And another.

https://sech.me/boinc/Amicable/workunit.php?wuid=12033885
https://sech.me/boinc/Amicable/workunit.php?wuid=12033891

So shouldn't these colossal things yield more than the usual amount of credit?

Ah well, both ended in a compute error after half a day...

I randomly sampled the tasks that I had completed over the past 3 days with varying run time and task size. Though not perfect, it seems to indicate that there is a good correlation between task size and run time. All tasks were completed on the same GPU. BTW, I"m running two tasks per GPU and the GPU run time shown in the graph is not normalized to one task. There is one outlier but if we ignore this single point, the regression-squared or R-squared increased from 52% to 95%.

Wondering if there is any chance to allocate higher credit points for larger task size? Some folks don't care about credits but just my one cent to keep things within reasonable perspective. Perhaps allocating task size of 10¹¹, 10¹² and 10¹³ with different fixed credit buckets?

https://postimg.cc/gx5J8Rg1

Yes, I'll adjust credit for these tasks.

Thank you sir!

I'm only getting compute errors for the longer tasks. Is kernel size to blame? Quite a bit of crunching time wasted.

exceeded elapsed time limit 28237.96 (10000000.00G/341.91G)

Hi, i see ,amicable pairs discovering are bit stall, or go slowly now.. We get to another phase" like before?

Hi, i see ,amicable pairs discovering are bit stall, or go slowly now.. We get to another phase" like before?

Wow , now is it going good...))) I like also this project app on memory using , becouse many boinc projest dont use memory and leave memory on computers just resting..in not use.. or is not optimised to use memory on computers ,just like another factor/buffer to improve computing on tasks. . not like "only cpu cores" and end..) we need more boinc projects where willl ram size another great key factor to do tasks .

I'm only getting compute errors for the longer tasks. Is kernel size to blame? Quite a bit of crunching time wasted.

exceeded elapsed time limit 28237.96 (10000000.00G/341.91G)

This is still happening. Every once in a while I get one of the much longer tasks and by now I simply abort them whenever I see them, since a) they always end in an error for me and b) credit doesn't seem to have been adjusted anyway (but feel free to prove me wrong). Any official comment on those?

So, this thread hasn't been posted to in a while. Wondering if anyone has played with optimal kernel setting for RTX40XX (60Ti, 70)?

---

So, this thread hasn't been posted to in a while. Wondering if anyone has played with optimal kernel setting for RTX40XX (60Ti, 70)?

You're having fun times on the 4070S,
how to manually change kernel from 23 to e.g. 24/25 for 4090 during tests
In which files would settings changes for kernel be saved?

---

If you're not getting full GPU utilization on RTX 4090, it's better to run several WUs per GPU in parallel than to increase the kernel size above 23.

@Steve Dodd

Can you tell us how you get such great times for the 4070S?

4090 TDP 450W without limit reaches ~63 seconds for 1 task,
Your 4070S looks much better.
I wanted to manually increase the karnel value from 23 to ~25/26, but in the files it is mentioned in several places, after editing the karnel value returns to 23, counting several tasks at the same time 4, it did not bring anything positive, the gain was a few seconds. For 4 tasks about ~300W from 200 to 300, it varies.
Let me know what can be improved

---

How can I do some manual testing? I've got three NVIDIA GPUs: RTX 4070TI, RTX 4060 & GTX 1660 Ti. They're all driven by a pair of Xeon E5-2687W v4 with a total of 256 GB RAM (https://www.passmark.com/baselines/V11/display.php?id=507992057675).

I think that I could possibly take advantage of multiple jobs, at least on the 4070 Ti maybe the 4060.