commit ecb178bb356fc058a51bbda0d083068b5d83ba2b
author Artem Belevich <tra@google.com> Wed Mar 21 22:22:59 2018 +0000
committer Artem Belevich <tra@google.com> Wed Mar 21 22:22:59 2018 +0000
tree 8f1e67971ee6bb3575f461000f388531c7a92a8e
parent 1dce44e8e82c09822e843ccd1df3c6c5de7839f4

[CUDA] Disable LTO for device-side compilations.

This fixes host-side LTO during CUDA compilation. Before, LTO
pipeline construction was clashing with CUDA pipeline construction.

At the moment there's no point doing LTO on device side as each
device-side TU is a complete program.  We will need to figure out
compilation pipeline construction for the device-side LTO when we
have working support for multi-TU device-side CUDA compilation.

Differential Revision: https://reviews.llvm.org/D44691

llvm-svn: 328161

clang/lib/Driver/Driver.cpp

diff --git a/clang/lib/Driver/Driver.cpp b/clang/lib/Driver/Driver.cpp
index 4712daf..ad65f6f 100644
--- a/clang/lib/Driver/Driver.cpp
+++ b/clang/lib/Driver/Driver.cpp
@@ -2171,7 +2171,7 @@
               break;
 
             CudaDeviceActions[I] = C.getDriver().ConstructPhaseAction(
-                C, Args, Ph, CudaDeviceActions[I]);
+                C, Args, Ph, CudaDeviceActions[I], Action::OFK_Cuda);
 
             if (Ph == phases::Assemble)
               break;
@@ -3011,8 +3011,9 @@
   Args.ClaimAllArgs(options::OPT_cuda_compile_host_device);
 }
 
-Action *Driver::ConstructPhaseAction(Compilation &C, const ArgList &Args,
-                                     phases::ID Phase, Action *Input) const {
+Action *Driver::ConstructPhaseAction(
+    Compilation &C, const ArgList &Args, phases::ID Phase, Action *Input,
+    Action::OffloadKind TargetDeviceOffloadKind) const {
   llvm::PrettyStackTraceString CrashInfo("Constructing phase actions");
 
   // Some types skip the assembler phase (e.g., llvm-bc), but we can't
@@ -3074,7 +3075,7 @@
     return C.MakeAction<CompileJobAction>(Input, types::TY_LLVM_BC);
   }
   case phases::Backend: {
-    if (isUsingLTO()) {
+    if (isUsingLTO() && TargetDeviceOffloadKind == Action::OFK_None) {
       types::ID Output =
           Args.hasArg(options::OPT_S) ? types::TY_LTO_IR : types::TY_LTO_BC;
       return C.MakeAction<BackendJobAction>(Input, Output);

clang/lib/Driver/ToolChains/Clang.cpp

diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
index a1feb3a..a86c537 100644
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -3249,7 +3249,11 @@
     if (JA.getType() == types::TY_LLVM_BC)
       CmdArgs.push_back("-emit-llvm-uselists");
 
-    if (D.isUsingLTO()) {
+    // Device-side jobs do not support LTO.
+    bool isDeviceOffloadAction = !(JA.isDeviceOffloading(Action::OFK_None) ||
+                                   JA.isDeviceOffloading(Action::OFK_Host));
+
+    if (D.isUsingLTO() && !isDeviceOffloadAction) {
       Args.AddLastArg(CmdArgs, options::OPT_flto, options::OPT_flto_EQ);
 
       // The Darwin and PS4 linkers currently use the legacy LTO API, which