[AMDGPU] gfx908 clang target

[kzhuravl]

LGTM

cfe/trunk/include/clang/Basic/Cuda.h

enum class CudaArch {
   GFX801,
   GFX802,
   GFX803,
   GFX810,
   GFX900,
   GFX902,
   GFX904,
   GFX906,
+  GFX908,
   GFX909,
   LAST,
 };
 const char *CudaArchToString(CudaArch A);
 
 // The input should have the form "sm_20".
 CudaArch StringToCudaArch(llvm::StringRef S);
 

cfe/trunk/lib/Basic/Cuda.cpp

const char *CudaArchToString(CudaArch A) {
   case CudaArch::GFX900: // vega, instinct
     return "gfx900";
   case CudaArch::GFX902: // TBA
     return "gfx902";
   case CudaArch::GFX904: // TBA
     return "gfx904";
   case CudaArch::GFX906: // TBA
     return "gfx906";
+  case CudaArch::GFX908: // TBA
+    return "gfx908";
   case CudaArch::GFX909: // TBA
     return "gfx909";
   }
   llvm_unreachable("invalid enum");
 }
 
 CudaArch StringToCudaArch(llvm::StringRef S) {
   return llvm::StringSwitch<CudaArch>(S)
return llvm::StringSwitch<CudaArch>(S)
       .Case("gfx801", CudaArch::GFX801)
       .Case("gfx802", CudaArch::GFX802)
       .Case("gfx803", CudaArch::GFX803)
       .Case("gfx810", CudaArch::GFX810)
       .Case("gfx900", CudaArch::GFX900)
       .Case("gfx902", CudaArch::GFX902)
       .Case("gfx904", CudaArch::GFX904)
       .Case("gfx906", CudaArch::GFX906)
+      .Case("gfx908", CudaArch::GFX908)
       .Case("gfx909", CudaArch::GFX909)
       .Default(CudaArch::UNKNOWN);
 }
 
 const char *CudaVirtualArchToString(CudaVirtualArch A) {
   switch (A) {
   case CudaVirtualArch::UNKNOWN:
     return "unknown";
CudaVirtualArch VirtualArchForCudaArch(CudaArch A) {
   case CudaArch::GFX801:
   case CudaArch::GFX802:
   case CudaArch::GFX803:
   case CudaArch::GFX810:
   case CudaArch::GFX900:
   case CudaArch::GFX902:
   case CudaArch::GFX904:
   case CudaArch::GFX906:
+  case CudaArch::GFX908:
   case CudaArch::GFX909:
     return CudaVirtualArch::COMPUTE_AMDGCN;
   }
   llvm_unreachable("invalid enum");
 }
 
 CudaVersion MinVersionForCudaArch(CudaArch A) {
   switch (A) {
CudaVersion MinVersionForCudaArch(CudaArch A) {
   case CudaArch::GFX801:
   case CudaArch::GFX802:
   case CudaArch::GFX803:
   case CudaArch::GFX810:
   case CudaArch::GFX900:
   case CudaArch::GFX902:
   case CudaArch::GFX904:
   case CudaArch::GFX906:
+  case CudaArch::GFX908:
   case CudaArch::GFX909:
     return CudaVersion::CUDA_70;
   }
   llvm_unreachable("invalid enum");
 }
 
 CudaVersion MaxVersionForCudaArch(CudaArch A) {
   switch (A) {

cfe/trunk/lib/Basic/Targets/AMDGPU.cpp

case GK_GFX1010:
       Features["ci-insts"] = true;
       Features["16-bit-insts"] = true;
       Features["dpp"] = true;
       Features["gfx8-insts"] = true;
       Features["gfx9-insts"] = true;
       Features["gfx10-insts"] = true;
       Features["s-memrealtime"] = true;
       break;
+    case GK_GFX908:
+      Features["dot3-insts"] = true;
+      Features["dot4-insts"] = true;
+      Features["dot5-insts"] = true;
+      Features["dot6-insts"] = true;
+      LLVM_FALLTHROUGH;
     case GK_GFX906:
       Features["dl-insts"] = true;
       Features["dot1-insts"] = true;
       Features["dot2-insts"] = true;
       LLVM_FALLTHROUGH;
     case GK_GFX909:
     case GK_GFX904:
     case GK_GFX902:

cfe/trunk/lib/Basic/Targets/NVPTX.cpp

std::string CUDAArchCode = [this] {
       case CudaArch::GFX801:
       case CudaArch::GFX802:
       case CudaArch::GFX803:
       case CudaArch::GFX810:
       case CudaArch::GFX900:
       case CudaArch::GFX902:
       case CudaArch::GFX904:
       case CudaArch::GFX906:
+      case CudaArch::GFX908:
       case CudaArch::GFX909:
       case CudaArch::LAST:
         break;
       case CudaArch::UNKNOWN:
         assert(false && "No GPU arch when compiling CUDA device code.");
         return "";
       case CudaArch::SM_20:
         return "200";

cfe/trunk/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp

if (Clause->getClauseKind() == OMPC_unified_shared_memory) {
       case CudaArch::GFX801:
       case CudaArch::GFX802:
       case CudaArch::GFX803:
       case CudaArch::GFX810:
       case CudaArch::GFX900:
       case CudaArch::GFX902:
       case CudaArch::GFX904:
       case CudaArch::GFX906:
+      case CudaArch::GFX908:
       case CudaArch::GFX909:
       case CudaArch::UNKNOWN:
         break;
       case CudaArch::LAST:
         llvm_unreachable("Unexpected Cuda arch.");
       }
     }
   }
static std::pair<unsigned, unsigned> getSMsBlocksPerSM(CodeGenModule &CGM) {
   case CudaArch::GFX801:
   case CudaArch::GFX802:
   case CudaArch::GFX803:
   case CudaArch::GFX810:
   case CudaArch::GFX900:
   case CudaArch::GFX902:
   case CudaArch::GFX904:
   case CudaArch::GFX906:
+  case CudaArch::GFX908:
   case CudaArch::GFX909:
   case CudaArch::UNKNOWN:
     break;
   case CudaArch::LAST:
     llvm_unreachable("Unexpected Cuda arch.");
   }
   llvm_unreachable("Unexpected NVPTX target without ptx feature.");
 }

cfe/trunk/test/CodeGenOpenCL/amdgpu-features.cl

 // REQUIRES: amdgpu-registered-target
 
 // Check that appropriate features are defined for every supported AMDGPU
 // "-target" and "-mcpu" options.
 
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx904 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX904 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx906 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX906 %s
+// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx908 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX908 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1010 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1010 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1011 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1011 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1012 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1012 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx801 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX801 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx700 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX700 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx600 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX600 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx601 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX601 %s
 
 // GFX904: "target-features"="+16-bit-insts,+ci-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx8-insts,+gfx9-insts,+s-memrealtime"
 // GFX906: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx8-insts,+gfx9-insts,+s-memrealtime"
+// GFX908: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx8-insts,+gfx9-insts,+s-memrealtime"
 // GFX1010: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime"
 // GFX1011: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime"
 // GFX1012: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime"
 // GFX801: "target-features"="+16-bit-insts,+ci-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx8-insts,+s-memrealtime"
 // GFX700: "target-features"="+ci-insts,+fp64-fp16-denormals,-fp32-denormals"
 // GFX600: "target-features"="+fp64-fp16-denormals,-fp32-denormals"
 // GFX601: "target-features"="+fp64-fp16-denormals,-fp32-denormals"
 
 kernel void test() {}

cfe/trunk/test/Driver/amdgpu-macros.cl

 // RUN: %clang -E -dM -target amdgcn -mcpu=polaris10 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX803 %s
 // RUN: %clang -E -dM -target amdgcn -mcpu=polaris11 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX803 %s
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx810 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX810 %s
 // RUN: %clang -E -dM -target amdgcn -mcpu=stoney %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX810 %s
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx900 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX900 %s
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx902 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX902 %s
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx904 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX904 %s
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx906 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX906 %s
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx908 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX908 %s
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx909 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX909 %s
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1010 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX1010 %s
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1011 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX1011 %s
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1012 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX1012 %s
 
 // GFX600-DAG: #define FP_FAST_FMA 1
 // GFX601-DAG: #define FP_FAST_FMA 1
 // GFX700-DAG: #define FP_FAST_FMA 1
 // GFX701-DAG: #define FP_FAST_FMA 1
 // GFX702-DAG: #define FP_FAST_FMA 1
 // GFX703-DAG: #define FP_FAST_FMA 1
 // GFX704-DAG: #define FP_FAST_FMA 1
 // GFX801-DAG: #define FP_FAST_FMA 1
 // GFX802-DAG: #define FP_FAST_FMA 1
 // GFX803-DAG: #define FP_FAST_FMA 1
 // GFX810-DAG: #define FP_FAST_FMA 1
 // GFX900-DAG: #define FP_FAST_FMA 1
 // GFX902-DAG: #define FP_FAST_FMA 1
 // GFX904-DAG: #define FP_FAST_FMA 1
 // GFX906-DAG: #define FP_FAST_FMA 1
+// GFX908-DAG: #define FP_FAST_FMA 1
 // GFX909-DAG: #define FP_FAST_FMA 1
 // GFX1010-DAG: #define FP_FAST_FMA 1
 // GFX1011-DAG: #define FP_FAST_FMA 1
 // GFX1012-DAG: #define FP_FAST_FMA 1
 
 // GFX600-DAG: #define FP_FAST_FMAF 1
 // GFX601-NOT: #define FP_FAST_FMAF 1
 // GFX700-NOT: #define FP_FAST_FMAF 1
 // GFX701-DAG: #define FP_FAST_FMAF 1
 // GFX702-DAG: #define FP_FAST_FMAF 1
 // GFX703-NOT: #define FP_FAST_FMAF 1
 // GFX704-NOT: #define FP_FAST_FMAF 1
 // GFX801-DAG: #define FP_FAST_FMAF 1
 // GFX802-NOT: #define FP_FAST_FMAF 1
 // GFX803-NOT: #define FP_FAST_FMAF 1
 // GFX810-NOT: #define FP_FAST_FMAF 1
 // GFX900-DAG: #define FP_FAST_FMAF 1
 // GFX902-DAG: #define FP_FAST_FMAF 1
 // GFX904-DAG: #define FP_FAST_FMAF 1
 // GFX906-DAG: #define FP_FAST_FMAF 1
+// GFX908-DAG: #define FP_FAST_FMAF 1
 // GFX909-DAG: #define FP_FAST_FMAF 1
 // GFX1010-DAG: #define FP_FAST_FMAF 1
 // GFX1011-DAG: #define FP_FAST_FMAF 1
 // GFX1012-DAG: #define FP_FAST_FMAF 1
 
 // ARCH-GCN-DAG: #define __AMDGCN__ 1
 // ARCH-GCN-DAG: #define __AMDGPU__ 1
 // ARCH-GCN-DAG: #define __AMD__ 1
 
 // GFX600-DAG: #define __HAS_FMAF__ 1
 // GFX601-DAG: #define __HAS_FMAF__ 1
 // GFX700-DAG: #define __HAS_FMAF__ 1
 // GFX701-DAG: #define __HAS_FMAF__ 1
 // GFX702-DAG: #define __HAS_FMAF__ 1
 // GFX703-DAG: #define __HAS_FMAF__ 1
 // GFX704-DAG: #define __HAS_FMAF__ 1
 // GFX801-DAG: #define __HAS_FMAF__ 1
 // GFX802-DAG: #define __HAS_FMAF__ 1
 // GFX803-DAG: #define __HAS_FMAF__ 1
 // GFX810-DAG: #define __HAS_FMAF__ 1
 // GFX900-DAG: #define __HAS_FMAF__ 1
 // GFX902-DAG: #define __HAS_FMAF__ 1
 // GFX904-DAG: #define __HAS_FMAF__ 1
 // GFX906-DAG: #define __HAS_FMAF__ 1
+// GFX908-DAG: #define __HAS_FMAF__ 1
 // GFX909-DAG: #define __HAS_FMAF__ 1
 // GFX1010-DAG: #define __HAS_FMAF__ 1
 // GFX1011-DAG: #define __HAS_FMAF__ 1
 // GFX1012-DAG: #define __HAS_FMAF__ 1
 
 // GFX600-DAG: #define __HAS_FP64__ 1
 // GFX601-DAG: #define __HAS_FP64__ 1
 // GFX700-DAG: #define __HAS_FP64__ 1
 // GFX701-DAG: #define __HAS_FP64__ 1
 // GFX702-DAG: #define __HAS_FP64__ 1
 // GFX703-DAG: #define __HAS_FP64__ 1
 // GFX704-DAG: #define __HAS_FP64__ 1
 // GFX801-DAG: #define __HAS_FP64__ 1
 // GFX802-DAG: #define __HAS_FP64__ 1
 // GFX803-DAG: #define __HAS_FP64__ 1
 // GFX810-DAG: #define __HAS_FP64__ 1
 // GFX900-DAG: #define __HAS_FP64__ 1
 // GFX902-DAG: #define __HAS_FP64__ 1
 // GFX904-DAG: #define __HAS_FP64__ 1
 // GFX906-DAG: #define __HAS_FP64__ 1
+// GFX908-DAG: #define __HAS_FP64__ 1
 // GFX909-DAG: #define __HAS_FP64__ 1
 // GFX1010-DAG: #define __HAS_FP64__ 1
 // GFX1011-DAG: #define __HAS_FP64__ 1
 // GFX1012-DAG: #define __HAS_FP64__ 1
 
 // GFX600-DAG: #define __HAS_LDEXPF__ 1
 // GFX601-DAG: #define __HAS_LDEXPF__ 1
 // GFX700-DAG: #define __HAS_LDEXPF__ 1
 // GFX701-DAG: #define __HAS_LDEXPF__ 1
 // GFX702-DAG: #define __HAS_LDEXPF__ 1
 // GFX703-DAG: #define __HAS_LDEXPF__ 1
 // GFX704-DAG: #define __HAS_LDEXPF__ 1
 // GFX801-DAG: #define __HAS_LDEXPF__ 1
 // GFX802-DAG: #define __HAS_LDEXPF__ 1
 // GFX803-DAG: #define __HAS_LDEXPF__ 1
 // GFX810-DAG: #define __HAS_LDEXPF__ 1
 // GFX900-DAG: #define __HAS_LDEXPF__ 1
 // GFX902-DAG: #define __HAS_LDEXPF__ 1
 // GFX904-DAG: #define __HAS_LDEXPF__ 1
 // GFX906-DAG: #define __HAS_LDEXPF__ 1
+// GFX908-DAG: #define __HAS_LDEXPF__ 1
 // GFX909-DAG: #define __HAS_LDEXPF__ 1
 // GFX1010-DAG: #define __HAS_LDEXPF__ 1
 // GFX1011-DAG: #define __HAS_LDEXPF__ 1
 // GFX1012-DAG: #define __HAS_LDEXPF__ 1
 
 // GFX600-DAG: #define __gfx600__ 1
 // GFX601-DAG: #define __gfx601__ 1
 // GFX700-DAG: #define __gfx700__ 1
 // GFX701-DAG: #define __gfx701__ 1
 // GFX702-DAG: #define __gfx702__ 1
 // GFX703-DAG: #define __gfx703__ 1
 // GFX704-DAG: #define __gfx704__ 1
 // GFX801-DAG: #define __gfx801__ 1
 // GFX802-DAG: #define __gfx802__ 1
 // GFX803-DAG: #define __gfx803__ 1
 // GFX810-DAG: #define __gfx810__ 1
 // GFX900-DAG: #define __gfx900__ 1
 // GFX902-DAG: #define __gfx902__ 1
 // GFX904-DAG: #define __gfx904__ 1
 // GFX906-DAG: #define __gfx906__ 1
+// GFX908-DAG: #define __gfx908__ 1
 // GFX909-DAG: #define __gfx909__ 1
 // GFX1010-DAG: #define __gfx1010__ 1
 // GFX1011-DAG: #define __gfx1011__ 1
 // GFX1012-DAG: #define __gfx1012__ 1

cfe/trunk/test/Driver/amdgpu-mcpu.cl

 // RUN: %clang -### -target amdgcn -mcpu=polaris10 %s 2>&1 | FileCheck --check-prefix=POLARIS10 %s
 // RUN: %clang -### -target amdgcn -mcpu=polaris11 %s 2>&1 | FileCheck --check-prefix=POLARIS11 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx810 %s 2>&1 | FileCheck --check-prefix=GFX810 %s
 // RUN: %clang -### -target amdgcn -mcpu=stoney %s 2>&1 | FileCheck --check-prefix=STONEY %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx900 %s 2>&1 | FileCheck --check-prefix=GFX900 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx902 %s 2>&1 | FileCheck --check-prefix=GFX902 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx904 %s 2>&1 | FileCheck --check-prefix=GFX904 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx906 %s 2>&1 | FileCheck --check-prefix=GFX906 %s
+// RUN: %clang -### -target amdgcn -mcpu=gfx908 %s 2>&1 | FileCheck --check-prefix=GFX908 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx909 %s 2>&1 | FileCheck --check-prefix=GFX909 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx1010 %s 2>&1 | FileCheck --check-prefix=GFX1010 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx1011 %s 2>&1 | FileCheck --check-prefix=GFX1011 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx1012 %s 2>&1 | FileCheck --check-prefix=GFX1012 %s
 
 // GFX600:    "-target-cpu" "gfx600"
 // TAHITI:    "-target-cpu" "tahiti"
 // GFX601:    "-target-cpu" "gfx601"

 // POLARIS10: "-target-cpu" "polaris10"
 // POLARIS11: "-target-cpu" "polaris11"
 // GFX810:    "-target-cpu" "gfx810"
 // STONEY:    "-target-cpu" "stoney"
 // GFX900:    "-target-cpu" "gfx900"
 // GFX902:    "-target-cpu" "gfx902"
 // GFX904:    "-target-cpu" "gfx904"
 // GFX906:    "-target-cpu" "gfx906"
+// GFX908:    "-target-cpu" "gfx908"
 // GFX909:    "-target-cpu" "gfx909"
 // GFX1010:   "-target-cpu" "gfx1010"
 // GFX1011:   "-target-cpu" "gfx1011"
 // GFX1012:   "-target-cpu" "gfx1012"

cfe/trunk/test/Driver/cuda-bad-arch.cu

 // RUN: | FileCheck -check-prefix BAD_CUDA9 %s
 
 // BAD_CUDA9: GPU arch sm_21 is supported by CUDA versions between 7.0 and 8.0
 
 // RUN: %clang -### -target x86_64-linux-gnu --cuda-gpu-arch=sm_20 -c %s 2>&1 \
 // RUN: | FileCheck -check-prefix OK %s
 // RUN: %clang -### -target x86_64-linux-gnu --cuda-gpu-arch=sm_52 -c %s 2>&1 \
 // RUN: | FileCheck -check-prefix OK %s
+// RUN: %clang -### -target x86_64-linux-gnu --cuda-gpu-arch=gfx908 -c %s 2>&1 \
+// RUN: | FileCheck -check-prefix OK %s
 // RUN: %clang -### -target x86_64-linux-gnu -c %s 2>&1 \
 // RUN: | FileCheck -check-prefix OK %s
 
 // We don't allow using NVPTX/AMDGCN for host compilation.
 // RUN: %clang -### --cuda-host-only -target nvptx-nvidia-cuda -c %s 2>&1 \
 // RUN: | FileCheck -check-prefix HOST_NVPTX %s
 // RUN: %clang -### --cuda-host-only -target amdgcn-amd-amdhsa -c %s 2>&1 \
 // RUN: | FileCheck -check-prefix HOST_AMDGCN %s
 
 // OK-NOT: error: Unsupported CUDA gpu architecture
 // HOST_NVPTX: error: unsupported architecture 'nvptx' for host compilation.
 // HOST_AMDGCN: error: unsupported architecture 'amdgcn' for host compilation.