Ioannis Assiouras

> I'm pretty sure this indicates that the card supports pcie atomics right? So in this case I don't think that can be the issue. Can you please try the...

> dmesg: read kernel buffer failed: Operation not permitted Can you try to run dmesg with sudo. Also, can you post the output of this: `grep flags /sys/class/kfd/kfd/topology/nodes/*/io_links/0/properties`

@JackAKirk there is no indication of missing pcie atomics from the logs as far as I can see. 1) Can you try to call printf from the kernel. Does that...

@JackAKirk printf is part of unit tests https://github.com/ROCm/hip-tests/tree/develop/catch/unit/printf and these are quite well tested on gfx1030. Although I do not know the frequency each particular card is being used and...

Hi @JackAKirk so to confirm, If you replace assert() with printf() in the vectoradd test does it go through or it still fail with a bus error.

Hi @JackAKirk but at the same time the printf unit tests pass, which is interesting. I would recommend we start with the printf unit test as a reference. The code...

Hi @JackAKirk the example with the assert works for me. I think that with the current implementation both the assert and printf require a synchronization on the host side before...

Hi @JackAKirk I managed to reproduce the hanging issue with assert on a w6800 machine on windows. I will create an internal ticket to investigate the issue and will come...

This is addressed by internal PR https://github.com/AMD-ROCm-Internal/clr/pull/597. Since it is for the internal repo you may not be able to access the link. I will update the status here once...

@BenWibking The issue has been resolved by this commit [Defer allocation of managed variable](https://github.com/ROCm/clr/commit/3f6f9d608122a21e780db184a179b55079df9bd9) that is now merged into the staging branch and will be included in a future release....