André Rösti
André Rösti
Let me rebase this on refactor-matmul. Then, once refactor-matmul is merged, we can merge this if you are cool with it
This also contains the fixes for the verification code on the host (`n_rows` vs `n_cols` confusion). Ready for review! @jgmelber
I would say yes. Per my understanding of this PR, my PR #527 contains a superset of this.On Aug 24, 2023, at 3:55 PM, Stephen Neuendorffer ***@***.***> wrote: @andrej is...
If we decide to merge in #527 this issue could probably be closed. Not sure what people's thoughts on 527 are though.
Joe pointed me to this, I hope it's cool that I left three quick comments. Looks good
Still a work in progress. I have yet to try @singagan's suggestions on how to get performance up.
Just updated my comment above with the command to compile the breaking example after changes in #1056.
I ran in to this again and dug a little deeper to get a minimal working example. See below. This should make it easier to debug instead of using the...
After some more testing, this appears to affect not just loops with one iteration. For example, giving the middle loop nine iterations and the inner one four gives the same...
Thank you Stephen. I did not update Vitis, I just rebuilt this repository. Which is weird because I feel like the bug would more likely be in libXAIE or the...