1)
Message boards :
News :
Separation Project Coming To An End
(Message 75547)
Posted 14 Jun 2023 by Toby Broom Post: Not really: "Consumer GPUs are really bad at double precision calculations (so manufacturers can sell more expensive enterprise units to researchers). Luckily, molecular dynamics really only requires single precision to be useful. Folding@Home uses single precision." https://fahbench.github.io/details.html |
2)
Message boards :
Number crunching :
Finally getting new tasks only seconds after running out. May not be worth the hassle.
(Message 71200)
Posted 1 Oct 2021 by Toby Broom Post: I'm happy to not work around the features in a major way, I can get a far bit of work with my powershell script. Enter-BoincSession $netmsg = Get-BoincMessage | Where-Object {$_.Body -like '*network*'} $boinctime = [INT] ((Get-Date) - $netmsg[($netmsg.Length -1)].Timestamp.LocalDateTime).TotalMinutes $mwtasks = (Get-BoincTask | Where-Object {$_.ProjectUrl -like '*milkyway*'}).Count If ($boinctime -ge 10){ Set-BoincMode -NetworkMode Always Start-Sleep -s 92 Get-BoincProject | Where-Object {$_.ProjectName -like '*milkyway*'} | Update-BoincProject } If ($mwtasks -eq 0){ Set-BoincMode -NetworkMode Always Start-Sleep -s 92 Get-BoincProject | Where-Object {$_.ProjectName -like '*milkyway*'} | Update-BoincProject } If (($mwtasks -gt 0) -and ($boinctime -eq 2)){Set-BoincMode -NetworkMode Never} $boinctime $mwtasks (Get-BoincStatus).NetworkMode You need the PSBoinc from https://www.powershellgallery.com/packages/PSBoinc/1.1 |
3)
Message boards :
Number crunching :
Finally getting new tasks only seconds after running out. May not be worth the hassle.
(Message 71192)
Posted 30 Sep 2021 by Toby Broom Post: For me this time out script does not work as I can make a WU in less than 92 sec so each time it runs it reports the completed tasks and then does not get anymore. Also, if I disable the network for 15 min, then report it the same sort of deal. It seems like its only possible to get task in batches of 300 with the current setup of the project |
4)
Message boards :
Number crunching :
Run Multiple WU's on Your GPU
(Message 71182)
Posted 29 Sep 2021 by Toby Broom Post: I assume the 3090 just can't do enough work to get to full power, in the Ampere SMs only half of the SM can do FP64 so, I can imagine the best case here is 3090 would be about half of max power which is about what you see I assume if you have 400 W BIOS, I have founders so I have 350 W and see about 180 W, with just one WU at a time even on my Titan V, its not full bore with 7 WUs at once |
5)
Message boards :
Number crunching :
Run Multiple WU's on Your GPU
(Message 71167)
Posted 28 Sep 2021 by Toby Broom Post: Yes, your correct. Based on the other discussions I try to write a script that will work around the limit by pausing the networking |
6)
Message boards :
Number crunching :
Run Multiple WU's on Your GPU
(Message 71164)
Posted 28 Sep 2021 by Toby Broom Post: However, if you have a work buffer should BOINC not cache a larger amount of WU's so the 10 min becomes less of an issue. I also assume that it would be better for the project to create larger work units? or at least an option for larger ones? |
7)
Message boards :
News :
New Poll Regarding GPU Application of N-Body
(Message 71023)
Posted 24 Jul 2021 by Toby Broom Post: Thanks for the comment. If the split of n body FP64 calculations is 1/8 and a consumer GPU is 1/64 and a high FP64 GPU is 1/2 then you would expect some speed up. Anyway I would vote for whatever the project team thinks gives best return on investment. |
8)
Message boards :
News :
New Poll Regarding GPU Application of N-Body
(Message 71016)
Posted 23 Jul 2021 by Toby Broom Post: If I have a high FP64 GPU then I assume it would be similar to the current WU, in terms of speed up? |
9)
Message boards :
Number crunching :
Finally getting new tasks only seconds after running out. May not be worth the hassle.
(Message 69645)
Posted 4 Apr 2020 by Toby Broom Post: Does the coproc_info work, it's not clear from the discussion? What edit is required? |
10)
Message boards :
Number crunching :
AMD FirePro S9150
(Message 67736)
Posted 28 Aug 2018 by Toby Broom Post: I just did, will post back if there is some news. |
11)
Message boards :
Number crunching :
AMD FirePro S9150
(Message 67727)
Posted 26 Aug 2018 by Toby Broom Post: Couldn't the project team fix this in the source code? Seems like you did all the work for them |
12)
Message boards :
Number crunching :
New Benchmark Thread - times wanted for any hardware, CPU or GPU, old or new!
(Message 67699)
Posted 6 Aug 2018 by Toby Broom Post: I have W8100 and I ran 2 WU at the same time and saw 100% usage with default app. Seems like others are often running many more in concurent? All WU's were either 227.23 or 227.25 credits Run Time CPU Time (sec) (sec) 69.12 17.61 77.13 16.77 73.16 17.39 77.13 17.34 77.15 16.91 66.1 16.56 65.15 16.34 77.16 15.14 69.15 14.89 78.15 15.02 83.16 15.91 71.15 17.47 78.15 19.14 79.15 16.66 71.13 15.88 69.15 17.09 79.16 17.95 76.15 17.08 67.11 17.5 73.16 18.17 ------------- Average 74 17 SD 5.1 1.1 74 / 2 = about 37 seconds for a single work unit App only reports 500GFLOP which is well below the theory 2000GFLOP |
13)
Message boards :
Number crunching :
GPU Requirements
(Message 60515)
Posted 5 Dec 2013 by Toby Broom Post: The 8xxx were rebrands of 7xxx for OEM only. |
14)
Message boards :
Number crunching :
GPU Requirements
(Message 60454)
Posted 25 Nov 2013 by Toby Broom Post: I run 5-6 WU's at once on my titan: <app_config> <app> <name>milkyway</name> <gpu_versions> <gpu_usage>0.15</gpu_usage> <cpu_usage>0.664</cpu_usage> </gpu_versions> </app> <app> <name>milkyway_separation__modified_fit</name> <gpu_versions> <gpu_usage>0.2</gpu_usage> <cpu_usage>0.664</cpu_usage> </gpu_versions> </app> </app_config> |
15)
Message boards :
News :
Users Auto-Aborting Work Units
(Message 60453)
Posted 25 Nov 2013 by Toby Broom Post: Thanks for tips on the titan config files. I got sick of my ATI card crashing my computer all the time! |
16)
Message boards :
Number crunching :
Catalyst is not OK
(Message 60429)
Posted 19 Nov 2013 by Toby Broom Post: Yeah, it's on my server, I just installed the catalyst drivers for Windows 7 and I'm good to go. It's plan Windows Sever 2008 R2, not WHS though. |
17)
Message boards :
Number crunching :
Catalyst is not OK
(Message 60420)
Posted 17 Nov 2013 by Toby Broom Post: My 7790 does MW, maybe the lower ones don't? I go on what Wikipedia says: http://en.wikipedia.org/wiki/Comparison_of_AMD_graphics_processing_units#Southern_Islands_.28HD_7xxx.29_Series It's kinda a lottery with drivers though, it generally takes me a lot of effort to find something that works. I'm using 13.5B2 these are the newest ones that I have tried that don't blue screen all the time. |
18)
Message boards :
Number crunching :
AMD Radeon R9 290X
(Message 60229)
Posted 27 Oct 2013 by Toby Broom Post: I think it's supposed to have both of these lines: CAL: ATI GPU 0: AMD Radeon HD 7870/7950/7970 series (Tahiti) OpenCL: AMD/ATI GPU 0: AMD Radeon HD 7870/7950/7970 series (Tahiti) I found when trying to find a stable config it wouldn't work unless there is both, sometimes I would get both sometimes not. I guess with the 290 you might be stuck as there isn't many driver options. e.g. I found 13.1 a fairly stable driver but my 7790 isn't supported in that driver. |
19)
Message boards :
Number crunching :
Bugcheck in Windows
(Message 59346)
Posted 14 Jul 2013 by Toby Broom Post: After a ton of messing around seems like the 13.4 drivers just aren't good for me. 13.1 & 13.6B2 are solid on Windows Server. Testing 13.1 on Win8, did briefly see some corruption? |
20)
Message boards :
Number crunching :
Bugcheck in Windows
(Message 59214)
Posted 3 Jul 2013 by Toby Broom Post: I see my computer will bug check after roughly 8hrs of running, I cranked the fan on my GPU (7870 XT) up to 90% an I don't see the temperature exceeding 70C. I'm seeing a little graphics corruption in windows too. Any suggestions? I ran the same GPU without any issues on another computer for a good while. The new PC is Windows 8 & X79 vs the old one was Windows Server 2008R2 with 5520 chipset. So it could be an AMD win8 driver or an X79 issue? |
©2023 Astroinformatics Group