| Index | Recent Threads | Unanswered Threads | Who's Active | Guidelines | Search |
 |
World Community Grid Forums
Category: Active Research
Forum: OpenPandemics - COVID-19 Project
Thread: Work unit availability |
| No member browsing this thread |
|
Thread Status: Active Total posts in this thread: 822
|
|
| Author |
|
|
Richard Haselgrove
Senior Cruncher United Kingdom Joined: Feb 19, 2021 Post Count: 360 Status: Offline Project Badges: 
|
only rtx2070 and gtx1050ti has errored so far That surprises me. There's a known problem with some of the slowest integrated iGPUs, but discrete GPUs like those should be OK. Are you sure that some other application, like Folding at Home, isn't competing for the resource? That's known to have been a problem, because sometimes their apps run at a higher process priority level than BOINC apps. |
||
|
|
Crystal Pellet
Veteran Cruncher Joined: May 21, 2008 Post Count: 1405 Status: Offline Project Badges: 
|
only rtx2070 and gtx1050ti has errored so far Do the tasks get enough CPU? The Nvidia cards need about 70-90% of 1 core for 1 GPU-task. My long runners on a GTX 970: Task -----------------------CPU / Elapsed OPNG_0043251_00027_1 0,62 / 0,63 OPNG_0043140_00116_0 0,67 / 0,68 OPNG_0043137_00054_0 0,75 / 0,76 OPNG_0042989_00017_0 0,63 / 0,81 OPNG_0042985_00110_0 0,48 / 0,59 OPNG_0042866_00055_0 0,79 / 0,97 OPNG_0042866_00048_0 0,52 / 0,70 OPNG_0042804_00087_1 0,46 / 0,63 OPNG_0042804_00078_1 0,53 / 0,78 OPNG_0042891_00023_0 0,45 / 0,61 OPNG_0042891_00021_0 0,47 / 0,63 OPNG_0042739_00083_0 0,50 / 0,66 |
||
|
|
Rickjb
Veteran Cruncher Australia Joined: Sep 17, 2006 Post Count: 666 Status: Offline Project Badges: 
|
@Crystal Pellet
How many simultaneous WUs are you running in your GTX970? I'm running 4 in mine. My last page (15 Wus) of Results Status for it shows they average about 0.6h on the current batch 0044xxx WUs, range 0.35h - 0.95h. Divide the 0.6h by the 4 WUs done at the same time = 0.15h = 8 min each. That's reasonable for a 970 I think, which sits at 9730 G3D Marks on the benchmarks list at https://www.videocardbenchmark.net/high_end_gpus.html . 4 simultaneous WUs may not be optimal in a GTX 970, but the variability in its diet of WCG WUs and the stop-start flows have not allowed me the optimise that number. Other members' experience would be interesting. In another machine I have a GTX1650 Super (9904 G3D Marks) doing 3 Wus per 0.4h = 8m ea, plus an AMD RX570 (about 7000 G3D Marks) doing 2 Wus per 1.0h = 30m ea (snore). I'm allocating a full CPU core to all types of GPU, including Intel, (<cpu_usage>1</cpu_usage> OR <avg_ncpus>1</avg_ncpus>), as that prevents the CPU parts of the GPU WUs having to share a CPU with another running task such as a CPU WU. The CPU speed probably affects the GPU total WU times. (The machine with the RX570 has only a 2600K at stock 3.4GHz, so I need to hasten that. The others have 3770Ks at 4.2GHz.) Yet another machine is running an RTX3060 (16700 G3D Marks) , doing 5 WUs per 0.35h = 4.2m ea. Hope this is of interest ... |
||
|
|
Crystal Pellet
Veteran Cruncher Joined: May 21, 2008 Post Count: 1405 Status: Offline Project Badges:
|
@Crystal Pellet I'm running 4 tasks concurrently at the max, but mostly I got only 3 tasks.How many simultaneous WUs are you running in your GTX970? During about the first 8-10 minutes of a task, the GPU is hardly used, only CPU-usage. |
||
|
|
erich56
Senior Cruncher Austria Joined: Feb 24, 2007 Post Count: 300 Status: Offline Project Badges: 
|
During about the first 8-10 minutes of a task, the GPU is hardly used, only CPU-usage. yes, I am observing this, too.In a way this is not really good for the GPU, since it produces the so-called "thermal cycle". Which means that the GPU's temperature changes from idle (around 30°C) to 60°C or even higher (depending on power setting, GPU clock setting and memory clock setting). In the GPUGRID forum, some time ago there was a very interesting posting from a specialist on this topic, with very thorough technical explanations. From what I remember in short, these constant temperature changes put quite a load and wear on the various components of the card, particularly on the solder joints. So a card which is exposed to the "thermal cycle" on a permanent basis will most probably not have the lifespan compared to a card which does not have to suffer the thermal cycle all the time. |
||
|
|
bluestang
Senior Cruncher USA Joined: Oct 1, 2010 Post Count: 274 Status: Offline Project Badges: 
|
These new longer WUs suck for points.
----------------------------------------And yes, I'm a points whore because that's my satisfaction for running projects along with helping the science. Longer should mean more points rewarded! |
||
|
|
Crystal Pellet
Veteran Cruncher Joined: May 21, 2008 Post Count: 1405 Status: Offline Project Badges:
|
WU's from batches 45070 and 45308 are running shorter than the previous long runners.
The Init.AutoGrid CPU-only-phase is about a third as from the longer ones. |
||
|
|
metalius
Cruncher Lithuania Joined: Aug 19, 2014 Post Count: 31 Status: Offline Project Badges: 
|
Longer should mean more points rewarded! Maybe, they went to Credit Screw. This explains all, if so. :D  |
||
|
|
bluestang
Senior Cruncher USA Joined: Oct 1, 2010 Post Count: 274 Status: Offline Project Badges:
|
Longer should mean more points rewarded! Maybe, they went to Credit Screw. This explains all, if so. :D LOL "Credit Screw" ... absolutely the correct way to pronounce that. |
||
|
|
kittyman
Advanced Cruncher Joined: May 14, 2020 Post Count: 140 Status: Offline Project Badges: 
|
The kitties are worried this morning. The supply of OPNG work seems to be drying up and their kibble bowl is emptying.
----------------------------------------And now the work server has been down for over half an hour. Meow?  |
||
|
|
|