Posts by ReiAyanami


log in
1) Message boards : Number crunching : Average Credit Decreasing? (Message 1796340)
Posted 15 days ago by Profile ReiAyanami
Have we hit the bottom?
All my RACs stopped dropping. Some may be moving upwards :)
2) Message boards : Number crunching : Average Credit Decreasing? (Message 1787289)
Posted 13 May 2016 by Profile ReiAyanami
Your didn't understand what I wrote.
what software you will switch then...?

I said within A PROJECT which you brought up.
If AP is more than MB, set your system to be able to process AP preferentially. That's what I meant.

project X pays much better

To solve this, simplest way is to make them not comparable.
This way users chose projects for their merit in their mind, not for credit.
Make them compete within the project if they WANT to.
3) Message boards : Number crunching : Average Credit Decreasing? (Message 1787279)
Posted 13 May 2016 by Profile ReiAyanami
one should have "many currencies" even inside single SETI project. For AP, and few for MB.

Isn't current continuous drop over a month mainly caused by trying to be fair among different projects?
Someone benefits from one software or one hardware over another within a project seems to me a different story. If someone wants to be more productive, it will be solved by switching them.
4) Message boards : Number crunching : Average Credit Decreasing? (Message 1787272)
Posted 13 May 2016 by Profile ReiAyanami
"pay" just disguise for "offer me more bragging rights" Not so nice sounding to use it for complaining, yeah?


Actually it sounds "nice".
It's been fun to upgrade my system or change settings and get more credits.
To assess what my investment, I want a credit system that reflects my calculation power and time relatively stably.
I'm learning that there are many factors to be considered and very difficult to satisfy everybody by reading these thread.

Still I consider the credit system, which can not reflect resources we put in is a bad one.

If it's so difficult to give equivalent credits among different projects why not using different currency for each project for now?
After a while, an appropriate exchange rate may be established.
5) Message boards : Number crunching : Average Credit Decreasing? (Message 1783476)
Posted 29 Apr 2016 by Profile ReiAyanami
It does mean that your RAC won't fall as far or as fast as it would have. So it will have helped, a bit.

RAC fell ~12% (7500) over last 3 weeks as everybody else despite the increased number of WU processed per day and is still going down. When I checked my position on stats page, at least the fastest machine stayed at the same place during this period.
Now I have no idea how I can optimize in terms of maximum RAC.
6) Message boards : Number crunching : Average Credit Decreasing? (Message 1783285)
Posted 28 Apr 2016 by Profile ReiAyanami
Interestingly the slower you crunch, the higher the 'award' with this strange 'system'.

A few weeks ago, I tried to increase my machines' performance by maximizing the total number of WU they process per day by changing app_config file. All machines are processing more WU per day now but does this mean it didn't do any good in terms of RAC?
7) Message boards : Number crunching : Average Credit Decreasing? (Message 1782442)
Posted 25 Apr 2016 by Profile ReiAyanami
All mine have been going down for over 2 weeks (between 9 to 12%) and still going.
It seems that effects are at least similar to many machines.
My fastest machine's been staying in the middle of the same page of the Top hosts for at least 6 months and I don't see too many position changes in my neighborhood.
Since I don't do anything other than SETI, this is not too bad.
Decreasing RAC certainly doesn't motivate me, though.
I prefer numbers reflect calculation power and time of my machines and something more stable....
8) Message boards : Number crunching : Can I further optimize multiple GPU calculations? (Message 1774733)
Posted 28 Mar 2016 by Profile ReiAyanami
I have tried what you suggested (increased CPUs to 2 for low loading and made cmdline file edit), but no change in the GPU utilization. It is still around 55%. I also tried POEM and found it can load both at about 77%.

I don'd have experience with AMD but...
Now I leaned that GPU and CPU applications use what ever they want under threads allocated by Operating sysytem, I tried to maximize GPU utilization. This time I used 3 WU per GPU and looked at the effect of freeing more CPU cores. I took data for past 5days until server went down.
With my systems:
i7-3930K with 3 x GTX 670, <GPU_usage>.33, <cpu_usage>.9
i7-950 with 1 x GTX 680, <GPU_usage>.33, <cpu_usage>1
Q6600 with 1 x GTX 950, <GPU_usage>.33, <cpu_usage>1
seem to work fastest.
With these settings, they all achieve 92%(with i7-950)-97%(with i7-3930K) GPU usage with a very little fluctuation most of the time and process GPU WU more than enough to compensate for the reduced CPU WU. GPU stays between 62C(GTX 670) and 67C(GTX 680) with no error. All 3 systems now process more total WU per day than ever, even though CPU usage stays between 60 to 70% (Enough processing power left to process what ever Windows wants to do and stay happy).
Too bad I can't download more WU now...I hope the system recovers soon.
9) Message boards : Number crunching : Can I further optimize multiple GPU calculations? (Message 1773029)
Posted 21 Mar 2016 by Profile ReiAyanami
Thank you very much for the help.
Also 11+9 = 8+12 = 20 so you may have some forgotten <max_concurrent>20</max_concurrent> in app_config.xml

You were right, I forgot that I set max at 20. I was thinking max was set within the program defined by <name> but obviously total.

I freed up 1 CPU thread for PC's with one Graphics card and 2 for 3 cards and GPU usage went up a little. Meanwhile, total CPU usage went down only by a few %. Will see if increased GPU work can make up for the decreased CPU work, or out performs the previous setting over all.

This setting is great because even with a little bit of work I have to do on these PC's time to time, it doesn't freeze up the screen anymore and doesn't hold up SETI work, either.
Thank you again!
10) Message boards : Number crunching : Can I further optimize multiple GPU calculations? (Message 1772486)
Posted 18 Mar 2016 by Profile ReiAyanami
I tested further and found that if I run 8 GPU tasks, all 12 CPU tasks run at the same time but not with 9 GPU tasks (<cpu_usage>.04). So this doesn't quite fit what described by BilBg. I wonder what I am overlooking here.
If I suspend all GPU tasks, then all 12 CPU tasks run, of course.
Now I suspended all CPU tasks and observed the CPU usage by GPU tasks (Why didn't I think about this earlier?), and I saw 8 threads keep working for GPU tasks and 4 threads get down to 0, average CPU usage being approximately 14%. Meanwhile average GPU usage of 85% (with CPU tasks running) goes up to 95%.
I still don't have a clue how CPU contributes to GPU tasks but for my 3 GPUs running 9 tasks seem to require 15% of total CPU usage on average.
It looks like if I can dedicate 2 threads to GPU tasks (16.7%), I may be able to maximize my GPU usage.
But again, I don't know the internal work of CPU assignment by the software to GPU tasks, this may not be the case...
Will see.
11) Message boards : Number crunching : Can I further optimize multiple GPU calculations? (Message 1772403)
Posted 18 Mar 2016 by Profile ReiAyanami
Thank you very much for the detailed explanation.
Your explanation is very clear in terms of how I can free up CPU cores.

May I ask a few more clarifications?

The <cpu_usage> is not used by (GPU) applications, they use as much CPU time as they need no matter what value you set for <cpu_usage>

<cpu_usage> is only used by BOINC - to decide if it should run less CPU tasks so GPU tasks/apps have enough free CPU


This is still confusing to me. Doesn't this mean <cpu_usage> value affect GPU application since it is deciding how much free CPU is allocated to GPU tasks?
If GPU application uses as much CPU time as they need, why do we need to free up CPU core? Also, this brings up another question of how many cores I should free up for my old PC to maximize the speed of GPU application. (And now I can test it by changing <cpu_usage> value, thank you)

i7-3930K with 3 x GTX 670, <GPU_usage>.33, <cpu_usage>.04

For this system with 3 GPUs <cpu_usage>.4 will make BOINC to:
3 GPUs * 3 GPU tasks * 0.4 = 3.6 = (truncated to) 3 = BOINC will run 3 less CPU task (will "free 3 CPU cores")


Here, 3 GPUs * 3 GPU tasks * 0.04 =0.36 = (truncated to) 0
But my PC only runs 11 CPU tasks, not 12.
I'm not restricting CPU usage and set as 100% of the CPUs and CPU time.

This PC uses above 85% of GPU and 98 to 99% of CPU while I'm not doing anything else but SETI calculations with this setting.
12) Message boards : Number crunching : Can I further optimize multiple GPU calculations? (Message 1772191)
Posted 17 Mar 2016 by Profile ReiAyanami
That's exactly why I asked for rational help to begin with.
When I look at the run time distributions on my main PC, usually 2/3 are 27-33 min WU's, and 20% or so of 10-12 min WU's and some in between. I'm sure there is a good reason for this but I don't know.
13) Message boards : Number crunching : Can I further optimize multiple GPU calculations? (Message 1772150)
Posted 17 Mar 2016 by Profile ReiAyanami
I understand your point.
With run time of a few thousand seconds and associated standard deviation of a few hundred, I can estimate the statistical power.
That's why I needed rational because I don't have any clue what's CPU's calculating and sequential events happening, i.e. Does GPU need to wait periodically for what's CPU feeds, etc.

I decided to start my experiment blindly but with Sidewinder's observation by increasing CPU usage to 0.4 for now and keep accumulating data.
Sadly I even don't know what CPU usage of 0.4 means, i.e., is this the upper limit, average, time, threads or something else?

With average run time of ~2500 and associated current estimated standard deviation of ~600 sec, it will take a while ;-)
14) Message boards : Number crunching : Can I further optimize multiple GPU calculations? (Message 1772011)
Posted 16 Mar 2016 by Profile ReiAyanami
On my Q8300 I needed to bump up my <cpu_usage> to 0.4 to keep my GPUs properly fed.


Thank you very much for the info.
I guess I can experiment with mine, too, now that I know I can further reduce the processing speed.
15) Message boards : Number crunching : Can I further optimize multiple GPU calculations? (Message 1772009)
Posted 16 Mar 2016 by Profile ReiAyanami
20 tasks is far too small a sample size to give you any indication of the performance of a processor, you need to run for two thousand tasks to get a meaningful sample of task types and wingmen - yes, that will take a couple of weeks to achieve.


I get similar averages if I take 20 tasks from 10 days ago or 20 days ago.
Also, I don't understand how wingmen's performance affect my calculation speed.
Am I missing something very fundamental?

My question is, simply put, by increasing CPU time from 0.04 can I reduce run time for GPU tasks, and if so, what enhancement can I expect by increased CPU time: Is it linear? Is it saturable?
16) Message boards : Number crunching : Can I further optimize multiple GPU calculations? (Message 1771941)
Posted 16 Mar 2016 by Profile ReiAyanami
I have 3 PC's currently working on SETI.

i7-3930K with 3 x GTX 670, <GPU_usage>.33, <cpu_usage>.04, Run time 1409sec, CPU time 243sec, 76 credits
i7-950 with 1 x GTX 680, <GPU_usage>.33, <cpu_usage>.04, Run time 1446sec, CPU time 199sec, 95 credits
Q6600 with 1 x GTX 950, <GPU_usage>.50, <cpu_usage>.04, Run time 2478sec, CPU time 812sec, 102 credits

Run time and CPU time and credits are average of latest 20 WU's for SETI at home v8.
With this setting, GPU usage stays above 80% most of the time.

If I change CPU usage assignment, will it affect Run time?
And does it affect credit?

I can always test this by changing the settings,
but could someone help me rationalize?
17) Message boards : News : UC Berkeley Big Give (Message 1764426)
Posted 12 Feb 2016 by Profile ReiAyanami
I guess I didn't use the same email address.
Well, I stay without a green star until next time I donate.........
18) Message boards : News : UC Berkeley Big Give (Message 1764363)
Posted 12 Feb 2016 by Profile ReiAyanami
Hi,
I made donation to SETI on December 31, 2015 (confirmation number 174637) but I don't see a green star yet. I wonder how soon the donation status will be updated and what the duration of the green star display.
Thank you.
19) Message boards : Number crunching : Panic Mode On (101) Server Problems? (Message 1757914)
Posted 21 Jan 2016 by Profile ReiAyanami
It's very quiet here. Are you all holding the breath?
20) Message boards : Number crunching : Panic Mode On (100) Server Problems? (Message 1731255)
Posted 2 Oct 2015 by Profile ReiAyanami
OK, it lasted only for another half an hour. Now I can't connect for last 3 hours....mmmm


Next 20

Copyright © 2016 University of California