You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by GitBox <gi...@apache.org> on 2022/10/11 16:34:14 UTC

[GitHub] [tvm] adstraw opened a new pull request, #13037: [Hexagon] Enable multi input Async DMA; same queue / stage

adstraw opened a new pull request, #13037:
URL: https://github.com/apache/tvm/pull/13037

   Instead of a single `async_commit_queue_scope` encompassing several `async_scope` attributes e.g. as follows:
   
   ```
           with T.attr(0, "async_commit_queue_scope", 0):
               with T.attr(0, "async_scope", 1):
                   for ax0 in T.serial(64):
                       A_global_vtcm_1[ax0] = A[ax0]
               T.attr(0, "async_scope", 1)
               for ax0 in T.serial(64):
                   B_global_vtcm_1[ax0] = B[ax0]
    ```
   
   Force each `async_scope` to be in its own `async_commit_queue_scope` attribute e.g. as follows:
   
   ```
           with T.attr(0, "async_commit_queue_scope", 0):
               T.attr(0, "async_scope", 1)
               for ax0 in T.serial(64):
                   A_global_vtcm_1[ax0] = A[ax0]
           with T.attr(0, "async_commit_queue_scope", 0):
               T.attr(0, "async_scope", 1)
               for ax0 in T.serial(64):
                   B_global_vtcm_1[ax0] = B[ax0]
   ```
   
   And adjust "in flight" wait counts accordingly.  In the former case (single `async_commit_queue_scope`) the "in flight" wait count is `1` and in the latter case (multiple `async_commit_queue_scope`) the "in flight" wait count is `n` where `n` is the number of `async_commit_queue_scope` attributes --- `2` in the example.
   
   This enables multiple input async DMA using the same queue / stage on Hexagon where before it was blocked due to the fact that "in flight" counts are managed for each individual DMA with no way to determine if a group of DMAs has completed.


-- 
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


[GitHub] [tvm] adstraw commented on pull request #13037: [Hexagon] Enable multi input Async DMA; same queue / stage

Posted by GitBox <gi...@apache.org>.
adstraw commented on PR #13037:
URL: https://github.com/apache/tvm/pull/13037#issuecomment-1274976615

   CC @masahi 


-- 
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


[GitHub] [tvm] masahi merged pull request #13037: [Hexagon] Enable multi input Async DMA; same queue / stage

Posted by GitBox <gi...@apache.org>.
masahi merged PR #13037:
URL: https://github.com/apache/tvm/pull/13037


-- 
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


[GitHub] [tvm] masahi commented on pull request #13037: [Hexagon] Enable multi input Async DMA; same queue / stage

Posted by GitBox <gi...@apache.org>.
masahi commented on PR #13037:
URL: https://github.com/apache/tvm/pull/13037#issuecomment-1275978653

   Interesting, for CUDA the former behavior is more natural - treating global to shared mem async copy for A and B matrices in GEMM as one "chunk". 
   
   All CUDA async copy examples and [the state of the art library](https://github.com/NVIDIA/cutlass) follow this approach, so I want to be able to preserve this behavior for CUDA. Is it possible to make "commit_queue_scope granularity" configurable?


-- 
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


[GitHub] [tvm] adstraw commented on pull request #13037: [Hexagon] Enable multi input Async DMA; same queue / stage

Posted by GitBox <gi...@apache.org>.
adstraw commented on PR #13037:
URL: https://github.com/apache/tvm/pull/13037#issuecomment-1276785052

   @tvm-bot rerun


-- 
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


[GitHub] [tvm] tvm-bot commented on pull request #13037: [Hexagon] Enable multi input Async DMA; same queue / stage

Posted by GitBox <gi...@apache.org>.
tvm-bot commented on PR #13037:
URL: https://github.com/apache/tvm/pull/13037#issuecomment-1276865071

   <!---bot-comment-->
   
   Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews from [Reviewers](https://github.com/apache/incubator-tvm/blob/master/CONTRIBUTORS.md#reviewers) by @-ing them in a comment.
   
   <!--bot-comment-docs-start-->
    * Built docs for commit 24c01e74ab94a540afdce80649c243190c7b70ed can be found [here](https://pr-docs.tlcpack.ai/PR-13037/4/docs/index.html).<!--bot-comment-docs-end-->
   
   <sub>Generated by [tvm-bot](https://github.com/apache/tvm/blob/main/ci/README.md#github-actions)</sub>


-- 
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