[LTO] Add -flto-jobs=N to control backend parallelism

Summary:
Currently, a linker option must be used to control the backend
parallelism of ThinLTO. The linker option varies depending on the
linker (e.g. gold vs ld64). Add a new clang option -flto-jobs=N
to control this.

I've added in the wiring to pass this to the gold plugin. I also
added in the logic to pass this down in the form I understand that
ld64 uses on MacOS, for the darwin target.

Reviewers: mehdi_amini, dexonsmith

Subscribers: mehdi_amini, cfe-commits

Differential Revision: https://reviews.llvm.org/D24826

llvm-svn: 282291

diff --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td
index ebb54b7f714dba340d3148bfe04d6e51318cbe8d..d017b0b1b2d103a444d95552467171030d7bb5f6 100644 (file)
--- a/clang/include/clang/Driver/Options.td
+++ b/clang/include/clang/Driver/Options.td
@@ -812,6 +812,11 @@ def flto : Flag<["-"], "flto">, Flags<[CC1Option]>, Group<f_Group>,
   HelpText<"Enable LTO in 'full' mode">;
 def fno_lto : Flag<["-"], "fno-lto">, Group<f_Group>,
   HelpText<"Disable LTO mode (default)">;
+def flto_jobs_EQ : Joined<["-"], "flto-jobs=">,
+  Flags<[CC1Option]>, Group<f_Group>,
+  HelpText<"Controls the backend parallelism of -flto=thin (default "
+           "of 0 means the number of threads will be derived from "
+           "the number of CPUs detected)">;
 def fthinlto_index_EQ : Joined<["-"], "fthinlto-index=">,
   Flags<[CC1Option]>, Group<f_Group>,
   HelpText<"Perform ThinLTO importing using provided function summary index">;

diff --git a/clang/lib/Driver/Tools.cpp b/clang/lib/Driver/Tools.cpp
index f6302225d5b7ab86051f8fcedc4be1f62edd80a5..d212af42cf1f5827e664a4a698e4d2710deeb0fd 100644 (file)
--- a/clang/lib/Driver/Tools.cpp
+++ b/clang/lib/Driver/Tools.cpp
@@ -1998,8 +1998,19 @@ static std::string getCPUName(const ArgList &Args, const llvm::Triple &T,
   }
 }
 
+static unsigned getLTOParallelism(const ArgList &Args, const Driver &D) {
+  unsigned Parallelism = 0;
+  Arg *LtoJobsArg = Args.getLastArg(options::OPT_flto_jobs_EQ);
+  if (LtoJobsArg &&
+      StringRef(LtoJobsArg->getValue()).getAsInteger(10, Parallelism))
+    D.Diag(diag::err_drv_invalid_int_value) << LtoJobsArg->getAsString(Args)
+                                            << LtoJobsArg->getValue();
+  return Parallelism;
+}
+
 static void AddGoldPlugin(const ToolChain &ToolChain, const ArgList &Args,
-                          ArgStringList &CmdArgs, bool IsThinLTO) {
+                          ArgStringList &CmdArgs, bool IsThinLTO,
+                          const Driver &D) {
   // Tell the linker to load the plugin. This has to come before AddLinkerInputs
   // as gold requires -plugin to come before any -plugin-opt that -Wl might
   // forward.
@@ -2032,6 +2043,10 @@ static void AddGoldPlugin(const ToolChain &ToolChain, const ArgList &Args,
   if (IsThinLTO)
     CmdArgs.push_back("-plugin-opt=thinlto");
 
+  if (unsigned Parallelism = getLTOParallelism(Args, D))
+    CmdArgs.push_back(Args.MakeArgString(Twine("-plugin-opt=jobs=") +
+                                         std::to_string(Parallelism)));
+
   // If an explicit debugger tuning argument appeared, pass it along.
   if (Arg *A = Args.getLastArg(options::OPT_gTune_Group,
                                options::OPT_ggdbN_Group)) {
@@ -7639,7 +7654,7 @@ void cloudabi::Linker::ConstructJob(Compilation &C, const JobAction &JA,
                    options::OPT_t, options::OPT_Z_Flag, options::OPT_r});
 
   if (D.isUsingLTO())
-    AddGoldPlugin(ToolChain, Args, CmdArgs, D.getLTOMode() == LTOK_Thin);
+    AddGoldPlugin(ToolChain, Args, CmdArgs, D.getLTOMode() == LTOK_Thin, D);
 
   AddLinkerInputs(ToolChain, Inputs, Args, CmdArgs);
 
@@ -8060,6 +8075,13 @@ void darwin::Linker::ConstructJob(Compilation &C, const JobAction &JA,
 
   getMachOToolChain().addProfileRTLibs(Args, CmdArgs);
 
+  if (unsigned Parallelism =
+          getLTOParallelism(Args, getToolChain().getDriver())) {
+    CmdArgs.push_back("-mllvm");
+    CmdArgs.push_back(
+        Args.MakeArgString(Twine("-threads=") + std::to_string(Parallelism)));
+  }
+
   if (!Args.hasArg(options::OPT_nostdlib, options::OPT_nodefaultlibs)) {
     if (getToolChain().getDriver().CCCIsCXX())
       getToolChain().AddCXXStdlibLibArgs(Args, CmdArgs);
@@ -8790,7 +8812,7 @@ void freebsd::Linker::ConstructJob(Compilation &C, const JobAction &JA,
   Args.AddAllArgs(CmdArgs, options::OPT_r);
 
   if (D.isUsingLTO())
-    AddGoldPlugin(ToolChain, Args, CmdArgs, D.getLTOMode() == LTOK_Thin);
+    AddGoldPlugin(ToolChain, Args, CmdArgs, D.getLTOMode() == LTOK_Thin, D);
 
   bool NeedsSanitizerDeps = addSanitizerRuntimes(ToolChain, Args, CmdArgs);
   AddLinkerInputs(ToolChain, Inputs, Args, CmdArgs);
@@ -9623,7 +9645,7 @@ void gnutools::Linker::ConstructJob(Compilation &C, const JobAction &JA,
   ToolChain.AddFilePathLibArgs(Args, CmdArgs);
 
   if (D.isUsingLTO())
-    AddGoldPlugin(ToolChain, Args, CmdArgs, D.getLTOMode() == LTOK_Thin);
+    AddGoldPlugin(ToolChain, Args, CmdArgs, D.getLTOMode() == LTOK_Thin, D);
 
   if (Args.hasArg(options::OPT_Z_Xlinker__no_demangle))
     CmdArgs.push_back("--no-demangle");

diff --git a/clang/test/Driver/lto-jobs.c b/clang/test/Driver/lto-jobs.c
new file mode 100644 (file)
index 0000000..5398677
--- /dev/null
+++ b/clang/test/Driver/lto-jobs.c
@@ -0,0 +1,11 @@
+// Confirm that -flto-jobs=N is passed to linker
+
+// RUN: %clang -target x86_64-unknown-linux -### %s -flto=thin -flto-jobs=5 2> %t
+// RUN: FileCheck -check-prefix=CHECK-LINK-THIN-JOBS-ACTION < %t %s
+//
+// CHECK-LINK-THIN-JOBS-ACTION: "-plugin-opt=jobs=5"
+
+// RUN: %clang -target x86_64-apple-darwin13.3.0 -### %s -flto=thin -flto-jobs=5 2> %t
+// RUN: FileCheck -check-prefix=CHECK-LINK-THIN-JOBS2-ACTION < %t %s
+//
+// CHECK-LINK-THIN-JOBS2-ACTION: "-mllvm" "-threads=5"