and commit Charles' patch?

[davide]

Please hold the press on this one for a bit.
I didn't see @chandlerc / @dblaikie comments on the RFC and they seem to not have been fully addressed.
I guess you may want to continue the discussion there before coming back to this.

test/tools/llvm-lto2/X86/dump-summary.ll

+; RUN: opt -module-summary %s -o %t.o
+; RUN: llvm-lto2 dump-summary %t.o | egrep 'Linkage:\s+0'
+; RUN: llvm-lto2 dump-summary %t.o | egrep 'Live:\s+false'
+; RUN: llvm-lto2 dump-summary %t.o | egrep 'NotEligibleToImport:\s+false'
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+@G = constant i32 2048, align 4
+@a = weak alias i32, i32* @G
+
+define void @boop() {
+  tail call void @afun()
+  ret void
+}
+
+declare void @afun()
+declare void @testtest()

tools/llvm-lto2/llvm-lto2.cpp

 // link-time optimization according to the provided symbol resolutions using the
 // resolution-based LTO interface, and outputs one or more object files.
 //
 // This program is intended to eventually replace llvm-lto which uses the legacy
 // LTO interface.
 //
 //===----------------------------------------------------------------------===//
 
-#include "llvm/LTO/Caching.h"
+#include "llvm/Bitcode/BitcodeReader.h"
 #include "llvm/CodeGen/CommandFlags.h"
 #include "llvm/IR/DiagnosticPrinter.h"
+#include "llvm/IR/ModuleSummaryIndexYAML.h"
+#include "llvm/LTO/Caching.h"
 #include "llvm/LTO/LTO.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/FileSystem.h"
 #include "llvm/Support/TargetSelect.h"
 #include "llvm/Support/Threading.h"
 
 using namespace llvm;
 using namespace lto;

 template <typename T> static T check(ErrorOr<T> E, std::string Msg) {
   if (E)
     return std::move(*E);
   check(E.getError(), Msg);
   return T();
 }
 
 static int usage() {
-  errs() << "Available subcommands: dump-symtab run\n";
+  errs() << "Available subcommands: dump-symtab dump-summary run\n";
   return 1;
 }
 
 static int run(int argc, char **argv) {
   cl::ParseCommandLineOptions(argc, argv, "Resolution-based LTO test harness");
 
   // FIXME: Workaround PR30396 which means that a symbol can appear
   // more than once if it is defined in module-level assembly and
for (StringRef F : make_range(argv + 1, argv + argc)) {
     }
 
     outs() << '\n';
   }
 
   return 0;
 }
 
+static int dumpSummary(int argc, char **argv) {
+  for (StringRef F : make_range(argv + 1, argv + argc)) {
+    std::unique_ptr<MemoryBuffer> MB = check(MemoryBuffer::getFile(F), F);
+    std::unique_ptr<ModuleSummaryIndex> Index =
+        check(getModuleSummaryIndex(*MB), F);
+
+    yaml::Output Out(outs());
+    Out << *Index;
+  }
+
+  return 0;
+}
+
 int main(int argc, char **argv) {
   InitializeAllTargets();
   InitializeAllTargetMCs();
   InitializeAllAsmPrinters();
   InitializeAllAsmParsers();
 
   // FIXME: This should use llvm::cl subcommands, but it isn't currently
   // possible to pass an argument not associated with a subcommand to a
   // subcommand (e.g. -use-new-pm).
   if (argc < 2)
     return usage();
 
   StringRef Subcommand = argv[1];
   // Ensure that argv[0] is correct after adjusting argv/argc.
   argv[1] = argv[0];
   if (Subcommand == "dump-symtab")
     return dumpSymtab(argc - 1, argv + 1);
+  if (Subcommand == "dump-summary")
+    return dumpSummary(argc - 1, argv + 1);
   if (Subcommand == "run")
     return run(argc - 1, argv + 1);
   return usage();
 }