[CUDA] Add option to generate relocatable device code

As a first step, pass '-c/--compile-only' to ptxas so that it
doesn't complain about references to external function. This
will successfully generate object files, but they won't work
at runtime because the registration routines need to adapted.

Differential Revision: https://reviews.llvm.org/D42921

llvm-svn: 324878

3 files changed, 29 insertions, 11 deletions

diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
index 2a8c9c97f55..185270c61ab 100644
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -4658,14 +4658,20 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
     CmdArgs.push_back(Args.MakeArgString(Flags));
   }
 
-  // Host-side cuda compilation receives device-side outputs as Inputs[1...].
-  // Include them with -fcuda-include-gpubinary.
-  if (IsCuda && Inputs.size() > 1)
-    for (auto I = std::next(Inputs.begin()), E = Inputs.end(); I != E; ++I) {
-      CmdArgs.push_back("-fcuda-include-gpubinary");
-      CmdArgs.push_back(I->getFilename());
+  if (IsCuda) {
+    // Host-side cuda compilation receives device-side outputs as Inputs[1...].
+    // Include them with -fcuda-include-gpubinary.
+    if (Inputs.size() > 1) {
+      for (auto I = std::next(Inputs.begin()), E = Inputs.end(); I != E; ++I) {
+        CmdArgs.push_back("-fcuda-include-gpubinary");
+        CmdArgs.push_back(I->getFilename());
+      }
     }
 
+    if (Args.hasFlag(options::OPT_fcuda_rdc, options::OPT_fno_cuda_rdc, false))
+      CmdArgs.push_back("-fcuda-rdc");
+  }
+
   // OpenMP offloading device jobs take the argument -fopenmp-host-ir-file-path
   // to specify the result of the compile phase on the host, so the meaningful
   // device declarations can be identified. Also, -fopenmp-is-device is passed
diff --git a/clang/lib/Driver/ToolChains/Cuda.cpp b/clang/lib/Driver/ToolChains/Cuda.cpp
index e513e818ebf..86a11847e5a 100644
--- a/clang/lib/Driver/ToolChains/Cuda.cpp
+++ b/clang/lib/Driver/ToolChains/Cuda.cpp
@@ -355,11 +355,17 @@ void NVPTX::Assembler::ConstructJob(Compilation &C, const JobAction &JA,
   for (const auto& A : Args.getAllArgValues(options::OPT_Xcuda_ptxas))
     CmdArgs.push_back(Args.MakeArgString(A));
 
-  // In OpenMP we need to generate relocatable code.
-  if (JA.isOffloading(Action::OFK_OpenMP) &&
-      Args.hasFlag(options::OPT_fopenmp_relocatable_target,
-                   options::OPT_fnoopenmp_relocatable_target,
-                   /*Default=*/ true))
+  bool Relocatable = false;
+  if (JA.isOffloading(Action::OFK_OpenMP))
+    // In OpenMP we need to generate relocatable code.
+    Relocatable = Args.hasFlag(options::OPT_fopenmp_relocatable_target,
+                               options::OPT_fnoopenmp_relocatable_target,
+                               /*Default=*/true);
+  else if (JA.isOffloading(Action::OFK_Cuda))
+    Relocatable = Args.hasFlag(options::OPT_fcuda_rdc,
+                               options::OPT_fno_cuda_rdc, /*Default=*/false);
+
+  if (Relocatable)
     CmdArgs.push_back("-c");
 
   const char *Exec;
@@ -540,6 +546,10 @@ void CudaToolChain::addClangTargetOptions(
     if (DriverArgs.hasFlag(options::OPT_fcuda_approx_transcendentals,
                            options::OPT_fno_cuda_approx_transcendentals, false))
       CC1Args.push_back("-fcuda-approx-transcendentals");
+
+    if (DriverArgs.hasFlag(options::OPT_fcuda_rdc, options::OPT_fno_cuda_rdc,
+                           false))
+      CC1Args.push_back("-fcuda-rdc");
   }
 
   if (DriverArgs.hasArg(options::OPT_nocudalib))
diff --git a/clang/lib/Frontend/CompilerInvocation.cpp b/clang/lib/Frontend/CompilerInvocation.cpp
index 95fd1665b40..5b5c24dfc58 100644
--- a/clang/lib/Frontend/CompilerInvocation.cpp
+++ b/clang/lib/Frontend/CompilerInvocation.cpp
@@ -2074,6 +2074,8 @@ static void ParseLangArgs(LangOptions &Opts, ArgList &Args, InputKind IK,
   if (Opts.CUDAIsDevice && Args.hasArg(OPT_fcuda_approx_transcendentals))
     Opts.CUDADeviceApproxTranscendentals = 1;
 
+  Opts.CUDARelocatableDeviceCode = Args.hasArg(OPT_fcuda_rdc);
+
   if (Opts.ObjC1) {
     if (Arg *arg = Args.getLastArg(OPT_fobjc_runtime_EQ)) {
       StringRef value = arg->getValue();