Folding Forum

Uhm... I find a bit strange that you have rusticl.icd and you lack mesa.icd. And rusticl shouldn't be enabled, unless a proper environment variable has been set. Never mind. Please: 1) verify the situation with: clinfo -l BTW: you can get much more info with clinfo alone. However try this: mv /etc/O...

Swooferfan wrote: ↑Thu Feb 26, 2026 12:50 pm So how do I do it?

Try: The file should be there.
--
Bye, Lem

My B580 has the latest firmware available from fwupdmgr Mine has: $ fwupdmgr get-devices ASUS System Product Name │ ├─Arc B580: │ │ Device ID: e32966e41f54b47823eef28bd8b4bd9e1018b923 │ │ Summary: Discrete Graphics Card │ │ Current version: 21.1174 │ │ [...] │ │ │ ├─Arc B580 (Data): │ │ Device ID: ...

Wow! I haven't changed anything, but here it is my first successful p18245 workunit on Intel, after 20 failed: 827,2,12. Only 2.7M PPDs though. However one swallow does not make a summer. We'll see. BTW: my b580 loves projects 16773/4/5, instead. With them It goes up to 3.7M PPDs, even if the base c...

The issue is with p18245 running on intel arc b580. In about 20 workunits, not a single one ended successfully. Linux kernel: 6.17.0-14-generic Driver: xe Mesa: 26.1.0~git2602112334.b651fd90d2d~q~mesaaco15 OpenCL: 26.01.36711.4 No problem with the nvidia card, by the way. And the Intel works well wi...

For me, fine wus have been (for instance):

2848,2,10
16186,2,9
...

The differences are in TPF (from 60 to 135 sec) and so in PPDs (from 9.5M to 2.8M) and in Watts (from 175-180 to 90). Interestingly enough my poor 5060ti performs on pair with a 5090 with the slow wus...
--
Bye, Lem

The same is happening here with:

18273,2,0
18203,2,2


TPF from 60 to 135 sec.

--
Bye, Lem

Lem, [...] Thank you for your polite answer, Bob. In my situation, I think that the only way to get a clue about the (small, I guess) improvements coming from properly set process affinities (on an AMD cpu, where all cores are equal - if they run at the same speed, which normally doesn't happen if ...

At best you have posted some kluges you think necessary Necessary? I've never ever written anything about necessity. to make up for a poor cooling solution in your system that leaves one CCD not as well called as the other and unable to run at as high a clock rate. LOL. Don't you know anything abou...

Where are the time per frame and PPD values from each test cases, taken from the same projects ? These are the only values we trust to measure FAH performance. BTW: you said "we". We? We who? Who are you? Is it something like a clan? Are you used to speak for others, and do they agree? &q...

muziqaz wrote: ↑Thu Feb 05, 2026 4:13 pm I would hint to you to Google what is "Case Study"

I would hint to you to google what quotation marks are.
--
Bye, Lem

Scientific simulation, if failed, wastes everyone's time. That is mission critical. First thing I care is returned science and stability. I don't want random users coming back to this forum with problems, and then we find out they installed someone's suggested script to "improve" things. ...

Few percent is margin of error. Not worth potentially messing up stability. No chance to mess up stability at all. It is always advised to leave things as they are and let Linux scheduler do it's job. Especially when you are doing mission critical workloads. BTW: in which sense f@h or BOINC on your...

And where are the results of all that? I don't know any exact way to measure neither performances nor efficiency with f@h, so I don't have any exact result to show. And we aren't speaking of huge gains, just fine tuning. Looking at my PPDs, I smell it's helped a bit though: I mean a few percent. I'...

I happen to fold on a system with and AMD 7950x and two discrete GPUs. My monitor is attached to my iGPU. My OS is Ubuntu Mate 25.10. Ryzen 7950x has two CCDs, that is two groups of 8 cores (16 virtual cores) each. Usually one CCD can run faster than the other: in my system I set CCD0 to run at 5,3G...