[all-commits] [llvm/llvm-project] d430d8: [CIR][CUDA] Do Runtime Kernel Registration (#188926)

[David Rivera via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: d430d89d5550e2e5aa1a72c7e5e1232ef1766da6
      https://github.com/llvm/llvm-project/commit/d430d89d5550e2e5aa1a72c7e5e1232ef1766da6
  Author: David Rivera <davidriverg at gmail.com>
  Date:   2026-04-15 (Wed, 15 Apr 2026)

  Changed paths:
    M clang/lib/CIR/Dialect/Transforms/LoweringPrepare.cpp
    M clang/test/CIR/CodeGenCUDA/device-stub.cu

  Log Message:
  -----------
  [CIR][CUDA] Do Runtime Kernel Registration (#188926)

Related:
https://github.com/issues/assigned?issue=llvm%7Cllvm-project%7C179278,
https://github.com/llvm/llvm-project/issues/175871

More registration shenanigans -> Generates `__cuda_register_globals`
that associates the fatbin with kernels that contain `__global__`
qualifiers with the runtime.

Generated equivalent runtime code:

``` C
  // Called once per kernel to register it with the CUDA runtime.
  void __cuda_register_globals(void **fatbinHandle) {
      __cudaRegisterFunction(
          fatbinHandle,
          (const char *)&_Z25__device_stub__kernelfunciii, // host-side stub ptr
          (char *)__cuda_kernelname_str,                   // device-side mangled name
          (char *)__cuda_kernelname_str,                   // device-side mangled name
          -1,      // thread limit (-1 = no limit)
          NULL, NULL, NULL, NULL, NULL
      );
  }

  void __cuda_module_ctor() {
      __cuda_gpubin_handle = __cudaRegisterFatBinary(&__cuda_fatbin_wrapper);
      __cuda_register_globals(__cuda_gpubin_handle); // ==== NEW
      // TODO: Register shadow variables
      __cudaRegisterFatBinaryEnd(__cuda_gpubin_handle); // CUDA >= 10.1
      atexit(__cuda_module_dtor);
  }
```



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications