Hey guys,

I know a lot of people say to leave a core open for GPU computing, but I have to say that I've found that to not really have much of an effect on crunching speed and I'd rather have that core running POGS and have MW run a bit slower on my GPU since POGS is CPU only.

Now the problem is with .94 required cpu cores by default if I try to run Einstein on my iGPU which required .5 cpu cores it stops a POGS unit.

I'm sure there is a way to write an app_info file however it's been a while since I've done any crunching and don't remember for the life of me how to properly set one up.

So if anyone could suggest a guide or has a file for just ATI GPU tasks that I could modify it would be appreciated!

Hi Astromancer,

App_info is ye olde waye; these days it's possible to use an app_config.xml file in the project's data directory. Mine looks like this (under Windows, save as ANSI, not UTF):

<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>

On a HD7950, i5-3570, W7-64 bit, other BOINC tasks claiming the cpu, my run times are between 45 and 150 seconds, depending on application (modified fit or not).

Thanks Kwartet!

I'm not sure why they set the required cpus so high when the GPU app uses almost no CPU for this project.

This 270x I just got is disappointingly slow. I'm pretty sure my old 5870 crunched faster than the new card. But it's a gaming computer and it's better for gaming. I guess you win some and you lose some.

One other thing while I'm thinking of it. IIRC the updated apps hosted at Arkayn's site have been integrated into the project for some time so there is no need to get any op apps at this point?

Hi Astromancer,

App_info is ye olde waye; these days it's possible to use an app_config.xml file in the project's data directory. Mine looks like this (under Windows, save as ANSI, not UTF):

<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>

On a HD7950, i5-3570, W7-64 bit, other BOINC tasks claiming the cpu, my run times are between 45 and 150 seconds, depending on application (modified fit or not).

Is that 45 seconds the time it takes to process two work units, or individually (completionTime / concurrentTasks)? My Radeon HD 7950 on Arch Linux completes one every 20-22 seconds.

45 seconds is good for two wu's.

I get better results using 0.5 cpus per 0.5 gpus.... 32 per WU two at a time HD 5870

dunx

P.S. @ 88% CPU utillisation - too leave a spare "core" for the GPUs....

I do not understand what this means:

7-1-2015 6:23:35 | Milkyway@Home | Bericht van de server: ATI GPU R600 (R38xx) does not support OpenCL

7-1-2015 6:23:35 | Milkyway@Home | Bericht van de server: An ATI GPU supporting double precision math is required

Yet my computer, from 2008, does work for years
http://boincstats.com/signature/-1/user/181746/sig.png

I do not understand what this means:

7-1-2015 6:23:35 | Milkyway@Home | Bericht van de server: ATI GPU R600 (R38xx) does not support OpenCL

7-1-2015 6:23:35 | Milkyway@Home | Bericht van de server: An ATI GPU supporting double precision math is required

Yet my computer, from 2008, does work for years
http://boincstats.com/signature/-1/user/181746/sig.png

And it is STILL doing work, it's just the graphics card that doesn't meet the minimum standards here, your cpu is doing just fine.

What model is your GPU? It's possible that it is supported by other projects; Moo! and Collatz seem to have pretty good support for older cards.

---

Click here to see My Detailed BOINC Stats