From: Rui Ueyama <ruiu@google.com>
Date: Fri, 11 Mar 2016 04:23:12 +0000 (+0000)
Subject: ELF: Add --thread option and partially parallelize writeTo().
X-Git-Tag: llvmorg-3.9.0-rc1~12018
X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=e98095026f2ca2466e24df8727fb56677ecab649;p=platform%2Fupstream%2Fllvm.git

ELF: Add --thread option and partially parallelize writeTo().

This patch adds --thread option and use parallel_for_each to write
sections in regular OutputSections.

This is the first patch to use more than one threads.

Note that --thread is off by default because it is experimental.
At this moment I still want to focus on single thread performance
because multi-threading is not a magic wand to fix performance
problems after all. It is generally very hard to make a slow program
faster by threads. Therefore, I want to make the linker as efficient
as possible first and then look for opportunity to make it even faster
using more than one core.

Here are some numbers to link programs with and without --threads
and using GNU gold. Numbers are in seconds.

Clang
  w/o --threads 0.697
  w --threads   0.528
  gold          1.643

Scylla
  w/o --threads 5.032
  w --threads   4.935
  gold          6.791

GNU gold
  w/o --threads 0.550
  w --threads   0.551
  gold          0.737

I limited the number of cores these processes can use to 4 using
perf command, so although my machine has 20 physical cores, the
performance gain I observed should be reproducible with a machine
which is not as beefy as mine.

llvm-svn: 263190
---

diff --git a/lld/ELF/Config.h b/lld/ELF/Config.h
index 273b756..aeaa0f9 100644
--- a/lld/ELF/Config.h
+++ b/lld/ELF/Config.h
@@ -74,6 +74,7 @@ struct Configuration {
   bool Static = false;
   bool StripAll;
   bool SysvHash = true;
+  bool Threads;
   bool Verbose;
   bool ZExecStack;
   bool ZNodelete;
diff --git a/lld/ELF/Driver.cpp b/lld/ELF/Driver.cpp
index 8fff516..064938a 100644
--- a/lld/ELF/Driver.cpp
+++ b/lld/ELF/Driver.cpp
@@ -239,6 +239,7 @@ void LinkerDriver::readConfigs(opt::InputArgList &Args) {
   Config->SaveTemps = Args.hasArg(OPT_save_temps);
   Config->Shared = Args.hasArg(OPT_shared);
   Config->StripAll = Args.hasArg(OPT_strip_all);
+  Config->Threads = Args.hasArg(OPT_threads);
   Config->Verbose = Args.hasArg(OPT_verbose);
 
   Config->DynamicLinker = getString(Args, OPT_dynamic_linker);
diff --git a/lld/ELF/Options.td b/lld/ELF/Options.td
index 24e9841..c11cb94 100644
--- a/lld/ELF/Options.td
+++ b/lld/ELF/Options.td
@@ -118,6 +118,8 @@ def strip_all : Flag<["--"], "strip-all">,
 def sysroot : Joined<["--"], "sysroot=">,
   HelpText<"Set the system root">;
 
+def threads : Joined<["--"], "threads">;
+
 def undefined : Joined<["--"], "undefined=">,
   HelpText<"Force undefined symbol during linking">;
 
diff --git a/lld/ELF/OutputSections.cpp b/lld/ELF/OutputSections.cpp
index 7970566..d9c0d16 100644
--- a/lld/ELF/OutputSections.cpp
+++ b/lld/ELF/OutputSections.cpp
@@ -12,6 +12,7 @@
 #include "LinkerScript.h"
 #include "SymbolTable.h"
 #include "Target.h"
+#include "lld/Core/Parallel.h"
 #include "llvm/Support/Dwarf.h"
 #include "llvm/Support/MathExtras.h"
 #include <map>
@@ -929,8 +930,13 @@ template <class ELFT> void OutputSection<ELFT>::writeTo(uint8_t *Buf) {
   ArrayRef<uint8_t> Filler = Script->getFiller(this->Name);
   if (!Filler.empty())
     fill(Buf, this->getSize(), Filler);
-  for (InputSection<ELFT> *C : Sections)
-    C->writeTo(Buf);
+  if (Config->Threads) {
+    parallel_for_each(Sections.begin(), Sections.end(),
+                      [=](InputSection<ELFT> *C) { C->writeTo(Buf); });
+  } else {
+    for (InputSection<ELFT> *C : Sections)
+      C->writeTo(Buf);
+  }
 }
 
 template <class ELFT>