Jan Stephan

Results 232 comments of Jan Stephan

Ah, I see. So lower numbers are worse. That is indeed a change for the worse then. How did you ensure that the requirements handling is correct in your third...

Hm, maybe open a bug report for Intel? I'm sure they would be interested to hear about this :-)

While the work in #1993 is certainly useful, isn't this failing for the kernel itself? So the thing that encapsulates `operator()(TAcc acc, ...)` isn't trivially copyable.

NVIDIA were able to reproduce the issue and the compiler team is looking into it.

Yes, it is NVIDIA bug 4160691.

Nope, I haven't heard from NVIDIA since my last update.

My ticket status on NVIDIA's bug tracker was changed from "Open - pending review" to "Open - Fix being tested". No further message was added.

NVIDIA closed the ticket. The fix will be available with CUDA 12.4.

Nope, they really wrote 12.4.