Where are they (CPUs)?

Message boards : Number crunching : Where are they (CPUs)?
Message board moderation

To post messages, you must log in.

1 · 2 · Next

AuthorMessage
Zapiao
Volunteer tester

Send message
Joined: 29 Oct 01
Posts: 110
Credit: 122,278
RAC: 0
Portugal
Message 1289749 - Posted: 30 Sep 2012, 15:43:19 UTC

30-09-2012 15:59:41 | | Starting BOINC client version 7.0.28 for windows_x86_64
30-09-2012 15:59:41 | | log flags: file_xfer, sched_ops, task
30-09-2012 15:59:41 | | Libraries: libcurl/7.25.0 OpenSSL/1.0.1 zlib/1.2.6
30-09-2012 15:59:41 | | Data directory: C:\ProgramData\BOINC
30-09-2012 15:59:41 | | Running under account Zapiao
30-09-2012 15:59:41 | | Processor: 4 GenuineIntel Intel(R) Core(TM) i3 CPU M 380 @ 2.53GHz [Family 6 Model 37 Stepping 5]
30-09-2012 15:59:41 | | Processor: 256.00 KB cache
30-09-2012 15:59:41 | | 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 tm2 popcnt pbe
30-09-2012 15:59:41 | | OS: Microsoft Windows 7: Home Premium x64 Edition, Service Pack 1, (06.01.7601.00)
30-09-2012 15:59:41 | | Memory: 2.99 GB physical, 5.97 GB virtual
30-09-2012 15:59:41 | | Disk: 149.04 GB total, 81.19 GB free
30-09-2012 15:59:41 | | Local time is UTC +1 hours
30-09-2012 15:59:41 | | ATI GPU 0: Cedar (CAL version 1.4.1741, 512MB, 479MB available, 240 GFLOPS peak)
30-09-2012 15:59:41 | | OpenCL: ATI GPU 0: Cedar (driver version CAL 1.4.1741 (VM), device version OpenCL 1.2 AMD-APP (938.2), 512MB, 479MB available)
30-09-2012 15:59:41 | SETI@home | Found app_info.xml; using anonymous platform
30-09-2012 15:59:41 | | Config: report completed tasks immediately
30-09-2012 15:59:41 | | Config: use all coprocessors

In boinc manager appears (4 CPU + 1 ATI GPU) but in cpu graph widget doesnt show any movement. Only ATI graph widget shows ATI at about 90%. So what are the CPUs doing? Are they lazy?
5470 ATI card, and it s crunching 1 WU at about 30 mnts, it s normal or i can increase the speed of crunching?.
By your command !!!
ID: 1289749 · Report as offensive
Zapiao
Volunteer tester

Send message
Joined: 29 Oct 01
Posts: 110
Credit: 122,278
RAC: 0
Portugal
Message 1289818 - Posted: 30 Sep 2012, 19:43:30 UTC - in response to Message 1289759.  

5470 ATI card, and it s crunching 1 WU at about 30 mnts, it s normal or i can increase the speed of crunching?
By your command !!!
ID: 1289818 · Report as offensive
Profile Mike Special Project $75 donor
Volunteer tester
Avatar

Send message
Joined: 17 Feb 01
Posts: 34253
Credit: 79,922,639
RAC: 80
Germany
Message 1289840 - Posted: 30 Sep 2012, 20:34:33 UTC

You only had short units so far.
AR 0.4 units will take much longer.



With each crime and every kindness we birth our future.
ID: 1289840 · Report as offensive
robertmiles
Volunteer tester

Send message
Joined: 16 Jan 12
Posts: 213
Credit: 4,117,756
RAC: 6
United States
Message 1289882 - Posted: 30 Sep 2012, 23:40:02 UTC - in response to Message 1289749.  

30-09-2012 15:59:41 | | Starting BOINC client version 7.0.28 for windows_x86_64
30-09-2012 15:59:41 | | log flags: file_xfer, sched_ops, task
30-09-2012 15:59:41 | | Libraries: libcurl/7.25.0 OpenSSL/1.0.1 zlib/1.2.6
30-09-2012 15:59:41 | | Data directory: C:\ProgramData\BOINC
30-09-2012 15:59:41 | | Running under account Zapiao
30-09-2012 15:59:41 | | Processor: 4 GenuineIntel Intel(R) Core(TM) i3 CPU M 380 @ 2.53GHz [Family 6 Model 37 Stepping 5]
30-09-2012 15:59:41 | | Processor: 256.00 KB cache
30-09-2012 15:59:41 | | 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 tm2 popcnt pbe
30-09-2012 15:59:41 | | OS: Microsoft Windows 7: Home Premium x64 Edition, Service Pack 1, (06.01.7601.00)
30-09-2012 15:59:41 | | Memory: 2.99 GB physical, 5.97 GB virtual
30-09-2012 15:59:41 | | Disk: 149.04 GB total, 81.19 GB free
30-09-2012 15:59:41 | | Local time is UTC +1 hours
30-09-2012 15:59:41 | | ATI GPU 0: Cedar (CAL version 1.4.1741, 512MB, 479MB available, 240 GFLOPS peak)
30-09-2012 15:59:41 | | OpenCL: ATI GPU 0: Cedar (driver version CAL 1.4.1741 (VM), device version OpenCL 1.2 AMD-APP (938.2), 512MB, 479MB available)
30-09-2012 15:59:41 | SETI@home | Found app_info.xml; using anonymous platform
30-09-2012 15:59:41 | | Config: report completed tasks immediately
30-09-2012 15:59:41 | | Config: use all coprocessors

In boinc manager appears (4 CPU + 1 ATI GPU) but in cpu graph widget doesnt show any movement. Only ATI graph widget shows ATI at about 90%. So what are the CPUs doing? Are they lazy?
5470 ATI card, and it s crunching 1 WU at about 30 mnts, it s normal or i can increase the speed of crunching?.


I've found that the version of BOINC I'm using won't download any CPU workunits at all unless it already has at least one GPU workunit, not necessarily from the same BOINC project. This happens even if it has no CPU workunits at all, but does have a GPU that BOINC can use.

For well-designed GPU workunits, the GPU does nearly all the work, and the CPU does little more than transferring data to and from the GPU.
ID: 1289882 · Report as offensive
Profile BilBg
Volunteer tester
Avatar

Send message
Joined: 27 May 07
Posts: 3720
Credit: 9,385,827
RAC: 0
Bulgaria
Message 1289968 - Posted: 1 Oct 2012, 7:28:39 UTC - in response to Message 1289749.  
Last modified: 1 Oct 2012, 7:33:43 UTC

In boinc manager appears (4 CPU + 1 ATI GPU) but in cpu graph widget doesnt show any movement. Only ATI graph widget shows ATI at about 90%.

It shows "Running (0.04 CPUs + 1 ATI GPUs)" (in Status column for AP task)
This is only to inform BOINC that the GPU app probably will use ~4% of one CPU core.


So what are the CPUs doing? Are they lazy?

Don't you remember??
- You disabled the CPU usage by <ncpus>0</ncpus> (You asked: "How can i configure to use only GPU in the cc_config file?")
http://setiathome.berkeley.edu/forum_thread.php?id=69430&postid=1286484#1286484


 


- ALF - "Find out what you don't do well ..... then don't do it!" :)
 
ID: 1289968 · Report as offensive
Claggy
Volunteer tester

Send message
Joined: 5 Jul 99
Posts: 4654
Credit: 47,537,079
RAC: 4
United Kingdom
Message 1289969 - Posted: 1 Oct 2012, 7:32:35 UTC - in response to Message 1289968.  

So what are the CPUs doing? Are they lazy?

Don't you remember??
- You disabled the CPU usage by <ncpus>0</ncpus> (You asked: "How can i configure to use only GPU in the cc_config file?")
http://setiathome.berkeley.edu/forum_thread.php?id=69430&postid=1286484#1286484


Wasn't that a different host?

Claggy
ID: 1289969 · Report as offensive
Profile BilBg
Volunteer tester
Avatar

Send message
Joined: 27 May 07
Posts: 3720
Credit: 9,385,827
RAC: 0
Bulgaria
Message 1289970 - Posted: 1 Oct 2012, 7:38:12 UTC - in response to Message 1289969.  
Last modified: 1 Oct 2012, 7:45:13 UTC


http://setiathome.berkeley.edu/forum_thread.php?id=69430&postid=1286511#1286511

http://setiathome.berkeley.edu/show_host_detail.php?hostid=6755411


"It is working!!!!!!! I am only getting WUs for ATI. Thank you for your assistance BUT my AMD it inst working"
'AMD': AMD C-60 APU with Radeon(tm) HD Graphics
'ATI': Intel(R) Core(TM) i3 CPU M 380 @ 2.53GHz + AMD ATI Radeon HD 5x00 series (Cedar) (512MB) driver: 1.4.1741 ("I have the same config in this other pc")


 


- ALF - "Find out what you don't do well ..... then don't do it!" :)
 
ID: 1289970 · Report as offensive
Zapiao
Volunteer tester

Send message
Joined: 29 Oct 01
Posts: 110
Credit: 122,278
RAC: 0
Portugal
Message 1289978 - Posted: 1 Oct 2012, 8:40:07 UTC

Yes it s the same pc but i dont have that option activated in cc file thats why i am asking where are the 4 cpus.
By your command !!!
ID: 1289978 · Report as offensive
Profile Fred E.
Volunteer tester

Send message
Joined: 22 Jul 99
Posts: 768
Credit: 24,140,697
RAC: 0
United States
Message 1289986 - Posted: 1 Oct 2012, 9:14:27 UTC

Yes it s the same pc but i dont have that option activated in cc file thats why i am asking where are the 4 cpus.

As the 2nd post in this thread said, you still don't have any cpu tasks for the cpu cores to crunch on host xxxx411. When BOiNC asks for both cpu and gpu tasks, Scheduler will send you GPU tasks first. If you want some cpu work, you can temporarily turn off gpu work fetch by changing the SETI@Home prefence on the website to not "use" ATI gpu. That will tell BOINC to stop asking for gpu work, and you should then get some cpu tasks. That preference does not prevent crunching the gpu tasks you already have. Remember to change it back when you get enough cpu work. Another approach is to lower your setting for min. days on hand to the point where BOINC decides you have enough, and only asks for cpu work. This method takes some experimentation to find that magic point.

Another Fred
Support SETI@home when you search the Web with GoodSearch or shop online with GoodShop.
ID: 1289986 · Report as offensive
Zapiao
Volunteer tester

Send message
Joined: 29 Oct 01
Posts: 110
Credit: 122,278
RAC: 0
Portugal
Message 1290154 - Posted: 1 Oct 2012, 18:48:28 UTC

http://setiathome.berkeley.edu/results.php?hostid=6780643 maybe this is the problem? This pc has NO WUs to crunch but in this page it has 250 ??????
By your command !!!
ID: 1290154 · Report as offensive
Claggy
Volunteer tester

Send message
Joined: 5 Jul 99
Posts: 4654
Credit: 47,537,079
RAC: 4
United Kingdom
Message 1290159 - Posted: 1 Oct 2012, 18:58:48 UTC - in response to Message 1290154.  

http://setiathome.berkeley.edu/results.php?hostid=6780643 maybe this is the problem? This pc has NO WUs to crunch but in this page it has 250 ??????

Yes, you're had 250 tasks allocated to this host recently, you're done two of them, and you're detached/re-attached the host so Abandoning most of those Wu's, and aborted all the other downloads:

<core_client_version>7.0.28</core_client_version>
<![CDATA[
<message>
WU download error: couldn't get input files:
<file_xfer_error>
<file_name>09au12aa.16869.12490.6.10.121</file_name>
<error_code>-197</error_code>
<error_message>user requested transfer abort</error_message>
</file_xfer_error>

</message>
]]>

Claggy
ID: 1290159 · Report as offensive
Zapiao
Volunteer tester

Send message
Joined: 29 Oct 01
Posts: 110
Credit: 122,278
RAC: 0
Portugal
Message 1290173 - Posted: 1 Oct 2012, 19:43:07 UTC - in response to Message 1290159.  

]
Yes, you're had 250 tasks allocated to this host recently, you're done two of them, and you're detached/re-attached the host so Abandoning most of those Wu's, and aborted all the other downloads:


So thats why i can t get more WUs right? It s possible to resend them ?
By your command !!!
ID: 1290173 · Report as offensive
rob smith Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer moderator
Volunteer tester

Send message
Joined: 7 Mar 03
Posts: 22158
Credit: 416,307,556
RAC: 380
United Kingdom
Message 1290183 - Posted: 1 Oct 2012, 20:05:40 UTC

As a user there's nothing you can do to get a task resent as that is a server side action.

If the server has "resend tasks" turned on, and the tasks are judged to be re-sendable then they will get resent to you, otherwise they will be sent out to someone else, and you will get a new batch of tasks.
Bob Smith
Member of Seti PIPPS (Pluto is a Planet Protest Society)
Somewhere in the (un)known Universe?
ID: 1290183 · Report as offensive
Zapiao
Volunteer tester

Send message
Joined: 29 Oct 01
Posts: 110
Credit: 122,278
RAC: 0
Portugal
Message 1290186 - Posted: 1 Oct 2012, 20:12:53 UTC - in response to Message 1290183.  
Last modified: 1 Oct 2012, 20:13:24 UTC

As a user there's nothing you can do to get a task resent as that is a server side action.

If the server has "resend tasks" turned on, and the tasks are judged to be re-sendable then they will get resent to you, otherwise they will be sent out to someone else, and you will get a new batch of tasks.

Damn !!!!!! And here we go again "01-10-2012 21:10:50 | SETI@home | Not reporting or requesting tasks" I am starting to be very VERY MAD with this !!!!!!!!!!!
By your command !!!
ID: 1290186 · Report as offensive
Profile Fred J. Verster
Volunteer tester
Avatar

Send message
Joined: 21 Apr 04
Posts: 3252
Credit: 31,903,643
RAC: 0
Netherlands
Message 1290190 - Posted: 1 Oct 2012, 20:18:13 UTC - in response to Message 1290183.  

As a user there's nothing you can do to get a task resent as that is a server side action.

If the server has "resend tasks" turned on, and the tasks are judged to be re-sendable then they will get resent to you, otherwise they will be sent out to someone else, and you will get a new batch of tasks.


For quite some time I think, in august I'd few 1000 tasks ended in
Time Limit Exeeded and they were all resended.

Haven't seen CPU work, in months, well an Astropulse :-/ on my slowest CPU (Q6600), instead of a HD5870 GPU?!

Only CUDA and OpenCL, only SETI Bêta has the 7 series MB work send out to CPU, stock app..

So you could help testing . . . . .




ID: 1290190 · Report as offensive
Profile Fred E.
Volunteer tester

Send message
Joined: 22 Jul 99
Posts: 768
Credit: 24,140,697
RAC: 0
United States
Message 1290197 - Posted: 1 Oct 2012, 20:27:04 UTC
Last modified: 1 Oct 2012, 20:30:55 UTC

And here we go again "01-10-2012 21:10:50 | SETI@home | Not reporting or requesting tasks" I am starting to be very VERY MAD with this !!!!!!!!!!!

Assume that message was from xxxx643 since the others haven't contacted the server today. What are you using for Minimum Work Buffer and max additional in yuor computing preferences?

Also, BOINC won't ask for work if you have a suspended task or a file transfer in retry status.
Edit: you don't have any tasks to cause those problems. Any chance you set that machine to No New Tasks?
Another Fred
Support SETI@home when you search the Web with GoodSearch or shop online with GoodShop.
ID: 1290197 · Report as offensive
Zapiao
Volunteer tester

Send message
Joined: 29 Oct 01
Posts: 110
Credit: 122,278
RAC: 0
Portugal
Message 1290231 - Posted: 1 Oct 2012, 22:53:36 UTC - in response to Message 1290197.  

And here we go again "01-10-2012 21:10:50 | SETI@home | Not reporting or requesting tasks" I am starting to be very VERY MAD with this !!!!!!!!!!!

Assume that message was from xxxx643 since the others haven't contacted the server today. What are you using for Minimum Work Buffer and max additional in yuor computing preferences?

Also, BOINC won't ask for work if you have a suspended task or a file transfer in retry status.
Edit: you don't have any tasks to cause those problems. Any chance you set that machine to No New Tasks?

It is set to 1000 and plus 10 days, everything is ok
01-10-2012 23:50:05 | | Starting BOINC client version 7.0.28 for windows_intelx86
01-10-2012 23:50:05 | | log flags: file_xfer, sched_ops, task
01-10-2012 23:50:05 | | Libraries: libcurl/7.25.0 OpenSSL/1.0.1 zlib/1.2.6
01-10-2012 23:50:05 | | Data directory: C:\ProgramData\BOINC
01-10-2012 23:50:05 | | Running under account Paula
01-10-2012 23:50:05 | | Processor: 2 GenuineIntel Intel(R) Core(TM)2 Duo CPU E4500 @ 2.20GHz [Family 6 Model 15 Stepping 13]
01-10-2012 23:50:05 | | Processor: 2.00 MB cache
01-10-2012 23:50:05 | | 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 nx lm tm2 pbe
01-10-2012 23:50:05 | | OS: Microsoft Windows Vista: Home Premium x86 Edition, (06.00.6000.00)
01-10-2012 23:50:05 | | Memory: 3.00 GB physical, 6.19 GB virtual
01-10-2012 23:50:05 | | Disk: 291.03 GB total, 255.00 GB free
01-10-2012 23:50:05 | | Local time is UTC +1 hours
01-10-2012 23:50:05 | | No usable GPUs found
01-10-2012 23:50:05 | SETI@home | Found app_info.xml; using anonymous platform
01-10-2012 23:50:05 | | Config: don't use coprocessors
01-10-2012 23:50:05 | SETI@home | URL http://setiathome.berkeley.edu/; Computer ID 6755331; resource share 100
01-10-2012 23:50:05 | SETI@home | General prefs: from SETI@home (last modified 16-Sep-2012 19:06:44)
01-10-2012 23:50:05 | SETI@home | Computer location: home
01-10-2012 23:50:05 | SETI@home | General prefs: no separate prefs for home; using your defaults
01-10-2012 23:50:05 | | Reading preferences override file
01-10-2012 23:50:05 | | Preferences:
01-10-2012 23:50:05 | | max memory usage when active: 3070.69MB
01-10-2012 23:50:05 | | max memory usage when idle: 3070.69MB
01-10-2012 23:50:05 | | max disk usage: 5.00GB
01-10-2012 23:50:05 | | don't use GPU while active
01-10-2012 23:50:05 | | (to change preferences, visit the web site of an attached project, or select Preferences in the Manager)
01-10-2012 23:50:05 | | Not using a proxy
01-10-2012 23:51:07 | SETI@home | General prefs: from SETI@home (last modified 16-Sep-2012 19:06:44)
01-10-2012 23:51:07 | SETI@home | Computer location: home
01-10-2012 23:51:07 | SETI@home | General prefs: no separate prefs for home; using your defaults
01-10-2012 23:51:07 | | Reading preferences override file
01-10-2012 23:51:07 | | Preferences:
01-10-2012 23:51:07 | | max memory usage when active: 3070.69MB
01-10-2012 23:51:07 | | max memory usage when idle: 3070.69MB
01-10-2012 23:51:07 | | max disk usage: 5.00GB
01-10-2012 23:51:07 | | don't use GPU while active
01-10-2012 23:51:07 | | (to change preferences, visit the web site of an attached project, or select Preferences in the Manager)
01-10-2012 23:51:09 | SETI@home | update requested by user
01-10-2012 23:51:13 | SETI@home | Sending scheduler request: Requested by user.
01-10-2012 23:51:13 | SETI@home | Not reporting or requesting tasks
01-10-2012 23:51:16 | SETI@home | Scheduler request completed

By your command !!!
ID: 1290231 · Report as offensive
Profile arkayn
Volunteer tester
Avatar

Send message
Joined: 14 May 99
Posts: 4438
Credit: 55,006,323
RAC: 0
United States
Message 1290243 - Posted: 1 Oct 2012, 23:42:36 UTC - in response to Message 1290231.  

And here we go again "01-10-2012 21:10:50 | SETI@home | Not reporting or requesting tasks" I am starting to be very VERY MAD with this !!!!!!!!!!!

Assume that message was from xxxx643 since the others haven't contacted the server today. What are you using for Minimum Work Buffer and max additional in yuor computing preferences?

Also, BOINC won't ask for work if you have a suspended task or a file transfer in retry status.
Edit: you don't have any tasks to cause those problems. Any chance you set that machine to No New Tasks?

It is set to 1000 and plus 10 days, everything is ok


I think I know your problem then, you set the minimum buffer to 3+ years and no task is available to run with that long of a time table.

Set it to 3 days + 3 days and you should start getting work.


ID: 1290243 · Report as offensive
Profile BilBg
Volunteer tester
Avatar

Send message
Joined: 27 May 07
Posts: 3720
Credit: 9,385,827
RAC: 0
Bulgaria
Message 1290298 - Posted: 2 Oct 2012, 4:39:58 UTC - in response to Message 1290231.  

It is set to 1000 and plus 10 days, everything is ok ...

Don't make me laugh :)))


 


- ALF - "Find out what you don't do well ..... then don't do it!" :)
 
ID: 1290298 · Report as offensive
Zapiao
Volunteer tester

Send message
Joined: 29 Oct 01
Posts: 110
Credit: 122,278
RAC: 0
Portugal
Message 1290952 - Posted: 3 Oct 2012, 22:31:16 UTC - in response to Message 1290298.  

Are you in the circus to laugh??????? Show some respect for the older ones ok? (you joined 27 May 07)
By your command !!!
ID: 1290952 · Report as offensive
1 · 2 · Next

Message boards : Number crunching : Where are they (CPUs)?


 
©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.