u99127 commented on PR #12564: URL: https://github.com/apache/tvm/pull/12564#issuecomment-1225923446
> One change made in #5252 (which added support for Hexagon to the runtime) was increasing the byte alignment from 64 to 128. This can cause problems when interacting with `dlpack`. For example `tests/python/contrib/test_dlpack.py` has a high chance of failing when run locally due to torch returning tensors with 64 rather than 128 byte alignment. I'm not sure why it doesnt fail in CI, perhaps the consistency of the environment always returns an appropriately aligned tensor. > > Changing the default alignment allows interoperability with both torch and newer versions of numpy that support dlpack. I've slightly modified the torch test to run multiple times to make sure its behavior is consistent. > > @kparzysz-quic do you think there are any drawbacks to decreasing the bit alignment requirement? > > cc @areusch CC @ekalda, @lhutton1 - What's the impact of changing the alignment from 128 to 64 in the context of Ethos-U ? Is this likely to have a meaningful performance or correctness issue in this case ? Ramana -- 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]
