Posts by Bikermatt

1) Message boards : News : CPU jobs on Linux (Message 48836) Posted 6 Feb 2018 by Bikermatt Post: * CPU threads are limited to 4 (you should still be able to crunch multiple WUs at once, please check) Let us know. Boinc is still assigning all of my 32 threads to one task even though it is only using 4.
2) Message boards : Number crunching : ADRIA_FAAH_WT batch (Message 46460) Posted 7 Feb 2017 by Bikermatt Post: I picked up one of these on my Win7 I7-6800K host with two GTX 980s. The task is 73% complete at 22 hours. I am only getting 67% GPU utilization but I am running 8 threads of evolution at home on the CPUs. With CPU tasks suspended GPU utilization is 79%.
3) Message boards : Graphics cards (GPUs) : GTX 10x0 Under utilised in GPU and RAM (Message 46022) Posted 31 Dec 2016 by Bikermatt Post: You could try running 2 tasks at once with a app_config.xml file in you projects directory. The latest GERARD_MO_ tasks were only giving me 54% GPU utilization on GTX980s in a win7 box with swan_sync enabled. Running two at a time I am getting 80% load. Same story with the GERARD_NONAGGRE tasks on my GTX670s. <app_config> <app> <name>acemdbeta</name> <gpu_versions> <gpu_usage>1</gpu_usage> <cpu_usage>1.00</cpu_usage> </gpu_versions> </app> <app> <name>acemdlong</name> <gpu_versions> <gpu_usage>.5</gpu_usage> <cpu_usage>1.00</cpu_usage> </gpu_versions> </app> <app> <name>acemdshort</name> <gpu_versions> <gpu_usage>.5</gpu_usage> <cpu_usage>1.00</cpu_usage> </gpu_versions> </app> </app_config>
4) Message boards : Number crunching : All Gerard WUs erroring (Message 42615) Posted 15 Jan 2016 by Bikermatt Post: One day more without Linux crunching and without status info...who cares? Someone didn't get their nap today. No, don't be a jerk. This has been a known problem with a known cause for a week now and no one has bothered to fix it. For many years there was a significant performance boost when crunching with Linux at this project. The developers actually recommended that you crunch with Linux. Many of us have dedicated Linux hosts to this project due to that fact. Now my Linux hosts are having to crunch mathematics crap and look for pulsars to keep my house warm. Could someone please fix this?
5) Message boards : News : Old Noelia WUs (Message 29330) Posted 6 Apr 2013 by Bikermatt Post: I just noticed I have two Noelia WU on my linux boxes for the first time in a few weeks. They were both stuck at 0% and the boxes had to be rebooted to get the gpu running again.
6) Message boards : News : Old Noelia WUs (Message 29070) Posted 8 Mar 2013 by Bikermatt Post: Been seeing multiple cases where new WU are not checkpointing (or showing progress in BOINC Manager). Have aborted a couple without improvement. Running on client v7.0.27 under linux x86. Yes I am still having problems in linux also. I thought it was just the NOELIAs but the new NATHANs are doing it also. The tasks will lock up or remain at 0% and the system has to be rebooted for the GPU to work again on any project. Might be the new app, my linux sytems had not needed a reboot in months before this.
7) Message boards : News : New project in long queue (Message 28942) Posted 3 Mar 2013 by Bikermatt Post: The Noelia workunits refuse to run on my 660ti linux system. They lock up or make no progress. I have finished one on two different linux systems with 670s without problems.
8) Message boards : News : New task on long queue from Nate, named RSP1120528 (Message 25510) Posted 5 Jun 2012 by Bikermatt Post: IMHO, this project is one that requires 24/7 crunching even on short tasks because in some cases, say getting a short-queue WU, crunching it a bit, shutting down the computer and then restarting calculation 24 or more hours later, you don't have the bonus. And that short-queue tasks are less-valued by the project evidenced by the fact that the project gives significantly less credits for crunching them invites, IMHO, volunteers to not crunch them, which means that those results will take longer to get Whether the project likes it or not, the "bonus" will cause uses to the chase credits that the project gives - as I see it. Yes, this is what I was trying to say earlier. These tasks were run on the same 570: 10,800.46 sec 8,100.00 points 32,500.30 sec 81,000.00 points 3x the run time = 10x the credit These tasks were run on the same gt240: 72,378.51 sec 8,100.00 points 291,447.05 sec 56,000.00 points 4x the run time = 7x the credit From a credit standpoint it isn't worth it to run the short tasks even on slow cards that do not get any bonus at all.
9) Message boards : News : New task on long queue from Nate, named RSP1120528 (Message 25450) Posted 2 Jun 2012 by Bikermatt Post: Long runs are for people with high end cards though. If you don't have a high end, and you don't want your card to crunch for days to complete one. That's exactly what the short queue is for. Unfortunately if you compare the credit granted per second of GPU time for the long versus short task you will notice the short tasks grant 2-3 times less credit for the amount of time crunched. Here is an example: http://www.gpugrid.net/results.php?hostid=98879 This is why people run the long tasks on slower cards. If the short tasks paid better more people would crunch them. If the credit granted is based on the work done during the task is this credit discrepancy due to short tasks not doing the same amount of work per second or is it due to how the bonus is calculated?
10) Message boards : News : New task on long queue, significantly longer than traditional tasks (Message 23894) Posted 11 Mar 2012 by Bikermatt Post: Man, I thought I was going crazy when I saw this task running for over 15 hours, before I read this post. I thought my card had downclocked or something, but windows wasn't reporting anything unusual. I just let it run and it finished fine, in about 20 hours on my overclocked GTX570. I thought about aborting one myself. Luckily when I saw one it only had a hour left so I let it finish. These are running at around 20 hours on a stock clocked GTX470 in Linux. Unfortunately with a 115 GB upload I cannot get them turned in fast enough. I have my cache set to 0.01 but they still download a few hours before they start so I run out of time.
11) Message boards : News : First part of server upgrade complete (Message 22698) Posted 15 Dec 2011 by Bikermatt Post: I'm not getting short or long tasks right now. Wed 14 Dec 2011 07:31:47 PM PST GPUGRID Message from server: No tasks sent Wed 14 Dec 2011 07:31:47 PM PST GPUGRID Message from server: No tasks are available for ACEMD2: GPU molecular dynamics Wed 14 Dec 2011 07:31:47 PM PST GPUGRID Message from server: No tasks are available for Long runs (8-12 hours on fastest card) server says over 3K short are available.... ACEMD2: GPU molecular dynamics 3,511 1,408 0.81 (0.04 - 10.22) 743 Edit: right as I posted one machine got a long task, another still will not get long or short tasks..
12) Message boards : Server and website : Task will not upload (Message 21710) Posted 20 Jul 2011 by Bikermatt Post: It worked. Thanks!
13) Message boards : Server and website : Task will not upload (Message 21705) Posted 20 Jul 2011 by Bikermatt Post: This task has been trying to upload since the most recent down time. I have restarted my system and others are working fine. Tue 19 Jul 2011 07:28:20 PM PDT GPUGRID [error] Error reported by file upload server: can't open file Tue 19 Jul 2011 07:28:20 PM PDT GPUGRID Temporarily failed upload of s0r119-TONI_SH2MS3-6-100-RND9601_1_4: transient upload error
14) Message boards : Server and website : Too many workunits (Message 20945) Posted 13 Apr 2011 by Bikermatt Post: Yes, I set this host's buffer to two days and the host picked up 5 tasks, for a total of 8 with only 2 GPUs. I aborted 3 of the tasks and set my buffer back to .01 days.
15) Message boards : Wish list : User reset for host error count (Message 20206) Posted 21 Jan 2011 by Bikermatt Post: Right now I have a host that can not get tasks because it was having errors on a lot of tasks. I think one of the video cards may be bad or I may be having a driver issue. Either way, I will not get tasks from GPU grid on this host for a while so it makes tracking down the problem very hard. I switched out a video card, but by the time the host starts getting tasks again I may not be around. If I didn’t fix the issue and the errors continue it could be a really long time before I get tasks again making fixing the problem even harder. I’m glad GPU grid shuts down my hosts because it saves bandwidth and alerts me that there is a problem. What would be nice though is if there were somewhere I could go to manually reset a host’s error count, it would allow troubleshooting and get hosts back online sooner once the user sees that there is a problem. Is there any way this is possible?
16) Message boards : Graphics cards (GPUs) : Linux and GTX295 (Message 19728) Posted 1 Dec 2010 by Bikermatt Post: From what I can see, all of your failures have been on device 1. You might what to take a closer look at that card. The GIANNI_DHFR tasks that are giving you errors are using a new algorithm and run a lot faster than than all of the other tasks on GPU grid. At the same time I have noticed one of my recently overclocked 470s now errors on the GIANNI_DHFR tasks quite often were it never did before. The card still runs all of the other tasks just fine So I'm thinking the GIANNI_DHFR tasks are probably more demanding also.
17) Message boards : Graphics cards (GPUs) : ACEMD2 6.12 cuda and 6.13 cuda31 for windows and linux (Message 19455) Posted 13 Nov 2010 by Bikermatt Post: The 6.13 app is running slower on my GTX 460 in Win7 compared to the 6.11 app. The GTX 460 is running good in Linux on the 6.13 app, so far I am seeing around 21ms per step for the IBUCH tasks. p2-IBUCH_15_PQpYEEIPI_101019-14-40-RND7762_2 # Time per step (avg over 1250000 steps): 33.258 ms # Approximate elapsed time for entire WU: 41573.039 s application version ACEMD2: GPU molecular dynamics v6.13 (cuda31) p25-IBUCH_3_PQpYEEIPI_101019-14-40-RND3646_1 # Time per step (avg over 275000 steps): 31.505 ms # Approximate elapsed time for entire WU: 39381.489 s application version ACEMD2: GPU molecular dynamics v6.11 (cuda31)
18) Message boards : Graphics cards (GPUs) : ACEMD2 6.12 cuda and 6.13 cuda31 for windows and linux (Message 19440) Posted 12 Nov 2010 by Bikermatt Post: GTX 470 driver 260.19.12 IBUCH__pYEEI tasks: 6.06 app ~ 11.2ms per step 6.13 app ~ 11.8ms per step The one input_-TONI task that I have ran was .7ms per step slower also. On a positive note, I do have a GTX 460 running in Linux now, I can't imagine it could perform worse than it did with the 6.11 app in Win7.
19) Message boards : Graphics cards (GPUs) : ACEMD2 6.12 cuda and 6.13 cuda31 for windows and linux (Message 19431) Posted 11 Nov 2010 by Bikermatt Post: In Linux app 6.12 driver 260.19.12 GT 240 at stock clocks: KASHIF_HIVPR tasks ~42ms per step IBUCH_*_pYEEI tasks: ~38ms per step My first 6.13 app just finished in Linux on a GTX 470 driver 260.19.12 also. It was an IBUCH and it ran about 800 sec longer than the 6.06 app, so not good for this one but we will see after a few different tasks have run.
20) Message boards : Graphics cards (GPUs) : ACEMD2 6.12 cuda and 6.13 cuda31 for windows and linux (Message 19426) Posted 11 Nov 2010 by Bikermatt Post: 6.12 task were running good on my GT240 now I have three in a row that have died. <core_client_version>6.10.56</core_client_version> <![CDATA[ <message> process exited with code 127 (0x7f, -129) </message> <stderr_txt> </stderr_txt> ]]> This is the same error that my GTX 470s are getting now, and they were getting the same error on the beta work units. Both systems are Ubuntu 10.4 with driver 260.19.12 The project has been reset on both systems, any suggestions?

Next 20