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 2020/07/17 22:30:35 UTC

[GitHub] [incubator-tvm] icemelon9 opened a new pull request #6089: [Relay][VM] Add ReshapeTensor instruction in the VM to replace the reshape op

icemelon9 opened a new pull request #6089:
URL: https://github.com/apache/incubator-tvm/pull/6089


   @jroesch @zhiics @mbrookhart Could you help review?


----------------------------------------------------------------
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.

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



[GitHub] [incubator-tvm] zhiics commented on pull request #6089: [Relay][VM] Add ReshapeTensor instruction in the VM to replace the reshape op

Posted by GitBox <gi...@apache.org>.
zhiics commented on pull request #6089:
URL: https://github.com/apache/incubator-tvm/pull/6089#issuecomment-661989123


   Thanks @icemelon9 @mbrookhart 


----------------------------------------------------------------
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.

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



[GitHub] [incubator-tvm] MarisaKirisame commented on pull request #6089: [Relay][VM] Add ReshapeTensor instruction in the VM to replace the reshape op

Posted by GitBox <gi...@apache.org>.
MarisaKirisame commented on pull request #6089:
URL: https://github.com/apache/incubator-tvm/pull/6089#issuecomment-666998820


   @icemelon9 is_reshape_only is incorrect. If a function return a constant it will wrap a reshape on it. Please fix it in a principle way (e.g. not by checking that the whole function has at least one reshape, as this will not work on reshape of constant).


----------------------------------------------------------------
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.

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



[GitHub] [incubator-tvm] zhiics commented on pull request #6089: [Relay][VM] Add ReshapeTensor instruction in the VM to replace the reshape op

Posted by GitBox <gi...@apache.org>.
zhiics commented on pull request #6089:
URL: https://github.com/apache/incubator-tvm/pull/6089#issuecomment-660402821


   Please check the error. It cannot be executed on 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.

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



[GitHub] [incubator-tvm] zhiics edited a comment on pull request #6089: [Relay][VM] Add ReshapeTensor instruction in the VM to replace the reshape op

Posted by GitBox <gi...@apache.org>.
zhiics edited a comment on pull request #6089:
URL: https://github.com/apache/incubator-tvm/pull/6089#issuecomment-660402821


   Please check the error. We have gpu context in the check_result.


----------------------------------------------------------------
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.

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



[GitHub] [incubator-tvm] zhiics merged pull request #6089: [Relay][VM] Add ReshapeTensor instruction in the VM to replace the reshape op

Posted by GitBox <gi...@apache.org>.
zhiics merged pull request #6089:
URL: https://github.com/apache/incubator-tvm/pull/6089


   


----------------------------------------------------------------
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.

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



[GitHub] [incubator-tvm] mbrookhart commented on pull request #6089: [Relay][VM] Add ReshapeTensor instruction in the VM to replace the reshape op

Posted by GitBox <gi...@apache.org>.
mbrookhart commented on pull request #6089:
URL: https://github.com/apache/incubator-tvm/pull/6089#issuecomment-660406275


   The GPU error seems to come from the check I added to fail early on GPU with dynamic models. I believe dynamic shapes wont work on cuda until we get heterogenous execution working for shape funcs, per our discussion in https://discuss.tvm.ai/t/issue-with-vm-execution-when-testing-gpu-immediately-after-cpu/7010/7
   
   @zhiics, any update on that work? Or should we limit this test to CPU?


----------------------------------------------------------------
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.

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



[GitHub] [incubator-tvm] zhiics commented on pull request #6089: [Relay][VM] Add ReshapeTensor instruction in the VM to replace the reshape op

Posted by GitBox <gi...@apache.org>.
zhiics commented on pull request #6089:
URL: https://github.com/apache/incubator-tvm/pull/6089#issuecomment-660424453


   @mbrookhart Yeah, I meant there is gpu context in the test. That's why the ci fails. We can probably just disable check_result for this test ATM. Heterogeneous execution needs this PR.


----------------------------------------------------------------
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.

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