diff options
| -rw-r--r-- | clang/lib/Driver/ToolChains/Cuda.cpp | 4 | ||||
| -rw-r--r-- | clang/test/Driver/openmp-offload.c | 8 |
2 files changed, 12 insertions, 0 deletions
diff --git a/clang/lib/Driver/ToolChains/Cuda.cpp b/clang/lib/Driver/ToolChains/Cuda.cpp index 70f472fb025..927704a6857 100644 --- a/clang/lib/Driver/ToolChains/Cuda.cpp +++ b/clang/lib/Driver/ToolChains/Cuda.cpp @@ -291,6 +291,10 @@ 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)) + CmdArgs.push_back("-c"); + const char *Exec; if (Arg *A = Args.getLastArg(options::OPT_ptxas_path_EQ)) Exec = A->getValue(); diff --git a/clang/test/Driver/openmp-offload.c b/clang/test/Driver/openmp-offload.c index 37a86aba942..527856d440d 100644 --- a/clang/test/Driver/openmp-offload.c +++ b/clang/test/Driver/openmp-offload.c @@ -669,3 +669,11 @@ // CHK-TWOCUBIN: clang-offload-bundler" "-type=o" "{{.*}}inputs={{.*}}tmp1.o" "-outputs={{.*}}.o,{{.*}}tmp1-openmp-nvptx64-nvidia-cuda.cubin" "-unbundle" // CHK-TWOCUBIN-NEXT: clang-offload-bundler" "-type=o" "{{.*}}inputs={{.*}}tmp2.o" "-outputs={{.*}}.o,{{.*}}tmp2-openmp-nvptx64-nvidia-cuda.cubin" "-unbundle" // CHK-TWOCUBIN-NEXT: nvlink" "-o" "{{.*}}-openmp-nvptx64-nvidia-cuda" {{.*}} "openmp-offload.c.tmp1-openmp-nvptx64-nvidia-cuda.cubin" "openmp-offload.c.tmp2-openmp-nvptx64-nvidia-cuda.cubin" + +/// ########################################################################### + +/// Check PTXAS is passed -c flag when offloading to an NVIDIA device using OpenMP. +// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -no-canonical-prefixes %s 2>&1 \ +// RUN: | FileCheck -check-prefix=CHK-PTXAS-DEFAULT %s + +// CHK-PTXAS-DEFAULT: ptxas{{.*}}" "-c" |
