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 2020/12/31 05:32:47 UTC
[GitHub] [tvm] Laurawly opened a new pull request #7187: [Fix] Tensor core type issue for dense
Laurawly opened a new pull request #7187:
URL: https://github.com/apache/tvm/pull/7187
As mentioned in PR #7146, previous tensor core code lacks type check and this PR is trying to fix that.
cc @jcf94 @merrymercy @Meteorix
----------------------------------------------------------------
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] [tvm] merrymercy removed a comment on pull request #7187: [Fix] Tensor core type issue for dense
Posted by GitBox <gi...@apache.org>.
merrymercy removed a comment on pull request #7187:
URL: https://github.com/apache/tvm/pull/7187#issuecomment-752963716
Do we allow `data.dtype == "float32"`?
The problem comes from this downcast, which may cause accuracy problem.
https://github.com/apache/tvm/blob/c02c9c528f91f9be3967b7d9ef9f1847f533590b/python/tvm/topi/cuda/dense_tensorcore.py#L72-L73
----------------------------------------------------------------
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] [tvm] merrymercy edited a comment on pull request #7187: [Fix] Tensor core type issue for dense
Posted by GitBox <gi...@apache.org>.
merrymercy edited a comment on pull request #7187:
URL: https://github.com/apache/tvm/pull/7187#issuecomment-752963716
Do we allow `data.dtype == "float32"`?
The problem comes from this downcast, which may cause accuracy problem.
https://github.com/apache/tvm/blob/c02c9c528f91f9be3967b7d9ef9f1847f533590b/python/tvm/topi/cuda/dense_tensorcore.py#L72-L73
----------------------------------------------------------------
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] [tvm] merrymercy edited a comment on pull request #7187: [Fix] Tensor core type issue for dense
Posted by GitBox <gi...@apache.org>.
merrymercy edited a comment on pull request #7187:
URL: https://github.com/apache/tvm/pull/7187#issuecomment-752963716
Should we check `data.dtype == "float16" and weight.dtype == "float16"`?
The problem comes from this downcast, which may cause accuracy problem.
https://github.com/apache/tvm/blob/c02c9c528f91f9be3967b7d9ef9f1847f533590b/python/tvm/topi/cuda/dense_tensorcore.py#L72-L73
----------------------------------------------------------------
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] [tvm] merrymercy commented on pull request #7187: [Fix] Tensor core type issue for dense
Posted by GitBox <gi...@apache.org>.
merrymercy commented on pull request #7187:
URL: https://github.com/apache/tvm/pull/7187#issuecomment-752963716
Should we check `data.dtype == "float16" and weight.dtype == "float16"`?
The problem comes from this downcast
https://github.com/apache/tvm/blob/c02c9c528f91f9be3967b7d9ef9f1847f533590b/python/tvm/topi/cuda/dense_tensorcore.py#L72-L73
----------------------------------------------------------------
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] [tvm] Laurawly commented on pull request #7187: [Fix] Tensor core type issue for dense
Posted by GitBox <gi...@apache.org>.
Laurawly commented on pull request #7187:
URL: https://github.com/apache/tvm/pull/7187#issuecomment-753026936
> Do we allow `data.dtype == "float32"`?
> The problem comes from this downcast, which may cause accuracy problem.
> https://github.com/apache/tvm/blob/c02c9c528f91f9be3967b7d9ef9f1847f533590b/python/tvm/topi/cuda/dense_tensorcore.py#L72-L73
Good catch, just removed it.
----------------------------------------------------------------
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] [tvm] merrymercy commented on pull request #7187: [Fix] Tensor core type issue for dense
Posted by GitBox <gi...@apache.org>.
merrymercy commented on pull request #7187:
URL: https://github.com/apache/tvm/pull/7187#issuecomment-752964279
Do we allow `data.dtype == "float32"`?
The problem comes from this downcast, which may cause accuracy problem.
https://github.com/apache/tvm/blob/c02c9c528f91f9be3967b7d9ef9f1847f533590b/python/tvm/topi/cuda/dense_tensorcore.py#L72-L73
----------------------------------------------------------------
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] [tvm] junrushao1994 merged pull request #7187: [Fix] Tensor core type issue for dense
Posted by GitBox <gi...@apache.org>.
junrushao1994 merged pull request #7187:
URL: https://github.com/apache/tvm/pull/7187
----------------------------------------------------------------
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