commit 8a5fc15aa45a1d5f83fe81771349e729a1ee64b7
author Yaxun Liu <Yaxun.Liu@amd.com> Wed Apr 04 21:19:27 2018 +0000
committer Yaxun Liu <Yaxun.Liu@amd.com> Wed Apr 04 21:19:27 2018 +0000
tree e6d720c0f77fafb7d1602b86d4e8ac91e7d5a534
parent c9a918c560aa2f524815dfb4ec68c3b24f3b211a

[CUDA] Add amdgpu sub archs

Patch by Greg Rodgers.
Revised and lit tests added by Yaxun Liu.

Differential Revision: https://reviews.llvm.org/D45277

llvm-svn: 329232

clang/lib/Basic/Cuda.cpp

diff --git a/clang/lib/Basic/Cuda.cpp b/clang/lib/Basic/Cuda.cpp
index b7e04bf..970c060 100644
--- a/clang/lib/Basic/Cuda.cpp
+++ b/clang/lib/Basic/Cuda.cpp
@@ -58,6 +58,32 @@
     return "sm_70";
   case CudaArch::SM_72:
     return "sm_72";
+  case CudaArch::GFX600: // tahiti
+    return "gfx600";
+  case CudaArch::GFX601: // pitcairn, verde, oland,hainan
+    return "gfx601";
+  case CudaArch::GFX700: // kaveri
+    return "gfx700";
+  case CudaArch::GFX701: // hawaii
+    return "gfx701";
+  case CudaArch::GFX702: // 290,290x,R390,R390x
+    return "gfx702";
+  case CudaArch::GFX703: // kabini mullins
+    return "gfx703";
+  case CudaArch::GFX704: // bonaire
+    return "gfx704";
+  case CudaArch::GFX801: // carrizo
+    return "gfx801";
+  case CudaArch::GFX802: // tonga,iceland
+    return "gfx802";
+  case CudaArch::GFX803: // fiji,polaris10
+    return "gfx803";
+  case CudaArch::GFX810: // stoney
+    return "gfx810";
+  case CudaArch::GFX900: // vega, instinct
+    return "gfx900";
+  case CudaArch::GFX902: // TBA
+    return "gfx902";
   }
   llvm_unreachable("invalid enum");
 }
@@ -78,6 +104,19 @@
       .Case("sm_62", CudaArch::SM_62)
       .Case("sm_70", CudaArch::SM_70)
       .Case("sm_72", CudaArch::SM_72)
+      .Case("gfx600", CudaArch::GFX600)
+      .Case("gfx601", CudaArch::GFX601)
+      .Case("gfx700", CudaArch::GFX700)
+      .Case("gfx701", CudaArch::GFX701)
+      .Case("gfx702", CudaArch::GFX702)
+      .Case("gfx703", CudaArch::GFX703)
+      .Case("gfx704", CudaArch::GFX704)
+      .Case("gfx801", CudaArch::GFX801)
+      .Case("gfx802", CudaArch::GFX802)
+      .Case("gfx803", CudaArch::GFX803)
+      .Case("gfx810", CudaArch::GFX810)
+      .Case("gfx900", CudaArch::GFX900)
+      .Case("gfx902", CudaArch::GFX902)
       .Default(CudaArch::UNKNOWN);
 }
 
@@ -111,6 +150,8 @@
     return "compute_70";
   case CudaVirtualArch::COMPUTE_72:
     return "compute_72";
+  case CudaVirtualArch::COMPUTE_AMDGCN:
+    return "compute_amdgcn";
   }
   llvm_unreachable("invalid enum");
 }
@@ -130,6 +171,7 @@
       .Case("compute_62", CudaVirtualArch::COMPUTE_62)
       .Case("compute_70", CudaVirtualArch::COMPUTE_70)
       .Case("compute_72", CudaVirtualArch::COMPUTE_72)
+      .Case("compute_amdgcn", CudaVirtualArch::COMPUTE_AMDGCN)
       .Default(CudaVirtualArch::UNKNOWN);
 }
 
@@ -166,6 +208,20 @@
     return CudaVirtualArch::COMPUTE_70;
   case CudaArch::SM_72:
     return CudaVirtualArch::COMPUTE_72;
+  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:
+    return CudaVirtualArch::COMPUTE_AMDGCN;
   }
   llvm_unreachable("invalid enum");
 }
@@ -194,6 +250,20 @@
     return CudaVersion::CUDA_90;
   case CudaArch::SM_72:
     return CudaVersion::CUDA_91;
+  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:
+    return CudaVersion::CUDA_70;
   }
   llvm_unreachable("invalid enum");
 }
@@ -204,6 +274,19 @@
     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:
     return CudaVersion::CUDA_80;
   default:
     return CudaVersion::LATEST;