Re: [PR] [Target] Support CUDA device function calls [tvm]

["Hzfengsy (via GitHub)" <gi...@apache.org>]

Hzfengsy commented on PR #18055:
URL: https://github.com/apache/tvm/pull/18055#issuecomment-3050957901

   @tqchen @Kathryn-cat I've updated a version to detect if a function is from hthe ost side and device side at an early stage (in BindTarget pass), here is an example of a mixture call to the same function
   
   ```python
   @I.ir_module
   class Module:
       @T.prim_func(private=True)
       def add(a: T.int32, b: T.int32) -> T.int32:
           return a + b
   
       @T.prim_func
       def main(
           A: T.Buffer((128, 128), "int32"),
           B: T.Buffer((128, 128), "int32"),
           C: T.Buffer((128, 128), "int32"),
       ):
           T.func_attr({"global_symbol": "main"})
           length: T.int32 = Module.add(64, 64)  # Call from host
           for bx in T.thread_binding(length, "blockIdx.x"):
               for tx in T.thread_binding(length, "threadIdx.x"):
                   C[bx, tx] = Module.add(A[bx, tx], B[bx, tx])  # Call from device
   ```
   
   Please review again when you have time


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org