Posted 11 days ago by
rebirther
all cuda120 tasks error out on my V100s. in the same way that crash's P100s were erroring.
did you omit support for CC 7.0 (titan V and V100 at this CC level)? as i pointed out before you need to explicitly add support for every CC level individually.
We can try to use cuda100 WUs with an app_config. Thats the oldest app which we are running.
<app_config>
<app_version>
<app_name>TF</app_name>
<plan_class>cuda100</plan_class>
<min_gpu_ram_mb>384</min_gpu_ram_mb>
<gpu_ram_used_mb>384</gpu_ram_used_mb>
<gpu_peak_flops_scale>0.22</gpu_peak_flops_scale>
<cpu_frac>0.01</cpu_frac>
</app_version>
</app_config>
Posted 11 days ago by
rebirther
If you are a new member create an account over the website.
Posted 13 days ago by
rebirther
S816
- n=500-600k
- runtime 5h07min-7h43min (AVX@3.8Ghz)
- 500-550k = 1800 credits
- 550-600k = 2300 credits
- Sierpinski / Riesel Base - long3
- deadline 4 days
- TOP5000 primes
Posted 13 days ago by
rebirther
R842
- n=100-300k
- runtime 10min21-1h23min (AVX@3.8Ghz)
- 100-150k = 80 credits
- 150-200k = 150 credits
- 200-250k = 240 credits
- 250-300k = 300 credits
- Riesel Base
- deadline 3 days
Posted 14 days ago by
rebirther
R275
- n=800k-1M
- runtime 5h57min-9h (AVX@3.8Ghz)
- 800-850k = 1950 credits
- 850-900k = 2100 credits
- 900-950k = 2400 credits
- 950k-1M = 2700 credits
- Sierpinski / Riesel Base - long2
- deadline 5 days
- TOP5000 primes
Posted 14 days ago by
rebirther
I have noticed this yeasterday in the WU generation.
414 WUs of S864 for long are affected and need to be reuploaded with an _a in wu name.
Posted 14 days ago by
rebirther
R867
- n=500-600k
- runtime 3h37min-5h11min (AVX@3.8Ghz)
- 500-550k = 1000 credits
- 550-600k = 1250 credits
- Sierpinski / Riesel Base - average
- deadline 3 days
- TOP5000 primes
Posted 14 days ago by
rebirther
S864
- n=500-600k
- runtime 4h40min-7h23min (AVX@3.8Ghz)
- 500-550k = 1800 credits
- 550-600k = 2200 credits
- Sierpinski / Riesel Base - long
- deadline 4 days
- TOP5000 primes
Posted 14 days ago by
rebirther
S866
- n=500-600k
- runtime 3h49min-6h (AVX@3.8Ghz)
- 500-550k = 1500 credits
- 550-600k = 1800 credits
- Sierpinski / Riesel Base - long
- deadline 4 days
- TOP5000 primes
Posted 14 days ago by
rebirther
S784
- n=400-600k
- runtime 1h52min-4h26min (AVX@3.8Ghz)
- 400-450k = 600 credits
- 450-500k = 700 credits
- 500-550k = 850 credits
- 550-600k = 1000 credits
- Sierpinski / Riesel Base - average2
- deadline 3 days
- TOP5000 primes
Posted 14 days ago by
rebirther
R91 tested to n=500k (400-500k)
3 primes found, 26 remain
43814*91^433332-1 found by [AF] Kalianthys (TOP5000)
223952*91^437353-1 found by Science United (TOP5000)
81030*91^440109-1 found by Aionel (TOP5000)
Posted 14 days ago by
rebirther
R75 tested to n=600k (500-600k)
2 primes found, 6 remain
968*75^522276-1 found by Science United (TOP5000)
856*75^530221-1 found by Cluster Physik (TOP5000)
Posted 15 days ago by
rebirther
R60
- n=400-600k
- runtime 54min-2h27min (AVX@3.8Ghz)
- 400-450k = 300 credits
- 450-500k = 450 credits
- 500-550k = 500 credits
- 550-600k = 550 credits
- Sierpinski / Riesel Base - average3
- deadline 3 days
- TOP5000 primes
Posted 15 days ago by
rebirther
The next batch of 50k tests is uploading.
The runtime is now ~2h40min on a RX5500 XT and decreasing on higher ranges.
Posted 17 days ago by
rebirther
S67 tested to n=500k (400-500k)
1 prime found, 28 remain
15592*67^405715+1 found by Science United (TOP5000)
Posted 19 days ago by
rebirther
Your GPU is not supported / too old or plan_class doesnt match driver / cuda version
Correct.
The GPU is EXCLUDED from use in this project and in BOINC itself. So why does only this project keep sending the redundant notice?
Example: PrimeGrid & Einstein do not give any such notice yet they support GPU work and apparently see that the GPU is excluded from use.
Shouldn't this project see that the GPU is excluded from use regardless of what hardware is installed like any of the other projects?
What BOINC version is running, nvidia is still activated in prefs?
Posted 19 days ago by
rebirther
rebirther,
Why is this is the ONLY project that keeps sending my PC the notice below?
I DON'T have GPU task enabled nor have GPU processing enabled for the corresponding PC's venue "home". The (very old) GPU in not used for BOINC.
SRBase: Notice from server
NVIDIA GPU: Upgrade to the latest driver to process tasks using your computer's GPU
Your GPU is not supported / too old or plan_class doesnt match driver / cuda version
Posted 19 days ago by
rebirther
All TF work for 74-75bit were sent out and loading on the server.
Does this mean we are close to finishing the range?
There are some GIMPs users outside BOINC but yes we are close.
Posted 19 days ago by
rebirther
R647 tested to n=300k (100-300k)
2 primes found 23 remain
314*647^109740-1 found by Science United
624*647^134475-1 found by Science United
Posted 19 days ago by
rebirther
S806 tested to n=600k (400-600k)
nothing found, 1 remain