[llvm] [LLVM] Fix offload and update CUDA ABI for all SM values (PR #159354)

Artem Belevich via llvm-commits llvm-commits at lists.llvm.org
Wed Sep 17 11:15:08 PDT 2025


================
@@ -951,8 +957,12 @@ enum : unsigned {
   EF_CUDA_SM86 = 0x56,
   EF_CUDA_SM87 = 0x57,
   EF_CUDA_SM89 = 0x59,
-  // The sm_90a variant uses the same machine flag.
   EF_CUDA_SM90 = 0x5a,
+  EF_CUDA_SM100 = 0x64,
+  EF_CUDA_SM101 = 0x65,
----------------
Artem-B wrote:

About that sm_101.
In CUDA-13 it's been renamed to sm_110.
You may want to check what NVIDIA tools end up generating for the same GPU in cuda-12.9 (sm_101) and 13.0(sm110), and whether NVIDIA kept the same ELF flags for them, or changed them.

https://github.com/llvm/llvm-project/pull/159354


More information about the llvm-commits mailing list