[clang] [llvm] [CUDA] Add support for CUDA-12.6 and sm_100 (PR #112028)

[via cfe-commits]

github-actions[bot] wrote:

<!--LLVM CODE FORMAT COMMENT: {clang-format}-->


:warning: C/C++ code formatter, clang-format found issues in your code. 
:warning:

<details>
<summary>
You can test this locally with the following command:
</summary>

``````````bash
git-clang-format --diff 7f1b465c6ae476e59dc90652d58fc648932d23b1 
aee63aee2c275d20596e9637905573815c01adee --extensions h,cpp,c -- 
clang/include/clang/Basic/Cuda.h clang/lib/Basic/Cuda.cpp 
clang/lib/Basic/Targets/NVPTX.cpp clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp 
clang/lib/Driver/ToolChains/Cuda.cpp 
clang/test/Misc/target-invalid-cpu-note/nvptx.c
``````````

</details>

<details>
<summary>
View the diff from clang-format here.
</summary>

``````````diff
diff --git a/clang/lib/Basic/Cuda.cpp b/clang/lib/Basic/Cuda.cpp
index c757bb7a16..08989b6c2c 100644
--- a/clang/lib/Basic/Cuda.cpp
+++ b/clang/lib/Basic/Cuda.cpp
@@ -224,7 +224,8 @@ CudaVersion MinVersionForOffloadArch(OffloadArch A) {
   case OffloadArch::SM_90a:
     return CudaVersion::CUDA_120;
   case OffloadArch::SM_100:
-    return CudaVersion::NEW; // TODO: use specific CUDA version once it's 
public.
+    return CudaVersion::NEW; // TODO: use specific CUDA version once it's
+                             // public.
   default:
     llvm_unreachable("invalid enum");
   }
diff --git a/clang/lib/Driver/ToolChains/Cuda.cpp 
b/clang/lib/Driver/ToolChains/Cuda.cpp
index 0a401fa5af..08c54f71bb 100644
--- a/clang/lib/Driver/ToolChains/Cuda.cpp
+++ b/clang/lib/Driver/ToolChains/Cuda.cpp
@@ -671,10 +671,10 @@ void NVPTX::getNVPTXTargetFeatures(const Driver &D, const 
llvm::Triple &Triple,
   case CudaVersion::CUDA_##CUDA_VER:                                           
\
     PtxFeature = "+ptx" #PTX_VER;                                              
\
     break;
-    // TODO: Use specific CUDA version once it's public.
-    case clang::CudaVersion::NEW:
-      PtxFeature = "+ptx86";
-      break;
+  // TODO: Use specific CUDA version once it's public.
+  case clang::CudaVersion::NEW:
+    PtxFeature = "+ptx86";
+    break;
     CASE_CUDA_VERSION(126, 85);
     CASE_CUDA_VERSION(125, 85);
     CASE_CUDA_VERSION(124, 84);

``````````

</details>


https://github.com/llvm/llvm-project/pull/112028
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits