[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

clang/include/clang/Driver/ToolChain.h

@@ -40,6 +40,7 @@ namespace driver {
   class Compilation;
   class CudaInstallationDetector;
   class Driver;
+  class InputInfo;
   class JobAction;
   class RegisterEffectiveTriple;
   class SanitizerArgs;
@@ -172,6 +173,11 @@ public:
   /// while the aux triple is the host (CPU) toolchain, e.g. x86-linux-gnu.
   virtual const llvm::Triple *getAuxTriple() const { return nullptr; }
 
+  /// Some toolchains need to modify the file name, for example to replace the
+  /// extension for object files with .cubin for OpenMP offloading to Nvidia
+  /// GPUs.
+  virtual std::string getInputFilename(const InputInfo &Input) const;
+
   llvm::Triple::ArchType getArch() const { return Triple.getArch(); }
   StringRef getArchName() const { return Triple.getArchName(); }
   StringRef getPlatform() const { return Triple.getVendorName(); }

clang/lib/Driver/ToolChain.cpp

@@ -215,6 +215,10 @@ StringRef ToolChain::getDefaultUniversalArchName() const {
   }
 }
 
+std::string ToolChain::getInputFilename(const InputInfo &Input) const {
+  return Input.getFilename();
+}
+
 bool ToolChain::IsUnwindTablesDefault(const ArgList &Args) const {
   return false;
 }

clang/lib/Driver/ToolChains/Clang.cpp

@@ -5310,12 +5310,15 @@ void OffloadBundler::ConstructJob(Compilation &C, const JobAction &JA,
     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 @@ void OffloadBundler::ConstructJob(Compilation &C, const JobAction &JA,
   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 @@ void OffloadBundler::ConstructJobMultipleOutputs(
   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");

clang/lib/Driver/ToolChains/Cuda.cpp

@@ -301,10 +301,7 @@ void NVPTX::Assembler::ConstructJob(Compilation &C, const JobAction &JA,
   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 @@ void NVPTX::OpenMPLinker::ConstructJob(Compilation &C, const JobAction &JA,
     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 @@ CudaToolChain::CudaToolChain(const Driver &D, const llvm::Triple &Triple,
   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,

clang/lib/Driver/ToolChains/Cuda.h

@@ -137,10 +137,12 @@ public:
                 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;

clang/test/Driver/openmp-offload-gpu.c

@@ -10,7 +10,8 @@
 /// ###########################################################################
 
 /// Check -Xopenmp-target uses one of the archs provided when several archs are used.
-// RUN:   %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_35 -Xopenmp-target -march=sm_60 %s 2>&1 \
+// RUN:   %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
+// RUN:          -Xopenmp-target -march=sm_35 -Xopenmp-target -march=sm_60 %s 2>&1 \
 // RUN:   | FileCheck -check-prefix=CHK-FOPENMP-TARGET-ARCHS %s
 
 // CHK-FOPENMP-TARGET-ARCHS: ptxas{{.*}}" "--gpu-name" "sm_60"
@@ -19,7 +20,9 @@
 /// ###########################################################################
 
 /// Check -Xopenmp-target -march=sm_35 works as expected when two triples are present.
-// RUN:   %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=powerpc64le-ibm-linux-gnu,nvptx64-nvidia-cuda -Xopenmp-target=nvptx64-nvidia-cuda -march=sm_35 %s 2>&1 \
+// RUN:   %clang -### -no-canonical-prefixes -fopenmp=libomp \
+// RUN:          -fopenmp-targets=powerpc64le-ibm-linux-gnu,nvptx64-nvidia-cuda \
+// RUN:          -Xopenmp-target=nvptx64-nvidia-cuda -march=sm_35 %s 2>&1 \
 // RUN:   | FileCheck -check-prefix=CHK-FOPENMP-TARGET-COMPILATION %s
 
 // CHK-FOPENMP-TARGET-COMPILATION: ptxas{{.*}}" "--gpu-name" "sm_35"
@@ -28,46 +31,70 @@
 /// ###########################################################################
 
 /// Check cubin file generation and usage by nvlink
-// RUN:   %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -save-temps %s 2>&1 \
-// RUN:   | FileCheck -check-prefix=CHK-CUBIN %s
-
-// CHK-CUBIN: clang{{.*}}" "-o" "{{.*}}.s"
-// CHK-CUBIN-NEXT: ptxas{{.*}}" "--output-file" {{.*}}.cubin" {{.*}}.s"
-// CHK-CUBIN-NEXT: nvlink" {{.*}}.cubin"
+// RUN:   %clang -### -no-canonical-prefixes -target powerpc64le-unknown-linux-gnu -fopenmp=libomp \
+// RUN:          -fopenmp-targets=nvptx64-nvidia-cuda -save-temps %s 2>&1 \
+// RUN:   | FileCheck -check-prefix=CHK-CUBIN-NVLINK %s
+/// Check cubin file generation and usage by nvlink when toolchain has BindArchAction
+// RUN:   %clang -### -no-canonical-prefixes -target x86_64-apple-darwin17.0.0 -fopenmp=libomp \
+// RUN:          -fopenmp-targets=nvptx64-nvidia-cuda %s 2>&1 \
+// RUN:   | FileCheck -check-prefix=CHK-CUBIN-NVLINK %s
 
+// CHK-CUBIN-NVLINK: clang{{.*}}" "-o" "[[PTX:.*\.s]]"
+// CHK-CUBIN-NVLINK-NEXT: ptxas{{.*}}" "--output-file" "[[CUBIN:.*\.cubin]]" {{.*}}"[[PTX]]"
+// CHK-CUBIN-NVLINK-NEXT: nvlink{{.*}}" {{.*}}"[[CUBIN]]"
 
 /// ###########################################################################
 
-/// Check cubin file generation and usage by nvlink when toolchain has BindArchAction
-// RUN:   %clang -### -no-canonical-prefixes -target x86_64-apple-darwin17.0.0 -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda %s 2>&1 \
-// RUN:   | FileCheck -check-prefix=CHK-CUBIN-DARWIN %s
+/// Check unbundlink of assembly file, cubin file generation and usage by nvlink
+// RUN:   touch %t.s
+// RUN:   %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -save-temps %t.s 2>&1 \
+// RUN:   | FileCheck -check-prefix=CHK-UNBUNDLING-PTXAS-CUBIN-NVLINK %s
 
-// CHK-CUBIN-DARWIN: clang{{.*}}" "-o" "{{.*}}.s"
-// CHK-CUBIN-DARWIN-NEXT: ptxas{{.*}}" "--output-file" {{.*}}.cubin" {{.*}}.s"
-// CHK-CUBIN-DARWIN-NEXT: nvlink" {{.*}}.cubin"
+/// Use DAG to ensure that assembly file has been unbundled.
+// CHK-UNBUNDLING-PTXAS-CUBIN-NVLINK-DAG: ptxas{{.*}}" "--output-file" "[[CUBIN:.*\.cubin]]" {{.*}}"[[PTX:.*\.s]]"
+// CHK-UNBUNDLING-PTXAS-CUBIN-NVLINK-DAG: clang-offload-bundler{{.*}}" "-type=s" {{.*}}"-outputs={{.*}}[[PTX]]
+// CHK-UNBUNDLING-PTXAS-CUBIN-NVLINK-DAG-SAME: "-unbundle"
+// CHK-UNBUNDLING-PTXAS-CUBIN-NVLINK: nvlink{{.*}}" {{.*}}"[[CUBIN]]"
+
+/// ###########################################################################
+
+/// Check cubin file generation and bundling
+// RUN:   %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -save-temps %s -c 2>&1 \
+// RUN:   | FileCheck -check-prefix=CHK-PTXAS-CUBIN-BUNDLING %s
+
+// CHK-PTXAS-CUBIN-BUNDLING: clang{{.*}}" "-o" "[[PTX:.*\.s]]"
+// CHK-PTXAS-CUBIN-BUNDLING-NEXT: ptxas{{.*}}" "--output-file" "[[CUBIN:.*\.cubin]]" {{.*}}"[[PTX]]"
+// CHK-PTXAS-CUBIN-BUNDLING: clang-offload-bundler{{.*}}" "-type=o" {{.*}}"-inputs={{.*}}[[CUBIN]]
+
+/// ###########################################################################
+
+/// Check cubin file unbundling and usage by nvlink
+// RUN:   touch %t.o
+// RUN:   %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -save-temps %t.o 2>&1 \
+// RUN:   | FileCheck -check-prefix=CHK-CUBIN-UNBUNDLING-NVLINK %s
+
+/// Use DAG to ensure that cubin file has been unbundled.
+// CHK-CUBIN-UNBUNDLING-NVLINK-DAG: nvlink{{.*}}" {{.*}}"[[CUBIN:.*\.cubin]]"
+// CHK-CUBIN-UNBUNDLING-NVLINK-DAG: clang-offload-bundler{{.*}}" "-type=o" {{.*}}"-outputs={{.*}}[[CUBIN]]
+// CHK-CUBIN-UNBUNDLING-NVLINK-DAG-SAME: "-unbundle"
 
 /// ###########################################################################
 
 /// Check cubin file generation and usage by nvlink
 // RUN:   touch %t1.o
 // RUN:   touch %t2.o
-// RUN:   %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda %t1.o %t2.o 2>&1 \
+// RUN:   %clang -### -no-canonical-prefixes -target powerpc64le-unknown-linux-gnu -fopenmp=libomp \
+// RUN:          -fopenmp-targets=nvptx64-nvidia-cuda %t1.o %t2.o 2>&1 \
+// RUN:   | FileCheck -check-prefix=CHK-TWOCUBIN %s
+/// Check cubin file generation and usage by nvlink when toolchain has BindArchAction
+// RUN:   %clang -### -no-canonical-prefixes -target x86_64-apple-darwin17.0.0 -fopenmp=libomp \
+// RUN:          -fopenmp-targets=nvptx64-nvidia-cuda %t1.o %t2.o 2>&1 \
 // RUN:   | FileCheck -check-prefix=CHK-TWOCUBIN %s
 
 // CHK-TWOCUBIN: nvlink{{.*}}openmp-offload-{{.*}}.cubin" "{{.*}}openmp-offload-{{.*}}.cubin"
 
 /// ###########################################################################
 
-/// Check cubin file generation and usage by nvlink when toolchain has BindArchAction
-// RUN:   touch %t1.o
-// RUN:   touch %t2.o
-// RUN:   %clang -### -no-canonical-prefixes -target x86_64-apple-darwin17.0.0 -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda %t1.o %t2.o 2>&1 \
-// RUN:   | FileCheck -check-prefix=CHK-TWOCUBIN-DARWIN %s
-
-// CHK-TWOCUBIN-DARWIN: nvlink{{.*}}openmp-offload-{{.*}}.cubin" "{{.*}}openmp-offload-{{.*}}.cubin"
-
-/// ###########################################################################
-
 /// Check PTXAS is passed -c flag when offloading to an NVIDIA device using OpenMP.
 // RUN:   %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -no-canonical-prefixes %s 2>&1 \
 // RUN:   | FileCheck -check-prefix=CHK-PTXAS-DEFAULT %s
@@ -77,7 +104,8 @@
 /// ###########################################################################
 
 /// PTXAS is passed -c flag by default when offloading to an NVIDIA device using OpenMP - disable it.
-// RUN:   %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -fnoopenmp-relocatable-target -save-temps -no-canonical-prefixes %s 2>&1 \
+// RUN:   %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -fnoopenmp-relocatable-target \
+// RUN:          -save-temps -no-canonical-prefixes %s 2>&1 \
 // RUN:   | FileCheck -check-prefix=CHK-PTXAS-NORELO %s
 
 // CHK-PTXAS-NORELO-NOT: ptxas{{.*}}" "-c"
@@ -86,7 +114,8 @@
 
 /// PTXAS is passed -c flag by default when offloading to an NVIDIA device using OpenMP
 /// Check that the flag is passed when -fopenmp-relocatable-target is used.
-// RUN:   %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -fopenmp-relocatable-target -save-temps -no-canonical-prefixes %s 2>&1 \
+// RUN:   %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -fopenmp-relocatable-target \
+// RUN:          -save-temps -no-canonical-prefixes %s 2>&1 \
 // RUN:   | FileCheck -check-prefix=CHK-PTXAS-RELO %s
 
 // CHK-PTXAS-RELO: ptxas{{.*}}" "-c"