Message boards :
Number crunching :
Multi core greater than 80 core
Message board moderation
Previous · 1 · 2 · 3 · 4 · 5 · 6 · 7 . . . 8 · Next
Author | Message |
---|---|
BilBg Send message Joined: 27 May 07 Posts: 3720 Credit: 9,385,827 RAC: 0 |
By Rerun I mean Re-Install, i.e.: Exit BOINC Run Lunatics_Win64v0.37_(SSE3+)_AP505r409_AKv8bx64_Cudax32f.exe Choose SSSE3 Â - ALF - "Find out what you don't do well ..... then don't do it!" :) Â |
Claggy Send message Joined: 5 Jul 99 Posts: 4654 Credit: 47,537,079 RAC: 4 |
and choose Astropulse r409 again too, Claggy |
Pepo Send message Joined: 5 Aug 99 Posts: 308 Credit: 418,019 RAC: 0 |
The BOINC client has no limit on the # of CPUs. David Anderson has reported on the mailing lists, that he has checked in a change [trac]changeset:23215[/trac], which is yet to be tested on such beast. Peter |
Bry B Send message Joined: 3 Apr 99 Posts: 53 Credit: 832,165 RAC: 0 |
sorry I am a little slow today, not feeling so well :( It took me a minute to remember what Lunatics was.. LOL Got it now. |
Bry B Send message Joined: 3 Apr 99 Posts: 53 Credit: 832,165 RAC: 0 |
so I added 3 NVIDIA GPU's to the box and loaded current drivers in the X64 160LP box. For some reason BOINC still doesnt see that I have useable GPU's. Is there a setting in the CC_config.html that will force this? Thanks in advance |
Bry B Send message Joined: 3 Apr 99 Posts: 53 Credit: 832,165 RAC: 0 |
so I added 3 NVIDIA GPU's to the box and loaded current drivers in the X64 160LP box. I added this <use_all_gpus>1</use_all_gpus> but I get no options in activity thats shows they are working like some of my workstations. |
BilBg Send message Joined: 27 May 07 Posts: 3720 Credit: 9,385,827 RAC: 0 |
What kind of "3 NVIDIA GPU's" (are they CUDA capable?) Post the first ~20 lines of BOINC messages (after BOINC restart) And of course do this again: Re-Install Lunatics: Exit BOINC Run Lunatics_Win64v0.37_(SSE3+)_AP505r409_AKv8bx64_Cudax32f.exe Choose SSSE3 Choose CUDA ! Â - ALF - "Find out what you don't do well ..... then don't do it!" :) Â |
Bry B Send message Joined: 3 Apr 99 Posts: 53 Credit: 832,165 RAC: 0 |
NVIDIA FX 1800 X2 Nvidia FX 3800 I did tick the CUDA setting, perhaps that was a mistake? |
Bry B Send message Joined: 3 Apr 99 Posts: 53 Credit: 832,165 RAC: 0 |
according to http://en.wikipedia.org/wiki/Nvidia_Quadro they all have CUDA CORES. FX1800= 64 FX3800=192 |
Bry B Send message Joined: 3 Apr 99 Posts: 53 Credit: 832,165 RAC: 0 |
3/10/2011 6:13:56 PM Starting BOINC client version 6.10.58 for windows_x86_64 3/10/2011 6:13:56 PM Config: use at most 160 CPUs 3/10/2011 6:13:56 PM Config: use all coprocessors 3/10/2011 6:13:56 PM log flags: file_xfer, sched_ops, task, sched_op_debug 3/10/2011 6:13:56 PM Libraries: libcurl/7.19.7 OpenSSL/0.9.8l zlib/1.2.3 3/10/2011 6:13:56 PM Data directory: C:\ProgramData\BOINC 3/10/2011 6:13:56 PM Running under account Administrator 3/10/2011 6:13:56 PM Processor: 60 GenuineIntel Intel(R) Xeon(R) CPU E7- 2870 @ 2.40GHz [Family 6 Model 47 Stepping 2] 3/10/2011 6:13:56 PM Using 160 CPUs 3/10/2011 6:13:56 PM Processor: 256.00 KB cache 3/10/2011 6:13:56 PM Processor features: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss htt tm pni ssse3 cx16 sse4_1 sse4_2 syscall nx lm vmx smx tm2 dca popcnt aes pbe 3/10/2011 6:13:56 PM OS: Microsoft Windows Server 2008 "R2": Enterprise x64 Edition, Service Pack 1, (06.01.7601.00) 3/10/2011 6:13:56 PM Memory: 95.99 GB physical, 191.98 GB virtual 3/10/2011 6:13:56 PM Disk: 136.60 GB total, 29.48 GB free 3/10/2011 6:13:56 PM Local time is UTC -8 hours 3/10/2011 6:13:56 PM No usable GPUs found 3/10/2011 6:13:56 PM SETI@home Found app_info.xml; using anonymous platform 3/10/2011 6:13:56 PM SETI@home URL http://setiathome.berkeley.edu/; Computer ID 5847405; resource share 100 3/10/2011 6:13:56 PM SETI@home General prefs: from SETI@home (last modified 09-Mar-2011 13:09:46) 3/10/2011 6:13:56 PM SETI@home Computer location: work 3/10/2011 6:13:56 PM General prefs: using separate prefs for work 3/10/2011 6:13:56 PM Reading preferences override file 3/10/2011 6:13:56 PM Preferences: 3/10/2011 6:13:56 PM max memory usage when active: 49146.76MB 3/10/2011 6:13:56 PM max memory usage when idle: 88464.17MB 3/10/2011 6:13:56 PM max disk usage: 10.00GB 3/10/2011 6:13:56 PM max CPUs used: 160 3/10/2011 6:13:56 PM (to change preferences, visit the web site of an attached project, or select Preferences in the Manager) 3/10/2011 6:13:56 PM Using proxy info from GUI 3/10/2011 6:13:56 PM Using HTTP proxy itgproxy:80 3/10/2011 6:13:56 PM SETI@home Started download of 12oc10aa.27947.4975.8.10.172 3/10/2011 6:13:56 PM SETI@home Started download of 12oc10aa.27947.4975.8.10.167 3/10/2011 6:13:56 PM GPUs have become unusable; disabling tasks 3/10/2011 6:13:58 PM SETI@home Finished download of 12oc10aa.27947.4975.8.10.172 3/10/2011 6:13:58 PM SETI@home Started download of 12oc10aa.27947.4975.8.10.178 3/10/2011 6:14:01 PM SETI@home Finished download of 12oc10aa.27947.4975.8.10.167 3/10/2011 6:14:01 PM SETI@home Started download of 12oc10aa.27947.4975.8.10.173 3/10/2011 6:14:04 PM SETI@home Finished download of 12oc10aa.27947.4975.8.10.178 3/10/2011 6:14:04 PM SETI@home Started download of 12oc10aa.27947.4975.8.10.179 3/10/2011 6:14:07 PM SETI@home Finished download of 12oc10aa.27947.4975.8.10.179 3/10/2011 6:14:07 PM SETI@home Started download of 12oc10aa.27947.4975.8.10.148 3/10/2011 6:14:08 PM SETI@home Finished download of 12oc10aa.27947.4975.8.10.173 3/10/2011 6:14:08 PM SETI@home Started download of 12oc10aa.27947.4975.8.10.192 3/10/2011 6:14:11 PM Re-reading cc_config.xml 3/10/2011 6:14:11 PM Re-read config file 3/10/2011 6:14:11 PM Config: use at most 160 CPUs 3/10/2011 6:14:11 PM Config: use all coprocessors 3/10/2011 6:14:11 PM log flags: file_xfer, sched_ops, task, sched_op_debug 3/10/2011 6:14:13 PM SETI@home Finished download of 12oc10aa.27947.4975.8.10.148 3/10/2011 6:14:13 PM SETI@home Finished download of 12oc10aa.27947.4975.8.10.192 3/10/2011 6:14:13 PM SETI@home Started download of 12oc10aa.27947.4975.8.10.198 3/10/2011 6:14:13 PM SETI@home Started download of 12oc10aa.27947.4975.8.10.204 3/10/2011 6:14:18 PM SETI@home Finished download of 12oc10aa.27947.4975.8.10.204 3/10/2011 6:14:18 PM SETI@home Started download of 12oc10aa.27947.4975.8.10.210 3/10/2011 6:14:19 PM SETI@home Finished download of 12oc10aa.27947.4975.8.10.198 3/10/2011 6:14:19 PM SETI@home Started download of 12oc10aa.27947.4975.8.10.216 3/10/2011 6:14:21 PM SETI@home Finished download of 12oc10aa.27947.4975.8.10.210 3/10/2011 6:14:21 PM SETI@home Started download of 12oc10aa.27947.4975.8.10.170 3/10/2011 6:14:22 PM SETI@home Finished download of 12oc10aa.27947.4975.8.10.216 3/10/2011 6:14:23 PM SETI@home Finished download of 12oc10aa.27947.4975.8.10.170 |
Bry B Send message Joined: 3 Apr 99 Posts: 53 Credit: 832,165 RAC: 0 |
Using NVIDIA driver 8.17.12.6717 2/17/2011 |
arkayn Send message Joined: 14 May 99 Posts: 4438 Credit: 55,006,323 RAC: 0 |
|
Bry B Send message Joined: 3 Apr 99 Posts: 53 Credit: 832,165 RAC: 0 |
Did you install as a service on the machine? Nope. installed Lunatics_Win64v0.37_(SSE3+)_AP505r409_AKv8bx64_Cuda normally |
HAL9000 Send message Joined: 11 Sep 99 Posts: 6534 Credit: 196,805,888 RAC: 57 |
To do the GPU processing you also need to have the right driver installed to work with the cuda app. I think the unified installer lists the version you need to have, or it is listed in their download area. GPU processing isn't as cut & dry as we would all like. For a while you had to have a monitor connected to each card or use a dummy plug to get BOINC to use the GPUs. I don't know if that is still true with the newest version. SETI@home classic workunits: 93,865 CPU time: 863,447 hours Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[ |
HAL9000 Send message Joined: 11 Sep 99 Posts: 6534 Credit: 196,805,888 RAC: 57 |
Did you install as a service on the machine? arkayn was asking if BOINC was installed as a service. SETI@home classic workunits: 93,865 CPU time: 863,447 hours Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[ |
BilBg Send message Joined: 27 May 07 Posts: 3720 Credit: 9,385,827 RAC: 0 |
arkayn was asking if BOINC was installed as a service. It is not (that is good) - I do not see "Running as a daemon" in the messages. Can GPU-Z see the 3 GPUs? http://www.techpowerup.com/gpuz/ Try also GPU Caps Viewer (it is 32 bit but maybe works on 64 bit OS?) http://www.ozone3d.net/gpu_caps_viewer/ Â - ALF - "Find out what you don't do well ..... then don't do it!" :) Â |
Pepo Send message Joined: 5 Aug 99 Posts: 308 Credit: 418,019 RAC: 0 |
arkayn wrote: Did you install as a service on the machine? bry b wrote: 3/10/2011 6:13:56 PM Running under account Administrator I suppose not, otherwise the client should have run under boinc_master? Additionally, the SETI installers will not help BOINC to recognize any GPUs, will they? What about giving a try to 6.12.18? Peter |
Bry B Send message Joined: 3 Apr 99 Posts: 53 Credit: 832,165 RAC: 0 |
arkayn wrote:Did you install as a service on the machine? The NOTICE tab seems broken on 6.12.18 for me. I cant get any data |
Bry B Send message Joined: 3 Apr 99 Posts: 53 Credit: 832,165 RAC: 0 |
arkayn wrote:Did you install as a service on the machine? Nevermind I found the log :) |
Bry B Send message Joined: 3 Apr 99 Posts: 53 Credit: 832,165 RAC: 0 |
Same deal with that version: 3/10/2011 6:34:46 PM | | Starting BOINC client version 6.12.18 for windows_x86_64 3/10/2011 6:34:46 PM | | Config: simulate 160 CPUs 3/10/2011 6:34:46 PM | | Config: use all coprocessors3/10/2011 6:34:46 PM | | log flags: file_xfer, sched_ops, task, sched_op_debug 3/10/2011 6:34:46 PM | | Libraries: libcurl/7.19.7 OpenSSL/0.9.8l zlib/1.2.5 3/10/2011 6:34:46 PM | | Data directory: C:\ProgramData\BOINC 3/10/2011 6:34:46 PM | | Running under account Administrator 3/10/2011 6:34:46 PM | | Processor: 60 GenuineIntel Intel(R) Xeon(R) CPU E7- 2870 @ 2.40GHz [Family 6 Model 47 Stepping 2] 3/10/2011 6:34:46 PM | | Using 160 CPUs 3/10/2011 6:34:46 PM | | Processor: 256.00 KB cache 3/10/2011 6:34:46 PM | | Processor features: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss htt tm pni ssse3 cx16 sse4_1 sse4_2 syscall nx lm vmx smx tm2 dca popcnt aes pbe 3/10/2011 6:34:46 PM | | OS: Microsoft Windows Server 2008 "R2": Enterprise x64 Edition, Service Pack 1, (06.01.7601.00) 3/10/2011 6:34:46 PM | | Memory: 95.99 GB physical, 191.98 GB virtual 3/10/2011 6:34:46 PM | | Disk: 136.60 GB total, 29.42 GB free 3/10/2011 6:34:46 PM | | Local time is UTC -8 hours 3/10/2011 6:34:46 PM | | No usable GPUs found 3/10/2011 6:34:46 PM | SETI@home | Found app_info.xml; using anonymous platform 3/10/2011 6:34:46 PM | SETI@home | URL http://setiathome.berkeley.edu/; Computer ID 5847405; resource share 100 3/10/2011 6:34:46 PM | SETI@home | General prefs: from SETI@home (last modified 09-Mar-2011 13:09:46) 3/10/2011 6:34:46 PM | SETI@home | Computer location: work 3/10/2011 6:34:46 PM | | General prefs: using separate prefs for work 3/10/2011 6:34:46 PM | | Reading preferences override file 3/10/2011 6:34:46 PM | | Preferences: 3/10/2011 6:34:46 PM | | max memory usage when active: 49146.76MB 3/10/2011 6:34:46 PM | | max memory usage when idle: 88464.17MB 3/10/2011 6:34:46 PM | | max disk usage: 10.00GB 3/10/2011 6:34:46 PM | | max CPUs used: 160 3/10/2011 6:34:46 PM | | (to change preferences, visit the web site of an attached project, or select Preferences in the Manager) 3/10/2011 6:34:46 PM | | Using proxy info from GUI 3/10/2011 6:34:46 PM | | Using HTTP proxy itgproxy:80 3/10/2011 6:34:46 PM | | GPUs have become unusable; disabling tasks3/10/2011 6:34:57 PM | | Re-reading cc_config.xml 3/10/2011 6:34:57 PM | | Config: simulate 160 CPUs 3/10/2011 6:34:57 PM | | Config: use all coprocessors3/10/2011 6:34:57 PM | | log flags: file_xfer, sched_ops, task, sched_op_debug 3/10/2011 6:35:13 PM | SETI@home | update requested by user |
©2024 University of California
SETI@home and Astropulse are funded by grants from the National Science Foundation, NASA, and donations from SETI@home volunteers. AstroPulse is funded in part by the NSF through grant AST-0307956.