[HIP] Use -mlink-builtin-bitcode to link device library

[yaxunl]

Summary

Use -mlink-builtin-bitcode instead of llvm-link to link
device library so that device library bitcode and user
device code can be compiled in a consistent way.

This is the same approach used by CUDA and OpenMP.

[ashi1]

LGTM

cfe/trunk/lib/Driver/ToolChains/HIP.cpp

 #if _WIN32 || _WIN64
 #define NULL_FILE "nul"
 #else
 #define NULL_FILE "/dev/null"
 #endif
 
 namespace {
 
-static void addBCLib(Compilation &C, const ArgList &Args,
+static void addBCLib(const Driver &D, const ArgList &Args,
                      ArgStringList &CmdArgs, ArgStringList LibraryPaths,
                      StringRef BCName) {
   StringRef FullName;
   for (std::string LibraryPath : LibraryPaths) {
     SmallString<128> Path(LibraryPath);
     llvm::sys::path::append(Path, BCName);
     FullName = Path;
     if (llvm::sys::fs::exists(FullName)) {
+      CmdArgs.push_back("-mlink-builtin-bitcode");
       CmdArgs.push_back(Args.MakeArgString(FullName));
       return;
     }
   }
-  C.getDriver().Diag(diag::err_drv_no_such_file) << BCName;
+  D.Diag(diag::err_drv_no_such_file) << BCName;
 }
 
 } // namespace
 
 const char *AMDGCN::Linker::constructLLVMLinkCommand(
     Compilation &C, const JobAction &JA, const InputInfoList &Inputs,
     const ArgList &Args, StringRef SubArchName,
     StringRef OutputFilePrefix) const {
   ArgStringList CmdArgs;
   // Add the input bc's created by compile step.
   for (const auto &II : Inputs)
     CmdArgs.push_back(II.getFilename());
 
-  ArgStringList LibraryPaths;
-
-  // Find in --hip-device-lib-path and HIP_LIBRARY_PATH.
-  for (auto Path : Args.getAllArgValues(options::OPT_hip_device_lib_path_EQ))
-    LibraryPaths.push_back(Args.MakeArgString(Path));
-
-  addDirectoryList(Args, LibraryPaths, "-L", "HIP_DEVICE_LIB_PATH");
-
-  llvm::SmallVector<std::string, 10> BCLibs;
-
-  // Add bitcode library in --hip-device-lib.
-  for (auto Lib : Args.getAllArgValues(options::OPT_hip_device_lib_EQ)) {
-    BCLibs.push_back(Args.MakeArgString(Lib));
-  }
-
-  // If --hip-device-lib is not set, add the default bitcode libraries.
-  if (BCLibs.empty()) {
-    // Get the bc lib file name for ISA version. For example,
-    // gfx803 => oclc_isa_version_803.amdgcn.bc.
-    std::string ISAVerBC =
-        "oclc_isa_version_" + SubArchName.drop_front(3).str() + ".amdgcn.bc";
-
-    llvm::StringRef FlushDenormalControlBC;
-    if (Args.hasArg(options::OPT_fcuda_flush_denormals_to_zero))
-      FlushDenormalControlBC = "oclc_daz_opt_on.amdgcn.bc";
-    else
-      FlushDenormalControlBC = "oclc_daz_opt_off.amdgcn.bc";
-
-    BCLibs.append({"hip.amdgcn.bc", "opencl.amdgcn.bc",
-                   "ocml.amdgcn.bc", "ockl.amdgcn.bc",
-                   "oclc_finite_only_off.amdgcn.bc",
-                   FlushDenormalControlBC,
-                   "oclc_correctly_rounded_sqrt_on.amdgcn.bc",
-                   "oclc_unsafe_math_off.amdgcn.bc", ISAVerBC});
-  }
-  for (auto Lib : BCLibs)
-    addBCLib(C, Args, CmdArgs, LibraryPaths, Lib);
-
   // Add an intermediate output file.
   CmdArgs.push_back("-o");
   std::string TmpName =
       C.getDriver().GetTemporaryPath(OutputFilePrefix.str() + "-linked", "bc");
   const char *OutputFileName =
       C.addTempFile(C.getArgs().MakeArgString(TmpName));
   CmdArgs.push_back(OutputFileName);
   SmallString<128> ExecPath(C.getDriver().Dir);
void HIPToolChain::addClangTargetOptions(
 
   // Default to "hidden" visibility, as object level linking will not be
   // supported for the foreseeable future.
   if (!DriverArgs.hasArg(options::OPT_fvisibility_EQ,
                          options::OPT_fvisibility_ms_compat)) {
     CC1Args.append({"-fvisibility", "hidden"});
     CC1Args.push_back("-fapply-global-visibility-to-externs");
   }
+  ArgStringList LibraryPaths;
+
+  // Find in --hip-device-lib-path and HIP_LIBRARY_PATH.
+  for (auto Path :
+       DriverArgs.getAllArgValues(options::OPT_hip_device_lib_path_EQ))
+    LibraryPaths.push_back(DriverArgs.MakeArgString(Path));
+
+  addDirectoryList(DriverArgs, LibraryPaths, "-L", "HIP_DEVICE_LIB_PATH");
+
+  llvm::SmallVector<std::string, 10> BCLibs;
+
+  // Add bitcode library in --hip-device-lib.
+  for (auto Lib : DriverArgs.getAllArgValues(options::OPT_hip_device_lib_EQ)) {
+    BCLibs.push_back(DriverArgs.MakeArgString(Lib));
+  }
+
+  // If --hip-device-lib is not set, add the default bitcode libraries.
+  if (BCLibs.empty()) {
+    // Get the bc lib file name for ISA version. For example,
+    // gfx803 => oclc_isa_version_803.amdgcn.bc.
+    std::string ISAVerBC =
+        "oclc_isa_version_" + GpuArch.drop_front(3).str() + ".amdgcn.bc";
+
+    llvm::StringRef FlushDenormalControlBC;
+    if (DriverArgs.hasArg(options::OPT_fcuda_flush_denormals_to_zero))
+      FlushDenormalControlBC = "oclc_daz_opt_on.amdgcn.bc";
+    else
+      FlushDenormalControlBC = "oclc_daz_opt_off.amdgcn.bc";
+
+    BCLibs.append({"hip.amdgcn.bc", "opencl.amdgcn.bc", "ocml.amdgcn.bc",
+                   "ockl.amdgcn.bc", "oclc_finite_only_off.amdgcn.bc",
+                   FlushDenormalControlBC,
+                   "oclc_correctly_rounded_sqrt_on.amdgcn.bc",
+                   "oclc_unsafe_math_off.amdgcn.bc", ISAVerBC});
+  }
+  for (auto Lib : BCLibs)
+    addBCLib(getDriver(), DriverArgs, CC1Args, LibraryPaths, Lib);
+
 }
 
 llvm::opt::DerivedArgList *
 HIPToolChain::TranslateArgs(const llvm::opt::DerivedArgList &Args,
                              StringRef BoundArch,
                              Action::OffloadKind DeviceOffloadKind) const {
   DerivedArgList *DAL =
       HostTC.TranslateArgs(Args, BoundArch, DeviceOffloadKind);

cfe/trunk/test/Driver/hip-device-libs.hip

 
 // RUN: %clang -### -target x86_64-linux-gnu \
 // RUN:   -x hip --cuda-gpu-arch=gfx900 \
 // RUN:   --hip-device-lib-path=%S/Inputs/hip_dev_lib \
 // RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
 // RUN: 2>&1 | FileCheck %s --check-prefixes=COM,NOFLUSHD
 
 
-// COM: [[LLVM_LINK:"*.llvm-link"]]
-// COM-SAME: "{{.*}}hip.amdgcn.bc" "{{.*}}opencl.amdgcn.bc"
-// COM-SAME: "{{.*}}ocml.amdgcn.bc" "{{.*}}ockl.amdgcn.bc"
-// FLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
-// NOFLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_off.amdgcn.bc"
-// COM-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"
+// COM: {{"[^"]*clang[^"]*"}}
+// COM-SAME: "-mlink-builtin-bitcode" "{{.*}}hip.amdgcn.bc"
+// COM-SAME: "-mlink-builtin-bitcode" "{{.*}}opencl.amdgcn.bc"
+// COM-SAME: "-mlink-builtin-bitcode" "{{.*}}ocml.amdgcn.bc"
+// COM-SAME: "-mlink-builtin-bitcode" "{{.*}}ockl.amdgcn.bc"
+// FLUSHD-SAME: "-mlink-builtin-bitcode" "{{.*}}oclc_daz_opt_on.amdgcn.bc"
+// NOFLUSHD-SAME: "-mlink-builtin-bitcode" "{{.*}}oclc_daz_opt_off.amdgcn.bc"
 

cfe/trunk/test/Driver/hip-toolchain-no-rdc.hip

 //
 
 // CHECK: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME: "-emit-llvm-bc"
 // CHECK-SAME: {{.*}} "-main-file-name" "a.cu" {{.*}} "-target-cpu" "gfx803"
 // CHECK-SAME: "-fcuda-is-device" "-fvisibility" "hidden"
 // CHECK-SAME: "-fapply-global-visibility-to-externs"
+// CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: {{.*}} "-o" [[A_BC_803:".*bc"]] "-x" "hip"
 // CHECK-SAME: {{.*}} [[A_SRC:".*a.cu"]]
 
 // CHECK: [[LLVM_LINK:"*.llvm-link"]] [[A_BC_803]]
-// CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: "-o" [[LINKED_BC_DEV_A_803:".*-gfx803-linked-.*bc"]]
 
 // CHECK: [[OPT:".*opt"]] [[LINKED_BC_DEV_A_803]] "-mtriple=amdgcn-amd-amdhsa"
 // CHECK-SAME: "-mcpu=gfx803"
 // CHECK-SAME: "-o" [[OPT_BC_DEV_A_803:".*-gfx803-optimized.*bc"]]
 
 // CHECK: [[LLC: ".*llc"]] [[OPT_BC_DEV_A_803]] "-mtriple=amdgcn-amd-amdhsa"
 // CHECK-SAME: "-filetype=obj"
 // CHECK-SAME: "-mcpu=gfx803" "-o" [[OBJ_DEV_A_803:".*-gfx803-.*o"]]
 
 // CHECK: [[LLD: ".*lld"]] "-flavor" "gnu" "--no-undefined" "-shared"
 // CHECK-SAME: "-o" "[[IMG_DEV_A_803:.*out]]" [[OBJ_DEV_A_803]]
 
 //
 // Compile device code in a.cu to code object for gfx900.
 //
 
 // CHECK: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME: "-emit-llvm-bc"
 // CHECK-SAME: {{.*}} "-main-file-name" "a.cu" {{.*}} "-target-cpu" "gfx900"
 // CHECK-SAME: "-fcuda-is-device" "-fvisibility" "hidden"
 // CHECK-SAME: "-fapply-global-visibility-to-externs"
+// CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: {{.*}} "-o" [[A_BC_900:".*bc"]] "-x" "hip"
 // CHECK-SAME: {{.*}} [[A_SRC]]
 
 // CHECK: [[LLVM_LINK:"*.llvm-link"]] [[A_BC_900]]
-// CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: "-o" [[LINKED_BC_DEV_A_900:".*-gfx900-linked-.*bc"]]
 
 // CHECK: [[OPT:".*opt"]] [[LINKED_BC_DEV_A_900]] "-mtriple=amdgcn-amd-amdhsa"
 // CHECK-SAME: "-mcpu=gfx900"
 // CHECK-SAME: "-o" [[OPT_BC_DEV_A_900:".*-gfx900-optimized.*bc"]]
 
 // CHECK: [[LLC: ".*llc"]] [[OPT_BC_DEV_A_900]] "-mtriple=amdgcn-amd-amdhsa"
 // CHECK-SAME: "-filetype=obj"

 //
 
 // CHECK: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME: "-emit-llvm-bc"
 // CHECK-SAME: {{.*}} "-main-file-name" "b.hip" {{.*}} "-target-cpu" "gfx803"
 // CHECK-SAME: "-fcuda-is-device" "-fvisibility" "hidden"
 // CHECK-SAME: "-fapply-global-visibility-to-externs"
+// CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: {{.*}} "-o" [[B_BC_803:".*bc"]] "-x" "hip"
 // CHECK-SAME: {{.*}} [[B_SRC:".*b.hip"]]
 
 // CHECK: [[LLVM_LINK:"*.llvm-link"]] [[B_BC_803]]
-// CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: "-o" [[LINKED_BC_DEV_B_803:".*-gfx803-linked-.*bc"]]
 
 // CHECK: [[OPT:".*opt"]] [[LINKED_BC_DEV_B_803]] "-mtriple=amdgcn-amd-amdhsa"
 // CHECK-SAME: "-mcpu=gfx803"
 // CHECK-SAME: "-o" [[OPT_BC_DEV_B_803:".*-gfx803-optimized.*bc"]]
 
 // CHECK: [[LLC: ".*llc"]] [[OPT_BC_DEV_B_803]] "-mtriple=amdgcn-amd-amdhsa"
 // CHECK-SAME: "-filetype=obj"
 // CHECK-SAME: "-mcpu=gfx803" "-o" [[OBJ_DEV_B_803:".*-gfx803-.*o"]]
 
 // CHECK: [[LLD: ".*lld"]] "-flavor" "gnu" "--no-undefined" "-shared"
 // CHECK-SAME: "-o" "[[IMG_DEV_B_803:.*out]]" [[OBJ_DEV_B_803]]
 
 //
 // Compile device code in b.hip to code object for gfx900.
 //
 
 // CHECK: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME: "-emit-llvm-bc"
 // CHECK-SAME: {{.*}} "-main-file-name" "b.hip" {{.*}} "-target-cpu" "gfx900"
 // CHECK-SAME: "-fcuda-is-device" "-fvisibility" "hidden"
 // CHECK-SAME: "-fapply-global-visibility-to-externs"
+// CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: {{.*}} "-o" [[B_BC_900:".*bc"]] "-x" "hip"
 // CHECK-SAME: {{.*}} [[B_SRC]]
 
 // CHECK: [[LLVM_LINK:"*.llvm-link"]] [[B_BC_900]]
-// CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: "-o" [[LINKED_BC_DEV_B_900:".*-gfx900-linked-.*bc"]]
 
 // CHECK: [[OPT:".*opt"]] [[LINKED_BC_DEV_B_900]] "-mtriple=amdgcn-amd-amdhsa"
 // CHECK-SAME: "-mcpu=gfx900"
 // CHECK-SAME: "-o" [[OPT_BC_DEV_B_900:".*-gfx900-optimized.*bc"]]
 
 // CHECK: [[LLC: ".*llc"]] [[OPT_BC_DEV_B_900]] "-mtriple=amdgcn-amd-amdhsa"
 // CHECK-SAME: "-filetype=obj"

cfe/trunk/test/Driver/hip-toolchain-rdc.hip

 // RUN: 2>&1 | FileCheck %s
 
 // CHECK: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME: "-emit-llvm-bc"
 // CHECK-SAME: {{.*}} "-main-file-name" "a.cu" {{.*}} "-target-cpu" "gfx803"
 // CHECK-SAME: "-fcuda-is-device" "-fgpu-rdc" "-fvisibility" "hidden"
 // CHECK-SAME: "-fapply-global-visibility-to-externs"
+// CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: {{.*}} "-o" [[A_BC:".*bc"]] "-x" "hip"
 // CHECK-SAME: {{.*}} [[A_SRC:".*a.cu"]]
 
 // CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME: "-emit-llvm-bc"
 // CHECK-SAME: {{.*}} "-main-file-name" "b.hip" {{.*}} "-target-cpu" "gfx803"
 // CHECK-SAME: "-fcuda-is-device" "-fgpu-rdc" "-fvisibility" "hidden"
 // CHECK-SAME: "-fapply-global-visibility-to-externs"
+// CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: {{.*}} "-o" [[B_BC:".*bc"]] "-x" "hip"
 // CHECK-SAME: {{.*}} [[B_SRC:".*b.hip"]]
 
 // CHECK: [[LLVM_LINK:"*.llvm-link"]] [[A_BC]] [[B_BC]]
-// CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: "-o" [[LINKED_BC_DEV1:".*-gfx803-linked-.*bc"]]
 
 // CHECK: [[OPT:".*opt"]] [[LINKED_BC_DEV1]] "-mtriple=amdgcn-amd-amdhsa"
 // CHECK-SAME: "-mcpu=gfx803"
 // CHECK-SAME: "-o" [[OPT_BC_DEV1:".*-gfx803-optimized.*bc"]]
 
 // CHECK: [[LLC: ".*llc"]] [[OPT_BC_DEV1]] "-mtriple=amdgcn-amd-amdhsa"
 // CHECK-SAME: "-filetype=obj"
 // CHECK-SAME: "-mcpu=gfx803" "-o" [[OBJ_DEV1:".*-gfx803-.*o"]]
 
 // CHECK: [[LLD: ".*lld"]] "-flavor" "gnu" "--no-undefined" "-shared"
 // CHECK-SAME: "-o" "[[IMG_DEV1:.*out]]" [[OBJ_DEV1]]
 
 // CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa" 
 // CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME: "-emit-llvm-bc"
 // CHECK-SAME: {{.*}} "-main-file-name" "a.cu" {{.*}} "-target-cpu" "gfx900"
-// CHECK-SAME: "-fcuda-is-device" {{.*}} "-o" [[A_BC:".*bc"]] "-x" "hip"
+// CHECK-SAME: "-fcuda-is-device" "-fgpu-rdc"
+// CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
+// CHECK-SAME: {{.*}} "-o" [[A_BC:".*bc"]] "-x" "hip"
 // CHECK-SAME: {{.*}} [[A_SRC]]
 
 // CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME: "-emit-llvm-bc"
 // CHECK-SAME: {{.*}} "-main-file-name" "b.hip" {{.*}} "-target-cpu" "gfx900"
-// CHECK-SAME: "-fcuda-is-device" {{.*}} "-o" [[B_BC:".*bc"]] "-x" "hip"
+// CHECK-SAME: "-fcuda-is-device" "-fgpu-rdc"
+// CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
+// CHECK-SAME: {{.*}} "-o" [[B_BC:".*bc"]] "-x" "hip"
 // CHECK-SAME: {{.*}} [[B_SRC]]
 
 // CHECK: [[LLVM_LINK]] [[A_BC]] [[B_BC]]
-// CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: "-o" [[LINKED_BC_DEV2:".*-gfx900-linked-.*bc"]]
 
 // CHECK: [[OPT]] [[LINKED_BC_DEV2]] "-mtriple=amdgcn-amd-amdhsa"
 // CHECK-SAME: "-mcpu=gfx900"
 // CHECK-SAME: "-o" [[OPT_BC_DEV2:".*-gfx900-optimized.*bc"]]
 
 // CHECK: [[LLC]] [[OPT_BC_DEV2]] "-mtriple=amdgcn-amd-amdhsa"
 // CHECK-SAME: "-filetype=obj"