[CUDA] Add support for sm101 and sm120 target architectures (#127187)

Add support for sm101 and sm120 target architectures. It requires CUDA
12.8.

---------

Co-authored-by: Sebastian Jodlowski <[email protected]>

Author: jodelek

clang/include/clang/Basic/BuiltinsNVPTX.td

@@ -21,12 +21,14 @@ class SM<string version, list<SMFeatures> newer_list> : SMFeatures {
                         !strconcat(f, "|", newer.Features));
 }
 
+let Features = "sm_120a" in def SM_120a : SMFeatures;
+let Features = "sm_101a" in def SM_101a : SMFeatures;
 let Features = "sm_100a" in def SM_100a : SMFeatures;
-
-def SM_100 : SM<"100", [SM_100a]>;
-
 let Features = "sm_90a" in def SM_90a : SMFeatures;
 
+def SM_120 : SM<"120", [SM_120a]>;
+def SM_101 : SM<"101", [SM_101a, SM_120]>;
+def SM_100 : SM<"100", [SM_100a, SM_101]>;
 def SM_90 : SM<"90", [SM_90a, SM_100]>;
 def SM_89 : SM<"89", [SM_90]>;
 def SM_87 : SM<"87", [SM_89]>;

clang/include/clang/Basic/Cuda.h

@@ -82,6 +82,10 @@ enum class OffloadArch {
   SM_90a,
   SM_100,
   SM_100a,
+  SM_101,
+  SM_101a,
+  SM_120,
+  SM_120a,
   GFX600,
   GFX601,
   GFX602,

clang/lib/Basic/Cuda.cpp

@@ -100,6 +100,10 @@ static const OffloadArchToStringMap arch_names[] = {
     SM(90a),                         // Hopper
     SM(100),                         // Blackwell
     SM(100a),                        // Blackwell
+    SM(101),                         // Blackwell
+    SM(101a),                        // Blackwell
+    SM(120),                         // Blackwell
+    SM(120a),                        // Blackwell
     GFX(600),  // gfx600
     GFX(601),  // gfx601
     GFX(602),  // gfx602
@@ -228,6 +232,10 @@ CudaVersion MinVersionForOffloadArch(OffloadArch A) {
     return CudaVersion::CUDA_120;
   case OffloadArch::SM_100:
   case OffloadArch::SM_100a:
+  case OffloadArch::SM_101:
+  case OffloadArch::SM_101a:
+  case OffloadArch::SM_120:
+  case OffloadArch::SM_120a:
     return CudaVersion::CUDA_128;
   default:
     llvm_unreachable("invalid enum");

clang/lib/Basic/Targets/NVPTX.cpp

@@ -185,7 +185,7 @@ void NVPTXTargetInfo::getTargetDefines(const LangOptions &Opts,
 
   if (Opts.CUDAIsDevice || Opts.OpenMPIsTargetDevice || !HostTarget) {
     // Set __CUDA_ARCH__ for the GPU specified.
-    std::string CUDAArchCode = [this] {
+    llvm::StringRef CUDAArchCode = [this] {
       switch (GPU) {
       case OffloadArch::GFX600:
       case OffloadArch::GFX601:
@@ -290,14 +290,27 @@ void NVPTXTargetInfo::getTargetDefines(const LangOptions &Opts,
       case OffloadArch::SM_100:
       case OffloadArch::SM_100a:
         return "1000";
+      case OffloadArch::SM_101:
+      case OffloadArch::SM_101a:
+         return "1010";
+      case OffloadArch::SM_120:
+      case OffloadArch::SM_120a:
+         return "1200";
       }
       llvm_unreachable("unhandled OffloadArch");
     }();
     Builder.defineMacro("__CUDA_ARCH__", CUDAArchCode);
-    if (GPU == OffloadArch::SM_90a)
-      Builder.defineMacro("__CUDA_ARCH_FEAT_SM90_ALL", "1");
-    if (GPU == OffloadArch::SM_100a)
-      Builder.defineMacro("__CUDA_ARCH_FEAT_SM100_ALL", "1");
+    switch(GPU) {
+      case OffloadArch::SM_90a:
+      case OffloadArch::SM_100a:
+      case OffloadArch::SM_101a:
+      case OffloadArch::SM_120a:
+        Builder.defineMacro("__CUDA_ARCH_FEAT_SM" + CUDAArchCode.drop_back() + "_ALL", "1");
+        break;
+      default:
+        // Do nothing if this is not an enhanced architecture.
+        break;
+    }
   }
 }
 

clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp

@@ -2278,6 +2278,10 @@ void CGOpenMPRuntimeGPU::processRequiresDirective(const OMPRequiresDecl *D) {
       case OffloadArch::SM_90a:
       case OffloadArch::SM_100:
       case OffloadArch::SM_100a:
+      case OffloadArch::SM_101:
+      case OffloadArch::SM_101a:
+      case OffloadArch::SM_120:
+      case OffloadArch::SM_120a:
       case OffloadArch::GFX600:
       case OffloadArch::GFX601:
       case OffloadArch::GFX602:

clang/test/Misc/target-invalid-cpu-note/nvptx.c

@@ -28,6 +28,10 @@
 // CHECK-SAME: {{^}}, sm_90a
 // CHECK-SAME: {{^}}, sm_100
 // CHECK-SAME: {{^}}, sm_100a
+// CHECK-SAME: {{^}}, sm_101
+// CHECK-SAME: {{^}}, sm_101a
+// CHECK-SAME: {{^}}, sm_120
+// CHECK-SAME: {{^}}, sm_120a
 // CHECK-SAME: {{^}}, gfx600
 // CHECK-SAME: {{^}}, gfx601
 // CHECK-SAME: {{^}}, gfx602