aboutsummaryrefslogtreecommitdiff
path: root/contrib/llvm-project/clang/lib/Driver/ToolChains/Cuda.h
diff options
context:
space:
mode:
Diffstat (limited to 'contrib/llvm-project/clang/lib/Driver/ToolChains/Cuda.h')
-rw-r--r--contrib/llvm-project/clang/lib/Driver/ToolChains/Cuda.h161
1 files changed, 99 insertions, 62 deletions
diff --git a/contrib/llvm-project/clang/lib/Driver/ToolChains/Cuda.h b/contrib/llvm-project/clang/lib/Driver/ToolChains/Cuda.h
index 6ae4415a563a..7a6a6fb20901 100644
--- a/contrib/llvm-project/clang/lib/Driver/ToolChains/Cuda.h
+++ b/contrib/llvm-project/clang/lib/Driver/ToolChains/Cuda.h
@@ -14,7 +14,6 @@
#include "clang/Driver/Multilib.h"
#include "clang/Driver/Tool.h"
#include "clang/Driver/ToolChain.h"
-#include "llvm/ADT/Optional.h"
#include "llvm/Support/Compiler.h"
#include "llvm/Support/VersionTuple.h"
#include <bitset>
@@ -30,18 +29,15 @@ private:
const Driver &D;
bool IsValid = false;
CudaVersion Version = CudaVersion::UNKNOWN;
- std::string DetectedVersion;
- bool DetectedVersionIsNotSupported = false;
std::string InstallPath;
std::string BinPath;
- std::string LibPath;
std::string LibDevicePath;
std::string IncludePath;
llvm::StringMap<std::string> LibDeviceMap;
// CUDA architectures for which we have raised an error in
// CheckCudaVersionSupportsArch.
- mutable std::bitset<(int)CudaArch::LAST> ArchsWithBadVersion;
+ mutable std::bitset<(int)OffloadArch::LAST> ArchsWithBadVersion;
public:
CudaInstallationDetector(const Driver &D, const llvm::Triple &HostTriple,
@@ -54,7 +50,7 @@ public:
///
/// If either Version or Arch is unknown, does not emit an error. Emits at
/// most one error per Arch.
- void CheckCudaVersionSupportsArch(CudaArch Arch) const;
+ void CheckCudaVersionSupportsArch(OffloadArch Arch) const;
/// Check whether we detected a valid Cuda install.
bool isValid() const { return IsValid; }
@@ -62,15 +58,16 @@ public:
void print(raw_ostream &OS) const;
/// Get the detected Cuda install's version.
- CudaVersion version() const { return Version; }
+ CudaVersion version() const {
+ return Version == CudaVersion::NEW ? CudaVersion::PARTIALLY_SUPPORTED
+ : Version;
+ }
/// Get the detected Cuda installation path.
StringRef getInstallPath() const { return InstallPath; }
/// Get the detected path to Cuda's bin directory.
StringRef getBinPath() const { return BinPath; }
/// Get the detected Cuda Include path.
StringRef getIncludePath() const { return IncludePath; }
- /// Get the detected Cuda library path.
- StringRef getLibPath() const { return LibPath; }
/// Get the detected Cuda device library path.
StringRef getLibDevicePath() const { return LibDevicePath; }
/// Get libdevice file for given architecture
@@ -84,85 +81,133 @@ namespace tools {
namespace NVPTX {
// Run ptxas, the NVPTX assembler.
-class LLVM_LIBRARY_VISIBILITY Assembler : public Tool {
- public:
- Assembler(const ToolChain &TC) : Tool("NVPTX::Assembler", "ptxas", TC) {}
+class LLVM_LIBRARY_VISIBILITY Assembler final : public Tool {
+public:
+ Assembler(const ToolChain &TC) : Tool("NVPTX::Assembler", "ptxas", TC) {}
- bool hasIntegratedCPP() const override { return false; }
+ bool hasIntegratedCPP() const override { return false; }
- void ConstructJob(Compilation &C, const JobAction &JA,
- const InputInfo &Output, const InputInfoList &Inputs,
- const llvm::opt::ArgList &TCArgs,
- const char *LinkingOutput) const override;
+ void ConstructJob(Compilation &C, const JobAction &JA,
+ const InputInfo &Output, const InputInfoList &Inputs,
+ const llvm::opt::ArgList &TCArgs,
+ const char *LinkingOutput) const override;
};
// Runs fatbinary, which combines GPU object files ("cubin" files) and/or PTX
// assembly into a single output file.
-class LLVM_LIBRARY_VISIBILITY Linker : public Tool {
- public:
- Linker(const ToolChain &TC) : Tool("NVPTX::Linker", "fatbinary", TC) {}
+class LLVM_LIBRARY_VISIBILITY FatBinary : public Tool {
+public:
+ FatBinary(const ToolChain &TC) : Tool("NVPTX::Linker", "fatbinary", TC) {}
- bool hasIntegratedCPP() const override { return false; }
+ bool hasIntegratedCPP() const override { return false; }
- void ConstructJob(Compilation &C, const JobAction &JA,
- const InputInfo &Output, const InputInfoList &Inputs,
- const llvm::opt::ArgList &TCArgs,
- const char *LinkingOutput) const override;
+ void ConstructJob(Compilation &C, const JobAction &JA,
+ const InputInfo &Output, const InputInfoList &Inputs,
+ const llvm::opt::ArgList &TCArgs,
+ const char *LinkingOutput) const override;
};
-class LLVM_LIBRARY_VISIBILITY OpenMPLinker : public Tool {
- public:
- OpenMPLinker(const ToolChain &TC)
- : Tool("NVPTX::OpenMPLinker", "nvlink", TC) {}
+// Runs nvlink, which links GPU object files ("cubin" files) into a single file.
+class LLVM_LIBRARY_VISIBILITY Linker final : public Tool {
+public:
+ Linker(const ToolChain &TC) : Tool("NVPTX::Linker", "nvlink", TC) {}
- bool hasIntegratedCPP() const override { return false; }
+ bool hasIntegratedCPP() const override { return false; }
- void ConstructJob(Compilation &C, const JobAction &JA,
- const InputInfo &Output, const InputInfoList &Inputs,
- const llvm::opt::ArgList &TCArgs,
- const char *LinkingOutput) const override;
+ void ConstructJob(Compilation &C, const JobAction &JA,
+ const InputInfo &Output, const InputInfoList &Inputs,
+ const llvm::opt::ArgList &TCArgs,
+ const char *LinkingOutput) const override;
};
+void getNVPTXTargetFeatures(const Driver &D, const llvm::Triple &Triple,
+ const llvm::opt::ArgList &Args,
+ std::vector<StringRef> &Features);
+
} // end namespace NVPTX
} // end namespace tools
namespace toolchains {
-class LLVM_LIBRARY_VISIBILITY CudaToolChain : public ToolChain {
+class LLVM_LIBRARY_VISIBILITY NVPTXToolChain : public ToolChain {
public:
- CudaToolChain(const Driver &D, const llvm::Triple &Triple,
- const ToolChain &HostTC, const llvm::opt::ArgList &Args,
- const Action::OffloadKind OK);
+ NVPTXToolChain(const Driver &D, const llvm::Triple &Triple,
+ const llvm::Triple &HostTriple, const llvm::opt::ArgList &Args,
+ bool Freestanding);
- const llvm::Triple *getAuxTriple() const override {
- return &HostTC.getTriple();
- }
-
- std::string getInputFilename(const InputInfo &Input) const override;
+ NVPTXToolChain(const Driver &D, const llvm::Triple &Triple,
+ const llvm::opt::ArgList &Args);
llvm::opt::DerivedArgList *
TranslateArgs(const llvm::opt::DerivedArgList &Args, StringRef BoundArch,
Action::OffloadKind DeviceOffloadKind) const override;
- void addClangTargetOptions(const llvm::opt::ArgList &DriverArgs,
- llvm::opt::ArgStringList &CC1Args,
- Action::OffloadKind DeviceOffloadKind) const override;
- llvm::DenormalMode getDefaultDenormalModeForType(
- const llvm::opt::ArgList &DriverArgs, const JobAction &JA,
- const llvm::fltSemantics *FPType = nullptr) const override;
+ void
+ addClangTargetOptions(const llvm::opt::ArgList &DriverArgs,
+ llvm::opt::ArgStringList &CC1Args,
+ Action::OffloadKind DeviceOffloadKind) const override;
// Never try to use the integrated assembler with CUDA; always fork out to
// ptxas.
bool useIntegratedAs() const override { return false; }
bool isCrossCompiling() const override { return true; }
bool isPICDefault() const override { return false; }
- bool isPIEDefault() const override { return false; }
+ bool isPIEDefault(const llvm::opt::ArgList &Args) const override {
+ return false;
+ }
+ bool HasNativeLLVMSupport() const override { return true; }
bool isPICDefaultForced() const override { return false; }
bool SupportsProfiling() const override { return false; }
+
+ bool IsMathErrnoDefault() const override { return false; }
+
bool supportsDebugInfoOption(const llvm::opt::Arg *A) const override;
- void adjustDebugInfoKind(codegenoptions::DebugInfoKind &DebugInfoKind,
+ void adjustDebugInfoKind(llvm::codegenoptions::DebugInfoKind &DebugInfoKind,
const llvm::opt::ArgList &Args) const override;
- bool IsMathErrnoDefault() const override { return false; }
+
+ // NVPTX supports only DWARF2.
+ unsigned GetDefaultDwarfVersion() const override { return 2; }
+ unsigned getMaxDwarfVersion() const override { return 2; }
+
+ /// Uses nvptx-arch tool to get arch of the system GPU. Will return error
+ /// if unable to find one.
+ virtual Expected<SmallVector<std::string>>
+ getSystemGPUArchs(const llvm::opt::ArgList &Args) const override;
+
+ CudaInstallationDetector CudaInstallation;
+
+protected:
+ Tool *buildAssembler() const override; // ptxas.
+ Tool *buildLinker() const override; // nvlink.
+
+private:
+ bool Freestanding = false;
+};
+
+class LLVM_LIBRARY_VISIBILITY CudaToolChain : public NVPTXToolChain {
+public:
+ CudaToolChain(const Driver &D, const llvm::Triple &Triple,
+ const ToolChain &HostTC, const llvm::opt::ArgList &Args);
+
+ const llvm::Triple *getAuxTriple() const override {
+ return &HostTC.getTriple();
+ }
+
+ bool HasNativeLLVMSupport() const override { return false; }
+
+ std::string getInputFilename(const InputInfo &Input) const override;
+
+ llvm::opt::DerivedArgList *
+ TranslateArgs(const llvm::opt::DerivedArgList &Args, StringRef BoundArch,
+ Action::OffloadKind DeviceOffloadKind) const override;
+ void
+ addClangTargetOptions(const llvm::opt::ArgList &DriverArgs,
+ llvm::opt::ArgStringList &CC1Args,
+ Action::OffloadKind DeviceOffloadKind) const override;
+
+ llvm::DenormalMode getDefaultDenormalModeForType(
+ const llvm::opt::ArgList &DriverArgs, const JobAction &JA,
+ const llvm::fltSemantics *FPType = nullptr) const override;
void AddCudaIncludeArgs(const llvm::opt::ArgList &DriverArgs,
llvm::opt::ArgStringList &CC1Args) const override;
@@ -184,19 +229,11 @@ public:
computeMSVCVersion(const Driver *D,
const llvm::opt::ArgList &Args) const override;
- unsigned GetDefaultDwarfVersion() const override { return 2; }
- // NVPTX supports only DWARF2.
- unsigned getMaxDwarfVersion() const override { return 2; }
-
const ToolChain &HostTC;
- CudaInstallationDetector CudaInstallation;
protected:
- Tool *buildAssembler() const override; // ptxas
- Tool *buildLinker() const override; // fatbinary (ok, not really a linker)
-
-private:
- const Action::OffloadKind OK;
+ Tool *buildAssembler() const override; // ptxas
+ Tool *buildLinker() const override; // fatbinary (ok, not really a linker)
};
} // end namespace toolchains
generated by cgit v1.2.3 (git 2.25.1) at 2025-09-24 01:34:46 +0000