i'm assuming that reducing "CPU consumption per GPU task" is one of the developers' goals in the attempt to get this app on par w/ the CUDA app? IIRC, BRP4 CUDA tasks only use 0.2 CPUs each...
Excellent news. My 7870 on my new system and my 5770 on my old system are currently crunching away. I haven't reduced core usage, but then for heat/noise reasons I don't let any projects use more than about 40% total CPU (doing that leaves all my fans turning at minimal RPMs which is good). We'll see if I have any issues once a unit is completed but so far so good. It doesn't seem to be quite as efficient as the crunching my work laptop with an NVidia 4200 is doing, but that's at first blush and as you said this is an initial release.
I'm just happy that my GPU can help with the work.
May be it is wrong, but i dont see opencl.dll in windows\system32 after installing Catalyst 12.4 from amd site.
no opencl.dll - no open cl :)
No capable GPU - from Boinc.
Got 12.4's installed actually from ATI/AMD, clean installed after using Driver Sweep, and I do have amdocl64.dll, amdoclcl64.dll and opencl.dll in C:\Windows\system32\
If you're using Windows installed drivers, these won't have it.
If you're using PC manufacturer drivers, it's possible these won't have it.
You do need AMD drivers. And those for 64bit Windows 7 and Vista do have:
[pre] Display Driver
OpenCL(tm) Driver
AMD Integrated Driver
Catalyst Control Center
[/pre]
By the way, at this time of writing, the BOINC domain is down. I have flagged it with Dave, although he'll probably knew already. If they can't do anything about it until someone's in the office, it'll take well into the day (here) before that's fixed, estimate 3pm at the least and don't hold me on to that. It's California time you have to work with and we don't know what caused the outage, other than that it appears someone forgot to pay their electricity bill. ;-)
It's too bad that neither WCG nor Einstein kept their mirror of the download link up to date. Now no one can download .27 or .28 :-(
i'm assuming that reducing "CPU consumption per GPU task" is one of the developers' goals in the attempt to get this app on par w/ the CUDA app? IIRC, BRP4 CUDA tasks only use 0.2 CPUs each...
Background:
In principle that's correct. However, large parts of the CPU efficiency are contributed by the GPU driver and the way it yields CPU resources to the OS (other processes) while doing GPU computations. Bottom line, you should probably never compare CUDA/NVIDIA to OpenCL/ATI directly. The same applies to comparing actual performance since NVIDIA and ATI GPUs have significantly different architectures. Another reason is that according our experiences so far, ATI GPUs cover a much wider range in relative performance than NVIDIA GPUs. So your mileage may vary significantly compared to other volunteers, depending on the actual ATI GPU model you use.
Some of the improvements we have in our pipeline will be applied to the CUDA and to the OpenCL apps, some are only applicable to one of the two. OpenCL on Intel/AMD many-core CPU will be yet another story...
I'm experiencing the same problem I had over @Albert:
Some artifacts appear on screen during the initial start-up phase.
The WU continue crunching, finished & reported.
@terencewee*:
You're using Catalyst 11.11 which is reasonably outdated. I highly recommend you update the Catalyst GPU driver to the latest version (at least 12.x) as stated in the first post of this thread.
Greetings
)
Greetings Oliver
Congratulations on this major achievement, I can now GPU crunch for Einstein. Have successfully crunched the following workunits
http://einsteinathome.org/workunit/123076333
http://einsteinathome.org/workunit/123232447
Using the following system setup
Intel Quad 8400, Win7 x64, Boinc 7.0.27 Catalyst 12.4. HD 5850 GPU Card
I am running 3 CPU YOYO workunits and 1 free core for two GPU tasks of Einstein, as they are using 0.5 cpu each.
Regards
Tazzduke
i'm assuming that reducing
)
i'm assuming that reducing "CPU consumption per GPU task" is one of the developers' goals in the attempt to get this app on par w/ the CUDA app? IIRC, BRP4 CUDA tasks only use 0.2 CPUs each...
I am running an ATI Radeon HD
)
I am running an ATI Radeon HD 3400 Series. Will this work?
It requires OpenCL 1.1, which
)
It requires OpenCL 1.1, which was introduced with HD 5000 series for Radeons, so no.
Soli Deo Gloria
Excellent news. My 7870 on
)
Excellent news. My 7870 on my new system and my 5770 on my old system are currently crunching away. I haven't reduced core usage, but then for heat/noise reasons I don't let any projects use more than about 40% total CPU (doing that leaves all my fans turning at minimal RPMs which is good). We'll see if I have any issues once a unit is completed but so far so good. It doesn't seem to be quite as efficient as the crunching my work laptop with an NVidia 4200 is doing, but that's at first blush and as you said this is an initial release.
I'm just happy that my GPU can help with the work.
RE: May be it is wrong, but
)
Got 12.4's installed actually from ATI/AMD, clean installed after using Driver Sweep, and I do have amdocl64.dll, amdoclcl64.dll and opencl.dll in C:\Windows\system32\
If you're using Windows installed drivers, these won't have it.
If you're using PC manufacturer drivers, it's possible these won't have it.
You do need AMD drivers. And those for 64bit Windows 7 and Vista do have:
[pre] Display Driver
OpenCL(tm) Driver
AMD Integrated Driver
Catalyst Control Center
[/pre]
By the way, at this time of writing, the BOINC domain is down. I have flagged it with Dave, although he'll probably knew already. If they can't do anything about it until someone's in the office, it'll take well into the day (here) before that's fixed, estimate 3pm at the least and don't hold me on to that. It's California time you have to work with and we don't know what caused the outage, other than that it appears someone forgot to pay their electricity bill. ;-)
It's too bad that neither WCG nor Einstein kept their mirror of the download link up to date. Now no one can download .27 or .28 :-(
Hey
)
Hey Gaurav!
The sched log says you're running 7.0.26 but we won't ship tasks for that version. Please make sure you really run 7.0.27.
Cheers,
Oliver
Einstein@Home Project
RE: i'm assuming that
)
Background:
In principle that's correct. However, large parts of the CPU efficiency are contributed by the GPU driver and the way it yields CPU resources to the OS (other processes) while doing GPU computations. Bottom line, you should probably never compare CUDA/NVIDIA to OpenCL/ATI directly. The same applies to comparing actual performance since NVIDIA and ATI GPUs have significantly different architectures. Another reason is that according our experiences so far, ATI GPUs cover a much wider range in relative performance than NVIDIA GPUs. So your mileage may vary significantly compared to other volunteers, depending on the actual ATI GPU model you use.
Some of the improvements we have in our pipeline will be applied to the CUDA and to the OpenCL apps, some are only applicable to one of the two. OpenCL on Intel/AMD many-core CPU will be yet another story...
Best,
Oliver
Einstein@Home Project
Oliver, I'm experiencing
)
Oliver,
I'm experiencing the same problem I had over @Albert:
Some artifacts appear on screen during the initial start-up phase.
The WU continue crunching, finished & reported.
But, the WU is flagged as validate error.
I had reported the same over @Albert (May-1st), but so far no response.
This mobile workstation crunched OpenCL WUs for SET AP/MB, DRTG, POEM++, PrimGrid and WCG (hcc-beta) all without any problems.
It had been crunching x3 POEM WUs at a time over past 2+ months without a single invalid WU. Host details @POEM.
Please, can you or anyone help me?
Thanks.
terencewee*
Sicituradastra.
@terencewee*: You're using
)
@terencewee*:
You're using Catalyst 11.11 which is reasonably outdated. I highly recommend you update the Catalyst GPU driver to the latest version (at least 12.x) as stated in the first post of this thread.
Hope this helps,
Oliver
Einstein@Home Project