diff options
| -rw-r--r-- | clang/lib/Driver/ToolChains.cpp | 4 | ||||
| -rw-r--r-- | clang/test/Driver/cuda-march.cu | 24 |
2 files changed, 27 insertions, 1 deletions
diff --git a/clang/lib/Driver/ToolChains.cpp b/clang/lib/Driver/ToolChains.cpp index fcc6dfe35d5..5043e53f164 100644 --- a/clang/lib/Driver/ToolChains.cpp +++ b/clang/lib/Driver/ToolChains.cpp @@ -4676,8 +4676,10 @@ CudaToolChain::TranslateArgs(const llvm::opt::DerivedArgList &Args, DAL->append(A); } - if (BoundArch) + if (BoundArch) { + DAL->eraseArg(options::OPT_march_EQ); DAL->AddJoinedArg(nullptr, Opts.getOption(options::OPT_march_EQ), BoundArch); + } return DAL; } diff --git a/clang/test/Driver/cuda-march.cu b/clang/test/Driver/cuda-march.cu new file mode 100644 index 00000000000..e06f70f5358 --- /dev/null +++ b/clang/test/Driver/cuda-march.cu @@ -0,0 +1,24 @@ +// Checks that cuda compilation does the right thing when passed -march. +// (Specifically, we want to pass it to host compilation, but not to device +// compilation or ptxas!) +// +// REQUIRES: clang-driver +// REQUIRES: x86-registered-target +// REQUIRES: nvptx-registered-target + +// RUN: %clang -### -target x86_64-linux-gnu -c -march=haswell %s 2>&1 | FileCheck %s + +// RUN: %clang -### -target x86_64-linux-gnu -c -march=haswell --cuda-gpu-arch=sm_20 %s 2>&1 | \ +// RUN: FileCheck %s + +// CHECK:clang +// CHECK: "-cc1" +// CHECK-SAME: "-triple" "nvptx +// CHECK-SAME: "-target-cpu" "sm_20" + +// CHECK: ptxas +// CHECK-SAME: "--gpu-name" "sm_20" + +// CHECK:clang +// CHECK-SAME: "-cc1" +// CHECK-SAME: "-target-cpu" "haswell" |
