[CUDA] Add utility functions for dealing with CUDA versions / architectures.
Summary:
Currently our handling of CUDA architectures is scattered all around
clang. This patch centralizes it.
A key advantage of this centralization is that you can now write a C++
switch on e.g. CudaArch and get a compile error if you don't handle one
of the enum values.
Reviewers: tra
Subscribers: cfe-commits
Differential Revision: http://reviews.llvm.org/D21867
llvm-svn: 274681
diff --git a/clang/lib/Driver/Driver.cpp b/clang/lib/Driver/Driver.cpp
index 7235bd0..78c3125 100644
--- a/clang/lib/Driver/Driver.cpp
+++ b/clang/lib/Driver/Driver.cpp
@@ -23,6 +23,7 @@
#include "clang/Driver/ToolChain.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/STLExtras.h"
+#include "llvm/ADT/SmallSet.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/ADT/StringSet.h"
#include "llvm/ADT/StringSwitch.h"
@@ -1022,9 +1023,10 @@
os << '"' << BIA->getArchName() << '"' << ", {"
<< PrintActions1(C, *BIA->input_begin(), Ids) << "}";
} else if (CudaDeviceAction *CDA = dyn_cast<CudaDeviceAction>(A)) {
- os << '"'
- << (CDA->getGpuArchName() ? CDA->getGpuArchName() : "(multiple archs)")
- << '"' << ", {" << PrintActions1(C, *CDA->input_begin(), Ids) << "}";
+ CudaArch Arch = CDA->getGpuArch();
+ if (Arch != CudaArch::UNKNOWN)
+ os << "'" << CudaArchToString(Arch) << "', ";
+ os << "{" << PrintActions1(C, *CDA->input_begin(), Ids) << "}";
} else {
const ActionList *AL;
if (CudaHostAction *CHA = dyn_cast<CudaHostAction>(A)) {
@@ -1380,24 +1382,25 @@
return C.MakeAction<CudaHostAction>(HostAction, ActionList());
// Collect all cuda_gpu_arch parameters, removing duplicates.
- SmallVector<const char *, 4> GpuArchList;
- llvm::StringSet<> GpuArchNames;
+ SmallVector<CudaArch, 4> GpuArchList;
+ llvm::SmallSet<CudaArch, 4> GpuArchs;
for (Arg *A : Args) {
if (!A->getOption().matches(options::OPT_cuda_gpu_arch_EQ))
continue;
A->claim();
- const auto& Arch = A->getValue();
- if (!CudaDeviceAction::IsValidGpuArchName(Arch))
- C.getDriver().Diag(clang::diag::err_drv_cuda_bad_gpu_arch) << Arch;
- else if (GpuArchNames.insert(Arch).second)
+ const auto &ArchStr = A->getValue();
+ CudaArch Arch = StringToCudaArch(ArchStr);
+ if (Arch == CudaArch::UNKNOWN)
+ C.getDriver().Diag(clang::diag::err_drv_cuda_bad_gpu_arch) << ArchStr;
+ else if (GpuArchs.insert(Arch).second)
GpuArchList.push_back(Arch);
}
// Default to sm_20 which is the lowest common denominator for supported GPUs.
// sm_20 code should work correctly, if suboptimally, on all newer GPUs.
if (GpuArchList.empty())
- GpuArchList.push_back("sm_20");
+ GpuArchList.push_back(CudaArch::SM_20);
// Replicate inputs for each GPU architecture.
Driver::InputList CudaDeviceInputs;
@@ -1463,7 +1466,7 @@
}
auto FatbinAction = C.MakeAction<CudaDeviceAction>(
C.MakeAction<LinkJobAction>(DeviceActions, types::TY_CUDA_FATBIN),
- /* GpuArchName = */ nullptr,
+ CudaArch::UNKNOWN,
/* AtTopLevel = */ false);
// Return a new host action that incorporates original host action and all
// device actions.
@@ -2047,8 +2050,8 @@
// Call BuildJobsForAction() again, now with correct device parameters.
InputInfo II = BuildJobsForAction(
C, *CDA->input_begin(), C.getSingleOffloadToolChain<Action::OFK_Cuda>(),
- CDA->getGpuArchName(), CDA->isAtTopLevel(), /*MultipleArchs=*/true,
- LinkingOutput, CachedResults);
+ CudaArchToString(CDA->getGpuArch()), CDA->isAtTopLevel(),
+ /*MultipleArchs=*/true, LinkingOutput, CachedResults);
// Currently II's Action is *CDA->input_begin(). Set it to CDA instead, so
// that one can retrieve II's GPU arch.
II.setAction(A);