[AMDGPU] Add -mcode-object-version=n

[yaxunl]

Summary

Add option -mcode-object-version=n to control code object version for
AMDGPU.

[yaxunl]

ping

[kzhuravl]

LGTM

clang/docs/ClangCommandLineReference.rst

 Align selected branches (fused, jcc, jmp) within 32-byte boundary
 
 .. option:: -mcmodel=<arg>, -mcmodel=medany (equivalent to -mcmodel=medium), -mcmodel=medlow (equivalent to -mcmodel=small)
 
 .. option:: -mcode-object-v3, -mno-code-object-v3
 
 Legacy option to specify code object ABI V2 (-mnocode-object-v3) or V3 (-mcode-object-v3) (AMDGPU only)
 
+.. option:: -mcode-object-version=<version>
+
+Specify code object ABI version. Defaults to 4. (AMDGPU only)
+
 .. option:: -mconsole<arg>
 
 .. program:: clang1
 .. option:: -mcpu=<arg>, -mv5 (equivalent to -mcpu=hexagonv5), -mv55 (equivalent to -mcpu=hexagonv55), -mv60 (equivalent to -mcpu=hexagonv60), -mv62 (equivalent to -mcpu=hexagonv62), -mv65 (equivalent to -mcpu=hexagonv65), -mv66 (equivalent to -mcpu=hexagonv66), -mv67 (equivalent to -mcpu=hexagonv67), -mv67t (equivalent to -mcpu=hexagonv67t)
 .. program:: clang
 
 .. option:: -mcrc, -mno-crc
 

clang/include/clang/Driver/Options.td

 def mtail_call : Flag<["-"], "mtail-call">, Group<m_wasm_Features_Group>;
 def mno_tail_call : Flag<["-"], "mno-tail-call">, Group<m_wasm_Features_Group>;
 def mreference_types : Flag<["-"], "mreference-types">, Group<m_wasm_Features_Group>;
 def mno_reference_types : Flag<["-"], "mno-reference-types">, Group<m_wasm_Features_Group>;
 def mexec_model_EQ : Joined<["-"], "mexec-model=">, Group<m_wasm_Features_Driver_Group>,
                      Values<"command,reactor">,
                      HelpText<"Execution model (WebAssembly only)">;
 
+def mcode_object_version_EQ : Joined<["-"], "mcode-object-version=">, Group<m_Group>,
+  HelpText<"Specify code object ABI version. Defaults to 4. (AMDGPU only)">,
+  MetaVarName<"<version>">, Values<"2,3,4">;
+
 def mcode_object_v3_legacy : Flag<["-"], "mcode-object-v3">, Group<m_Group>,
   HelpText<"Legacy option to specify code object ABI V2 (-mnocode-object-v3) or V3 (-mcode-object-v3) (AMDGPU only)">;
 def mno_code_object_v3_legacy : Flag<["-"], "mno-code-object-v3">, Group<m_Group>;
 
 def mcumode : Flag<["-"], "mcumode">, Group<m_amdgpu_Features_Group>,
   HelpText<"Specify CU (-mcumode) or WGP (-mno-cumode) wavefront execution mode (AMDGPU only)">;
 def mno_cumode : Flag<["-"], "mno-cumode">, Group<m_amdgpu_Features_Group>;
 

clang/lib/Driver/ToolChains/AMDGPU.cpp

void amdgpu::getAMDGPUTargetFeatures(const Driver &D,
   handleTargetFeaturesGroup(
     Args, Features, options::OPT_m_amdgpu_Features_Group);
 }
 
 /// AMDGPU Toolchain
 AMDGPUToolChain::AMDGPUToolChain(const Driver &D, const llvm::Triple &Triple,
                                  const ArgList &Args)
     : Generic_ELF(D, Triple, Args),
-      OptionsDefault({{options::OPT_O, "3"},
-                      {options::OPT_cl_std_EQ, "CL1.2"}}) {}
+      OptionsDefault(
+          {{options::OPT_O, "3"}, {options::OPT_cl_std_EQ, "CL1.2"}}) {
+  // Check code object version options. Emit warnings for legacy options
+  // and errors for the last invalid code object version options.
+  // It is done here to avoid repeated warning or error messages for
+  // each tool invocation.
+  (void)getOrCheckAMDGPUCodeObjectVersion(D, Args, /*Diagnose=*/true);
+}
 
 Tool *AMDGPUToolChain::buildLinker() const {
   return new tools::amdgpu::Linker(*this);
 }
 
 DerivedArgList *
 AMDGPUToolChain::TranslateArgs(const DerivedArgList &Args, StringRef BoundArch,
                                Action::OffloadKind DeviceOffloadKind) const {

clang/lib/Driver/ToolChains/Clang.cpp

case llvm::Reloc::ROPI:
     return "ropi";
   case llvm::Reloc::RWPI:
     return "rwpi";
   case llvm::Reloc::ROPI_RWPI:
     return "ropi-rwpi";
   }
   llvm_unreachable("Unknown Reloc::Model kind");
 }
-
-static void HandleAmdgcnLegacyOptions(const Driver &D,
+static void handleAMDGPUCodeObjectVersionOptions(const Driver &D,
                                                  const ArgList &Args,
                                                  ArgStringList &CmdArgs) {
-  if (auto *CodeObjArg = Args.getLastArg(options::OPT_mcode_object_v3_legacy,
-                                         options::OPT_mno_code_object_v3_legacy)) {
-    if (CodeObjArg->getOption().getID() == options::OPT_mcode_object_v3_legacy) {
-      D.Diag(diag::warn_drv_deprecated_arg) << "-mcode-object-v3" <<
-        "-mllvm --amdhsa-code-object-version=3";
-      CmdArgs.push_back("-mllvm");
-      CmdArgs.push_back("--amdhsa-code-object-version=3");
-    } else {
-      D.Diag(diag::warn_drv_deprecated_arg) << "-mno-code-object-v3" <<
-        "-mllvm --amdhsa-code-object-version=2";
-      CmdArgs.push_back("-mllvm");
-      CmdArgs.push_back("--amdhsa-code-object-version=2");
-    }
-  }
+  unsigned CodeObjVer = getOrCheckAMDGPUCodeObjectVersion(D, Args);
+  CmdArgs.insert(CmdArgs.begin() + 1,
+                 Args.MakeArgString(Twine("--amdhsa-code-object-version=") +
+                                    Twine(CodeObjVer)));
+  CmdArgs.insert(CmdArgs.begin() + 1, "-mllvm");
 }
 
 void Clang::AddPreprocessingOptions(Compilation &C, const JobAction &JA,
                                     const Driver &D, const ArgList &Args,
                                     ArgStringList &CmdArgs,
                                     const InputInfo &Output,
                                     const InputInfoList &Inputs) const {
   const bool IsIAMCU = getToolChain().getTriple().isOSIAMCU();

   if (IsOpenMPDevice) {
     CmdArgs.push_back("-fopenmp-is-device");
     if (OpenMPDeviceInput) {
       CmdArgs.push_back("-fopenmp-host-ir-file-path");
       CmdArgs.push_back(Args.MakeArgString(OpenMPDeviceInput->getFilename()));
     }
   }
 
-  HandleAmdgcnLegacyOptions(D, Args, CmdArgs);
   if (Triple.isAMDGPU()) {
+    handleAMDGPUCodeObjectVersionOptions(D, Args, CmdArgs);
+
     if (Args.hasFlag(options::OPT_munsafe_fp_atomics,
                      options::OPT_mno_unsafe_fp_atomics))
       CmdArgs.push_back("-munsafe-fp-atomics");
   }
 
   // For all the host OpenMP offloading compile jobs we need to pass the targets
   // information using -fopenmp-targets= option.
   if (JA.isHostOffloading(Action::OFK_OpenMP)) {
void ClangAs::ConstructJob(Compilation &C, const JobAction &JA,
   const llvm::Triple &T = getToolChain().getTriple();
   Arg *A;
   if (getDebugFissionKind(D, Args, A) == DwarfFissionKind::Split &&
       T.isOSBinFormatELF()) {
     CmdArgs.push_back("-split-dwarf-output");
     CmdArgs.push_back(SplitDebugName(JA, Args, Input, Output));
   }
 
-  HandleAmdgcnLegacyOptions(D, Args, CmdArgs);
+  if (Triple.isAMDGPU())
+    handleAMDGPUCodeObjectVersionOptions(D, Args, CmdArgs);
 
   assert(Input.isFilename() && "Invalid input.");
   CmdArgs.push_back(Input.getFilename());
 
   const char *Exec = getToolChain().getDriver().getClangProgramPath();
   if (D.CC1Main && !D.CCGenDiagnostics) {
     // Invoke cc1as directly in this process.
     C.addCommand(std::make_unique<CC1Command>(JA, *this,

clang/lib/Driver/ToolChains/CommonArgs.h

 
 /// \p Flag must be a flag accepted by the driver with its leading '-' removed,
 //     otherwise '-print-multi-lib' will not emit them correctly.
 void addMultilibFlag(bool Enabled, const char *const Flag,
                      Multilib::flags_list &Flags);
 
 void addX86AlignBranchArgs(const Driver &D, const llvm::opt::ArgList &Args,
                            llvm::opt::ArgStringList &CmdArgs, bool IsLTO);
+
+unsigned getOrCheckAMDGPUCodeObjectVersion(const Driver &D,
+                                           const llvm::opt::ArgList &Args,
+                                           bool Diagnose = false);
 } // end namespace tools
 } // end namespace driver
 } // end namespace clang
 
 #endif // LLVM_CLANG_LIB_DRIVER_TOOLCHAINS_COMMONARGS_H

clang/lib/Driver/ToolChains/CommonArgs.cpp

if (const Arg *A = Args.getLastArg(options::OPT_mpad_max_prefix_size_EQ)) {
     if (Value.getAsInteger(10, PrefixSize)) {
       D.Diag(diag::err_drv_invalid_argument_to_option)
           << Value << A->getOption().getName();
     } else {
       addArg("-x86-pad-max-prefix-size=" + Twine(PrefixSize));
     }
   }
 }
+
+unsigned tools::getOrCheckAMDGPUCodeObjectVersion(
+    const Driver &D, const llvm::opt::ArgList &Args, bool Diagnose) {
+  const unsigned MinCodeObjVer = 2;
+  const unsigned MaxCodeObjVer = 4;
+  unsigned CodeObjVer = 4;
+
+  // Emit warnings for legacy options even if they are overridden.
+  if (Diagnose) {
+    if (Args.hasArg(options::OPT_mno_code_object_v3_legacy))
+      D.Diag(diag::warn_drv_deprecated_arg) << "-mno-code-object-v3"
+                                            << "-mcode-object-version=2";
+
+    if (Args.hasArg(options::OPT_mcode_object_v3_legacy))
+      D.Diag(diag::warn_drv_deprecated_arg) << "-mcode-object-v3"
+                                            << "-mcode-object-version=3";
+  }
+
+  // The last of -mcode-object-v3, -mno-code-object-v3 and
+  // -mcode-object-version=<version> wins.
+  if (auto *CodeObjArg =
+          Args.getLastArg(options::OPT_mcode_object_v3_legacy,
+                          options::OPT_mno_code_object_v3_legacy,
+                          options::OPT_mcode_object_version_EQ)) {
+    if (CodeObjArg->getOption().getID() ==
+        options::OPT_mno_code_object_v3_legacy) {
+      CodeObjVer = 2;
+    } else if (CodeObjArg->getOption().getID() ==
+               options::OPT_mcode_object_v3_legacy) {
+      CodeObjVer = 3;
+    } else {
+      auto Remnant =
+          StringRef(CodeObjArg->getValue()).getAsInteger(0, CodeObjVer);
+      if (Diagnose &&
+          (Remnant || CodeObjVer < MinCodeObjVer || CodeObjVer > MaxCodeObjVer))
+        D.Diag(diag::err_drv_invalid_int_value)
+            << CodeObjArg->getAsString(Args) << CodeObjArg->getValue();
+    }
+  }
+  return CodeObjVer;
+}

clang/lib/Driver/ToolChains/HIP.cpp

void AMDGCN::constructHIPFatbinCommand(Compilation &C, const JobAction &JA,
   BundlerArgs.push_back(
       Args.MakeArgString("-bundle-align=" + Twine(HIPCodeObjectAlign)));
 
   // ToDo: Remove the dummy host binary entry which is required by
   // clang-offload-bundler.
   std::string BundlerTargetArg = "-targets=host-x86_64-unknown-linux";
   std::string BundlerInputArg = "-inputs=" NULL_FILE;
 
+  // TODO: Change the bundle ID as requested by HIP runtime.
+  // For code object version 2 and 3, the offload kind in bundle ID is 'hip'
+  // for backward compatibility. For code object version 4 and greater, the
+  // offload kind in bundle ID is 'hipv4'.
+  std::string OffloadKind = "hip";
   for (const auto &II : Inputs) {
     const auto* A = II.getAction();
-    BundlerTargetArg = BundlerTargetArg + ",hip-amdgcn-amd-amdhsa--" +
+    BundlerTargetArg = BundlerTargetArg + "," + OffloadKind +
+                       "-amdgcn-amd-amdhsa--" +
                        StringRef(A->getOffloadingArch()).str();
     BundlerInputArg = BundlerInputArg + "," + II.getFilename();
   }
   BundlerArgs.push_back(Args.MakeArgString(BundlerTargetArg));
   BundlerArgs.push_back(Args.MakeArgString(BundlerInputArg));
 
   std::string Output = std::string(OutputFileName);
   auto BundlerOutputArg =

clang/test/Driver/amdgpu-features-as.s

 // RUN: %clang -### -target amdgcn-amd-amdhsa -mcpu=gfx900 -mcode-object-v3 %s 2>&1 | FileCheck --check-prefix=CODE-OBJECT-V3 %s
-// CODE-OBJECT-V3: warning: argument '-mcode-object-v3' is deprecated, use '-mllvm --amdhsa-code-object-version=3' instead [-Wdeprecated]
+// CODE-OBJECT-V3: warning: argument '-mcode-object-v3' is deprecated, use '-mcode-object-version=3' instead [-Wdeprecated]
 // CODE-OBJECT-V3: "-mllvm" "--amdhsa-code-object-version=3"
 
 // RUN: %clang -### -target amdgcn-amd-amdhsa amdgcn -mcpu=gfx900 -mno-code-object-v3 %s 2>&1 | FileCheck --check-prefix=NO-CODE-OBJECT-V3 %s
-// NO-CODE-OBJECT-V3: warning: argument '-mno-code-object-v3' is deprecated, use '-mllvm --amdhsa-code-object-version=2' instead [-Wdeprecated]
+// NO-CODE-OBJECT-V3: warning: argument '-mno-code-object-v3' is deprecated, use '-mcode-object-version=2' instead [-Wdeprecated]
 // NO-CODE-OBJECT-V3: "-mllvm" "--amdhsa-code-object-version=2"
 
 // RUN: %clang -### -target amdgcn-amd-amdhsa -mcpu=gfx900 -mcode-object-v3 -mno-code-object-v3 -mcode-object-v3 %s 2>&1 | FileCheck --check-prefix=MUL-CODE-OBJECT-V3 %s
-// MUL-CODE-OBJECT-V3: warning: argument '-mcode-object-v3' is deprecated, use '-mllvm --amdhsa-code-object-version=3' instead [-Wdeprecated]
+// MUL-CODE-OBJECT-V3: warning: argument '-mcode-object-v3' is deprecated, use '-mcode-object-version=3' instead [-Wdeprecated]
 // MUL-CODE-OBJECT-V3: "-mllvm" "--amdhsa-code-object-version=3"

clang/test/Driver/amdgpu-features.c

 // RUN: %clang -### -target amdgcn-amd-amdhsa -mcpu=gfx700 -mcode-object-v3 %s 2>&1 | FileCheck --check-prefix=CODE-OBJECT-V3 %s
-// CODE-OBJECT-V3: warning: argument '-mcode-object-v3' is deprecated, use '-mllvm --amdhsa-code-object-version=3' instead [-Wdeprecated]
+// CODE-OBJECT-V3: warning: argument '-mcode-object-v3' is deprecated, use '-mcode-object-version=3' instead [-Wdeprecated]
 // CODE-OBJECT-V3: "-mllvm" "--amdhsa-code-object-version=3"
 
 // RUN: %clang -### -target amdgcn-amd-amdhsa amdgcn -mcpu=gfx700 -mno-code-object-v3 %s 2>&1 | FileCheck --check-prefix=NO-CODE-OBJECT-V3 %s
-// NO-CODE-OBJECT-V3: warning: argument '-mno-code-object-v3' is deprecated, use '-mllvm --amdhsa-code-object-version=2' instead [-Wdeprecated]
+// NO-CODE-OBJECT-V3: warning: argument '-mno-code-object-v3' is deprecated, use '-mcode-object-version=2' instead [-Wdeprecated]
 // NO-CODE-OBJECT-V3: "-mllvm" "--amdhsa-code-object-version=2"
 
 // RUN: %clang -### -target amdgcn-amd-amdhsa -mcpu=gfx700 -mcode-object-v3 -mno-code-object-v3 -mcode-object-v3 %s 2>&1 | FileCheck --check-prefix=MUL-CODE-OBJECT-V3 %s
-// MUL-CODE-OBJECT-V3: warning: argument '-mcode-object-v3' is deprecated, use '-mllvm --amdhsa-code-object-version=3' instead [-Wdeprecated]
+// MUL-CODE-OBJECT-V3: warning: argument '-mcode-object-v3' is deprecated, use '-mcode-object-version=3' instead [-Wdeprecated]
 // MUL-CODE-OBJECT-V3: "-mllvm" "--amdhsa-code-object-version=3"
 
 // RUN: %clang -### -target amdgcn-amdhsa -mcpu=gfx900:xnack+ %s 2>&1 | FileCheck --check-prefix=XNACK %s
 // XNACK: "-target-feature" "+xnack"
 
 // RUN: %clang -### -target amdgcn-amdpal -mcpu=gfx900:xnack- %s 2>&1 | FileCheck --check-prefix=NO-XNACK %s
 // NO-XNACK: "-target-feature" "-xnack"
 

clang/test/Driver/hip-autolink.hip

 // REQUIRES: clang-driver
 // REQUIRES: x86-registered-target
 // REQUIRES: amdgpu-registered-target
 //
 // RUN: %clang --target=i386-pc-windows-msvc --cuda-gpu-arch=gfx906 -nogpulib \
 // RUN:   --cuda-device-only %s -### 2>&1 | FileCheck --check-prefix=DEV %s
 // RUN: %clang --target=i386-pc-windows-msvc --cuda-gpu-arch=gfx906 -nogpulib \
 // RUN:   --cuda-host-only %s -### 2>&1 | FileCheck --check-prefix=HOST %s
 
-// DEV: "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// DEV: "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa"
 // DEV-SAME: "-fno-autolink"
 
 // HOST: "-cc1" "-triple" "i386-pc-windows-msvc{{.*}}"
 // HOST-NOT: "-fno-autolink"

clang/test/Driver/hip-code-object-version.hip

+// REQUIRES: clang-driver, amdgpu-registered-target
+
+// Check bundle ID for code object v3.
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -mcode-object-v3 \
+// RUN:   --offload-arch=gfx906 -nogpulib \
+// RUN:   %s 2>&1 | FileCheck -check-prefixes=V3,V3-WARN %s
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -mcode-object-version=3 \
+// RUN:   --offload-arch=gfx906 -nogpulib \
+// RUN:   %s 2>&1 | FileCheck -check-prefix=V3 %s
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -mcode-object-version=4 -mcode-object-version=3 \
+// RUN:   --offload-arch=gfx906 -nogpulib \
+// RUN:   %s 2>&1 | FileCheck -check-prefix=V3 %s
+
+// V3-WARN: warning: argument '-mcode-object-v3' is deprecated, use '-mcode-object-version=3' instead [-Wdeprecated]
+// V3: "-mllvm" "--amdhsa-code-object-version=3"
+// V3: "-targets=host-x86_64-unknown-linux,hip-amdgcn-amd-amdhsa--gfx906"
+
+// Check bundle ID for code object v2.
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -mno-code-object-v3 \
+// RUN:   --offload-arch=gfx906 -nogpulib \
+// RUN:   %s 2>&1 | FileCheck -check-prefixes=V2,V2-WARN %s
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -mcode-object-version=2 \
+// RUN:   --offload-arch=gfx906 -nogpulib \
+// RUN:   %s 2>&1 | FileCheck -check-prefix=V2 %s
+
+// V2-WARN: warning: argument '-mno-code-object-v3' is deprecated, use '-mcode-object-version=2' instead [-Wdeprecated]
+// V2: "-mllvm" "--amdhsa-code-object-version=2"
+// V2: "-targets=host-x86_64-unknown-linux,hip-amdgcn-amd-amdhsa--gfx906"
+
+// Check bundle ID for code object version 4.
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -mcode-object-version=4 \
+// RUN:   --offload-arch=gfx906 -nogpulib \
+// RUN:   %s 2>&1 | FileCheck -check-prefix=V4 %s
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   --offload-arch=gfx906 -nogpulib \
+// RUN:   %s 2>&1 | FileCheck -check-prefix=V4 %s
+
+// V4: "-mllvm" "--amdhsa-code-object-version=4"
+// V4: "-targets=host-x86_64-unknown-linux,hip-amdgcn-amd-amdhsa--gfx906"
+
+// Check invalid code object version option.
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -mcode-object-version=1 \
+// RUN:   --offload-arch=gfx906 -nogpulib \
+// RUN:   %s 2>&1 | FileCheck -check-prefix=INVALID %s
+// INVALID: error: invalid integral value '1' in '-mcode-object-version=1'
+// INVALID-NOT: error: invalid integral value
+
+// Check warnings are emitted for legacy options before -mcode-object-version options.
+// Check warnings are emitted only once.
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -mno-code-object-v3 -mcode-object-v3 -mcode-object-version=4 \
+// RUN:   --offload-arch=gfx906 -nogpulib \
+// RUN:   %s 2>&1 | FileCheck -check-prefixes=WARN %s
+// WARN: warning: argument '-mno-code-object-v3' is deprecated, use '-mcode-object-version=2' instead [-Wdeprecated]
+// WARN: warning: argument '-mcode-object-v3' is deprecated, use '-mcode-object-version=3' instead [-Wdeprecated]
+// WARN-NOT: warning: argument {{.*}} is deprecated

clang/test/Driver/hip-device-compile.hip

 
 // RUN: %clang -c -S --cuda-device-only -### -target x86_64-linux-gnu \
 // RUN:   -o a.s -x hip --cuda-gpu-arch=gfx900 \
 // RUN:   --hip-device-lib=lib1.bc \
 // RUN:   --hip-device-lib-path=%S/Inputs/hip_multiple_inputs/lib1 \
 // RUN:   %S/Inputs/hip_multiple_inputs/a.cu \
 // RUN: 2>&1 | FileCheck -check-prefixes=CHECK,ASM %s
 
-// CHECK: {{".*clang.*"}} "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK: {{".*clang.*"}} "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // BC-SAME: "-emit-llvm-bc"
 // LL-SAME: "-emit-llvm"
 // ASM-NOT: "-emit-llvm"
 // CHECK-SAME: "-main-file-name" "a.cu"
 // CHECK-SAME: "-fcuda-is-device"
 // CHECK-SAME: {{".*lib1.bc"}}
 // CHECK-SAME: "-target-cpu" "gfx900"

clang/test/Driver/hip-host-cpu-features.hip

 // REQUIRES: clang-driver
 // REQUIRES: x86-registered-target
 // REQUIRES: amdgpu-registered-target
 
 // RUN: %clang -### -c -target x86_64-linux-gnu -march=znver2 --cuda-gpu-arch=gfx803 -nogpulib %s 2>&1 | FileCheck %s -check-prefix=HOSTCPU
 // RUN: %clang -### -c -target x86_64-linux-gnu -msse3 --cuda-gpu-arch=gfx803 -nogpulib %s 2>&1 | FileCheck %s -check-prefix=HOSTSSE3
 // RUN: %clang -### -c -target x86_64-linux-gnu --gpu-use-aux-triple-only -march=znver2 --cuda-gpu-arch=gfx803 -nogpulib %s 2>&1 | FileCheck %s -check-prefix=NOHOSTCPU
 
-// HOSTCPU: "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// HOSTCPU: "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa"
 // HOSTCPU-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // HOSTCPU-SAME: "-aux-target-cpu" "znver2"
 
-// HOSTSSE3: "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// HOSTSSE3: "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa"
 // HOSTSSE3-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // HOSTSSE3-SAME: "-aux-target-feature" "+sse3"
 
-// NOHOSTCPU: "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// NOHOSTCPU: "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa"
 // NOHOSTCPU-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // NOHOSTCPU-NOT: "-aux-target-cpu" "znver2"

clang/test/Driver/hip-rdc-device-only.hip

 
 // RUN: %clang -### -save-temps -target x86_64-linux-gnu \
 // RUN:   -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
 // RUN:   -S -nogpuinc -nogpulib --cuda-device-only -fgpu-rdc \
 // RUN:   %S/Inputs/hip_multiple_inputs/a.cu \
 // RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
 // RUN: 2>&1 | FileCheck -check-prefix=SAVETEMP %s
 
-// COMMON: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// COMMON: [[CLANG:".*clang.*"]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa"
 // COMMON-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // EMITBC-SAME: "-emit-llvm-bc"
 // EMITLL-SAME: "-emit-llvm"
 // COMMON-SAME: {{.*}} "-main-file-name" "a.cu"
 // COMMON-SAME: "-fcuda-is-device" "-fgpu-rdc" "-fcuda-allow-variadic-functions" "-fvisibility" "hidden"
 // COMMON-SAME: "-fapply-global-visibility-to-externs"
 // COMMON-SAME: "-target-cpu" "gfx803"
 // EMITBC-SAME: {{.*}} "-o" {{"a.*bc"}} "-x" "hip"
 // EMITLL-SAME: {{.*}} "-o" {{"a.*ll"}} "-x" "hip"
 // CHECK-SAME: {{.*}} {{".*a.cu"}}
 
-// COMMON: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// COMMON: [[CLANG]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa"
 // COMMON-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // EMITBC-SAME: "-emit-llvm-bc"
 // EMITLL-SAME: "-emit-llvm"
 // COMMON-SAME: {{.*}} "-main-file-name" "a.cu"
 // COMMON-SAME: "-fcuda-is-device" "-fgpu-rdc" "-fcuda-allow-variadic-functions" "-fvisibility" "hidden"
 // COMMON-SAME: "-fapply-global-visibility-to-externs"
 // COMMON-SAME: "-target-cpu" "gfx900"
 // EMITBC-SAME: {{.*}} "-o" {{"a.*bc"}} "-x" "hip"
 // EMITLL-SAME: {{.*}} "-o" {{"a.*ll"}} "-x" "hip"
 // COMMON-SAME: {{.*}} {{".*a.cu"}}
 
-// COMMON: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// COMMON: [[CLANG]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa"
 // COMMON-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // EMITBC-SAME: "-emit-llvm-bc"
 // EMITLL-SAME: "-emit-llvm"
 // COMMON-SAME: {{.*}} "-main-file-name" "b.hip"
 // COMMON-SAME: "-fcuda-is-device" "-fgpu-rdc" "-fcuda-allow-variadic-functions" "-fvisibility" "hidden"
 // COMMON-SAME: "-fapply-global-visibility-to-externs"
 // COMMON-SAME: "-target-cpu" "gfx803"
 // EMITBC-SAME: {{.*}} "-o" {{"b.*bc"}} "-x" "hip"
 // EMITLL-SAME: {{.*}} "-o" {{"b.*ll"}} "-x" "hip"
 // COMMON-SAME: {{.*}} {{".*b.hip"}}
 
-// COMMON: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// COMMON: [[CLANG]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa"
 // COMMON-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // EMITBC-SAME: "-emit-llvm-bc"
 // EMITLL-SAME: "-emit-llvm"
 // COMMON-SAME: {{.*}} "-main-file-name" "b.hip"
 // COMMON-SAME: "-fcuda-is-device" "-fgpu-rdc" "-fcuda-allow-variadic-functions" "-fvisibility" "hidden"
 // COMMON-SAME: "-fapply-global-visibility-to-externs"
 // COMMON-SAME: "-target-cpu" "gfx900"
 // EMITBC-SAME: {{.*}} "-o" {{"b.*bc"}} "-x" "hip"
 // EMITLL-SAME: {{.*}} "-o" {{"b.*ll"}} "-x" "hip"
 // COMMON-SAME: {{.*}} {{".*b.hip"}}
 
-// SAVETEMP: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
+// SAVETEMP: [[CLANG:".*clang.*"]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
 // SAVETEMP-SAME: "-E"
 // SAVETEMP-SAME: {{.*}} "-main-file-name" "a.cu" {{.*}} "-target-cpu" "gfx803"
 // SAVETEMP-SAME: {{.*}} "-o" [[A_GFX803_CUI:"a.*cui"]] "-x" "hip" {{".*a.cu"}}
-// SAVETEMP-NEXT: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
+// SAVETEMP-NEXT: [[CLANG]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
 // SAVETEMP-SAME: "-emit-llvm-bc"
 // SAVETEMP-SAME: {{.*}} "-main-file-name" "a.cu" {{.*}} "-target-cpu" "gfx803"
 // SAVETEMP-SAME: {{.*}} "-o" [[A_GFX803_TMP_BC:"a.*tmp.bc"]] "-x" "hip-cpp-output" [[A_GFX803_CUI]]
-// SAVETEMP-NEXT: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
+// SAVETEMP-NEXT: [[CLANG]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
 // SAVETEMP-SAME: "-emit-llvm"
 // SAVETEMP-SAME: {{.*}} "-main-file-name" "a.cu" {{.*}} "-target-cpu" "gfx803"
 // SAVETEMP-SAME: {{.*}} "-o" {{"a.*.ll"}} "-x" "ir" [[A_GFX803_TMP_BC]]
 
-// SAVETEMP: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
+// SAVETEMP: [[CLANG]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
 // SAVETEMP-SAME: "-E"
 // SAVETEMP-SAME: {{.*}} "-main-file-name" "a.cu" {{.*}} "-target-cpu" "gfx900"
 // SAVETEMP-SAME: {{.*}} "-o" [[A_GFX900_CUI:"a.*cui"]] "-x" "hip" {{".*a.cu"}}
-// SAVETEMP-NEXT: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
+// SAVETEMP-NEXT: [[CLANG]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
 // SAVETEMP-SAME: "-emit-llvm-bc"
 // SAVETEMP-SAME: {{.*}} "-main-file-name" "a.cu" {{.*}} "-target-cpu" "gfx900"
 // SAVETEMP-SAME: {{.*}} "-o" [[A_GFX900_TMP_BC:"a.*tmp.bc"]] "-x" "hip-cpp-output" [[A_GFX900_CUI]]
-// SAVETEMP-NEXT: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
+// SAVETEMP-NEXT: [[CLANG]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
 // SAVETEMP-SAME: "-emit-llvm"
 // SAVETEMP-SAME: {{.*}} "-main-file-name" "a.cu" {{.*}} "-target-cpu" "gfx900"
 // SAVETEMP-SAME: {{.*}} "-o" {{"a.*.ll"}} "-x" "ir" [[A_GFX900_TMP_BC]]
 
-// SAVETEMP: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
+// SAVETEMP: [[CLANG]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
 // SAVETEMP-SAME: "-E"
 // SAVETEMP-SAME: {{.*}} "-main-file-name" "b.hip" {{.*}} "-target-cpu" "gfx803"
 // SAVETEMP-SAME: {{.*}} "-o" [[B_GFX803_CUI:"b.*cui"]] "-x" "hip" {{".*b.hip"}}
-// SAVETEMP-NEXT: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
+// SAVETEMP-NEXT: [[CLANG]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
 // SAVETEMP-SAME: "-emit-llvm-bc"
 // SAVETEMP-SAME: {{.*}} "-main-file-name" "b.hip" {{.*}} "-target-cpu" "gfx803"
 // SAVETEMP-SAME: {{.*}} "-o" [[B_GFX803_TMP_BC:"b.*tmp.bc"]] "-x" "hip-cpp-output" [[B_GFX803_CUI]]
-// SAVETEMP-NEXT: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
+// SAVETEMP-NEXT: [[CLANG]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
 // SAVETEMP-SAME: "-emit-llvm"
 // SAVETEMP-SAME: {{.*}} "-main-file-name" "b.hip" {{.*}} "-target-cpu" "gfx803"
 // SAVETEMP-SAME: {{.*}} "-o" {{"b.*.ll"}} "-x" "ir" [[B_GFX803_TMP_BC]]
 
-// SAVETEMP: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
+// SAVETEMP: [[CLANG]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
 // SAVETEMP-SAME: "-E"
 // SAVETEMP-SAME: {{.*}} "-main-file-name" "b.hip" {{.*}} "-target-cpu" "gfx900"
 // SAVETEMP-SAME: {{.*}} "-o" [[B_GFX900_CUI:"b.*cui"]] "-x" "hip" {{".*b.hip"}}
-// SAVETEMP-NEXT: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
+// SAVETEMP-NEXT: [[CLANG]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
 // SAVETEMP-SAME: "-emit-llvm-bc"
 // SAVETEMP-SAME: {{.*}} "-main-file-name" "b.hip" {{.*}} "-target-cpu" "gfx900"
 // SAVETEMP-SAME: {{.*}} "-o" [[B_GFX900_TMP_BC:"b.*tmp.bc"]] "-x" "hip-cpp-output" [[B_GFX900_CUI]]
-// SAVETEMP-NEXT: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
+// SAVETEMP-NEXT: [[CLANG]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
 // SAVETEMP-SAME: "-emit-llvm"
 // SAVETEMP-SAME: {{.*}} "-main-file-name" "b.hip" {{.*}} "-target-cpu" "gfx900"
 // SAVETEMP-SAME: {{.*}} "-o" {{"b.*.ll"}} "-x" "ir" [[B_GFX900_TMP_BC]]

clang/test/Driver/hip-target-id.hip

 // RUN: %clang -### -target x86_64-linux-gnu \
 // RUN:   -x hip \
 // RUN:   --offload-arch=gfx908:xnack+:sramecc+ \
 // RUN:   --offload-arch=gfx908:xnack+:sramecc- \
 // RUN:   --rocm-path=%S/Inputs/rocm \
 // RUN:   -fgpu-rdc \
 // RUN:   %s 2>&1 | FileCheck --check-prefixes=CHECK %s
 
-// CHECK: [[CLANG:"[^"]*clang[^"]*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK: [[CLANG:"[^"]*clang[^"]*"]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-target-cpu" "gfx908"
 // CHECK-SAME: "-target-feature" "+sramecc"
 // CHECK-SAME: "-target-feature" "+xnack"
 
-// TMP: [[CLANG:"[^"]*clang[^"]*"]] "-cc1as" "-triple" "amdgcn-amd-amdhsa"
+// TMP: [[CLANG:"[^"]*clang[^"]*"]] "-cc1as" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa"
 // TMP-SAME: "-target-cpu" "gfx908"
 // TMP-SAME: "-target-feature" "+sramecc"
 // TMP-SAME: "-target-feature" "+xnack"
 
 // CHECK: [[LLD:"[^"]*lld[^"]*"]] {{.*}} "-plugin-opt=mcpu=gfx908"
 // CHECK-SAME: "-plugin-opt=-mattr=+sramecc,+xnack"
 
-// CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK: [[CLANG]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-target-cpu" "gfx908"
 // CHECK-SAME: "-target-feature" "-sramecc"
 // CHECK-SAME: "-target-feature" "+xnack"
 
 // CHECK: [[LLD]] {{.*}} "-plugin-opt=mcpu=gfx908"
 // CHECK-SAME: "-plugin-opt=-mattr=-sramecc,+xnack"
 
 // CHECK: {{"[^"]*clang-offload-bundler[^"]*"}}

clang/test/Driver/hip-toolchain-device-only.hip

 // REQUIRES: clang-driver, amdgpu-registered-target
 
 // RUN: %clang -### -target x86_64-linux-gnu \
 // RUN:   --offload-arch=gfx803 --offload-arch=gfx900 \
 // RUN:   --cuda-device-only -nogpuinc -nogpulib -c \
 // RUN:   %s 2>&1 | FileCheck %s
 
 // CHECK-NOT: error:
 
-// CHECK: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK: [[CLANG:".*clang.*"]] "-cc1"{{.*}} "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-fcuda-is-device"
 // CHECK-SAME: "-target-cpu" "gfx803"
 // CHECK-SAME: {{.*}} "-o" [[OBJ_DEV_A_803:".*o"]] "-x" "hip"
 
 // CHECK: [[LLD: ".*lld.*"]] "-flavor" "gnu" "--no-undefined" "-shared"
 // CHECK-SAME: "-o" "[[IMG_DEV_A_803:.*out]]" [[OBJ_DEV_A_803]]
 
-// CHECK: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK: [[CLANG:".*clang.*"]] "-cc1"{{.*}} "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-emit-obj"
 // CHECK-SAME: "-fcuda-is-device"
 // CHECK-SAME: "-target-cpu" "gfx900"
 // CHECK-SAME: {{.*}} "-o" [[OBJ_DEV_A_900:".*o"]] "-x" "hip"
 
 // CHECK: [[LLD]] "-flavor" "gnu" "--no-undefined" "-shared"
 // CHECK-SAME: "-o" "[[IMG_DEV_A_900:.*out]]" [[OBJ_DEV_A_900]]
 
 // CHECK: [[BUNDLER:".*clang-offload-bundler"]] "-type=o"
 // CHECK-SAME: "-targets={{.*}},hip-amdgcn-amd-amdhsa--gfx803,hip-amdgcn-amd-amdhsa--gfx900"
 // CHECK-SAME: "-inputs={{.*}},[[IMG_DEV_A_803]],[[IMG_DEV_A_900]]" "-outputs=[[BUNDLE_A:.*hipfb]]"

clang/test/Driver/hip-toolchain-mllvm.hip

 // REQUIRES: clang-driver
 // REQUIRES: x86-registered-target
 // REQUIRES: amdgpu-registered-target
 
 // RUN: %clang -### -target x86_64-linux-gnu \
 // RUN:   --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
 // RUN:   -mllvm -amdgpu-function-calls=0 \
 // RUN:   %s 2>&1 | FileCheck %s
 
 // RUN: %clang -### -target x86_64-linux-gnu \
 // RUN:   --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
 // RUN:   -fgpu-rdc -mllvm -amdgpu-function-calls=0 \
 // RUN:   %s 2>&1 | FileCheck -check-prefixes=CHECK,RDC %s
 
-// CHECK: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK: [[CLANG:".*clang.*"]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME: {{.*}} "-target-cpu" "gfx803"
 // CHECK-SAME: {{.*}} "-mllvm" "-amdgpu-function-calls=0" {{.*}}
 
 // CHECK-NOT: {{".*opt"}}
 // CHECK-NOT: {{".*llc"}}
 // RDC: [[LLD:".*lld.*"]] {{.*}} "-plugin-opt=-amdgpu-function-calls=0"
 
-// CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK: [[CLANG]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME: {{.*}} "-target-cpu" "gfx900"
 // CHECK-SAME: {{.*}} "-mllvm" "-amdgpu-function-calls=0" {{.*}}
 
 // CHECK-NOT: {{".*opt"}}
 // CHECK-NOT: {{".*llc"}}
 // RDC: [[LLD:".*lld.*"]] {{.*}} "-plugin-opt=-amdgpu-function-calls=0"

clang/test/Driver/hip-toolchain-no-rdc.hip

 // RUN:   -fuse-ld=lld -nogpuinc \
 // RUN:   %T/a.o %T/b.o \
 // RUN: 2>&1 | FileCheck -check-prefixes=LKONLY %s
 
 //
 // Compile device code in a.cu to code object for gfx803.
 //
 
-// CHECK: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK: [[CLANG:".*clang.*"]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME: "-emit-obj"
 // CHECK-SAME: {{.*}} "-main-file-name" "a.cu"
 // CHECK-SAME: "-fcuda-is-device" "-mllvm" "-amdgpu-internalize-symbols"
 // CHECK-SAME: "-fcuda-allow-variadic-functions" "-fvisibility" "hidden"
 // CHECK-SAME: "-fapply-global-visibility-to-externs"
 // CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: "-target-cpu" "gfx803"
 // CHECK-SAME: {{.*}} "-o" [[OBJ_DEV_A_803:".*o"]] "-x" "hip"
 // CHECK-SAME: {{.*}} [[A_SRC:".*a.cu"]]
 
 // CHECK-NOT: {{".*llvm-link"}}
 // CHECK-NOT: {{".*opt"}}
 // CHECK-NOT: {{".*llc"}}
 
 // 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: [[CLANG:".*clang.*"]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME: "-emit-obj"
 // CHECK-SAME: {{.*}} "-main-file-name" "a.cu"
 // CHECK-SAME: "-fcuda-is-device" "-mllvm" "-amdgpu-internalize-symbols"
 // CHECK-SAME: "-fcuda-allow-variadic-functions" "-fvisibility" "hidden"
 // CHECK-SAME: "-fapply-global-visibility-to-externs"
 // CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: "-target-cpu" "gfx900"

 // CHECK-SAME: {{.*}} "-fcuda-include-gpubinary" "[[BUNDLE_A]]"
 // CHECK-SAME: {{.*}} "-o" [[A_OBJ_HOST:".*o"]] "-x" "hip"
 // CHECK-SAME: {{.*}} [[A_SRC]]
 
 //
 // Compile device code in b.hip to code object for gfx803.
 //
 
-// CHECK: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK: [[CLANG:".*clang.*"]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME: "-emit-obj"
 // CHECK-SAME: {{.*}} "-main-file-name" "b.hip"
 // CHECK-SAME: "-fcuda-is-device" "-mllvm" "-amdgpu-internalize-symbols"
 // CHECK-SAME: "-fcuda-allow-variadic-functions" "-fvisibility" "hidden"
 // CHECK-SAME: "-fapply-global-visibility-to-externs"
 // CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: "-target-cpu" "gfx803"
 // CHECK-SAME: {{.*}} "-o" [[OBJ_DEV_B_803:".*o"]] "-x" "hip"
 // CHECK-SAME: {{.*}} [[B_SRC:".*b.hip"]]
 
 // CHECK-NOT: {{".*llvm-link"}}
 // CHECK-NOT: {{".*opt"}}
 // CHECK-NOT: {{".*llc"}}
 
 // CHECK: [[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: [[CLANG:".*clang.*"]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME: "-emit-obj"
 // CHECK-SAME: {{.*}} "-main-file-name" "b.hip"
 // CHECK-SAME: "-fcuda-is-device" "-mllvm" "-amdgpu-internalize-symbols"
 // CHECK-SAME: "-fcuda-allow-variadic-functions" "-fvisibility" "hidden"
 // CHECK-SAME: "-fapply-global-visibility-to-externs"
 // CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: "-target-cpu" "gfx900"

clang/test/Driver/hip-toolchain-opt.hip

 
 // RUN: %clang -### -Og \
 // RUN:   -target x86_64-unknown-linux-gnu \
 // RUN:   --cuda-gpu-arch=gfx900 \
 // RUN:   -c -nogpulib \
 // RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
 // RUN: 2>&1 | FileCheck --check-prefixes=ALL,Og %s
 
-// ALL: "{{.*}}clang{{.*}}" "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// ALL: "{{.*}}clang{{.*}}" "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-triple" "amdgcn-amd-amdhsa"
 // DEFAULT-NOT: "-O{{.}}"
 // O0-SAME: "-O0"
 // O1-SAME: "-O1"
 // O2-SAME: "-O2"
 // O3-SAME: "-O3"
 // Os-SAME: "-Os"
 // Oz-SAME: "-Oz"
 // Og-SAME: "-Og"

clang/test/Driver/hip-toolchain-rdc-separate.hip

 // REQUIRES: clang-driver
 // REQUIRES: x86-registered-target
 // REQUIRES: amdgpu-registered-target
 
 // RUN: %clang -c -### -target x86_64-linux-gnu \
 // RUN:   -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
 // RUN:   --hip-device-lib=lib1.bc --hip-device-lib=lib2.bc \
 // RUN:   --hip-device-lib-path=%S/Inputs/hip_multiple_inputs/lib1 \
 // RUN:   --hip-device-lib-path=%S/Inputs/hip_multiple_inputs/lib2 \
 // RUN:   -fuse-ld=lld -fgpu-rdc -nogpuinc \
 // RUN:   %S/Inputs/hip_multiple_inputs/a.cu \
 // RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
 // RUN: 2>&1 | FileCheck %s
 
-// CHECK: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK: [[CLANG:".*clang.*"]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-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"
 // CHECK-SAME: "-fcuda-is-device" "-fgpu-rdc" "-fcuda-allow-variadic-functions" "-fvisibility" "hidden"
 // CHECK-SAME: "-fapply-global-visibility-to-externs"
 // CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: "-target-cpu" "gfx803"
 // CHECK-SAME: {{.*}} "-o" "[[A_BC1:.*bc]]" "-x" "hip"
 // CHECK-SAME: {{.*}} [[A_SRC:".*a.cu"]]
 
-// CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK: [[CLANG]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-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"
 // CHECK-SAME: "-fcuda-is-device" "-fgpu-rdc"
 // CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: "-target-cpu" "gfx900"
 // CHECK-SAME: {{.*}} "-o" "[[A_BC2:.*bc]]" "-x" "hip"
 // CHECK-SAME: {{.*}} [[A_SRC]]
 
 // CHECK: [[CLANG]] "-cc1" "-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME: "-aux-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-emit-obj"
 // CHECK-SAME: {{.*}} "-main-file-name" "a.cu"
 // CHECK-SAME: {{.*}} "-o" "[[A_OBJ_HOST:.*o]]" "-x" "hip"
 // CHECK-SAME: {{.*}} [[A_SRC]]
 
 // CHECK: [[BUNDLER:".*clang-offload-bundler"]] "-type=o"
 // CHECK-SAME: "-targets=hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900,host-x86_64-unknown-linux-gnu"
 // CHECK-SAME: "-outputs=[[A_O:.*a.o]]" "-inputs=[[A_BC1]],[[A_BC2]],[[A_OBJ_HOST]]"
 
-// CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK: [[CLANG]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-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"
 // CHECK-SAME: "-fcuda-is-device" "-fgpu-rdc" "-fcuda-allow-variadic-functions" "-fvisibility" "hidden"
 // CHECK-SAME: "-fapply-global-visibility-to-externs"
 // CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: "-target-cpu" "gfx803"
 // CHECK-SAME: {{.*}} "-o" "[[B_BC1:.*bc]]" "-x" "hip"
 // CHECK-SAME: {{.*}} [[B_SRC:".*b.hip"]]
 
-// CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK: [[CLANG]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-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"
 // CHECK-SAME: "-fcuda-is-device" "-fgpu-rdc"
 // CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: "-target-cpu" "gfx900"
 // CHECK-SAME: {{.*}} "-o" "[[B_BC2:.*bc]]" "-x" "hip"
 // CHECK-SAME: {{.*}} [[B_SRC]]

clang/test/Driver/hip-toolchain-rdc-static-lib.hip

 // CHECK: [[CLANG]] "-cc1" "-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME: "-aux-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-emit-obj"
 // CHECK-SAME: {{.*}} "-main-file-name" "b.hip"
 // CHECK-SAME: {{.*}} "-o" [[B_OBJ_HOST:".*o"]] "-x" "hip"
 // CHECK-SAME: {{.*}} [[B_SRC:".*b.hip"]]
 
 // generate image for device side path on gfx803
-// CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK: [[CLANG]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-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"
 // CHECK-SAME: "-fcuda-is-device" "-fgpu-rdc"
 // CHECK-SAME: "-target-cpu" "gfx803"
 // CHECK-SAME: {{.*}} "-o" [[A_BC1:".*bc"]] "-x" "hip"
 // CHECK-SAME: {{.*}} [[A_SRC]]
 
-// CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK: [[CLANG]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-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"
 // CHECK-SAME: "-fcuda-is-device" "-fgpu-rdc"
 // CHECK-SAME: "-target-cpu" "gfx803"
 // CHECK-SAME: {{.*}} "-o" [[B_BC1:".*bc"]] "-x" "hip"
 // CHECK-SAME: {{.*}} [[B_SRC]]
 
 // CHECK-NOT: "*.llvm-link"
 // CHECK-NOT: ".*opt"
 // CHECK-NOT: ".*llc"
 // CHECK: [[LLD: ".*lld.*"]] {{.*}} "-plugin-opt=-amdgpu-internalize-symbols"
 // CHECK-SAME: "-plugin-opt=mcpu=gfx803"
 // CHECK-SAME: "-o" "[[IMG_DEV1:.*out]]" [[A_BC1]] [[B_BC1]]
 
 // generate image for device side path on gfx900
-// CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK: [[CLANG]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-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"
 // CHECK-SAME: "-fcuda-is-device" "-fgpu-rdc"
 // CHECK-SAME: "-target-cpu" "gfx900"
 // CHECK-SAME: {{.*}} "-o" [[A_BC2:".*bc"]] "-x" "hip"
 // CHECK-SAME: {{.*}} [[A_SRC]]
 
-// CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK: [[CLANG]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-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"
 // CHECK-SAME: "-fcuda-is-device" "-fgpu-rdc"
 // CHECK-SAME: "-target-cpu" "gfx900"
 // CHECK-SAME: {{.*}} "-o" [[B_BC2:".*bc"]] "-x" "hip"
 // CHECK-SAME: {{.*}} [[B_SRC]]
 

clang/test/Driver/hip-toolchain-rdc.hip

 // CHECK: [[CLANG]] "-cc1" "-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME: "-aux-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-emit-obj"
 // CHECK-SAME: {{.*}} "-main-file-name" "b.hip"
 // CHECK-SAME: {{.*}} "-o" [[B_OBJ_HOST:".*o"]] "-x" "hip"
 // CHECK-SAME: {{.*}} [[B_SRC:".*b.hip"]]
 
 // generate image for device side path on gfx803
-// CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK: [[CLANG]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-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"
 // CHECK-SAME: "-fcuda-is-device" "-fgpu-rdc" "-fcuda-allow-variadic-functions" "-fvisibility" "hidden"
 // CHECK-SAME: "-fapply-global-visibility-to-externs"
 // CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: "-target-cpu" "gfx803"
 // CHECK-SAME: {{.*}} "-o" [[A_BC1:".*bc"]] "-x" "hip"
 // CHECK-SAME: {{.*}} [[A_SRC]]
 
-// CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK: [[CLANG]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-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"
 // CHECK-SAME: "-fcuda-is-device" "-fgpu-rdc" "-fcuda-allow-variadic-functions" "-fvisibility" "hidden"
 // CHECK-SAME: "-fapply-global-visibility-to-externs"
 // CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: "-target-cpu" "gfx803"
 // CHECK-SAME: {{.*}} "-o" [[B_BC1:".*bc"]] "-x" "hip"
 // CHECK-SAME: {{.*}} [[B_SRC]]
 
 // CHECK-NOT: "*.llvm-link"
 // CHECK-NOT: ".*opt"
 // CHECK-NOT: ".*llc"
 // CHECK: {{".*lld.*"}} {{.*}} "-plugin-opt=-amdgpu-internalize-symbols"
 // CHECK-SAME: "-plugin-opt=mcpu=gfx803"
 // CHECK-SAME: "-o" "[[IMG_DEV1:.*.out]]" [[A_BC1]] [[B_BC1]]
 
 // generate image for device side path on gfx900
-// CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK: [[CLANG]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-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"
 // CHECK-SAME: "-fcuda-is-device" "-fgpu-rdc"
 // CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: "-target-cpu" "gfx900"
 // CHECK-SAME: {{.*}} "-o" [[A_BC2:".*bc"]] "-x" "hip"
 // CHECK-SAME: {{.*}} [[A_SRC]]
 
-// CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK: [[CLANG]] "-cc1" "-mllvm" "--amdhsa-code-object-version=4" "-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"
 // CHECK-SAME: "-fcuda-is-device" "-fgpu-rdc"
 // CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: "-target-cpu" "gfx900"
 // CHECK-SAME: {{.*}} "-o" [[B_BC2:".*bc"]] "-x" "hip"
 // CHECK-SAME: {{.*}} [[B_SRC]]