[OpenMP] Customize CUDA-based tool chain selection
Summary: This patch provides a generic way of selecting CUDA based tool chains as host-device pairs.
Reviewers: arpith-jacob, caomhin, carlo.bertolli, ABataev, Hahnfeld, jlebar, hfinkel, tstellar
Reviewed By: Hahnfeld
Subscribers: rengolin, cfe-commits
Differential Revision: https://reviews.llvm.org/D29658
llvm-svn: 307271
diff --git a/clang/lib/Driver/Driver.cpp b/clang/lib/Driver/Driver.cpp
index faced06..8031d78 100644
--- a/clang/lib/Driver/Driver.cpp
+++ b/clang/lib/Driver/Driver.cpp
@@ -572,8 +572,22 @@
if (TT.getArch() == llvm::Triple::UnknownArch)
Diag(clang::diag::err_drv_invalid_omp_target) << Val;
else {
- const ToolChain &TC = getToolChain(C.getInputArgs(), TT);
- C.addOffloadDeviceToolChain(&TC, Action::OFK_OpenMP);
+ const ToolChain *TC;
+ // CUDA toolchains have to be selected differently. They pair host
+ // and device in their implementation.
+ if (TT.isNVPTX()) {
+ const ToolChain *HostTC =
+ C.getSingleOffloadToolChain<Action::OFK_Host>();
+ assert(HostTC && "Host toolchain should be always defined.");
+ auto &CudaTC =
+ ToolChains[TT.str() + "/" + HostTC->getTriple().str()];
+ if (!CudaTC)
+ CudaTC = llvm::make_unique<toolchains::CudaToolChain>(
+ *this, TT, *HostTC, C.getInputArgs());
+ TC = CudaTC.get();
+ } else
+ TC = &getToolChain(C.getInputArgs(), TT);
+ C.addOffloadDeviceToolChain(TC, Action::OFK_OpenMP);
}
}
} else