tqchen edited a comment on pull request #8463: URL: https://github.com/apache/tvm/pull/8463#issuecomment-879967726
Thanks @masahi . Sorry was being late on this. I think it worthwhile to think a bit more. In general, there are two kinds of information that we normally carry throughout the program: - K0: The information in the declaration/allocation site - K1: The information that carries as part of type (of the Var) which is being used through out the usage site in the code base. The Buffer object was intended for the declaration site information. There are in general two kinds of design choices here: - C0: On one hand, the information being present in the declaration site K0 can be duplicated with the information present in the allocation site, so we could remove the duplication (for example, dtype and scope are duplicated in the type atm). - C1: On the other hand, one could argue that the type annotation should be made independent from the type annotation that also shares with the usage site, so we could let the allocation site contain a duplicated set of information and check consistency during construction. Right now this PR follows C0 partially. I wonder if we should also consider the choice between C0 and C1. In the particular case of Buffer, I feel that we should give C1 a serious consideration. We can also use the text format to illustrate the potential differences between the two. ```python # Choice C0: the information was already duplicated on the lhs, so do not present on rhs ptr : Pointer[float32, "gpu"] = allocate_buffer(32) # Choice C1: ptr : Pointer[float32, "gpu"] = allocate_buffer(32, "float32", "gpu") ``` -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
