[ThinLTO] Default backend threads to heavyweight_hardware_concurrency

[tejohnson]

Summary

Changes default backend parallelism from thread::hardware_concurrency to
the new llvm::heavyweight_hardware_concurrency, which for X86 Linux
defaults to the number of physical cores (and will fall back to
thread::hardware_concurrency otherwise). This avoid oversubscribing
the physical cores using hyperthreading.

[mehdi_amini]

LGTM.

lib/LTO/LTO.cpp

 #include "llvm/Object/ModuleSummaryIndexObjectFile.h"
 #include "llvm/Support/ManagedStatic.h"
 #include "llvm/Support/MemoryBuffer.h"
 #include "llvm/Support/Path.h"
 #include "llvm/Support/SHA1.h"
 #include "llvm/Support/SourceMgr.h"
 #include "llvm/Support/TargetRegistry.h"
 #include "llvm/Support/ThreadPool.h"
+#include "llvm/Support/Threading.h"
 #include "llvm/Support/raw_ostream.h"
 #include "llvm/Target/TargetMachine.h"
 #include "llvm/Target/TargetOptions.h"
 #include "llvm/Transforms/IPO.h"
 #include "llvm/Transforms/IPO/PassManagerBuilder.h"
 #include "llvm/Transforms/Utils/SplitModule.h"
 
 #include <set>

 
 LTO::RegularLTOState::RegularLTOState(unsigned ParallelCodeGenParallelismLevel,
                                       Config &Conf)
     : ParallelCodeGenParallelismLevel(ParallelCodeGenParallelismLevel),
       Ctx(Conf) {}
 
 LTO::ThinLTOState::ThinLTOState(ThinBackend Backend) : Backend(Backend) {
   if (!Backend)
-    this->Backend = createInProcessThinBackend(thread::hardware_concurrency());
+    this->Backend =
+        createInProcessThinBackend(llvm::heavyweight_hardware_concurrency());
 }
 
 LTO::LTO(Config Conf, ThinBackend Backend,
          unsigned ParallelCodeGenParallelismLevel)
     : Conf(std::move(Conf)),
       RegularLTO(ParallelCodeGenParallelismLevel, this->Conf),
       ThinLTO(std::move(Backend)) {}
 

lib/LTO/ThinLTOCodeGenerator.cpp

 #include "llvm/Object/IRObjectFile.h"
 #include "llvm/Object/ModuleSummaryIndexObjectFile.h"
 #include "llvm/Support/CachePruning.h"
 #include "llvm/Support/Debug.h"
 #include "llvm/Support/Path.h"
 #include "llvm/Support/SHA1.h"
 #include "llvm/Support/TargetRegistry.h"
 #include "llvm/Support/ThreadPool.h"
+#include "llvm/Support/Threading.h"
 #include "llvm/Target/TargetMachine.h"
 #include "llvm/Transforms/IPO.h"
 #include "llvm/Transforms/IPO/FunctionImport.h"
 #include "llvm/Transforms/IPO/Internalize.h"
 #include "llvm/Transforms/IPO/PassManagerBuilder.h"
 #include "llvm/Transforms/ObjCARC.h"
 #include "llvm/Transforms/Utils/FunctionImportUtils.h"
 
 #include <numeric>
 
 using namespace llvm;
 
 #define DEBUG_TYPE "thinlto"
 
 namespace llvm {
 // Flags -discard-value-names, defined in LTOCodeGenerator.cpp
 extern cl::opt<bool> LTODiscardValueNames;
 }
 
 namespace {
 
-static cl::opt<int> ThreadCount("threads",
-                                cl::init(std::thread::hardware_concurrency()));
+static cl::opt<int>
+    ThreadCount("threads", cl::init(llvm::heavyweight_hardware_concurrency()));
 
 static void diagnosticHandler(const DiagnosticInfo &DI) {
   DiagnosticPrinterRawOStream DP(errs());
   DI.print(DP);
   errs() << '\n';
 }
 
 // Simple helper to save temporary files for debug.

tools/gold/gold-plugin.cpp

enum OutputType {
     OT_DISABLE,
     OT_BC_ONLY,
     OT_SAVE_TEMPS
   };
   static OutputType TheOutputType = OT_NORMAL;
   static unsigned OptLevel = 2;
   // Default parallelism of 0 used to indicate that user did not specify.
   // Actual parallelism default value depends on implementation.
-  // Currently only affects ThinLTO, where the default is the
-  // hardware_concurrency.
+  // Currently only affects ThinLTO, where the default is
+  // llvm::heavyweight_hardware_concurrency.
   static unsigned Parallelism = 0;
   // Default regular LTO codegen parallelism (number of partitions).
   static unsigned ParallelCodeGenParallelismLevel = 1;
 #ifdef NDEBUG
   static bool DisableVerify = true;
 #else
   static bool DisableVerify = false;
 #endif

tools/llvm-lto2/llvm-lto2.cpp

 // LTO interface.
 //
 //===----------------------------------------------------------------------===//
 
 #include "llvm/LTO/Caching.h"
 #include "llvm/LTO/LTO.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/TargetSelect.h"
+#include "llvm/Support/Threading.h"
 
 using namespace llvm;
 using namespace lto;
 using namespace object;
 
 static cl::list<std::string> InputFilenames(cl::Positional, cl::OneOrMore,
                                             cl::desc("<input bitcode files>"));
 

 
 static cl::opt<bool>
     ThinLTODistributedIndexes("thinlto-distributed-indexes", cl::init(false),
                               cl::desc("Write out individual index and "
                                        "import files for the "
                                        "distributed backend case"));
 
 static cl::opt<int> Threads("-thinlto-threads",
-                            cl::init(thread::hardware_concurrency()));
+                            cl::init(llvm::heavyweight_hardware_concurrency()));
 
 static cl::list<std::string> SymbolResolutions(
     "r",
     cl::desc("Specify a symbol resolution: filename,symbolname,resolution\n"
              "where \"resolution\" is a sequence (which may be empty) of the\n"
              "following characters:\n"
              " p - prevailing: the linker has chosen this definition of the\n"
              "     symbol\n"