vinx13 commented on PR #80: URL: https://github.com/apache/tvm-rfcs/pull/80#issuecomment-1163436021
@wrongtest `producer_acquire, producer_commit, consumer_wait, consumer_release` are high level CUDA C++ API, CUDA pipeline at `cuda::thread_scope::thread_scope_block` is equivalent to low-level PTX `commit / wait`, these four primitives are implemented with internal counting to emit count-based async pipeline. (CUDA pipeline can also be in shared scope, which requires a more complicated implementation) -- 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]
