[OpenMP] Consistently use cubin extension for nvlink
This was previously done in some places, but for example not for
bundling so that single object compilation with -c failed. In
addition cubin was used for all file types during unbundling which
is incorrect for assembly files that are passed to ptxas.
Tighten up the tests so that we can't regress in that area.
Differential Revision: https://reviews.llvm.org/D40250
llvm-svn: 318763
diff --git a/clang/lib/Driver/ToolChain.cpp b/clang/lib/Driver/ToolChain.cpp
index 89c996c..fac0a5b 100644
--- a/clang/lib/Driver/ToolChain.cpp
+++ b/clang/lib/Driver/ToolChain.cpp
@@ -215,6 +215,10 @@
}
}
+std::string ToolChain::getInputFilename(const InputInfo &Input) const {
+ return Input.getFilename();
+}
+
bool ToolChain::IsUnwindTablesDefault(const ArgList &Args) const {
return false;
}
diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
index eae86c0..2f1fa4a 100644
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -5310,12 +5310,15 @@
if (I)
Triples += ',';
+ // Find ToolChain for this input.
Action::OffloadKind CurKind = Action::OFK_Host;
const ToolChain *CurTC = &getToolChain();
const Action *CurDep = JA.getInputs()[I];
if (const auto *OA = dyn_cast<OffloadAction>(CurDep)) {
+ CurTC = nullptr;
OA->doOnEachDependence([&](Action *A, const ToolChain *TC, const char *) {
+ assert(CurTC == nullptr && "Expected one dependence!");
CurKind = A->getOffloadingDeviceKind();
CurTC = TC;
});
@@ -5336,7 +5339,17 @@
for (unsigned I = 0; I < Inputs.size(); ++I) {
if (I)
UB += ',';
- UB += Inputs[I].getFilename();
+
+ // Find ToolChain for this input.
+ const ToolChain *CurTC = &getToolChain();
+ if (const auto *OA = dyn_cast<OffloadAction>(JA.getInputs()[I])) {
+ CurTC = nullptr;
+ OA->doOnEachDependence([&](Action *, const ToolChain *TC, const char *) {
+ assert(CurTC == nullptr && "Expected one dependence!");
+ CurTC = TC;
+ });
+ }
+ UB += CurTC->getInputFilename(Inputs[I]);
}
CmdArgs.push_back(TCArgs.MakeArgString(UB));
@@ -5396,13 +5409,7 @@
for (unsigned I = 0; I < Outputs.size(); ++I) {
if (I)
UB += ',';
- SmallString<256> OutputFileName(Outputs[I].getFilename());
- // Change extension of target files for OpenMP offloading
- // to NVIDIA GPUs.
- if (DepInfo[I].DependentToolChain->getTriple().isNVPTX() &&
- JA.isOffloading(Action::OFK_OpenMP))
- llvm::sys::path::replace_extension(OutputFileName, "cubin");
- UB += OutputFileName;
+ UB += DepInfo[I].DependentToolChain->getInputFilename(Outputs[I]);
}
CmdArgs.push_back(TCArgs.MakeArgString(UB));
CmdArgs.push_back("-unbundle");
diff --git a/clang/lib/Driver/ToolChains/Cuda.cpp b/clang/lib/Driver/ToolChains/Cuda.cpp
index 44ec16e..4a5cf3d 100644
--- a/clang/lib/Driver/ToolChains/Cuda.cpp
+++ b/clang/lib/Driver/ToolChains/Cuda.cpp
@@ -301,10 +301,7 @@
CmdArgs.push_back("--gpu-name");
CmdArgs.push_back(Args.MakeArgString(CudaArchToString(gpu_arch)));
CmdArgs.push_back("--output-file");
- SmallString<256> OutputFileName(Output.getFilename());
- if (JA.isOffloading(Action::OFK_OpenMP))
- llvm::sys::path::replace_extension(OutputFileName, "cubin");
- CmdArgs.push_back(Args.MakeArgString(OutputFileName));
+ CmdArgs.push_back(Args.MakeArgString(TC.getInputFilename(Output)));
for (const auto& II : Inputs)
CmdArgs.push_back(Args.MakeArgString(II.getFilename()));
@@ -431,11 +428,8 @@
if (!II.isFilename())
continue;
- SmallString<256> Name(II.getFilename());
- llvm::sys::path::replace_extension(Name, "cubin");
-
- const char *CubinF =
- C.addTempFile(C.getArgs().MakeArgString(Name));
+ const char *CubinF = C.addTempFile(
+ C.getArgs().MakeArgString(getToolChain().getInputFilename(II)));
CmdArgs.push_back(CubinF);
}
@@ -463,6 +457,20 @@
getProgramPaths().push_back(getDriver().Dir);
}
+std::string CudaToolChain::getInputFilename(const InputInfo &Input) const {
+ // Only object files are changed, for example assembly files keep their .s
+ // extensions. CUDA also continues to use .o as they don't use nvlink but
+ // fatbinary.
+ if (!(OK == Action::OFK_OpenMP && Input.getType() == types::TY_Object))
+ return ToolChain::getInputFilename(Input);
+
+ // Replace extension for object files with cubin because nvlink relies on
+ // these particular file names.
+ SmallString<256> Filename(ToolChain::getInputFilename(Input));
+ llvm::sys::path::replace_extension(Filename, "cubin");
+ return Filename.str();
+}
+
void CudaToolChain::addClangTargetOptions(
const llvm::opt::ArgList &DriverArgs,
llvm::opt::ArgStringList &CC1Args,
diff --git a/clang/lib/Driver/ToolChains/Cuda.h b/clang/lib/Driver/ToolChains/Cuda.h
index 23cca03..3d08cec 100644
--- a/clang/lib/Driver/ToolChains/Cuda.h
+++ b/clang/lib/Driver/ToolChains/Cuda.h
@@ -137,10 +137,12 @@
const ToolChain &HostTC, const llvm::opt::ArgList &Args,
const Action::OffloadKind OK);
- virtual const llvm::Triple *getAuxTriple() const override {
+ const llvm::Triple *getAuxTriple() const override {
return &HostTC.getTriple();
}
+ std::string getInputFilename(const InputInfo &Input) const override;
+
llvm::opt::DerivedArgList *
TranslateArgs(const llvm::opt::DerivedArgList &Args, StringRef BoundArch,
Action::OffloadKind DeviceOffloadKind) const override;