[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

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@318763 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/clang/Driver/ToolChain.h b/include/clang/Driver/ToolChain.h
index 943ec4a5c9803efdc938c525b4006e1fb1472fc9..1206794e93db655068bd07c3081b6ab264d6f774 100644 (file)
--- a/include/clang/Driver/ToolChain.h
+++ b/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(); }

diff --git a/lib/Driver/ToolChain.cpp b/lib/Driver/ToolChain.cpp
index 89c996ca5a168d5a84eee32d4472d6aa356864e6..fac0a5bbff5f053401d96596ea65d06f22ee2adb 100644 (file)
--- a/lib/Driver/ToolChain.cpp
+++ b/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;
 }

diff --git a/lib/Driver/ToolChains/Clang.cpp b/lib/Driver/ToolChains/Clang.cpp
index eae86c05729b1df61bd167804044777ef2300812..2f1fa4af807f1d8a30e1e8e3e14793cd3ddc1f6e 100644 (file)
--- a/lib/Driver/ToolChains/Clang.cpp
+++ b/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");

diff --git a/lib/Driver/ToolChains/Cuda.cpp b/lib/Driver/ToolChains/Cuda.cpp
index 44ec16e8b86dca1a3a1f878c0aae0966cbc2f5f0..4a5cf3dc6aec4a334ef0990b884c0352ef2ad368 100644 (file)
--- a/lib/Driver/ToolChains/Cuda.cpp
+++ b/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,

diff --git a/lib/Driver/ToolChains/Cuda.h b/lib/Driver/ToolChains/Cuda.h
index 23cca03eb2035b7dc2f4992c12e2481f3d361b1c..3d08cec1643ee1d03e4026b59ac83d307a3fdf8f 100644 (file)
--- a/lib/Driver/ToolChains/Cuda.h
+++ b/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;

diff --git a/test/Driver/openmp-offload-gpu.c b/test/Driver/openmp-offload-gpu.c
index abef552a6e63996da792443a9e6b65fdb64898a1..ad53f96112aeb9fb2bb1f4b4902457eaef7c1aeb 100644 (file)
--- a/test/Driver/openmp-offload-gpu.c
+++ b/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"
@@ -28,43 +31,67 @@
 /// ###########################################################################
 
 /// 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
+// 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]]"
+
+/// ###########################################################################
 
-// CHK-CUBIN: clang{{.*}}" "-o" "{{.*}}.s"
-// CHK-CUBIN-NEXT: ptxas{{.*}}" "--output-file" {{.*}}.cubin" {{.*}}.s"
-// CHK-CUBIN-NEXT: nvlink" {{.*}}.cubin"
+/// 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
 
+/// 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 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 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-CUBIN-DARWIN: clang{{.*}}" "-o" "{{.*}}.s"
-// CHK-CUBIN-DARWIN-NEXT: ptxas{{.*}}" "--output-file" {{.*}}.cubin" {{.*}}.s"
-// CHK-CUBIN-DARWIN-NEXT: nvlink" {{.*}}.cubin"
+// 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 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:   | FileCheck -check-prefix=CHK-TWOCUBIN %s
+/// 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
 
-// CHK-TWOCUBIN: nvlink{{.*}}openmp-offload-{{.*}}.cubin" "{{.*}}openmp-offload-{{.*}}.cubin"
+/// 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 when toolchain has BindArchAction
+/// Check cubin file generation and usage by nvlink
 // 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
+// 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-DARWIN: nvlink{{.*}}openmp-offload-{{.*}}.cubin" "{{.*}}openmp-offload-{{.*}}.cubin"
+// CHK-TWOCUBIN: nvlink{{.*}}openmp-offload-{{.*}}.cubin" "{{.*}}openmp-offload-{{.*}}.cubin"
 
 /// ###########################################################################
 
@@ -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"