Exec, CmdArgs, Inputs, Output));
}
+void NVPTX::getNVPTXTargetFeatures(const Driver &D, const llvm::Triple &Triple,
+ const llvm::opt::ArgList &Args,
+ std::vector<StringRef> &Features,
+ Optional<clang::CudaVersion> CudaVersion) {
+ if (!CudaVersion) {
+ CudaInstallationDetector CudaInstallation(D, Triple, Args);
+ CudaVersion = CudaInstallation.version();
+ }
+
+ // New CUDA versions often introduce new instructions that are only supported
+ // by new PTX version, so we need to raise PTX level to enable them in NVPTX
+ // back-end.
+ const char *PtxFeature = nullptr;
+ switch (*CudaVersion) {
+#define CASE_CUDA_VERSION(CUDA_VER, PTX_VER) \
+ case CudaVersion::CUDA_##CUDA_VER: \
+ PtxFeature = "+ptx" #PTX_VER; \
+ break;
+ CASE_CUDA_VERSION(115, 75);
+ CASE_CUDA_VERSION(114, 74);
+ CASE_CUDA_VERSION(113, 73);
+ CASE_CUDA_VERSION(112, 72);
+ CASE_CUDA_VERSION(111, 71);
+ CASE_CUDA_VERSION(110, 70);
+ CASE_CUDA_VERSION(102, 65);
+ CASE_CUDA_VERSION(101, 64);
+ CASE_CUDA_VERSION(100, 63);
+ CASE_CUDA_VERSION(92, 61);
+ CASE_CUDA_VERSION(91, 61);
+ CASE_CUDA_VERSION(90, 60);
+#undef CASE_CUDA_VERSION
+ default:
+ PtxFeature = "+ptx42";
+ }
+ Features.push_back(PtxFeature);
+}
+
/// CUDA toolchain. Our assembler is ptxas, and our "linker" is fatbinary,
/// which isn't properly a linker but nonetheless performs the step of stitching
/// together object files from the assembler into a single blob.
clang::CudaVersion CudaInstallationVersion = CudaInstallation.version();
- // New CUDA versions often introduce new instructions that are only supported
- // by new PTX version, so we need to raise PTX level to enable them in NVPTX
- // back-end.
- const char *PtxFeature = nullptr;
- switch (CudaInstallationVersion) {
-#define CASE_CUDA_VERSION(CUDA_VER, PTX_VER) \
- case CudaVersion::CUDA_##CUDA_VER: \
- PtxFeature = "+ptx" #PTX_VER; \
- break;
- CASE_CUDA_VERSION(115, 75);
- CASE_CUDA_VERSION(114, 74);
- CASE_CUDA_VERSION(113, 73);
- CASE_CUDA_VERSION(112, 72);
- CASE_CUDA_VERSION(111, 71);
- CASE_CUDA_VERSION(110, 70);
- CASE_CUDA_VERSION(102, 65);
- CASE_CUDA_VERSION(101, 64);
- CASE_CUDA_VERSION(100, 63);
- CASE_CUDA_VERSION(92, 61);
- CASE_CUDA_VERSION(91, 61);
- CASE_CUDA_VERSION(90, 60);
-#undef CASE_CUDA_VERSION
- default:
- PtxFeature = "+ptx42";
- }
- CC1Args.append({"-target-feature", PtxFeature});
+ std::vector<StringRef> Features;
+ NVPTX::getNVPTXTargetFeatures(getDriver(), getTriple(), DriverArgs, Features,
+ CudaInstallationVersion);
+ for (StringRef PtxFeature : Features)
+ CC1Args.append({"-target-feature", DriverArgs.MakeArgString(PtxFeature)});
if (DriverArgs.hasFlag(options::OPT_fcuda_short_ptr,
options::OPT_fno_cuda_short_ptr, false))
CC1Args.append({"-mllvm", "--nvptx-short-ptr"});