[HIP] Add GPU arch gfx1010, gfx1011, and gfx1012

[ashi1]

LGTM!

[tra]

lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp

4973–4992

Just a side note:
I wonder if we need these at all -- we'll end up failing with misleading "Unexpected NVPTX target without ptx feature" assertion. We may just remove all non-SM_xx arch cases and replace them with default: calling llvm_unreachable(). Perhaps in a separate patch.

[yaxunl]

lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp

4973–4992

I think it is intentional not to use default here, otherwise people may forget to update this part when a new nvptx arch is added.

I could let gfx archs go to the path with llvm_unreachable("Unexpected Cuda arch.") though.

include/clang/Basic/Cuda.h

enum class CudaArch {
   GFX802,
   GFX803,
   GFX810,
   GFX900,
   GFX902,
   GFX904,
   GFX906,
   GFX909,
+  GFX1010,
+  GFX1011,
+  GFX1012,
   LAST,
 };
 const char *CudaArchToString(CudaArch A);
 
 // The input should have the form "sm_20".
 CudaArch StringToCudaArch(llvm::StringRef S);
 
 enum class CudaVirtualArch {

lib/Basic/Cuda.cpp

const char *CudaArchToString(CudaArch A) {
   case CudaArch::GFX902: // TBA
     return "gfx902";
   case CudaArch::GFX904: // TBA
     return "gfx904";
   case CudaArch::GFX906: // TBA
     return "gfx906";
   case CudaArch::GFX909: // TBA
     return "gfx909";
+  case CudaArch::GFX1010: // TBA
+    return "gfx1010";
+  case CudaArch::GFX1011: // TBA
+    return "gfx1011";
+  case CudaArch::GFX1012: // TBA
+    return "gfx1012";
   }
   llvm_unreachable("invalid enum");
 }
 
 CudaArch StringToCudaArch(llvm::StringRef S) {
   return llvm::StringSwitch<CudaArch>(S)
       .Case("sm_20", CudaArch::SM_20)
       .Case("sm_21", CudaArch::SM_21)
return llvm::StringSwitch<CudaArch>(S)
       .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("gfx909", CudaArch::GFX909)
+      .Case("gfx1010", CudaArch::GFX1010)
+      .Case("gfx1011", CudaArch::GFX1011)
+      .Case("gfx1012", CudaArch::GFX1012)
       .Default(CudaArch::UNKNOWN);
 }
 
 const char *CudaVirtualArchToString(CudaVirtualArch A) {
   switch (A) {
   case CudaVirtualArch::UNKNOWN:
     return "unknown";
   case CudaVirtualArch::COMPUTE_20:
CudaVirtualArch VirtualArchForCudaArch(CudaArch A) {
   case CudaArch::GFX802:
   case CudaArch::GFX803:
   case CudaArch::GFX810:
   case CudaArch::GFX900:
   case CudaArch::GFX902:
   case CudaArch::GFX904:
   case CudaArch::GFX906:
   case CudaArch::GFX909:
+  case CudaArch::GFX1010:
+  case CudaArch::GFX1011:
+  case CudaArch::GFX1012:
     return CudaVirtualArch::COMPUTE_AMDGCN;
   }
   llvm_unreachable("invalid enum");
 }
 
 CudaVersion MinVersionForCudaArch(CudaArch A) {
   switch (A) {
   case CudaArch::LAST:
CudaVersion MinVersionForCudaArch(CudaArch A) {
   case CudaArch::GFX802:
   case CudaArch::GFX803:
   case CudaArch::GFX810:
   case CudaArch::GFX900:
   case CudaArch::GFX902:
   case CudaArch::GFX904:
   case CudaArch::GFX906:
   case CudaArch::GFX909:
+  case CudaArch::GFX1010:
+  case CudaArch::GFX1011:
+  case CudaArch::GFX1012:
     return CudaVersion::CUDA_70;
   }
   llvm_unreachable("invalid enum");
 }
 
 CudaVersion MaxVersionForCudaArch(CudaArch A) {
   switch (A) {
   case CudaArch::UNKNOWN:
     return CudaVersion::UNKNOWN;
   case CudaArch::SM_20:
   case CudaArch::SM_21:
   case CudaArch::GFX600:
   case CudaArch::GFX601:
   case CudaArch::GFX700:
   case CudaArch::GFX701:
   case CudaArch::GFX702:
   case CudaArch::GFX703:
   case CudaArch::GFX704:
   case CudaArch::GFX801:
   case CudaArch::GFX802:
   case CudaArch::GFX803:
   case CudaArch::GFX810:
   case CudaArch::GFX900:
   case CudaArch::GFX902:
+  case CudaArch::GFX1010:
+  case CudaArch::GFX1011:
+  case CudaArch::GFX1012:
     return CudaVersion::CUDA_80;
   default:
     return CudaVersion::LATEST;
   }
 }
 
 static CudaVersion ToCudaVersion(llvm::VersionTuple Version) {
   int IVer =

lib/Basic/Targets/NVPTX.cpp

std::string CUDAArchCode = [this] {
       case CudaArch::GFX802:
       case CudaArch::GFX803:
       case CudaArch::GFX810:
       case CudaArch::GFX900:
       case CudaArch::GFX902:
       case CudaArch::GFX904:
       case CudaArch::GFX906:
       case CudaArch::GFX909:
+      case CudaArch::GFX1010:
+      case CudaArch::GFX1011:
+      case CudaArch::GFX1012:
       case CudaArch::LAST:
         break;
       case CudaArch::UNKNOWN:
         assert(false && "No GPU arch when compiling CUDA device code.");
         return "";
       case CudaArch::SM_20:
         return "200";
       case CudaArch::SM_21:

lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp

if (Clause->getClauseKind() == OMPC_unified_shared_memory) {
       case CudaArch::GFX802:
       case CudaArch::GFX803:
       case CudaArch::GFX810:
       case CudaArch::GFX900:
       case CudaArch::GFX902:
       case CudaArch::GFX904:
       case CudaArch::GFX906:
       case CudaArch::GFX909:
+      case CudaArch::GFX1010:
+      case CudaArch::GFX1011:
+      case CudaArch::GFX1012:
       case CudaArch::UNKNOWN:
         break;
       case CudaArch::LAST:
         llvm_unreachable("Unexpected Cuda arch.");
       }
     }
   }
   CGOpenMPRuntime::checkArchForUnifiedAddressing(D);
static std::pair<unsigned, unsigned> getSMsBlocksPerSM(CodeGenModule &CGM) {
   case CudaArch::SM_60:
   case CudaArch::SM_61:
   case CudaArch::SM_62:
     return {56, 32};
   case CudaArch::SM_70:
   case CudaArch::SM_72:
   case CudaArch::SM_75:
     return {84, 32};
   case CudaArch::GFX600:
   case CudaArch::GFX601:
   case CudaArch::GFX700:
   case CudaArch::GFX701:
   case CudaArch::GFX702:
   case CudaArch::GFX703:
   case CudaArch::GFX704:
   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::GFX909:
+  case CudaArch::GFX1010:
+  case CudaArch::GFX1011:
+  case CudaArch::GFX1012:
   case CudaArch::UNKNOWN:
     break;
   case CudaArch::LAST:
     llvm_unreachable("Unexpected Cuda arch.");
   }
   llvm_unreachable("Unexpected NVPTX target without ptx feature.");
 }
 
 void CGOpenMPRuntimeNVPTX::clear() {