Siddhartha Menon

> For the most recent [CI failure](https://github.com/uxlfoundation/oneDNN/actions/runs/17325118469/job/49187346077?pr=2849), that failed test case passed on my local develop machine I believe the one you posted was the last successful test. Since you...

@dzarukin Would appreciate a review from @uxlfoundation/onednn-arch, thanks!

I did some poking around and I am having some difficulty reproducing failures seen in `graph_fusions` from within the standalone drivers. I don't know if this is because of `NaN/Infs`...

I tried modifying this line in the `benchdnn --matmul` buffer fill function: https://github.com/uxlfoundation/oneDNN/blob/aed0c1a497b09f8b97b7932bc7afa8e2c13c3953/tests/benchdnn/matmul/matmul.cpp#L476 I changed this to: ```cpp float val = 65500.f; ``` to try and trigger an overflow. But...

@dzarukin Thank you for the insights. I think you're right with the long chains causing this issue. Though the underlying ACL matmul kernel is accumulating to f32 here. If we...

Thanks @dzarukin, I'll look into it. There's several other classes of bugs hiding behind the `graph_fusions` failure. I'll do some more triaging and then share some details here.

I don't think there are any major comments on our end. Out of interest, here is a link to some similar work that has gone into the TOSA specification. Any...

> -DDNNL_ENABLE_CONCURRENT_EXEC=ON Is this needed to trigger your bug?