diff --git a/clang/include/clang/Basic/Cuda.h b/clang/include/clang/Basic/Cuda.h
--- a/clang/include/clang/Basic/Cuda.h
+++ b/clang/include/clang/Basic/Cuda.h
@@ -37,6 +37,7 @@
 CudaVersion CudaStringToVersion(const llvm::Twine &S);
 
 enum class CudaArch {
+  UNUSED,
   UNKNOWN,
   SM_20,
   SM_21,
diff --git a/clang/lib/Basic/Cuda.cpp b/clang/lib/Basic/Cuda.cpp
--- a/clang/lib/Basic/Cuda.cpp
+++ b/clang/lib/Basic/Cuda.cpp
@@ -64,6 +64,7 @@
   { CudaArch::GFX##gpu, "gfx" #gpu, "compute_amdgcn" }
 CudaArchToStringMap arch_names[] = {
     // clang-format off
+    {CudaArch::UNUSED, "", ""},
     SM2(20, "compute_20"), SM2(21, "compute_20"), // Fermi
     SM(30), SM(32), SM(35), SM(37),  // Kepler
     SM(50), SM(52), SM(53),          // Maxwell
diff --git a/clang/lib/Basic/Targets/NVPTX.cpp b/clang/lib/Basic/Targets/NVPTX.cpp
--- a/clang/lib/Basic/Targets/NVPTX.cpp
+++ b/clang/lib/Basic/Targets/NVPTX.cpp
@@ -204,6 +204,7 @@
       case CudaArch::GFX1031:
       case CudaArch::LAST:
         break;
+      case CudaArch::UNUSED:
       case CudaArch::UNKNOWN:
         assert(false && "No GPU arch when compiling CUDA device code.");
         return "";
diff --git a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
--- a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
@@ -5034,6 +5034,7 @@
       case CudaArch::GFX1012:
       case CudaArch::GFX1030:
       case CudaArch::GFX1031:
+      case CudaArch::UNUSED:
       case CudaArch::UNKNOWN:
         break;
       case CudaArch::LAST:
@@ -5095,6 +5096,7 @@
   case CudaArch::GFX1012:
   case CudaArch::GFX1030:
   case CudaArch::GFX1031:
+  case CudaArch::UNUSED:
   case CudaArch::UNKNOWN:
     break;
   case CudaArch::LAST:
diff --git a/clang/lib/Driver/Driver.cpp b/clang/lib/Driver/Driver.cpp
--- a/clang/lib/Driver/Driver.cpp
+++ b/clang/lib/Driver/Driver.cpp
@@ -2517,7 +2517,7 @@
 
       // If we have a fat binary, add it to the list.
       if (CudaFatBinary) {
-        AddTopLevel(CudaFatBinary, CudaArch::UNKNOWN);
+        AddTopLevel(CudaFatBinary, CudaArch::UNUSED);
         CudaDeviceActions.clear();
         CudaFatBinary = nullptr;
         return;
diff --git a/clang/test/Driver/hip-phases.hip b/clang/test/Driver/hip-phases.hip
--- a/clang/test/Driver/hip-phases.hip
+++ b/clang/test/Driver/hip-phases.hip
@@ -219,6 +219,12 @@
 // DBIN-DAG: [[P0:[0-9]+]]: input, "{{.*}}hip-phases.hip", [[T:hip]], (device-[[T]], [[ARCH:gfx803]])
 // DBIN-DAG: [[P1:[0-9]+]]: preprocessor, {[[P0]]}, [[T]]-cpp-output, (device-[[T]], [[ARCH]])
 // DBIN-DAG: [[P2:[0-9]+]]: compiler, {[[P1]]}, ir, (device-[[T]], [[ARCH]])
+// DBIN-DAG: [[P3:[0-9]+]]: backend, {[[P2]]}, assembler, (device-[[T]], [[ARCH]])
+// DBIN-DAG: [[P4:[0-9]+]]: assembler, {[[P3]]}, object, (device-[[T]], [[ARCH]])
+// DBIN-DAG: [[P5:[0-9]+]]: linker, {[[P4]]}, image, (device-[[T]], [[ARCH]])
+// DBIN-DAG: [[P6:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa:[[ARCH]])" {[[P5]]}, image
+// DBIN-DAG: [[P7:[0-9]+]]: linker, {[[P6]]}, hip-fatbin, (device-hip, )
+// DBIN-DAG: [[P8:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa:)" {[[P7]]}, hip-fatbin
 // DBIN-NOT: host
 //
 // Test single gpu architecture up to the assemble phase in device-only
@@ -230,6 +236,8 @@
 // DASM-DAG: [[P0:[0-9]+]]: input, "{{.*}}hip-phases.hip", [[T:hip]], (device-[[T]], [[ARCH:gfx803]])
 // DASM-DAG: [[P1:[0-9]+]]: preprocessor, {[[P0]]}, [[T]]-cpp-output, (device-[[T]], [[ARCH]])
 // DASM-DAG: [[P2:[0-9]+]]: compiler, {[[P1]]}, ir, (device-[[T]], [[ARCH]])
+// DASM-DAG: [[P3:[0-9]+]]: backend, {[[P2]]}, assembler, (device-[[T]], [[ARCH]])
+// DASM-DAG: [[P4:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa:[[ARCH]])" {[[P3]]}, assembler
 // DASM-NOT: host
 
 //
@@ -242,9 +250,19 @@
 // DBIN2-DAG: [[P0:[0-9]+]]: input, "{{.*}}hip-phases.hip", [[T:hip]], (device-[[T]], [[ARCH:gfx803]])
 // DBIN2-DAG: [[P1:[0-9]+]]: preprocessor, {[[P0]]}, [[T]]-cpp-output, (device-[[T]], [[ARCH]])
 // DBIN2-DAG: [[P2:[0-9]+]]: compiler, {[[P1]]}, ir, (device-[[T]], [[ARCH]])
-// DBIN2-DAG: [[P6:[0-9]+]]: input, "{{.*}}hip-phases.hip", [[T]], (device-[[T]], [[ARCH2:gfx900]])
-// DBIN2-DAG: [[P7:[0-9]+]]: preprocessor, {[[P6]]}, [[T]]-cpp-output, (device-[[T]], [[ARCH2]])
-// DBIN2-DAG: [[P8:[0-9]+]]: compiler, {[[P7]]}, ir, (device-[[T]], [[ARCH2]])
+// DBIN2-DAG: [[P3:[0-9]+]]: backend, {[[P2]]}, assembler, (device-[[T]], [[ARCH]])
+// DBIN2-DAG: [[P4:[0-9]+]]: assembler, {[[P3]]}, object, (device-[[T]], [[ARCH]])
+// DBIN2-DAG: [[P5:[0-9]+]]: linker, {[[P4]]}, image, (device-[[T]], [[ARCH]])
+// DBIN2-DAG: [[P6:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa:[[ARCH]])" {[[P5]]}, image
+// DBIN2-DAG: [[P7:[0-9]+]]: input, "{{.*}}hip-phases.hip", [[T]], (device-[[T]], [[ARCH2:gfx900]])
+// DBIN2-DAG: [[P8:[0-9]+]]: preprocessor, {[[P7]]}, [[T]]-cpp-output, (device-[[T]], [[ARCH2]])
+// DBIN2-DAG: [[P9:[0-9]+]]: compiler, {[[P8]]}, ir, (device-[[T]], [[ARCH2]])
+// DBIN2-DAG: [[P10:[0-9]+]]: backend, {[[P9]]}, assembler, (device-[[T]], [[ARCH2]])
+// DBIN2-DAG: [[P11:[0-9]+]]: assembler, {[[P10]]}, object, (device-[[T]], [[ARCH2]])
+// DBIN2-DAG: [[P12:[0-9]+]]: linker, {[[P11]]}, image, (device-[[T]], [[ARCH2]])
+// DBIN2-DAG: [[P13:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa:[[ARCH2]])" {[[P12]]}, image
+// DBIN2-DAG: [[P14:[0-9]+]]: linker, {[[P6]], [[P13]]}, hip-fatbin, (device-hip, )
+// DBIN2-DAG: [[P15:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa:)" {[[P14]]}, hip-fatbin
 // DBIN2-NOT: host
 //
 // Test two gpu architectures up to the assemble phase in device-only
@@ -257,9 +275,13 @@
 // DASM2-DAG: [[P0:[0-9]+]]: input, "{{.*}}hip-phases.hip", [[T:hip]], (device-[[T]], [[ARCH:gfx803]])
 // DASM2-DAG: [[P1:[0-9]+]]: preprocessor, {[[P0]]}, [[T]]-cpp-output, (device-[[T]], [[ARCH]])
 // DASM2-DAG: [[P2:[0-9]+]]: compiler, {[[P1]]}, ir, (device-[[T]], [[ARCH]])
+// DASM2-DAG: [[P3:[0-9]+]]: backend, {[[P2]]}, assembler, (device-[[T]], [[ARCH]])
+// DASM2-DAG: [[P4:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa:[[ARCH]])" {[[P3]]}, assembler
 // DASM2-DAG: [[P5:[0-9]+]]: input, "{{.*}}hip-phases.hip", [[T]], (device-[[T]], [[ARCH2:gfx900]])
 // DASM2-DAG: [[P6:[0-9]+]]: preprocessor, {[[P5]]}, [[T]]-cpp-output, (device-[[T]], [[ARCH2]])
 // DASM2-DAG: [[P7:[0-9]+]]: compiler, {[[P6]]}, ir, (device-[[T]], [[ARCH2]])
+// DASM2-DAG: [[P8:[0-9]+]]: backend, {[[P7]]}, assembler, (device-[[T]], [[ARCH2]])
+// DASM2-DAG: [[P9:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa:[[ARCH2]])" {[[P8]]}, assembler
 // DASM2-NOT: host
 
 //
diff --git a/clang/test/Driver/hip-toolchain-device-only.hip b/clang/test/Driver/hip-toolchain-device-only.hip
new file mode 100644
--- /dev/null
+++ b/clang/test/Driver/hip-toolchain-device-only.hip
@@ -0,0 +1,29 @@
+// 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 -check-prefixes=CHECK,LINK %s
+
+// CHECK-NOT: error:
+
+// 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-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]]"