various things got tested over the last two months, it hasn't been working for that long :) last update is from a week ago. If you want to switch early I believe you can add the testing repos with…
Blender 3.3 already had oneAPI support but was linking differently if I remember well.. the bug sounds more like a runtime symbols conflict issue, with the graphics compiler maybe loading earlier…
"perhaps a race condition related to shader compilation" that definitely sounds like the issue. Unfortunately, driver 101.2115 is the latest for UHD 620, it's not getting regular updates…
great! by running this tool in parallel, can you then share how much GPU memory is left from both GPUs during the failure ?
fix landed in 3.6.2: fd83fdf4f3
It's possible something else is missing higher level: can you re-run the binary with ZES_ENABLE_SYSMAN=1 environment variable set ?
The graphics driver with the fix, 101.4644, is now available here: https://www.intel.com/content/www/us/en/download/726609/intel-arc-iris-xe-graphics-whql-windows.html
If you have a graphical environment, do you know if it's taking memory on GPU 2 specifically ? Can you monitor the graphics memory usage while trying to render on both with the 2022-12 sycl build…
Thanks, it's getting us closer to what went wrong. test kernel ran fine with similar command but next kernel failed
---> piextKernelSetArgPointer( : 0x7f2e08082280 :…
The behavior with 20230707 is maybe not that much related to the issue with 2022-12. the crash is in level zero runtime, not loader, and according to your backtrace, happens during the first…
that's.. interesting, so with 20230707, you can render on each gpu once, but not on both concurrently nor switching for a next render. can you get the backtrace for the segfault below ?
…
Now it's failing even with the simple test kernel, that will make debugging much easier.. if it's the same bug :). I need a bit more debug info to progress.
Please set these environment…
Weird, when I experienced this on rockylinux, ln -s /usr/lib64/libtinfo.so.6 /usr/lib64/libtinfo.so.5 worked.
Anyway, I've checked a bit further: https://packages.debian.org/sid/libtinfo5…
Here is a build with a newer version of SYCL (close to 2023-WW27): https://ph0b.com/uploads/blender-3.6.1-git20230728.embree3dpcpp20230707-x86_64.tar.gz can you let me know how it goes?
Good, so that's really the sycl compiler/runtime version that makes it break or not. I'll make some new builds with more recent versions to try, tomorrow or Monday.
you can symlink libtinfo.so.6 to libtinfo.so.5 for the sake of this test, that should work, but no need to bother with this, you actually have two GPUs and both can be used by Blender 3.5 so there…