aboutsummaryrefslogtreecommitdiff
path: root/contrib/llvm-project/clang/lib/Driver/ToolChains/Cuda.cpp
diff options
context:
space:
mode:
Diffstat (limited to 'contrib/llvm-project/clang/lib/Driver/ToolChains/Cuda.cpp')
-rw-r--r--contrib/llvm-project/clang/lib/Driver/ToolChains/Cuda.cpp102
1 files changed, 52 insertions, 50 deletions
diff --git a/contrib/llvm-project/clang/lib/Driver/ToolChains/Cuda.cpp b/contrib/llvm-project/clang/lib/Driver/ToolChains/Cuda.cpp
index ffc606dd554b..d14776c5f5ba 100644
--- a/contrib/llvm-project/clang/lib/Driver/ToolChains/Cuda.cpp
+++ b/contrib/llvm-project/clang/lib/Driver/ToolChains/Cuda.cpp
@@ -326,13 +326,13 @@ void CudaInstallationDetector::AddCudaIncludeArgs(
void CudaInstallationDetector::CheckCudaVersionSupportsArch(
CudaArch Arch) const {
if (Arch == CudaArch::UNKNOWN || Version == CudaVersion::UNKNOWN ||
- ArchsWithBadVersion.count(Arch) > 0)
+ ArchsWithBadVersion[(int)Arch])
return;
auto MinVersion = MinVersionForCudaArch(Arch);
auto MaxVersion = MaxVersionForCudaArch(Arch);
if (Version < MinVersion || Version > MaxVersion) {
- ArchsWithBadVersion.insert(Arch);
+ ArchsWithBadVersion[(int)Arch] = true;
D.Diag(diag::err_drv_cuda_version_unsupported)
<< CudaArchToString(Arch) << CudaVersionToString(MinVersion)
<< CudaVersionToString(MaxVersion) << InstallPath
@@ -384,7 +384,7 @@ static DeviceDebugInfoLevel mustEmitDebugInfo(const ArgList &Args) {
}
return IsDebugEnabled ? EmitSameDebugInfoAsHost : DebugDirectivesOnly;
}
- return DisableDebugInfo;
+ return willEmitRemarks(Args) ? DebugDirectivesOnly : DisableDebugInfo;
}
void NVPTX::Assembler::ConstructJob(Compilation &C, const JobAction &JA,
@@ -494,7 +494,7 @@ void NVPTX::Assembler::ConstructJob(Compilation &C, const JobAction &JA,
JA, *this,
ResponseFileSupport{ResponseFileSupport::RF_Full, llvm::sys::WEM_UTF8,
"--options-file"},
- Exec, CmdArgs, Inputs));
+ Exec, CmdArgs, Inputs, Output));
}
static bool shouldIncludePTX(const ArgList &Args, const char *gpu_arch) {
@@ -563,7 +563,7 @@ void NVPTX::Linker::ConstructJob(Compilation &C, const JobAction &JA,
JA, *this,
ResponseFileSupport{ResponseFileSupport::RF_Full, llvm::sys::WEM_UTF8,
"--options-file"},
- Exec, CmdArgs, Inputs));
+ Exec, CmdArgs, Inputs, Output));
}
void NVPTX::OpenMPLinker::ConstructJob(Compilation &C, const JobAction &JA,
@@ -600,11 +600,6 @@ void NVPTX::OpenMPLinker::ConstructJob(Compilation &C, const JobAction &JA,
CmdArgs.push_back("-arch");
CmdArgs.push_back(Args.MakeArgString(GPUArch));
- // Assume that the directory specified with --libomptarget_nvptx_path
- // contains the static library libomptarget-nvptx.a.
- if (const Arg *A = Args.getLastArg(options::OPT_libomptarget_nvptx_path_EQ))
- CmdArgs.push_back(Args.MakeArgString(Twine("-L") + A->getValue()));
-
// Add paths specified in LIBRARY_PATH environment variable as -L options.
addDirectoryList(Args, CmdArgs, "-L", "LIBRARY_PATH");
@@ -614,9 +609,6 @@ void NVPTX::OpenMPLinker::ConstructJob(Compilation &C, const JobAction &JA,
llvm::sys::path::append(DefaultLibPath, "lib" CLANG_LIBDIR_SUFFIX);
CmdArgs.push_back(Args.MakeArgString(Twine("-L") + DefaultLibPath));
- // Add linking against library implementing OpenMP calls on NVPTX target.
- CmdArgs.push_back("-lomptarget-nvptx");
-
for (const auto &II : Inputs) {
if (II.getType() == types::TY_LLVM_IR ||
II.getType() == types::TY_LTO_IR ||
@@ -644,7 +636,7 @@ void NVPTX::OpenMPLinker::ConstructJob(Compilation &C, const JobAction &JA,
JA, *this,
ResponseFileSupport{ResponseFileSupport::RF_Full, llvm::sys::WEM_UTF8,
"--options-file"},
- Exec, CmdArgs, Inputs));
+ Exec, CmdArgs, Inputs, Output));
}
/// CUDA toolchain. Our assembler is ptxas, and our "linker" is fatbinary,
@@ -720,33 +712,30 @@ void CudaToolChain::addClangTargetOptions(
CC1Args.push_back("-mlink-builtin-bitcode");
CC1Args.push_back(DriverArgs.MakeArgString(LibDeviceFile));
+ std::string CudaVersionStr;
+
// 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 (CudaInstallation.version()) {
- case CudaVersion::CUDA_110:
- PtxFeature = "+ptx70";
- break;
- case CudaVersion::CUDA_102:
- PtxFeature = "+ptx65";
- break;
- case CudaVersion::CUDA_101:
- PtxFeature = "+ptx64";
- break;
- case CudaVersion::CUDA_100:
- PtxFeature = "+ptx63";
- break;
- case CudaVersion::CUDA_92:
- PtxFeature = "+ptx61";
- break;
- case CudaVersion::CUDA_91:
- PtxFeature = "+ptx61";
- break;
- case CudaVersion::CUDA_90:
- PtxFeature = "+ptx60";
+#define CASE_CUDA_VERSION(CUDA_VER, PTX_VER) \
+ case CudaVersion::CUDA_##CUDA_VER: \
+ CudaVersionStr = #CUDA_VER; \
+ PtxFeature = "+ptx" #PTX_VER; \
break;
+ 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:
+ // If unknown CUDA version, we take it as CUDA 8.0. Same assumption is also
+ // made in libomptarget/deviceRTLs.
+ CudaVersionStr = "80";
PtxFeature = "+ptx42";
}
CC1Args.append({"-target-feature", PtxFeature});
@@ -761,9 +750,6 @@ void CudaToolChain::addClangTargetOptions(
if (DeviceOffloadingKind == Action::OFK_OpenMP) {
SmallVector<StringRef, 8> LibraryPaths;
- if (const Arg *A = DriverArgs.getLastArg(options::OPT_libomptarget_nvptx_path_EQ))
- LibraryPaths.push_back(A->getValue());
-
// Add user defined library paths from LIBRARY_PATH.
llvm::Optional<std::string> LibPath =
llvm::sys::Process::GetEnv("LIBRARY_PATH");
@@ -781,22 +767,38 @@ void CudaToolChain::addClangTargetOptions(
llvm::sys::path::append(DefaultLibPath, Twine("lib") + CLANG_LIBDIR_SUFFIX);
LibraryPaths.emplace_back(DefaultLibPath.c_str());
- std::string LibOmpTargetName =
- "libomptarget-nvptx-" + GpuArch.str() + ".bc";
- bool FoundBCLibrary = false;
- for (StringRef LibraryPath : LibraryPaths) {
- SmallString<128> LibOmpTargetFile(LibraryPath);
- llvm::sys::path::append(LibOmpTargetFile, LibOmpTargetName);
- if (llvm::sys::fs::exists(LibOmpTargetFile)) {
+ // First check whether user specifies bc library
+ if (const Arg *A =
+ DriverArgs.getLastArg(options::OPT_libomptarget_nvptx_bc_path_EQ)) {
+ std::string LibOmpTargetName(A->getValue());
+ if (llvm::sys::fs::exists(LibOmpTargetName)) {
CC1Args.push_back("-mlink-builtin-bitcode");
- CC1Args.push_back(DriverArgs.MakeArgString(LibOmpTargetFile));
- FoundBCLibrary = true;
- break;
+ CC1Args.push_back(DriverArgs.MakeArgString(LibOmpTargetName));
+ } else {
+ getDriver().Diag(diag::err_drv_omp_offload_target_bcruntime_not_found)
+ << LibOmpTargetName;
+ }
+ } else {
+ bool FoundBCLibrary = false;
+
+ std::string LibOmpTargetName = "libomptarget-nvptx-cuda_" +
+ CudaVersionStr + "-" + GpuArch.str() +
+ ".bc";
+
+ for (StringRef LibraryPath : LibraryPaths) {
+ SmallString<128> LibOmpTargetFile(LibraryPath);
+ llvm::sys::path::append(LibOmpTargetFile, LibOmpTargetName);
+ if (llvm::sys::fs::exists(LibOmpTargetFile)) {
+ CC1Args.push_back("-mlink-builtin-bitcode");
+ CC1Args.push_back(DriverArgs.MakeArgString(LibOmpTargetFile));
+ FoundBCLibrary = true;
+ break;
+ }
}
+ if (!FoundBCLibrary)
+ getDriver().Diag(diag::err_drv_omp_offload_target_missingbcruntime)
+ << LibOmpTargetName;
}
- if (!FoundBCLibrary)
- getDriver().Diag(diag::warn_drv_omp_offload_target_missingbcruntime)
- << LibOmpTargetName;
}
}
generated by cgit v1.2.3 (git 2.25.1) at 2024-09-21 13:10:10 +0000