Posts by Helli


log in
1) Message boards : Number crunching : Question about dedicating CPU cores to GPU support w/Lunatics apps. (Message 1480592)
Posted 158 days ago by Profile Helli
Thanks for your generous Advice, Mike.
I will try it at my Best...

Helli
2) Message boards : Number crunching : Question about dedicating CPU cores to GPU support w/Lunatics apps. (Message 1480506)
Posted 158 days ago by Profile Helli
I think it was suggested that by modifying app_info, one could basically get Boinc to 'auto switch', and dedicate the CPU cores to the GPUs when needed, but release them for CPU MB or AP work when the GPUs are doing MB and don't need them.
If so, that would make better use of my CPU resources between AP splitting runs.

How would that work with multiple GPUs? And with 2 AP tasks per GPU? It the setting per GPU? Per running instance of the app?


Edit app_info.xml and change the "avg CPU" and "max CPU" lines as follows:

<app_version>
<app_name>astropulse_v6</app_name>
<version_num>604</version_num>
<avg_ncpus>1.0</avg_ncpus>
<max_ncpus>1.0</max_ncpus>

There are two app sections for 1843, so either pick the right plan class or just do both of them.

This will reserve 1 cpu core for each task running and release them when not needed. A value of .5 will reserve 1 for every two tasks running - you might want to try that if you install the Beta Juan mentioned. I use .5 for cuda 50 tasks (2 at a time) and do not reserve any cores in BOINC's computing preferences. I use app_config.xml for these settings but you can't do that with your version of BOINC.




Thank you, I have been waiting for this. :-)

Helli


@Helli
On your system i would suggest to set it like this.

<avg_ncpus>0.5</avg_ncpus>
<max_ncpus>0.5</max_ncpus>

Also add this to the comandline or ap_cmdline_win_x86_SSE2_OpenCL_NV.txt file

-unroll 12 -ffa_block 12288 -ffa_block_fetch 6144

This should speed your 780 up.



Thanks Mike, i will try your advise immediately.

......




Mike, i've added a (second) GTX780 to my Rig - do i have to change
something for optimal workload?

Perhaps - i'm running two Workunits per GPU.

Helli
3) Message boards : Number crunching : Question about dedicating CPU cores to GPU support w/Lunatics apps. (Message 1467315)
Posted 189 days ago by Profile Helli
I think it was suggested that by modifying app_info, one could basically get Boinc to 'auto switch', and dedicate the CPU cores to the GPUs when needed, but release them for CPU MB or AP work when the GPUs are doing MB and don't need them.
If so, that would make better use of my CPU resources between AP splitting runs.

How would that work with multiple GPUs? And with 2 AP tasks per GPU? It the setting per GPU? Per running instance of the app?


Edit app_info.xml and change the "avg CPU" and "max CPU" lines as follows:

<app_version>
<app_name>astropulse_v6</app_name>
<version_num>604</version_num>
<avg_ncpus>1.0</avg_ncpus>
<max_ncpus>1.0</max_ncpus>

There are two app sections for 1843, so either pick the right plan class or just do both of them.

This will reserve 1 cpu core for each task running and release them when not needed. A value of .5 will reserve 1 for every two tasks running - you might want to try that if you install the Beta Juan mentioned. I use .5 for cuda 50 tasks (2 at a time) and do not reserve any cores in BOINC's computing preferences. I use app_config.xml for these settings but you can't do that with your version of BOINC.




Thank you, I have been waiting for this. :-)

Helli


@Helli
On your system i would suggest to set it like this.

<avg_ncpus>0.5</avg_ncpus>
<max_ncpus>0.5</max_ncpus>

Also add this to the comandline or ap_cmdline_win_x86_SSE2_OpenCL_NV.txt file

-unroll 12 -ffa_block 12288 -ffa_block_fetch 6144

This should speed your 780 up.



Thanks Mike, i will try your advise immediately.


Depends....
Helli has 8 cores available, not just 4.
......


Mark, i had disabled HT as Mike has viewed my Setup. The last weeks
i had run the GTX780 alone because i wanted to know how much the
GTX780 can do... (38k) ;-)

Helli
4) Message boards : Number crunching : Question about dedicating CPU cores to GPU support w/Lunatics apps. (Message 1467239)
Posted 189 days ago by Profile Helli
I think it was suggested that by modifying app_info, one could basically get Boinc to 'auto switch', and dedicate the CPU cores to the GPUs when needed, but release them for CPU MB or AP work when the GPUs are doing MB and don't need them.
If so, that would make better use of my CPU resources between AP splitting runs.

How would that work with multiple GPUs? And with 2 AP tasks per GPU? It the setting per GPU? Per running instance of the app?


Edit app_info.xml and change the "avg CPU" and "max CPU" lines as follows:

<app_version>
<app_name>astropulse_v6</app_name>
<version_num>604</version_num>
<avg_ncpus>1.0</avg_ncpus>
<max_ncpus>1.0</max_ncpus>

There are two app sections for 1843, so either pick the right plan class or just do both of them.

This will reserve 1 cpu core for each task running and release them when not needed. A value of .5 will reserve 1 for every two tasks running - you might want to try that if you install the Beta Juan mentioned. I use .5 for cuda 50 tasks (2 at a time) and do not reserve any cores in BOINC's computing preferences. I use app_config.xml for these settings but you can't do that with your version of BOINC.




Thank you, I have been waiting for this. :-)

Helli
5) Message boards : Number crunching : 2013 Fundraiser (Message 1364709)
Posted 451 days ago by Profile Helli
Thank you for your gift to:

SETI@home

We received your gift of $100.00 via Visa on 05/04/2013. Your confirmation number is 112868.


Done! :-)
6) Message boards : Number crunching : Panic Mode On (51) Server problems? (Message 1134417)
Posted 1095 days ago by Profile Helli
Yup, a few are flowing. Shorties. 5 minutes each. But if you can do
16 Workunits in five Minutes then you have to be very patiently. ;-)

Helli
7) Message boards : Number crunching : Panic Mode On (51) Server problems? (Message 1134411)
Posted 1095 days ago by Profile Helli
Similar here. Cache ran empty three hours ago, but 1054 WU stuck in
download queque: HTTP error. No Download actually...

Helli
8) Message boards : Number crunching : CLOSED* SETI/BOINC Milestones [ v2.0 ] - XXIII *CLOSED (Message 1128354)
Posted 1110 days ago by Profile Helli
Thanks Mark.

But..the reason why im before Morten Ross and Peter Sprogis - i have
1200 WUs left. Enough for one day ;-)

Helli
9) Message boards : Number crunching : CLOSED* SETI/BOINC Milestones [ v2.0 ] - XXIII *CLOSED (Message 1126720)
Posted 1115 days ago by Profile Helli
Well, two little Milestones for me: Reaching 60M on SETI and
breaking 100K RAC with one Rig with only two GTX590 (CPU idle). :)

Hope to reach 110K soon. :D

Helli
10) Message boards : Number crunching : PSU replacement for Jason (Message 1124546)
Posted 1122 days ago by Profile Helli
....

The awesome support means I can get a Corsair Gold AX-1200 on the way, which will probably serve as primary while the RMA on the unit takes place, as well as serve for future upgrades.
....

Jason



These donations are always well invested. :-)

Helli
11) Message boards : Number crunching : Validation inconclusive with V0.38g installer (Message 1121665)
Posted 1130 days ago by Profile Helli
My Guess is, the GT 240 will win! :D LOL

Helli
12) Message boards : Number crunching : CLOSED- SETI/BOINC Milestones [ v2.0 ] - XXII -CLOSED (Message 1120131)
Posted 1133 days ago by Profile Helli
.... What was it 5 years ago?



2,2k ;-)

Top Hosts 06/21/2006

Helli
13) Message boards : Number crunching : x38g on ATOM ION (Message 1119704)
Posted 1135 days ago by Profile Helli
For such leaked driver search on Guru3d...

Like here: http://forums.guru3d.com/showthread.php?t=340247

Helli
14) Message boards : Number crunching : Validation inconclusive with V0.38g installer (Message 1119393)
Posted 1136 days ago by Profile Helli
Thanks guys for clarifying this situation and Jason for sharing his deep inside view.

Helli
15) Message boards : Number crunching : Validation inconclusive with V0.38g installer (Message 1119364)
Posted 1136 days ago by Profile Helli
Yes, i don't say we will see this rare Situation often. But could this
Situation happen?

Helli
16) Message boards : Number crunching : Validation inconclusive with V0.38g installer (Message 1119360)
Posted 1136 days ago by Profile Helli
No Helli, it means that you will have to wait for another wingman to complete before you get credit.
...


Thanks Perry for the quick reply.

If, in this example, the 2nd wingman (the 3rd Result) has also a Lunatics App, do
i get credit, even the two Lunatics Results are equal and gets validated?


I wanted to know if there is a chance, that you dont't get credits for
your hard work, even with the Stock Client, only because two results
from 3rd Party Clients gets validated...

Helli
17) Message boards : Number crunching : Validation inconclusive with V0.38g installer (Message 1119354)
Posted 1136 days ago by Profile Helli
Does that mean, if i have a result done with the stock client and
my wingman has used the lunatcs app, the chance that my stock
client result gets valitated are only 50% ?

Helli
18) Message boards : Cafe SETI : Mystery Photo Game 19 (Message 1118949)
Posted 1137 days ago by Profile Helli
LOL

Looks like the monthly ration of pink condoms to me.... :D

hehe


Helli
19) Message boards : Number crunching : Panic Mode On (48) Server problems? (Message 1118925)
Posted 1137 days ago by Profile Helli
Uuuh...looks like AP is out of Work because i'm able to
download 1600 MB Workunits in the last 17 Minutes! :-)

Helli

It seems they are all going to you.


Pierre-PC

1334 SETI@home 19-6-2011 7:54:51 Sending scheduler request: To fetch work.
1335 SETI@home 19-6-2011 7:54:51 Requesting new tasks for CPU
1336 SETI@home 19-6-2011 7:54:55 Scheduler request completed: got 0 new tasks
1337 SETI@home 19-6-2011 7:54:55 Project has no tasks available
1338 SETI@home 19-6-2011 7:59:58 update requested by user
1339 SETI@home 19-6-2011 8:00:01 Sending scheduler request: Requested by user.
1340 SETI@home 19-6-2011 8:00:01 Requesting new tasks for CPU
1341 SETI@home 19-6-2011 8:00:09 Scheduler request completed: got 0 new tasks
1342 SETI@home 19-6-2011 8:00:09 Project has no tasks available
1343 SETI@home 19-6-2011 8:14:14 Sending scheduler request: To fetch work.
1344 SETI@home 19-6-2011 8:14:14 Requesting new tasks for CPU
1345 SETI@home 19-6-2011 8:14:21 Scheduler request completed: got 0 new tasks
1346 SETI@home 19-6-2011 8:14:21 Project has no tasks available
1347 SETI@home 19-6-2011 8:36:27 Sending scheduler request: To fetch work.
1348 SETI@home 19-6-2011 8:36:27 Requesting new tasks for CPU
1349 SETI@home 19-6-2011 8:36:31 Scheduler request completed: got 0 new tasks
1350 SETI@home 19-6-2011 8:36:31 Project has no tasks available



Oops! That was yours? :D

Well, i'm waiting again to fill my half empty Cache to its max.

19.06.2011 08:41:55 SETI@home Reporting 7 completed tasks, requesting new tasks for GPU 19.06.2011 08:42:00 SETI@home Finished upload of 11ap11ab.32135.9883.10.10.101_1_0 19.06.2011 08:42:20 SETI@home Computation for task 10ap11ab.9182.14382.14.10.43_0 finished 19.06.2011 08:42:20 SETI@home Starting 10ap11ab.19660.11110.15.10.97_0 19.06.2011 08:42:20 SETI@home [cpu_sched] Starting 10ap11ab.19660.11110.15.10.97_0 (initial) 19.06.2011 08:42:20 SETI@home Starting task 10ap11ab.19660.11110.15.10.97_0 using setiathome_enhanced version 608 19.06.2011 08:42:22 SETI@home Started upload of 10ap11ab.9182.14382.14.10.43_0_0 19.06.2011 08:42:25 SETI@home Scheduler request completed: got 0 new tasks 19.06.2011 08:42:25 SETI@home Message from server: Project has no tasks available 19.06.2011 08:42:27 SETI@home Finished upload of 10ap11ab.9182.14382.14.10.43_0_0


Helli
20) Message boards : Number crunching : Panic Mode On (48) Server problems? (Message 1118920)
Posted 1137 days ago by Profile Helli
Uuuh...looks like AP is out of Work because i'm able to
download 1600 MB Workunits in the last 17 Minutes! :-)

Helli


Next 20

Copyright © 2014 University of California