Revert r310489 and follow-up commits r310505, r310519, r310537 and r310549

Commit r310489 caused 'openmp-offload.c' test failures on Darwin and other
platforms:
http://lab.llvm.org:8080/green/job/clang-stage1-cmake-RA-incremental_check/39230/testReport/junit/Clang/Driver/openmp_offload_c/

The follow-up commits tried to fix the test, but the test is still failing.

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@310580 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/clang/Driver/Options.td b/include/clang/Driver/Options.td
index a303143850ed1ab1292c88b2d9f2b148e8d8283b..c86941181b75cb913c2e2b326e3c0bfe27d57595 100644 (file)
--- a/include/clang/Driver/Options.td
+++ b/include/clang/Driver/Options.td
@@ -544,8 +544,6 @@ def no_cuda_version_check : Flag<["--"], "no-cuda-version-check">,
 def no_cuda_noopt_device_debug : Flag<["--"], "no-cuda-noopt-device-debug">;
 def cuda_path_EQ : Joined<["--"], "cuda-path=">, Group<i_Group>,
   HelpText<"CUDA installation path">;
-def fopenmp_ptx_EQ : Joined<["--"], "fopenmp-ptx=">, Flags<[DriverOption]>,
-  HelpText<"Pass a PTX version +ptxXX, default +ptx42 (for PTX version 4.2) used by OpenMP device offloading.">;
 def ptxas_path_EQ : Joined<["--"], "ptxas-path=">, Group<i_Group>,
   HelpText<"Path to ptxas (used for compiling CUDA code)">;
 def fcuda_flush_denormals_to_zero : Flag<["-"], "fcuda-flush-denormals-to-zero">,

diff --git a/lib/Driver/ToolChains/Cuda.cpp b/lib/Driver/ToolChains/Cuda.cpp
index a0bbd526becf41ddccf11d97165e4174b62529c2..643c3404d1503d239ae3cadfa67cc9ad366c1c0a 100644 (file)
--- a/lib/Driver/ToolChains/Cuda.cpp
+++ b/lib/Driver/ToolChains/Cuda.cpp
@@ -484,13 +484,7 @@ void CudaToolChain::addClangTargetOptions(
   // than LLVM defaults to. Use PTX4.2 which is the PTX version that
   // came with CUDA-7.0.
   CC1Args.push_back("-target-feature");
-
-  if (DeviceOffloadingKind == Action::OFK_OpenMP)
-    CC1Args.push_back(
-        DriverArgs.getLastArgValue(options::OPT_fopenmp_ptx_EQ,
-                                   "+ptx42").data());
-  else
-    CC1Args.push_back("+ptx42");
+  CC1Args.push_back("+ptx42");
 }
 
 void CudaToolChain::AddCudaIncludeArgs(const ArgList &DriverArgs,
@@ -533,14 +527,10 @@ CudaToolChain::TranslateArgs(const llvm::opt::DerivedArgList &Args,
     }
 
     StringRef Arch = DAL->getLastArgValue(options::OPT_march_EQ);
-    if (Arch.empty()) {
-      // Default compute capability for CUDA toolchain is the
-      // lowest compute capability supported by the installed
-      // CUDA version.
+    if (Arch.empty())
+      // Default compute capability for CUDA toolchain is sm_20.
       DAL->AddJoinedArg(nullptr,
-          Opts.getOption(options::OPT_march_EQ),
-          CudaInstallation.getLowestExistingArch());
-    }
+          Opts.getOption(options::OPT_march_EQ), "sm_20");
 
     return DAL;
   }

diff --git a/lib/Driver/ToolChains/Cuda.h b/lib/Driver/ToolChains/Cuda.h
index 9b3d6d70cd71e0a73517cf8aaaa62273df33ed5b..1e30aa72702a7b2b062d192e7c3b79123d3a1811 100644 (file)
--- a/lib/Driver/ToolChains/Cuda.h
+++ b/lib/Driver/ToolChains/Cuda.h
@@ -76,17 +76,6 @@ public:
   std::string getLibDeviceFile(StringRef Gpu) const {
     return LibDeviceMap.lookup(Gpu);
   }
-  /// \brief Get lowest available compute capability
-  /// for which a libdevice library exists.
-  std::string getLowestExistingArch() const {
-    std::string LibDeviceFile;
-    for (auto key : LibDeviceMap.keys()) {
-      LibDeviceFile = LibDeviceMap.lookup(key);
-      if (!LibDeviceFile.empty())
-        return key;
-    }
-    llvm_unreachable("no libdevice exists.");
-  }
 };
 
 namespace tools {

diff --git a/test/Driver/openmp-offload.c b/test/Driver/openmp-offload.c
index 8527f88b0c8cf20282311c495558160fc5e8ee12..cd2ca3e3d6e33ec0f7e8504fc2a1c29d909fe3f8 100644 (file)
--- a/test/Driver/openmp-offload.c
+++ b/test/Driver/openmp-offload.c
@@ -691,7 +691,7 @@
 /// ###########################################################################
 
 /// Check PTXAS is passed -c flag when offloading to an NVIDIA device using OpenMP.
-// RUN:   %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda %s 2>&1 \
+// RUN:   %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -no-canonical-prefixes %s 2>&1 \
 // RUN:   | FileCheck -check-prefix=CHK-PTXAS-DEFAULT %s
 
 // CHK-PTXAS-DEFAULT: ptxas{{.*}}" "-c"
@@ -699,7 +699,7 @@
 /// ###########################################################################
 
 /// PTXAS is passed -c flag by default when offloading to an NVIDIA device using OpenMP - disable it.
-// RUN:   %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -fnoopenmp-relocatable-target %s 2>&1 \
+// RUN:   %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -fnoopenmp-relocatable-target -save-temps -no-canonical-prefixes %s 2>&1 \
 // RUN:   | FileCheck -check-prefix=CHK-PTXAS-NORELO %s
 
 // CHK-PTXAS-NORELO-NOT: ptxas{{.*}}" "-c"
@@ -708,23 +708,7 @@
 
 /// 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 -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -fopenmp-relocatable-target %s 2>&1 \
+// RUN:   %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -fopenmp-relocatable-target -save-temps -no-canonical-prefixes %s 2>&1 \
 // RUN:   | FileCheck -check-prefix=CHK-PTXAS-RELO %s
 
 // CHK-PTXAS-RELO: ptxas{{.*}}" "-c"
-
-/// ###########################################################################
-
-/// Check PTXAS is passed the compute capability passed to the driver.
-// RUN:   %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda --fopenmp-ptx=+ptx52 %s 2>&1 \
-// RUN:   | FileCheck -check-prefix=CHK-PTXAS-VERSION %s
-
-// CHK-PTXAS-VERSION: clang{{.*}}.bc" {{.*}}"-target-feature" "+ptx52"
-
-/// ###########################################################################
-
-/// Check PTXAS is passed the compute capability passed to the driver.
-// RUN:   %clang -### -no-canonical-prefixes -target x86_64-apple-darwin17.0.0 -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda --fopenmp-ptx=+ptx52 %s 2>&1 \
-// RUN:   | FileCheck -check-prefix=CHK-PTXAS-DARWIN-VERSION %s
-
-// CHK-PTXAS-DARWIN-VERSION: clang{{.*}}.bc" {{.*}}"-target-feature" "+ptx52"