def no_cuda_noopt_device_debug : Flag<["--"], "no-cuda-noopt-device-debug">;
def cuda_path_EQ : Joined<["--"], "cuda-path=">, Group<i_Group>,
HelpText<"CUDA installation path">;
-def fopenmp_ptx_EQ : Joined<["--"], "fopenmp-ptx=">, Flags<[DriverOption]>,
- HelpText<"Pass a PTX version +ptxXX, default +ptx42 (for PTX version 4.2) used by OpenMP device offloading.">;
def ptxas_path_EQ : Joined<["--"], "ptxas-path=">, Group<i_Group>,
HelpText<"Path to ptxas (used for compiling CUDA code)">;
def fcuda_flush_denormals_to_zero : Flag<["-"], "fcuda-flush-denormals-to-zero">,
// than LLVM defaults to. Use PTX4.2 which is the PTX version that
// came with CUDA-7.0.
CC1Args.push_back("-target-feature");
-
- if (DeviceOffloadingKind == Action::OFK_OpenMP)
- CC1Args.push_back(
- DriverArgs.getLastArgValue(options::OPT_fopenmp_ptx_EQ,
- "+ptx42").data());
- else
- CC1Args.push_back("+ptx42");
+ CC1Args.push_back("+ptx42");
}
void CudaToolChain::AddCudaIncludeArgs(const ArgList &DriverArgs,
}
StringRef Arch = DAL->getLastArgValue(options::OPT_march_EQ);
- if (Arch.empty()) {
- // Default compute capability for CUDA toolchain is the
- // lowest compute capability supported by the installed
- // CUDA version.
+ if (Arch.empty())
+ // Default compute capability for CUDA toolchain is sm_20.
DAL->AddJoinedArg(nullptr,
- Opts.getOption(options::OPT_march_EQ),
- CudaInstallation.getLowestExistingArch());
- }
+ Opts.getOption(options::OPT_march_EQ), "sm_20");
return DAL;
}
std::string getLibDeviceFile(StringRef Gpu) const {
return LibDeviceMap.lookup(Gpu);
}
- /// \brief Get lowest available compute capability
- /// for which a libdevice library exists.
- std::string getLowestExistingArch() const {
- std::string LibDeviceFile;
- for (auto key : LibDeviceMap.keys()) {
- LibDeviceFile = LibDeviceMap.lookup(key);
- if (!LibDeviceFile.empty())
- return key;
- }
- llvm_unreachable("no libdevice exists.");
- }
};
namespace tools {
/// ###########################################################################
/// Check PTXAS is passed -c flag when offloading to an NVIDIA device using OpenMP.
-// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda %s 2>&1 \
+// 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"
/// ###########################################################################
/// PTXAS is passed -c flag by default when offloading to an NVIDIA device using OpenMP - disable it.
-// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -fnoopenmp-relocatable-target %s 2>&1 \
+// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -fnoopenmp-relocatable-target -save-temps -no-canonical-prefixes %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-PTXAS-NORELO %s
// CHK-PTXAS-NORELO-NOT: ptxas{{.*}}" "-c"
/// PTXAS is passed -c flag by default when offloading to an NVIDIA device using OpenMP
/// Check that the flag is passed when -fopenmp-relocatable-target is used.
-// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -fopenmp-relocatable-target %s 2>&1 \
+// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -fopenmp-relocatable-target -save-temps -no-canonical-prefixes %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-PTXAS-RELO %s
// CHK-PTXAS-RELO: ptxas{{.*}}" "-c"
-
-/// ###########################################################################
-
-/// Check PTXAS is passed the compute capability passed to the driver.
-// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda --fopenmp-ptx=+ptx52 %s 2>&1 \
-// RUN: | FileCheck -check-prefix=CHK-PTXAS-VERSION %s
-
-// CHK-PTXAS-VERSION: clang{{.*}}.bc" {{.*}}"-target-feature" "+ptx52"
-
-/// ###########################################################################
-
-/// Check PTXAS is passed the compute capability passed to the driver.
-// RUN: %clang -### -no-canonical-prefixes -target x86_64-apple-darwin17.0.0 -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda --fopenmp-ptx=+ptx52 %s 2>&1 \
-// RUN: | FileCheck -check-prefix=CHK-PTXAS-DARWIN-VERSION %s
-
-// CHK-PTXAS-DARWIN-VERSION: clang{{.*}}.bc" {{.*}}"-target-feature" "+ptx52"