21)
Message boards :
Number crunching :
app_info.xml Help
(Message 64951)
Posted 29 Jul 2016 by ![]() Post: Milkyway updated the 'Milkyway' apps from 1.20 to 1.36. Have a look in my/the thread, Message 64939. If you have an app_info.xml file in the project folder, you need to update apps on your own. It don't go automatically. In your case, if you don't get new tasks, compare the versions numbers (or apps) in the app_info.xml file with the versions numbers of the currently available apps here (or look to their creation/release dates). |
22)
Message boards :
Number crunching :
AMD Radeon R9 Fury X - app_info.xml and apps - optimizations
(Message 64945)
Posted 27 Jul 2016 by ![]() Post: I read a lot in the forum and found that the GPU apps can be fine tuned. I found:
|
23)
Message boards :
News :
Server Maintanence
(Message 64944)
Posted 27 Jul 2016 by ![]() Post: Jake... Maybe one day an Intel iGPU OpenCL Milkyway app will be released? NVIDIA and ATI/AMD OpenCL apps are available - it would be a big deal to 'translate' it to Intel iGPU? I have an Intel HD Graphics (no number ;-) iGPU in my J1900 CPU. ---------------------------------------------------------------- BTW. I read a lot in the forum and found that the GPU apps can be tuned. I found:
|
24)
Message boards :
Number crunching :
AMD Radeon R9 Fury X - app_info.xml and apps - optimizations
(Message 64939)
Posted 25 Jul 2016 by ![]() Post: Because of my Messsage 64935... I have inter alia four AMD Radeon R9 Fury X VGA cards and it's still not possible to get work, if the project is 'stock'. I need to use (the following entries and apps are correct?) an app_info.xml file. [Windows 64Bit, (N-Body Sim. non-MultiThread (Single-Thread) CPU app)] <app_info> <app> <name>milkyway_nbody</name> <user_friendly_name>Milkyway N-Body Sim.</user_friendly_name> </app> <file_info> <name>milkyway_nbody_1.62_windows_x86_64.exe</name> <executable/> </file_info> <app_version> <app_name>milkyway_nbody</app_name> <version_num>162</version_num> <platform>windows_x86_64</platform> <file_ref> <file_name>milkyway_nbody_1.62_windows_x86_64.exe</file_name> <main_program/> </file_ref> </app_version> <app> <name>milkyway</name> <user_friendly_name>Milkyway</user_friendly_name> </app> <file_info> <name>milkyway_1.36_windows_x86_64.exe</name> <executable/> </file_info> <app_version> <app_name>milkyway</app_name> <version_num>136</version_num> <platform>windows_x86_64</platform> <file_ref> <file_name>milkyway_1.36_windows_x86_64.exe</file_name> <main_program/> </file_ref> </app_version> <app> <name>milkyway</name> </app> <file_info> <name>milkyway_1.36_windows_x86_64__opencl_ati_101.exe</name> <executable/> </file_info> <app_version> <app_name>milkyway</app_name> <version_num>136</version_num> <platform>windows_x86_64</platform> <avg_ncpus>1</avg_ncpus> <max_ncpus>1</max_ncpus> <plan_class>opencl_ati_101</plan_class> <cmdline></cmdline> <coproc> <type>ATI</type> <count>1</count> </coproc> <file_ref> <file_name>milkyway_1.36_windows_x86_64__opencl_ati_101.exe</file_name> <main_program/> </file_ref> </app_version> <app> <name>milkyway_separation__modified_fit</name> <user_friendly_name>Milkyway Sep. (Mod. Fit)</user_friendly_name> </app> <file_info> <name>milkyway_separation__modified_fit_1.36_windows_x86_64.exe</name> <executable/> </file_info> <app_version> <app_name>milkyway_separation__modified_fit</app_name> <version_num>136</version_num> <platform>windows_x86_64</platform> <file_ref> <file_name>milkyway_separation__modified_fit_1.36_windows_x86_64.exe</file_name> <main_program/> </file_ref> </app_version> <app> <name>milkyway_separation__modified_fit</name> </app> <file_info> <name>milkyway_separation__modified_fit_1.36_windows_x86_64__opencl_ati_101.exe</name> <executable/> </file_info> <app_version> <app_name>milkyway_separation__modified_fit</app_name> <version_num>136</version_num> <platform>windows_x86_64</platform> <avg_ncpus>1</avg_ncpus> <max_ncpus>1</max_ncpus> <plan_class>opencl_ati_101</plan_class> <cmdline></cmdline> <coproc> <type>ATI</type> <count>1</count> </coproc> <file_ref> <file_name>milkyway_separation__modified_fit_1.36_windows_x86_64__opencl_ati_101.exe</file_name> <main_program/> </file_ref> </app_version> </app_info> http://milkyway.cs.rpi.edu/milkyway/download/milkyway_nbody_1.62_windows_x86_64.exe http://milkyway.cs.rpi.edu/milkyway/download/milkyway_1.36_windows_x86_64.exe http://milkyway.cs.rpi.edu/milkyway/download/milkyway_1.36_windows_x86_64__opencl_ati_101.exe http://milkyway.cs.rpi.edu/milkyway/download/milkyway_separation__modified_fit_1.36_windows_x86_64.exe http://milkyway.cs.rpi.edu/milkyway/download/milkyway_separation__modified_fit_1.36_windows_x86_64__opencl_ati_101.exe BTW. Is the milkyway_separation__modified_fit part superfluous now, so I could delete this part in red (and this two apps)? - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - I made a forum search because of the project prefs point: Frequency (in Hz) that should try to complete individual work chunks. Higher numbers may run slower but will provide a more responsive system. Lower may be faster but more laggy. default 60 (corresponds to 60 fps) It looks like just the outdated Milkyway 1.20 ATI app used this settings. The currently Milkyway 1.36 ATI app don't use it. I set '1' (one) but the app use/show: Using a target frequency of 60.0 Is this OK, or a bug? - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - I'm a bit disappointed that a project task last ~ 16 seconds with the Milkyway 1.36 ATI app on one FuryX VGA card (1 WU/GPU). I looked to other PCs, e.g. hostid=590597 with 'R9 200 Series - Hawaii' VGA cards. This VGA card have just 44 ComputeUnits (CUs) A task last ~ 15 seconds. The/my FuryX have 64 CUs. But a task last ~ 16 seconds. Is there something wrong - possibilities to optimize/fine tune? Thanks. |
25)
Message boards :
Number crunching :
"Completed, can't validate" - what's this?
(Message 64936)
Posted 25 Jul 2016 by ![]() Post: de_modfit_fast_15_3s_fixedangles_simBPLfixed2_1_1469198227_3079440 http://milkyway.cs.rpi.edu/milkyway/workunit.php?wuid=1239937928 Too many errors (may have bug) Three members (wingmen) aborted this task... What happen with this task? It's lost? Will send out again? Thanks. |
26)
Message boards :
News :
Server Maintanence
(Message 64935)
Posted 25 Jul 2016 by ![]() Post: How long the Milkyway server will not be reachable? So I guess the BOINC server software will remain 'old'? I have inter alia four AMD Radeon R9 Fury X VGA cards and it's still not possible to get work, if the project is 'stock'. I need to use (the following entries and apps are correct?) an app_info.xml file. (One day (soon?) it will be possible to get work without app_info.xml file?) [BTW. BBCode's pre and code don't work properly.] [Windows 64Bit, (N-Body Sim. non-MultiThread (Single-Thread) CPU app)] <app_info> <app> <name>milkyway_nbody</name> <user_friendly_name>Milkyway N-Body Sim.</user_friendly_name> </app> <file_info> <name>milkyway_nbody_1.62_windows_x86_64.exe</name> <executable/> </file_info> <app_version> <app_name>milkyway_nbody</app_name> <version_num>162</version_num> <platform>windows_x86_64</platform> <file_ref> <file_name>milkyway_nbody_1.62_windows_x86_64.exe</file_name> <main_program/> </file_ref> </app_version> <app> <name>milkyway</name> <user_friendly_name>Milkyway</user_friendly_name> </app> <file_info> <name>milkyway_1.36_windows_x86_64.exe</name> <executable/> </file_info> <app_version> <app_name>milkyway</app_name> <version_num>136</version_num> <platform>windows_x86_64</platform> <file_ref> <file_name>milkyway_1.36_windows_x86_64.exe</file_name> <main_program/> </file_ref> </app_version> <app> <name>milkyway</name> </app> <file_info> <name>milkyway_1.36_windows_x86_64__opencl_ati_101.exe</name> <executable/> </file_info> <app_version> <app_name>milkyway</app_name> <version_num>136</version_num> <platform>windows_x86_64</platform> <avg_ncpus>1</avg_ncpus> <max_ncpus>1</max_ncpus> <plan_class>opencl_ati_101</plan_class> <cmdline></cmdline> <coproc> <type>ATI</type> <count>1</count> </coproc> <file_ref> <file_name>milkyway_1.36_windows_x86_64__opencl_ati_101.exe</file_name> <main_program/> </file_ref> </app_version> <app> <name>milkyway_separation__modified_fit</name> <user_friendly_name>Milkyway Sep. (Mod. Fit)</user_friendly_name> </app> <file_info> <name>milkyway_separation__modified_fit_1.36_windows_x86_64.exe</name> <executable/> </file_info> <app_version> <app_name>milkyway_separation__modified_fit</app_name> <version_num>136</version_num> <platform>windows_x86_64</platform> <file_ref> <file_name>milkyway_separation__modified_fit_1.36_windows_x86_64.exe</file_name> <main_program/> </file_ref> </app_version> <app> <name>milkyway_separation__modified_fit</name> </app> <file_info> <name>milkyway_separation__modified_fit_1.36_windows_x86_64__opencl_ati_101.exe</name> <executable/> </file_info> <app_version> <app_name>milkyway_separation__modified_fit</app_name> <version_num>136</version_num> <platform>windows_x86_64</platform> <avg_ncpus>1</avg_ncpus> <max_ncpus>1</max_ncpus> <plan_class>opencl_ati_101</plan_class> <cmdline></cmdline> <coproc> <type>ATI</type> <count>1</count> </coproc> <file_ref> <file_name>milkyway_separation__modified_fit_1.36_windows_x86_64__opencl_ati_101.exe</file_name> <main_program/> </file_ref> </app_version> </app_info> http://milkyway.cs.rpi.edu/milkyway/download/milkyway_nbody_1.62_windows_x86_64.exe http://milkyway.cs.rpi.edu/milkyway/download/milkyway_1.36_windows_x86_64.exe http://milkyway.cs.rpi.edu/milkyway/download/milkyway_1.36_windows_x86_64__opencl_ati_101.exe http://milkyway.cs.rpi.edu/milkyway/download/milkyway_separation__modified_fit_1.36_windows_x86_64.exe http://milkyway.cs.rpi.edu/milkyway/download/milkyway_separation__modified_fit_1.36_windows_x86_64__opencl_ati_101.exe BTW. Is the milkyway_separation__modified_fit part superfluous now, so I could delete this part in red (and this two apps)? Thanks. |
27)
Message boards :
Number crunching :
Admins, please app_info.xml file for 290/390/Fury series VGA cards...
(Message 64496)
Posted 24 Apr 2016 by ![]() Post: I don't know if the: milkyway_separation_1.20_windows_x86_64.exe (17-Jun-2013) milkyway_separation_1.20_windows_x86_64__opencl_amd_ati.exe (17-Jun-2013) - are the correct, or they are Beta apps (at least they are available in the Milkyway/Download folder). If I look (+ed correct) to the stock Milkyway PCs, they have running (the outdated?): milkyway_separation_1.00_windows_x86_64.exe (08-Feb-2012) milkyway_separation_1.02_windows_x86_64__opencl_amd_ati.exe (10-Feb-2012) So it would be good if one of the admins could/would jump in this thread... ;-) BTW. On my FuryX's the v1.20 app is running well. |
28)
Message boards :
Number crunching :
Admins, please app_info.xml file for 290/390/Fury series VGA cards...
(Message 64495)
Posted 24 Apr 2016 by ![]() Post: After some more headache, this should work for MilkyWay@Home N-Body Simulation (just CPU app, http://milkyway.cs.rpi.edu/milkyway/apps.php) <app> <name>milkyway_nbody</name> <user_friendly_name>MilkyWay@Home N-Body Simulation</user_friendly_name> </app> <file_info> <name>milkyway_nbody_1.60_windows_x86_64.exe</name> <executable/> </file_info> <app_version> <app_name>milkyway_nbody</app_name> <version_num>160</version_num> <platform>windows_x86_64</platform> <file_ref> <file_name>milkyway_nbody_1.60_windows_x86_64.exe</file_name> <main_program/> </file_ref> </app_version> http://milkyway.cs.rpi.edu/milkyway/download/milkyway_nbody_1.60_windows_x86_64.exe For example you could insert it at the top between: <app_info> - and: <app> <name>milkyway</name> (...) |
29)
Message boards :
Number crunching :
Admins, please app_info.xml file for 290/390/Fury series VGA cards...
(Message 64494)
Posted 24 Apr 2016 by ![]() Post: OK, after some headache, I got it, problem solved -> my FuryX VGA cards get Milkyway project tasks... :-) Before you want to do this also, be aware - app_info.xml file usage is only for advanced users. http://boinc.berkeley.edu/wiki/Anonymous_platform The following is for 64 bit Windows OS, CPU & AMD/ATI apps (MilkyWay@Home & Milkyway@Home Separation (Modified Fit), without MilkyWay@Home N-Body Simulation). My app_info.xml file (strange BBCs (pre) and (code) don't work properly): <app_info> <app> <name>milkyway</name> <user_friendly_name>MilkyWay@Home</user_friendly_name> </app> <file_info> <name>milkyway_separation_1.20_windows_x86_64.exe</name> <executable/> </file_info> <app_version> <app_name>milkyway</app_name> <version_num>120</version_num> <platform>windows_x86_64</platform> <file_ref> <file_name>milkyway_separation_1.20_windows_x86_64.exe</file_name> <main_program/> </file_ref> </app_version> <app> <name>milkyway</name> </app> <file_info> <name>milkyway_separation_1.20_windows_x86_64__opencl_amd_ati.exe</name> <executable/> </file_info> <app_version> <app_name>milkyway</app_name> <version_num>120</version_num> <platform>windows_x86_64</platform> <avg_ncpus>0.25</avg_ncpus> <max_ncpus>0.25</max_ncpus> <plan_class>opencl_amd_ati</plan_class> <cmdline></cmdline> <coproc> <type>ATI</type> <count>1</count> </coproc> <file_ref> <file_name>milkyway_separation_1.20_windows_x86_64__opencl_amd_ati.exe</file_name> <main_program/> </file_ref> </app_version> <app> <name>milkyway_separation__modified_fit</name> <user_friendly_name>Milkyway@Home Separation (Modified Fit)</user_friendly_name> </app> <file_info> <name>milkyway_separation__modified_fit_1.36_windows_x86_64.exe</name> <executable/> </file_info> <app_version> <app_name>milkyway_separation__modified_fit</app_name> <version_num>136</version_num> <platform>windows_x86_64</platform> <file_ref> <file_name>milkyway_separation__modified_fit_1.36_windows_x86_64.exe</file_name> <main_program/> </file_ref> </app_version> <app> <name>milkyway_separation__modified_fit</name> </app> <file_info> <name>milkyway_separation__modified_fit_1.36_windows_x86_64__opencl_ati_101.exe</name> <executable/> </file_info> <app_version> <app_name>milkyway_separation__modified_fit</app_name> <version_num>136</version_num> <platform>windows_x86_64</platform> <avg_ncpus>0.5</avg_ncpus> <max_ncpus>0.5</max_ncpus> <plan_class>opencl_ati_101</plan_class> <cmdline></cmdline> <coproc> <type>ATI</type> <count>1</count> </coproc> <file_ref> <file_name>milkyway_separation__modified_fit_1.36_windows_x86_64__opencl_ati_101.exe</file_name> <main_program/> </file_ref> </app_version> </app_info> You can edit this entries related to/for your PC: <avg_ncpus>***</avg_ncpus> <max_ncpus>***</max_ncpus> <coproc> <type>ATI</type> <count>1</count> </coproc> - for just 1 project task on 1 GPU. (AFAIK, the 290/390/Fury series VGA cards can do with the currently drivers just 1 task/GPU. But it looks like no problem for Milkyway, because the GPU Load is at maximum. I tested Crimson 16.3.2 and still just 1 task/GPU (at least at SETI@home). But I need to use Crimson 15.12, because with 16.3.2 my FuryX's make invalid AstroPulse results at SETI@home.) Download URLs of the apps: http://milkyway.cs.rpi.edu/milkyway/download/milkyway_separation_1.20_windows_x86_64.exe http://milkyway.cs.rpi.edu/milkyway/download/milkyway_separation_1.20_windows_x86_64__opencl_amd_ati.exe http://milkyway.cs.rpi.edu/milkyway/download/milkyway_separation__modified_fit_1.36_windows_x86_64.exe http://milkyway.cs.rpi.edu/milkyway/download/milkyway_separation__modified_fit_1.36_windows_x86_64__opencl_ati_101.exe BTW. I use BOINC v7.6.23 Beta (other/better detection of the new AMD VGA cards): http://boinc.berkeley.edu/dev/forum_thread.php?id=10204&postid=67990#67990 |
30)
Message boards :
Number crunching :
Admins, please app_info.xml file for 290/390/Fury series VGA cards...
(Message 64490)
Posted 22 Apr 2016 by ![]() Post: I have my PC running since October last year. Dual Xeon CPU Board with four AMD Radeon R9 Fury X VGA cards. I added Milkyway in BOINC but my PC got no tasks for the GPUs. I searched this forum and read the Milkyway server software need an update for to send tasks to the 'new' 290/390/Fury series VGA cards. The FuryX is available since mid last year. 9 months later - and still not possible to get work? The admins don't want the performance of the 'new' 290/390/Fury series VGA cards? Up to the time the Milkyway server will send tasks to the 'new' VGA cards automatically - it's possible that the admins make a sticky (just read & closed, no new messages possible to write) thread in this forum with instruction how to set up an app_info.xml file with all CPU & GPU apps? I need it just for Windows, but also for Linux it would be helpful I guess... Also the download URLs of all needed files. For example, SETI have this kind of thread in the forum. And a 2nd thread for questions of the members. Thanks. [EDIT: Up to the time the admins do this maybe, I would be grateful if I could get help here in this thread before. ;-)] |
31)
Message boards :
Number crunching :
What is the cause of these 'validate errors'
(Message 63696)
Posted 10 Jun 2015 by ![]() Post: I got also 1 (until now) validate error: http://milkyway.cs.rpi.edu/milkyway/workunit.php?wuid=845965973 The <stderr_txt> isn't complete. |
32)
Message boards :
Number crunching :
How to increase GPU Load at NVidia VGA card?
(Message 63695)
Posted 10 Jun 2015 by ![]() Post: I have a NV GT730. I have let run: MilkyWay@Home v1.02 (opencl_nvidia) [0.4% CPU time usage] Milkyway@Home Separation (Modified Fit) v1.36 (opencl_nvidia_101) [2.7% CPU time usage] ... the GPU Load is just ~50% each on the GT730 with 1 app/WU. How could I increase the GPU Load? With the prefs? Currently they are default: - - - - - - - - - - Maximum CPU % for graphics 0 ... 100 - 20 Frequency (in Hz) that should try to complete individual work chunks. Higher numbers may run slower but will provide a more responsive system. Lower may be faster but more laggy. - 60 default 60 (corresponds to 60 fps) Period (in milliseconds) to check for scene updates - 30 Change how fast the view randomly moves around - 5 Make particles bigger or smaller - 250 Make particles bigger or smaller when using uglier particles - 40 - - - - - - - - - - How (with which values) I should change it? Or I should create an app_config.xml file for to let run 2 WUs/GPU? How should look the entries? Thanks. |
33)
Message boards :
Number crunching :
4x HD7990 in one PC?
(Message 61000)
Posted 7 Feb 2014 by ![]() Post: I would like to build a new machine. 4x AMD Radeon HD7990 (dual GPU) graphic cards with ASUS Z9PE-D8 WS Motherboard and 2x Intel Xeon E5-2630v2 CPUs. My question: Is this possible? 1 HD7990 use up to 375W fully loaded (in web test up to 395W). 2x 8pin PCIe power connector, 2x 150W= 300W Over the PCIe slot 75W How much wattage can go over the 24pin power connector? I calculate with 50W for the motherboard/system-RAM, and then 4x 75W/PCIe slot= 300W (The both CPUs get power over 2x EPS power connector.) So over the 24pin power connector must come at least 350W. Can the 24pin power connector/cable of the power supply deliver at least 350W, or is this too much for the cable/plug or the plug at the motherboard? I see now, the motherboard have also a 4pin molex plug. Is this a connection to the motherboard or from the motherboard to other equipment? In which direction go the power? How much wattage can go over this connection? Thanks. (BTW. Yes, this machine will do primary SETI, but during the weekly server maintenance there this machine will do Milkyway. ;-) |
34)
Message boards :
Number crunching :
Stock CPU app results need wingmen for confirmation?
(Message 56230)
Posted 19 Nov 2012 by ![]() Post: So I understood it correct, that currently are no optimized CPU apps available? Currently are the stock CPU apps the only solution? Is someone working at optimized CPU apps? Are MW@h *cuda23* apps (maybe 3rd party) available? (The stock OpenCL app need at least NVIDIA driver 266.58, if I remember correct. But, I need to sticky with NVIDIA driver 190.38) Thanks. |
35)
Message boards :
Number crunching :
Stock CPU app results need wingmen for confirmation?
(Message 56228)
Posted 19 Nov 2012 by ![]() Post: My machine crunch currently MW@h WUs with the stock v1.00 CPU app. If I remember correct, MW@h results don't need wingmen for confirmation .. But, all CPU results of my machine need 2 wingman for confirmation. Is the stock CPU app buggy? Are optimized CPU apps available which use the CPU instructions? Or use the stock CPU app these already? Thanks. |
36)
Message boards :
Number crunching :
app_info.xml file for 2 WUs/nVIDIA GPU ?
(Message 53305)
Posted 19 Feb 2012 by ![]() Post: Hi community, a teammate would like to let run 2 WUs/GTX460. How need to look the app_info.xml file for to let run both CPU apps and the GPU app of MW@h? Thanks. |
37)
Message boards :
Number crunching :
HTTP Scheduler issues
(Message 53147)
Posted 13 Feb 2012 by ![]() Post: Thanks to all! I did first the easiest way ;-) - I pressed a few times the update button - after a few times BOINC said: Milkyway@home 13.02.2012 23:05:03 update requested by user Milkyway@home 13.02.2012 23:05:08 Fetching scheduler list Milkyway@home 13.02.2012 23:05:09 Master file download succeeded Milkyway@home 13.02.2012 23:05:14 Sending scheduler request: Requested by user. Milkyway@home 13.02.2012 23:05:14 Not reporting or requesting tasks Milkyway@Home 13.02.2012 23:05:17 Scheduler request completed ..later: Milkyway@Home 13.02.2012 23:25:33 Sending scheduler request: To fetch work. Milkyway@Home 13.02.2012 23:25:33 Requesting new tasks for NVIDIA GPU Milkyway@Home 13.02.2012 23:25:36 Scheduler request completed: got 1 new tasks Milkyway@Home 13.02.2012 23:25:38 Started download of milkyway_separation_1.02_windows_intelx86__opencl_nvidia.exe What are the best/fastest project settings for a nVIDIA GPU? The GTX260 is only for crunching (secondary GPU) so lags are not a problem.. ;-) Like this? Maximum CPU% for graphics (0...100): 100 Frequency (in Hz) that should try to complete individual work chunks. Higher numbers may run slower but will provide a more responsive system. Lower may be faster but more laggy. default 60.0 (corresponds to 60 fps): 1 Thanks. |
38)
Message boards :
Number crunching :
HTTP Scheduler issues
(Message 53142)
Posted 13 Feb 2012 by ![]() Post: Sorry for offtopic. My machine wanted again - after a longer break - MW@h WUs. My machine: E7600 + GTX260, WinXP 32bit, nVIDIA driver 275.33, stock - no app_info.xml file, BOINC (V6.12.33) message: Milkyway@home 13.02.2012 21:02:40 Sending scheduler request: To fetch work. Milkyway@home 13.02.2012 21:02:40 Requesting new tasks for NVIDIA GPU Milkyway@home 13.02.2012 21:02:43 Scheduler request failed: HTTP file not found It's my machine or is there something wrong with the MW@h scheduler server? Thanks. |
39)
Message boards :
News :
N-body updated to 0.80
(Message 51962)
Posted 13 Dec 2011 by ![]() Post: Additional.. little bit off topic.. sorry. Since I calculate MW@h WUs, I find it a pity that on my E7600 + GTX260 I have max 12 WUs/whole machine. It's 6 WUs/CPU(-thread), right? It's possible to make it little bit better? CPU and GPU WU limit in progress separately? In past, sometimes I have 12 CPU WUs and no GPU WUs in BOINC, because of the combined WU limit in progress. There I needed to un-/check always the CPU in the project settings, for to have CPU and GPU busy - very cumbersome.. It would be nice to have a CPU and GPU WU limit in progress separately here at MW@h. E.g. currently S@h have 50 WUs/CPU(-thread) and 400 WUs/GPU (limit of tasks in progress). So I guess here at MW@h it could be also possible (if the server software is the same). ;-) I don't mean the same limit, maybe 12 WUs/GPU and 4 WUs/CPU(-thread). But if currently the n-body lasts only 10 seconds.. then maybe currently also 12 WUs/CPU(-thread). |
40)
Message boards :
News :
N-body updated to 0.80
(Message 51960)
Posted 13 Dec 2011 by ![]() Post: So I understand correct, at Duo CPUs (2 threads) the whole CPU is used for one n-body WU? BOINC said 2 CPUs. (After looking to client_state.xml there are entries: <avg_ncpus>2.000000</avg_ncpus> and <max_ncpus>2.000000</max_ncpus>) Or all n-body CPU WUs need 2 threads, independent which CPU? Is really the whole CPU @ 100 % used (Duo CPU), or it's only a calculation thing for BOINC how to calculate the WU cache? It was too fast for me to look in Task Manager. If BOINC say 2 CPUs/1 WU for n-body, then the GPU stop the calculation, because stock it's 0.05 CPU/1 GPU for the MW@h GPU WUs. So maybe it's possible to cancel the thread usage for CPU WUs (upper mentioned entries)? So the GPU wouldn't stop the calculation. |
©2023 Astroinformatics Group