[OpenMP][AMDGPU] Add support for linking libomptarget bitcode

pdhaliwal-amd · pdhaliwal-amd · commit 79401b43ce4e · 2021-02-12T00:42:41.000-05:00
This patch uses the existing logic of CUDA for searching libomptarget and extracts it to a common method. Reviewed By: JonChesterfield, tianshilei1992 Differential Revision: https://reviews.llvm.org/D96248
diff --git a/clang/include/clang/Basic/DiagnosticDriverKinds.td b/clang/include/clang/Basic/DiagnosticDriverKinds.td
@@ -261,7 +261,7 @@ def err_drv_omp_host_target_not_supported : Error<
 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.">;
+  "No library '%0' found in the default clang lib directory or in LIBRARY_PATH. Please use --libomptarget-%1-bc-path to specify %1 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.">,
diff --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td
@@ -942,6 +942,8 @@ def fuse_cuid_EQ : Joined<["-"], "fuse-cuid=">,
            "file path and command line options) | 'random' (ID's generated as "
            "random numbers) | 'none' (disabled). Default is 'hash'. This option "
            "will be overriden by option '-cuid=[ID]' if it is specified." >;
+def libomptarget_amdgcn_bc_path_EQ : Joined<["--"], "libomptarget-amdgcn-bc-path=">, Group<i_Group>,
+  HelpText<"Path to libomptarget-amdgcn bitcode library">;
 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]>,
diff --git a/clang/lib/Driver/ToolChains/AMDGPUOpenMP.cpp b/clang/lib/Driver/ToolChains/AMDGPUOpenMP.cpp
@@ -190,6 +190,12 @@ void AMDGPUOpenMPToolChain::addClangTargetOptions(
   CC1Args.push_back(DriverArgs.MakeArgStringRef(GpuArch));
   CC1Args.push_back("-fcuda-is-device");
   CC1Args.push_back("-emit-llvm-bc");
+
+  if (DriverArgs.hasArg(options::OPT_nogpulib))
+    return;
+  std::string BitcodeSuffix = "amdgcn-" + GpuArch.str();
+  addOpenMPDeviceRTL(getDriver(), DriverArgs, CC1Args, BitcodeSuffix,
+                     getTriple());
 }
 
 llvm::opt::DerivedArgList *AMDGPUOpenMPToolChain::TranslateArgs(
diff --git a/clang/lib/Driver/ToolChains/CommonArgs.cpp b/clang/lib/Driver/ToolChains/CommonArgs.cpp
@@ -1627,3 +1627,63 @@ void tools::addMachineOutlinerArgs(const Driver &D,
     }
   }
 }
+
+void tools::addOpenMPDeviceRTL(const Driver &D,
+                               const llvm::opt::ArgList &DriverArgs,
+                               llvm::opt::ArgStringList &CC1Args,
+                               StringRef BitcodeSuffix,
+                               const llvm::Triple &Triple) {
+  SmallVector<StringRef, 8> LibraryPaths;
+  // Add user defined library paths from LIBRARY_PATH.
+  llvm::Optional<std::string> LibPath =
+      llvm::sys::Process::GetEnv("LIBRARY_PATH");
+  if (LibPath) {
+    SmallVector<StringRef, 8> Frags;
+    const char EnvPathSeparatorStr[] = {llvm::sys::EnvPathSeparator, '\0'};
+    llvm::SplitString(*LibPath, Frags, EnvPathSeparatorStr);
+    for (StringRef Path : Frags)
+      LibraryPaths.emplace_back(Path.trim());
+  }
+
+  // Add path to lib / lib64 folder.
+  SmallString<256> DefaultLibPath = llvm::sys::path::parent_path(D.Dir);
+  llvm::sys::path::append(DefaultLibPath, Twine("lib") + CLANG_LIBDIR_SUFFIX);
+  LibraryPaths.emplace_back(DefaultLibPath.c_str());
+
+  OptSpecifier LibomptargetBCPathOpt =
+      Triple.isAMDGCN() ? options::OPT_libomptarget_amdgcn_bc_path_EQ
+                        : options::OPT_libomptarget_nvptx_bc_path_EQ;
+
+  StringRef ArchPrefix = Triple.isAMDGCN() ? "amdgcn" : "nvptx";
+  // First check whether user specifies bc library
+  if (const Arg *A = DriverArgs.getLastArg(LibomptargetBCPathOpt)) {
+    std::string LibOmpTargetName(A->getValue());
+    if (llvm::sys::fs::exists(LibOmpTargetName)) {
+      CC1Args.push_back("-mlink-builtin-bitcode");
+      CC1Args.push_back(DriverArgs.MakeArgString(LibOmpTargetName));
+    } else {
+      D.Diag(diag::err_drv_omp_offload_target_bcruntime_not_found)
+          << LibOmpTargetName;
+    }
+  } else {
+    bool FoundBCLibrary = false;
+
+    std::string LibOmpTargetName =
+        "libomptarget-" + BitcodeSuffix.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)
+      D.Diag(diag::err_drv_omp_offload_target_missingbcruntime)
+          << LibOmpTargetName << ArchPrefix;
+  }
+}
diff --git a/clang/lib/Driver/ToolChains/CommonArgs.h b/clang/lib/Driver/ToolChains/CommonArgs.h
@@ -145,6 +145,10 @@ unsigned getOrCheckAMDGPUCodeObjectVersion(const Driver &D,
 void addMachineOutlinerArgs(const Driver &D, const llvm::opt::ArgList &Args,
                             llvm::opt::ArgStringList &CmdArgs,
                             const llvm::Triple &Triple, bool IsLTO);
+
+void addOpenMPDeviceRTL(const Driver &D, const llvm::opt::ArgList &DriverArgs,
+                        llvm::opt::ArgStringList &CC1Args,
+                        StringRef BitcodeSuffix, const llvm::Triple &Triple);
 } // end namespace tools
 } // end namespace driver
 } // end namespace clang
diff --git a/clang/lib/Driver/ToolChains/Cuda.cpp b/clang/lib/Driver/ToolChains/Cuda.cpp
@@ -749,56 +749,10 @@ void CudaToolChain::addClangTargetOptions(
         CudaVersionToString(CudaInstallation.version())));
 
   if (DeviceOffloadingKind == Action::OFK_OpenMP) {
-    SmallVector<StringRef, 8> LibraryPaths;
-    // Add user defined library paths from LIBRARY_PATH.
-    llvm::Optional<std::string> LibPath =
-        llvm::sys::Process::GetEnv("LIBRARY_PATH");
-    if (LibPath) {
-      SmallVector<StringRef, 8> Frags;
-      const char EnvPathSeparatorStr[] = {llvm::sys::EnvPathSeparator, '\0'};
-      llvm::SplitString(*LibPath, Frags, EnvPathSeparatorStr);
-      for (StringRef Path : Frags)
-        LibraryPaths.emplace_back(Path.trim());
-    }
-
-    // Add path to lib / lib64 folder.
-    SmallString<256> DefaultLibPath =
-        llvm::sys::path::parent_path(getDriver().Dir);
-    llvm::sys::path::append(DefaultLibPath, Twine("lib") + CLANG_LIBDIR_SUFFIX);
-    LibraryPaths.emplace_back(DefaultLibPath.c_str());
-
-    // 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(LibOmpTargetName));
-      } else {
-        getDriver().Diag(diag::err_drv_omp_offload_target_bcruntime_not_found)
-            << LibOmpTargetName;
-      }
-    } else {
-      bool FoundBCLibrary = false;
-
-      std::string LibOmpTargetName = "libomptarget-nvptx-cuda_" +
-                                     CudaVersionStr + "-" + 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;
-    }
+    std::string BitcodeSuffix =
+        "nvptx-cuda_" + CudaVersionStr + "-" + GpuArch.str();
+    addOpenMPDeviceRTL(getDriver(), DriverArgs, CC1Args, BitcodeSuffix,
+                       getTriple());
   }
 }
 
diff --git a/clang/test/Driver/Inputs/hip_dev_lib/libomptarget-amdgcn-gfx803.bc b/clang/test/Driver/Inputs/hip_dev_lib/libomptarget-amdgcn-gfx803.bc
diff --git a/clang/test/Driver/Inputs/hip_dev_lib/libomptarget-amdgcn-gfx906.bc b/clang/test/Driver/Inputs/hip_dev_lib/libomptarget-amdgcn-gfx906.bc
diff --git a/clang/test/Driver/amdgpu-openmp-toolchain.c b/clang/test/Driver/amdgpu-openmp-toolchain.c
@@ -1,11 +1,11 @@
 // REQUIRES: amdgpu-registered-target
-// RUN:   %clang -### --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx906 %s 2>&1 \
+// RUN:   env LIBRARY_PATH=%S/Inputs/hip_dev_lib %clang -### --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx906 %s 2>&1 \
 // RUN:   | FileCheck %s
 
 // verify the tools invocations
 // CHECK: clang{{.*}}"-cc1" "-triple" "x86_64-unknown-linux-gnu"{{.*}}"-x" "c"{{.*}}
 // CHECK: clang{{.*}}"-cc1" "-triple" "x86_64-unknown-linux-gnu"{{.*}}"-x" "ir"{{.*}}
-// CHECK: clang{{.*}}"-cc1"{{.*}}"-triple" "amdgcn-amd-amdhsa"{{.*}}"-target-cpu" "gfx906" "-fcuda-is-device" "-emit-llvm-bc"{{.*}}
+// CHECK: clang{{.*}}"-cc1"{{.*}}"-triple" "amdgcn-amd-amdhsa"{{.*}}"-target-cpu" "gfx906" "-fcuda-is-device" "-emit-llvm-bc" "-mlink-builtin-bitcode"{{.*}}libomptarget-amdgcn-gfx906.bc"{{.*}}
 // CHECK: llvm-link{{.*}}"-o" "{{.*}}amdgpu-openmp-toolchain-{{.*}}-gfx906-linked-{{.*}}.bc"
 // CHECK: llc{{.*}}amdgpu-openmp-toolchain-{{.*}}-gfx906-linked-{{.*}}.bc" "-mtriple=amdgcn-amd-amdhsa" "-mcpu=gfx906" "-filetype=obj" "-o"{{.*}}amdgpu-openmp-toolchain-{{.*}}-gfx906-{{.*}}.o"
 // CHECK: lld{{.*}}"-flavor" "gnu" "--no-undefined" "-shared" "-o"{{.*}}amdgpu-openmp-toolchain-{{.*}}.out" "{{.*}}amdgpu-openmp-toolchain-{{.*}}-gfx906-{{.*}}.o"
@@ -34,3 +34,9 @@
 // CHECK-PHASES: 15: assembler, {14}, object, (host-openmp)
 // CHECK-PHASES: 16: linker, {4, 15}, image, (host-openmp)
 
+// handling of --libomptarget-amdgcn-bc-path
+// RUN:   %clang -### --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx803 --libomptarget-amdgcn-bc-path=%S/Inputs/hip_dev_lib/libomptarget-amdgcn-gfx803.bc %s 2>&1 | FileCheck %s --check-prefix=CHECK-LIBOMPTARGET
+// CHECK-LIBOMPTARGET: clang{{.*}}"-cc1"{{.*}}"-triple" "amdgcn-amd-amdhsa"{{.*}}"-target-cpu" "gfx803" "-fcuda-is-device" "-emit-llvm-bc" "-mlink-builtin-bitcode"{{.*}}Inputs/hip_dev_lib/libomptarget-amdgcn-gfx803.bc"{{.*}}
+
+// RUN:   %clang -### --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx803 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-NOGPULIB
+// CHECK-NOGPULIB-NOT: clang{{.*}}"-cc1"{{.*}}"-triple" "amdgcn-amd-amdhsa"{{.*}}"-target-cpu" "gfx803" "-fcuda-is-device" "-emit-llvm-bc" "-mlink-builtin-bitcode"{{.*}}libomptarget-amdgcn-gfx803.bc"{{.*}}
