Welcome to MilkyWay@home

Posts by 10esseeTony

1) Message boards : Number crunching : Milkyway has been selected for a Formula BOINC Sprint May 21-23 (Message 69844)
Posted 21 May 2020 by 10esseeTony
Post:
I hope your servers are up to the task. :)
2) Message boards : News : nbody 1.64 release for Mac (Message 66573)
Posted 26 Aug 2017 by 10esseeTony
Post:
Shayol Ghul, I would suggest not running Milkyway on your CPU, in your situation.

Find a project that does not have a GPU app, and run that on your CPU instead.

To the Admins/developers: Do you STILL have a much too low limit (80 tasks?) for Milkyway?
3) Message boards : Number crunching : Original Titan, scoring poorly, need help (Message 63900)
Posted 5 Sep 2015 by 10esseeTony
Post:
Well, perhaps this thread will prove somewhat useful to someone else in the future. More info can be found below:

http://forums.anandtech.com/showthread.php?t=2446534
4) Message boards : Number crunching : Original Titan, scoring poorly, need help (Message 63898)
Posted 4 Sep 2015 by 10esseeTony
Post:
I've found an option to enable more cores to be used for double precision, but that didn't help.

My research so far is that perhaps the massive double precision processing is only available in CUDA format, not in Open_CL tasks.

Thoughts?
5) Message boards : Number crunching : Original Titan, scoring poorly, need help (Message 63895)
Posted 3 Sep 2015 by 10esseeTony
Post:
I have been using Radeon 280X's, and they all can complete one Milkyway@home v1.02 task in less than 24 seconds.

I have acquired an original GeForce Titan, and the double precision according to Wikipedia should be at LEAST 30% more than the 280X, but instead of <24 seconds, a single task requires 220-390 seconds, as well as a significant increase in CPU time.

Are the opencl_nvidia tasks not as optimized as the opencl_amd_ati tasks? Is there some configuration file I need to optimize?

Running multiple MW tasks raises the card's utilization from mid 70% to 99%, but the length of the individual tasks likewise increases (as expected).

Anyone have a solution to make a Titan run as it should on MW?
6) Message boards : News : New Modfit Runs (Message 63121)
Posted 7 Feb 2015 by 10esseeTony
Post:
Thanks Dunx.

I'm a GUI kinda guy, so bear with me.

Does that go in the app_config file?

Do I replace the "N" with a number or does that stand for, ahem, "N"finite? :D


PS: Everything is working as expected today, lot's of work units for all my machines. And they are even (correctly) getting priority over other projects as I've instructed. Woot woot!
7) Message boards : Number crunching : Auto-aborted GPU WU when changing video cards (Message 63120)
Posted 7 Feb 2015 by 10esseeTony
Post:
Thanks for looking into it mikey. Milkyway is the last holdout that I'm aware of that still allows the HD4850, which is a shame, because at 200GFLOPS double precision and 110watts max, it's one heck of a performer that can be picked up on ebay for only $30 or less. It's a great option for old dual core PC's with wimpy power supplies.

To answer most of your questions with a single response, I got it working again by formatting and installing Windows 10 beta. When that expires in April it will be time to turn off the 'heaters' anyway. :)

The PC is only for crunching, although it's located in my daughters room (as a heater), she only uses it when her Macbook isn't yet unpacked for her weekend visit, or the Mac is just a few inches further away than she feels like reaching. :)

It's odd that the link to that machine shows it has the card installed, I was given the option to use the GPU in the BOINC Manager, but the error msg says it's missing the coprocessor.

I used to think it was a server-side error, sending OpenCL 1.02 tasks, that just took some time to correct, thus I let it run (CPU crunching) for a few days and yet it did not self repair. Not the first time I had the problem, the other times it self corrected in a fair amount of time.

Thanks again for trying.
8) Message boards : News : New Modfit Runs (Message 63114)
Posted 7 Feb 2015 by 10esseeTony
Post:
Hmmmmm. Magically I now have tens of minutes of WU to crunch (vs 1-2 minutes). Perhaps the Weiss IS listening in?
9) Message boards : News : New Modfit Runs (Message 63113)
Posted 6 Feb 2015 by 10esseeTony
Post:
///Begin playful yet serious rant to Jake///

Jake, I appreciate what you guys are up to and am honored to be able to contribute to the cause.

BUT, (there's always a 'butt' in every crowd), we'd like to hear from you. You opened this thread telling us to let you know any problems, etc. Let us know you're listening, that you're either considering our ideas/problems, or that you're just ignoring them. :) It's ok, this is part computer science after all, and if NOT utilizing the system efficiently is part of the research, just let us know.

Many have complained that the fast units are TOO fast, and they complete in almost as little time as it takes the CPU to send it back to you, and for the server to send a replacement. Some run out they are so fast.

Solution to problem A, the idle time while the CPU packages the result, is to run multiple tasks per GPU.

But you really have to do something about the quanity of GPU tasks sent at once. Or at least tell us NO, we're not going to address that at this time. SETI gladly sends a half day's worth at a time, or however many BOINC is set to receive, so we know it's possible.

I assume you're catering to those poor Nvidia folks whose double precision scores, frankly, are embarassing (except the mighty Titan series, repect due there). I suppose 10 WU would meet the goal of the standard .5 day's worth of work for those with Nvidia cards.

But here's a screenshot of my (new) primary MW@H cruncher. It's running about what, 30-40 minutes an hour, maybe? And I've not even added the final GPU yet, while waiting for the new PSU.

http://www.facebook.com/photo.php?fbid=10153140531602074&l=8c7c80e012

Shameful waste! (Actually I'm just crying because this was supposed to put me over the top and enable me to overcome/outscore some teamates. :P )


///END playful yet serious rant to Jake///

Now for the rest of you, as you've helped tremendously in getting me manually set up to run multiple tasks per GPU, can anyone help me manually configure to update more frequently and or get more GPU tasks per update? Maybe this is my fault, not Mr. Weiss's.

Thanks.
10) Message boards : Number crunching : Auto-aborted GPU WU when changing video cards (Message 63112)
Posted 6 Feb 2015 by 10esseeTony
Post:
http://milkyway.cs.rpi.edu/milkyway/results.php?hostid=594815

http://milkyway.cs.rpi.edu/milkyway/show_host_detail.php?hostid=594815
11) Message boards : News : New Modfit Runs (Message 63107)
Posted 6 Feb 2015 by 10esseeTony
Post:
...My experience is that leaving a core free to feed the GPU adds so little output that it's not worth doing, ...


I would have to very very strongly disagree to that as a general rule, my HD4850 crunch time on a full size (not fast) WU went from 6 minutes to 2 minutes on a dual core machine, by leaving one core free. And I notice tens of seconds difference on my 8 thread machines with 280X's if I give them a bit of CPU power.
12) Message boards : Number crunching : Auto-aborted GPU WU when changing video cards (Message 63105)
Posted 6 Feb 2015 by 10esseeTony
Post:
Well, going from a hd4850 to a 280x it fixed itself within an hour.

My other machine going from a 280x down to a hd4850 is still aborting after 2 days.

I've uninstalled BOINC and the drivers half a dozen times and reinstalled. :-/
13) Message boards : Number crunching : Auto-aborted GPU WU when changing video cards (Message 63104)
Posted 6 Feb 2015 by 10esseeTony
Post:
Hello all, I have a number of Windows boxes, and I've recently acquired a few more video cards, ATI HD4850's and 280X's.

I've been a bit undecided as to which cards should go into which machines, due to PCIe slots, case size, PSU limitations, etc.

My problem is that when changing from a 4850 to a 280X or vice versa, (and uninstalling and reinstalling the correct drivers), BOINC automatically aborts any and all incoming GPU workunits.

I go to my account, and the computer shows the correct video card is recognized by the server. I uninstall and reinstall BOINC, and STILL get auto-aborted workunits.

Other than "QUIT SWAPPING CARDS!" does anyone have any advice? :)
14) Message boards : Number crunching : Computation errors (Message 63103)
Posted 6 Feb 2015 by 10esseeTony
Post:
My Radeon HD5970 is likewise only having problems with the MilkyWay@home 1.02 units.

Did the aforementioned drivers fix the problem?
15) Message boards : Number crunching : ATI Card Recommendation (Message 62951)
Posted 4 Jan 2015 by 10esseeTony
Post:
Without knowing why you need a MB powered card, I can only guess that you are wanting to bump up an old/spare desktop, and don't want to shell out for a power supply. I feel you, I currently have 6 old desktops in an unused bedroom and I'm using them to heat my home. Seriously, and for the same cost as just running the heat, except science is gettin dunn! Sorry, I got excited there for a moment.

So, if you're trying to get out of a Power Supply upgrade, but you have 1-2 available 4pin Molex (old school) connectors, you can get a pig tail that lets you power a lower end 6pin graphics card using those spare molex connectors.



I have one such system, and it's running a Radeon HD4850, which has a double precision score of 200 GFLOPS, and maxes out at a reasonable 110watts I think. You can occasionally find them on ebay for about $30.

That's about your best choice due to $$$, low wattage, and GFLOPS. The 5850 is a bit more power hungry, but twice as powerful, but the prices on ebay are stupid, oops, I meant...steep.



I find this link very useful: http://en.wikipedia.org/wiki/List_of_AMD_graphics_processing_units#Radeon_R700_.28HD_4xxx.29_Series
16) Message boards : News : New Modfit Runs (Message 62948)
Posted 4 Jan 2015 by 10esseeTony
Post:
the file has to be named app_config.xml not app-config.xml



Cha-ching! Yep, now it's running 2 WU per GPU. Thanks. And I don't smell smoke...yet. :)

Just curious, instead of .5 for double workunits, what would one put for triple WUs? EDIT: Oh Jeez, I get it. It's MATH. :P So don't need that answered anymore.




Hans: 0 should maximize the work being buffered, it's odd that you're running out of work. UNLESS you are only running out of work for the GPU. In which case I agree we need more computationally intensive workunits, and less network activity.

I've noticed if I set the project to "no new work" I run out of GPU tasks in 10-20 minutes but still have a day's worth of CPU processing to do. I couldn't hazard a guess as to that being a BOINC issue, not differentiating between CPU and GPU work, or BOINC having a limit on the maximum number of tasks, or Milkyway simply not sending as much as possible for the GPU.


Hans if you do have "0" (unlimited) set for the work buffer, try something smaller such as .5 for half a days work. I've noticed when running multiple projects that sometimes one of the projects will refuse to get new work, because it sees that the other projects have already filled up the buffer. Not sure a smaller buffer will help that, but anything is possible.
17) Message boards : News : New Modfit Runs (Message 62938)
Posted 3 Jan 2015 by 10esseeTony
Post:
....the runs might not fully utilize your GPU. ...try configuring your GPU to run 2 of these at the same time...

Jake


Uhm, is there a tutorial for that?

Copy this in Notepad (not Word):


<app_config>
<app>
<name>milkyway</name>
<gpu_versions>
<gpu_usage>0.5</gpu_usage>
<cpu_usage>0.05</cpu_usage>
</gpu_versions>
</app>
<app>
<name>milkyway_separation__modified_fit</name>
<gpu_versions>
<gpu_usage>0.5</gpu_usage>
<cpu_usage>0.05</cpu_usage>
</gpu_versions>
</app>
</app_config>


Save the file as "app-config.xml" and place the file here:
(Unhide your folders if you haven't already)
Program data\Boinc\Projects\MilkyWay
Restart Boinc and you'll be running two at a time.


I'm afraid that did nothing on neither my dual GPU machine nor my single GPU box. :( Not even after triple checking I'd followed the instructions.

So, having successfully (but unintentionally) 'hijacked' a thread, I'd like to try and return the focus to these fast work units.

These fast units, due to the standard GUI interface issues of the BOINC client, don't keep the GPU's busy enough. I've dropped from almost a million credits per 24 hours to 650k a day. I don't give a crap about the credits, the point is that these efficient fast WU's have resulted in almost a third less processing power, apparently.

Again, even my lowly 6 year old ATI HD4850 can crunch these WU's very quickly. And if it's possible from a computer science perspective, I think the project would better benefit from a denser, more prolonged set of WU's, that help to minimize/offset the 2-6 seconds of 'downtime' that occurs between WU's.
18) Message boards : News : New Modfit Runs (Message 62925)
Posted 1 Jan 2015 by 10esseeTony
Post:
....the runs might not fully utilize your GPU. ...try configuring your GPU to run 2 of these at the same time...

Jake


Uhm, is there a tutorial for that?
19) Message boards : News : New Modfit Runs (Message 62923)
Posted 1 Jan 2015 by 10esseeTony
Post:
I frequently run out of work for short periods of time when there's a high percentage of "fast" WUs.

My GPU goes through 2 of them in about 20 seconds.

Would it be possible to increase the amount of work done in the fast WUs, so that the required amount of communication with the server drops?



You may need to update/increase the "Minimum Work Buffer" under the Tools/Computing Preferences/Network settings tab. Add .5 to 1 day to whatever it currently is set at.
20) Message boards : News : New Modfit Runs (Message 62922)
Posted 1 Jan 2015 by 10esseeTony
Post:
My 7970 graphics cards can each tear through a "fast" workunit in 8-12 seconds, but then there is a 2-6 second pause while BOINC does whatever it does between workunits before the next one starts. This is highly inefficient from a processing point of view. Even my poor 6 year old Radeon HD4650 can crunch these units quickly (70 seconds).

WE NEED BIGGER WORKUNITS FOR GPU's.

WE NEED BIGGER WORKUNITS FOR GPU's.

WE NEED BIGGER WORKUNITS FOR GPU's.

That being said, de_nbody_08_05 has tied up 7 CPU cores for 37 hours. 8(




©2021 Astroinformatics Group