[Clang][OpenMP][NVPTX] Replace libomptarget-nvptx-path with libomptarget-nvptx-bc-path

shiltian · shiltian · commit 5ad038aafa3a · 2021-01-23T14:42:38.000-05:00
D94700 removed the static library so we no longer need to pass `-llibomptarget-nvptx` to `nvlink`. Since the bitcode library is the only device runtime for now, instead of emitting a warning when it is not found, an error should be raised. We also set a new option `libomptarget-nvptx-bc-path` to let user choose which bitcode library is being used. Reviewed By: JonChesterfield Differential Revision: https://reviews.llvm.org/D95161
diff --git a/clang/docs/ClangCommandLineReference.rst b/clang/docs/ClangCommandLineReference.rst
@@ -1143,9 +1143,9 @@ Set directory to include search path with prefix
 
 Add directory to SYSTEM include search path, absolute paths are relative to -isysroot
 
-.. option:: --libomptarget-nvptx-path=<arg>
+.. option:: --libomptarget-nvptx-bc-path=<arg>
 
-Path to libomptarget-nvptx libraries
+Path to libomptarget-nvptx bitcode library
 
 .. option:: --ptxas-path=<arg>
 
diff --git a/clang/include/clang/Basic/DiagnosticDriverKinds.td b/clang/include/clang/Basic/DiagnosticDriverKinds.td
@@ -263,12 +263,12 @@ def err_drv_omp_host_target_not_supported : Error<
   "The target '%0' is not a supported OpenMP host target.">;
 def err_drv_expecting_fopenmp_with_fopenmp_targets : Error<
   "The option -fopenmp-targets must be used in conjunction with a -fopenmp option compatible with offloading, please use -fopenmp=libomp or -fopenmp=libiomp5.">;
+def err_drv_omp_offload_target_missingbcruntime : Error<
+  "No library '%0' found in the default clang lib directory or in LIBRARY_PATH. Please use --libomptarget-nvptx-bc-path to specify nvptx bitcode library.">;
+def err_drv_omp_offload_target_bcruntime_not_found : Error<"Bitcode library '%0' does not exist.">;
 def warn_drv_omp_offload_target_duplicate : Warning<
   "The OpenMP offloading target '%0' is similar to target '%1' already specified - will be ignored.">,
   InGroup<OpenMPTarget>;
-def warn_drv_omp_offload_target_missingbcruntime : Warning<
-  "No library '%0' found in the default clang lib directory or in LIBRARY_PATH. Expect degraded performance due to no inlining of runtime functions on target devices.">,
-  InGroup<OpenMPTarget>;
 def err_drv_unsupported_embed_bitcode
     : Error<"%0 is not supported with -fembed-bitcode">;
 def err_drv_bitcode_unsupported_on_toolchain : Error<
diff --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td
@@ -992,8 +992,8 @@ def gpu_max_threads_per_block_EQ : Joined<["--"], "gpu-max-threads-per-block=">,
 def gpu_instrument_lib_EQ : Joined<["--"], "gpu-instrument-lib=">,
   HelpText<"Instrument device library for HIP, which is a LLVM bitcode containing "
   "__cyg_profile_func_enter and __cyg_profile_func_exit">;
-def libomptarget_nvptx_path_EQ : Joined<["--"], "libomptarget-nvptx-path=">, Group<i_Group>,
-  HelpText<"Path to libomptarget-nvptx libraries">;
+def libomptarget_nvptx_bc_path_EQ : Joined<["--"], "libomptarget-nvptx-bc-path=">, Group<i_Group>,
+  HelpText<"Path to libomptarget-nvptx bitcode library">;
 def dD : Flag<["-"], "dD">, Group<d_Group>, Flags<[CC1Option]>,
   HelpText<"Print macro definitions in -E mode in addition to normal output">;
 def dI : Flag<["-"], "dI">, Group<d_Group>, Flags<[CC1Option]>,
diff --git a/clang/lib/Driver/ToolChains/Cuda.cpp b/clang/lib/Driver/ToolChains/Cuda.cpp
@@ -600,11 +600,6 @@ void NVPTX::OpenMPLinker::ConstructJob(Compilation &C, const JobAction &JA,
   CmdArgs.push_back("-arch");
   CmdArgs.push_back(Args.MakeArgString(GPUArch));
 
-  // Assume that the directory specified with --libomptarget_nvptx_path
-  // contains the static library libomptarget-nvptx.a.
-  if (const Arg *A = Args.getLastArg(options::OPT_libomptarget_nvptx_path_EQ))
-    CmdArgs.push_back(Args.MakeArgString(Twine("-L") + A->getValue()));
-
   // Add paths specified in LIBRARY_PATH environment variable as -L options.
   addDirectoryList(Args, CmdArgs, "-L", "LIBRARY_PATH");
 
@@ -614,9 +609,6 @@ void NVPTX::OpenMPLinker::ConstructJob(Compilation &C, const JobAction &JA,
   llvm::sys::path::append(DefaultLibPath, "lib" CLANG_LIBDIR_SUFFIX);
   CmdArgs.push_back(Args.MakeArgString(Twine("-L") + DefaultLibPath));
 
-  // Add linking against library implementing OpenMP calls on NVPTX target.
-  CmdArgs.push_back("-lomptarget-nvptx");
-
   for (const auto &II : Inputs) {
     if (II.getType() == types::TY_LLVM_IR ||
         II.getType() == types::TY_LTO_IR ||
@@ -761,9 +753,6 @@ void CudaToolChain::addClangTargetOptions(
 
   if (DeviceOffloadingKind == Action::OFK_OpenMP) {
     SmallVector<StringRef, 8> LibraryPaths;
-    if (const Arg *A = DriverArgs.getLastArg(options::OPT_libomptarget_nvptx_path_EQ))
-      LibraryPaths.push_back(A->getValue());
-
     // Add user defined library paths from LIBRARY_PATH.
     llvm::Optional<std::string> LibPath =
         llvm::sys::Process::GetEnv("LIBRARY_PATH");
@@ -781,22 +770,37 @@ void CudaToolChain::addClangTargetOptions(
     llvm::sys::path::append(DefaultLibPath, Twine("lib") + CLANG_LIBDIR_SUFFIX);
     LibraryPaths.emplace_back(DefaultLibPath.c_str());
 
-    std::string LibOmpTargetName =
-      "libomptarget-nvptx-" + GpuArch.str() + ".bc";
-    bool FoundBCLibrary = false;
-    for (StringRef LibraryPath : LibraryPaths) {
-      SmallString<128> LibOmpTargetFile(LibraryPath);
-      llvm::sys::path::append(LibOmpTargetFile, LibOmpTargetName);
-      if (llvm::sys::fs::exists(LibOmpTargetFile)) {
+    // First check whether user specifies bc library
+    if (const Arg *A =
+            DriverArgs.getLastArg(options::OPT_libomptarget_nvptx_bc_path_EQ)) {
+      std::string LibOmpTargetName(A->getValue());
+      if (llvm::sys::fs::exists(LibOmpTargetName)) {
         CC1Args.push_back("-mlink-builtin-bitcode");
-        CC1Args.push_back(DriverArgs.MakeArgString(LibOmpTargetFile));
-        FoundBCLibrary = true;
-        break;
+        CC1Args.push_back(DriverArgs.MakeArgString(LibOmpTargetName));
+      } else {
+        getDriver().Diag(diag::err_drv_omp_offload_target_bcruntime_not_found)
+            << LibOmpTargetName;
+      }
+    } else {
+      bool FoundBCLibrary = false;
+
+      std::string LibOmpTargetName =
+          "libomptarget-nvptx-" + GpuArch.str() + ".bc";
+
+      for (StringRef LibraryPath : LibraryPaths) {
+        SmallString<128> LibOmpTargetFile(LibraryPath);
+        llvm::sys::path::append(LibOmpTargetFile, LibOmpTargetName);
+        if (llvm::sys::fs::exists(LibOmpTargetFile)) {
+          CC1Args.push_back("-mlink-builtin-bitcode");
+          CC1Args.push_back(DriverArgs.MakeArgString(LibOmpTargetFile));
+          FoundBCLibrary = true;
+          break;
+        }
       }
+      if (!FoundBCLibrary)
+        getDriver().Diag(diag::err_drv_omp_offload_target_missingbcruntime)
+            << LibOmpTargetName;
     }
-    if (!FoundBCLibrary)
-      getDriver().Diag(diag::warn_drv_omp_offload_target_missingbcruntime)
-          << LibOmpTargetName;
   }
 }
 
diff --git a/clang/test/Driver/Inputs/libomptarget/libomptarget-nvptx-test.bc b/clang/test/Driver/Inputs/libomptarget/libomptarget-nvptx-test.bc
diff --git a/clang/test/Driver/openmp-offload-gpu.c b/clang/test/Driver/openmp-offload-gpu.c
@@ -34,22 +34,6 @@
 
 /// ###########################################################################
 
-/// Check that -lomptarget-nvptx is passed to nvlink.
-// RUN:   %clang -### -no-canonical-prefixes -fopenmp=libomp \
-// RUN:          -fopenmp-targets=nvptx64-nvidia-cuda %s 2>&1 \
-// RUN:   | FileCheck -check-prefix=CHK-NVLINK %s
-/// Check that the value of --libomptarget-nvptx-path is forwarded to nvlink.
-// RUN:   %clang -### -no-canonical-prefixes -fopenmp=libomp \
-// RUN:          --libomptarget-nvptx-path=/path/to/libomptarget/ \
-// RUN:          -fopenmp-targets=nvptx64-nvidia-cuda %s 2>&1 \
-// RUN:   | FileCheck -check-prefixes=CHK-NVLINK,CHK-LIBOMPTARGET-NVPTX-PATH %s
-
-// CHK-NVLINK: nvlink
-// CHK-LIBOMPTARGET-NVPTX-PATH-SAME: "-L/path/to/libomptarget/"
-// CHK-NVLINK-SAME: "-lomptarget-nvptx"
-
-/// ###########################################################################
-
 /// Check cubin file generation and usage by nvlink
 // RUN:   %clang -### -no-canonical-prefixes -target powerpc64le-unknown-linux-gnu -fopenmp=libomp \
 // RUN:          -fopenmp-targets=nvptx64-nvidia-cuda -save-temps %s 2>&1 \
@@ -173,13 +157,15 @@
 // RUN:   -Xopenmp-target -march=sm_20 --cuda-path=%S/Inputs/CUDA_80/usr/local/cuda \
 // RUN:   -fopenmp-relocatable-target -save-temps -no-canonical-prefixes %s 2>&1 \
 // RUN:   | FileCheck -check-prefix=CHK-BCLIB %s
-/// The user can override default detection using --libomptarget-nvptx-path=.
-// RUN:   %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda --libomptarget-nvptx-path=%S/Inputs/libomptarget \
+/// The user can override default detection using --libomptarget-nvptx-bc-path=.
+// RUN:   %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
+// RUN:   --libomptarget-nvptx-bc-path=%S/Inputs/libomptarget/libomptarget-nvptx-test.bc \
 // RUN:   -Xopenmp-target -march=sm_20 --cuda-path=%S/Inputs/CUDA_80/usr/local/cuda \
 // RUN:   -fopenmp-relocatable-target -save-temps -no-canonical-prefixes %s 2>&1 \
-// RUN:   | FileCheck -check-prefix=CHK-BCLIB %s
+// RUN:   | FileCheck -check-prefix=CHK-BCLIB-USER %s
 
 // CHK-BCLIB: clang{{.*}}-triple{{.*}}nvptx64-nvidia-cuda{{.*}}-mlink-builtin-bitcode{{.*}}libomptarget-nvptx-sm_20.bc
+// CHK-BCLIB-USER: clang{{.*}}-triple{{.*}}nvptx64-nvidia-cuda{{.*}}-mlink-builtin-bitcode{{.*}}libomptarget-nvptx-test.bc
 // CHK-BCLIB-NOT: {{error:|warning:}}
 
 /// ###########################################################################
@@ -191,7 +177,18 @@
 // RUN:   -fopenmp-relocatable-target -save-temps -no-canonical-prefixes %s 2>&1 \
 // RUN:   | FileCheck -check-prefix=CHK-BCLIB-WARN %s
 
-// CHK-BCLIB-WARN: No library 'libomptarget-nvptx-sm_20.bc' found in the default clang lib directory or in LIBRARY_PATH. Expect degraded performance due to no inlining of runtime functions on target devices.
+// CHK-BCLIB-WARN: No library 'libomptarget-nvptx-sm_20.bc' found in the default clang lib directory or in LIBRARY_PATH. Please use --libomptarget-nvptx-bc-path to specify nvptx bitcode library.
+
+/// ###########################################################################
+
+/// Check that the error is thrown when the libomptarget bitcode library does not exist.
+// RUN:   %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
+// RUN:   -Xopenmp-target -march=sm_20 --cuda-path=%S/Inputs/CUDA_80/usr/local/cuda \
+// RUN:   --libomptarget-nvptx-bc-path=not-exist.bc \
+// RUN:   -fopenmp-relocatable-target -save-temps -no-canonical-prefixes %s 2>&1 \
+// RUN:   | FileCheck -check-prefix=CHK-BCLIB-ERROR %s
+
+// CHK-BCLIB-ERROR: Bitcode library 'not-exist.bc' does not exist.
 
 /// Check that debug info is emitted in dwarf-2
 // RUN:   %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g -O1 --no-cuda-noopt-device-debug 2>&1 \
