OpenCL/GPU app?

Message boards : Number crunching : OpenCL/GPU app?
Message board moderation

To post messages, you must log in.

AuthorMessage
zombie67 [MM]
Avatar

Send message
Joined: 19 Aug 11
Posts: 31
Credit: 63,078,601
RAC: 27,106
Message 555 - Posted: 18 Mar 2012, 23:41:26 UTC

Any chance of an app for our GPUs? I know some math does not port well to GPUs. But maybe this one would?
Reno, NV
Team: SETI.USA
ID: 555 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile Eric Driver
Project administrator
Project developer
Project tester
Project scientist

Send message
Joined: 8 Jul 11
Posts: 1318
Credit: 403,802,678
RAC: 289,026
Message 557 - Posted: 19 Mar 2012, 1:45:50 UTC - in response to Message 555.  

Any chance of an app for our GPUs? I know some math does not port well to GPUs. But maybe this one would?


Greg and I discussed this a while back, and came to the conclusion that it might be possible but would require alot of work. We are using the pari/gp library to do the number theoretic calculations, and although this is open source code, it would require non-trivial modifications. We are also using the gmp library, which may not port well. But I am not an expert on GPUs, so maybe someone else can chime in here with some better insight.

Eric
ID: 557 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
frankhagen

Send message
Joined: 19 Aug 11
Posts: 76
Credit: 2,002,860
RAC: 0
Message 560 - Posted: 19 Mar 2012, 16:33:12 UTC - in response to Message 557.  

Any chance of an app for our GPUs? I know some math does not port well to GPUs. But maybe this one would?


Greg and I discussed this a while back, and came to the conclusion that it might be possible but would require alot of work. We are using the pari/gp library to do the number theoretic calculations, and although this is open source code, it would require non-trivial modifications. We are also using the gmp library, which may not port well. But I am not an expert on GPUs, so maybe someone else can chime in here with some better insight.



well, at least GMP-ECM has a working CUDA-branch, you don't happen to be using that lib?

primegrid recently started a world-record hunt for Generalized Fermat-primes using CUDA-apps. current runtimes are up into several days on fastest GPU's, but would take months most likely on current high-end CPU's.

that app allready owns the top 4 spots. ;)

ID: 560 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile Eric Driver
Project administrator
Project developer
Project tester
Project scientist

Send message
Joined: 8 Jul 11
Posts: 1318
Credit: 403,802,678
RAC: 289,026
Message 562 - Posted: 19 Mar 2012, 17:45:50 UTC - in response to Message 560.  


well, at least GMP-ECM has a working CUDA-branch, you don't happen to be using that lib?

primegrid recently started a world-record hunt for Generalized Fermat-primes using CUDA-apps. current runtimes are up into several days on fastest GPU's, but would take months most likely on current high-end CPU's.

that app allready owns the top 4 spots. ;)


No, we need the standard GMP. And even if GMP had cuda support, we still have the pari/gp library to deal with. We use pari for computing integral bases, checking irreducibility, computing field discriminants, and also factoring large integers. It's a large amount of code that would need to be "cudified". It would be a fun undertaking, if only I had the time.
ID: 562 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile Crunch3r
Avatar

Send message
Joined: 13 Sep 11
Posts: 5
Credit: 5,004,016
RAC: 0
Message 575 - Posted: 22 Mar 2012, 23:12:50 UTC - in response to Message 562.  


well, at least GMP-ECM has a working CUDA-branch, you don't happen to be using that lib?

primegrid recently started a world-record hunt for Generalized Fermat-primes using CUDA-apps. current runtimes are up into several days on fastest GPU's, but would take months most likely on current high-end CPU's.

that app allready owns the top 4 spots. ;)


No, we need the standard GMP. And even if GMP had cuda support, we still have the pari/gp library to deal with. We use pari for computing integral bases, checking irreducibility, computing field discriminants, and also factoring large integers. It's a large amount of code that would need to be "cudified". It would be a fun undertaking, if only I had the time.


Well... i'm not sure why you don't upload a copy of the code somewhere for users to have a look at it. Maybe one will have time to look at it an port it to use a GPU.

Actually, since you're using GPL'ed GMP and PARI, you'll have to release your source code upone request (cosider this post a request ;) ), or otherwhise you're violating GPL.

TIA
ID: 575 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile Eric Driver
Project administrator
Project developer
Project tester
Project scientist

Send message
Joined: 8 Jul 11
Posts: 1318
Credit: 403,802,678
RAC: 289,026
Message 577 - Posted: 22 Mar 2012, 23:57:22 UTC - in response to Message 575.  


Well... i'm not sure why you don't upload a copy of the code somewhere for users to have a look at it. Maybe one will have time to look at it an port it to use a GPU.

Actually, since you're using GPL'ed GMP and PARI, you'll have to release your source code upone request (cosider this post a request ;) ), or otherwhise you're violating GPL.

TIA


I may just do that. I'd like to clean it up first, before I open it up for the whole world to see. Maybe someone will even see a way to make it more efficient; after all I'm really a mathematician/engineer and not a programmer.
ID: 577 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile Greg Tucker
Project administrator
Project developer
Project tester

Send message
Joined: 8 Jul 11
Posts: 46
Credit: 7,144,042
RAC: 0
Message 579 - Posted: 23 Mar 2012, 16:00:18 UTC - in response to Message 575.  


well, at least GMP-ECM has a working CUDA-branch, you don't happen to be using that lib?

primegrid recently started a world-record hunt for Generalized Fermat-primes using CUDA-apps. current runtimes are up into several days on fastest GPU's, but would take months most likely on current high-end CPU's.

that app allready owns the top 4 spots. ;)


No, we need the standard GMP. And even if GMP had cuda support, we still have the pari/gp library to deal with. We use pari for computing integral bases, checking irreducibility, computing field discriminants, and also factoring large integers. It's a large amount of code that would need to be "cudified". It would be a fun undertaking, if only I had the time.


Well... i'm not sure why you don't upload a copy of the code somewhere for users to have a look at it. Maybe one will have time to look at it an port it to use a GPU.

Actually, since you're using GPL'ed GMP and PARI, you'll have to release your source code upone request (cosider this post a request ;) ), or otherwhise you're violating GPL.

TIA


You can link userspace apps to GPL libraries and not encumber under the GPL.

I'm all for posting the source though.

ID: 579 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
frankhagen

Send message
Joined: 19 Aug 11
Posts: 76
Credit: 2,002,860
RAC: 0
Message 580 - Posted: 23 Mar 2012, 18:50:20 UTC - in response to Message 579.  

I'm all for posting the source though.


where can i sign? ;)

ID: 580 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile Steve Hawker*

Send message
Joined: 1 Jul 12
Posts: 13
Credit: 2,099,843
RAC: 0
Message 694 - Posted: 19 Jul 2012, 1:31:07 UTC

Eric,

Any news on the GPU front? I would dearly love to have my GPU crunch away on this project.

S.
ID: 694 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile Eric Driver
Project administrator
Project developer
Project tester
Project scientist

Send message
Joined: 8 Jul 11
Posts: 1318
Credit: 403,802,678
RAC: 289,026
Message 695 - Posted: 19 Jul 2012, 4:13:20 UTC - in response to Message 694.  

Eric,

Any news on the GPU front? I would dearly love to have my GPU crunch away on this project.

S.


Well, it would be a ton of work and right now I just don't have the time. But I'll find some time this weekend to post the source code and see if any expert GPU programmers want to take a crack at it.
ID: 695 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Gandalf_the_Grey
Avatar

Send message
Joined: 3 May 13
Posts: 13
Credit: 102,701
RAC: 0
Message 824 - Posted: 4 May 2013, 3:25:11 UTC

Has anyone rethought the GPU tasking issue in the last year?

Thanks

ID: 824 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile Eric Driver
Project administrator
Project developer
Project tester
Project scientist

Send message
Joined: 8 Jul 11
Posts: 1318
Credit: 403,802,678
RAC: 289,026
Message 826 - Posted: 4 May 2013, 9:04:14 UTC - in response to Message 824.  

We had a volunteer named Erno who actually did the OpenCL port and got something working. If I recall, a portion of the computation was still being done on the cpu, and the overall speed improvement was something like 20%. We've been meaning to look at it some more to see if we could find ways to improve the speed.
ID: 826 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Gandalf_the_Grey
Avatar

Send message
Joined: 3 May 13
Posts: 13
Credit: 102,701
RAC: 0
Message 828 - Posted: 4 May 2013, 9:17:25 UTC - in response to Message 826.  
Last modified: 4 May 2013, 9:50:17 UTC

We had a volunteer named Erno who actually did the OpenCL port and got something working. If I recall, a portion of the computation was still being done on the cpu, and the overall speed improvement was something like 20%. We've been meaning to look at it some more to see if we could find ways to improve the speed.

With WCG's completion of their HCC1 project, crunchers will be looking for a home for their GPUs. A WU that can function with an app_config.xml configuration of 0.2C + 0.2ATI (as the Hcc1 did) would surely expedite the completion of your projects as well. It is my understanding that WCG realized their project's completion two or three years ahead of time. That fact by itself should stimulate the interest of any Project coordinator. I am not a programmer, but IMO the GPU trick is to keep the WUs small.

Respectfully,
Gandalf
ID: 828 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile Aurel
Avatar

Send message
Joined: 25 Feb 13
Posts: 216
Credit: 9,899,302
RAC: 0
Message 985 - Posted: 15 Mar 2014, 15:08:49 UTC - in response to Message 828.  
Last modified: 15 Mar 2014, 15:10:40 UTC

Hi Eric,

Any news on the GPU front? I found this:http://geraldine.fjfi.cvut.cz/mmg/index.php?page=cuda

CUDA-expert from the "Department of Mathematics at the Czech Technical University in Prague" can help us. They have an CUDA-Research-Center.

The group-site by NVIDIA: http://research.nvidia.com/content/ctu-crc-summary
Take a look at it, if you want help. ;)
I think they will help this project.
ID: 985 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile Eric Driver
Project administrator
Project developer
Project tester
Project scientist

Send message
Joined: 8 Jul 11
Posts: 1318
Credit: 403,802,678
RAC: 289,026
Message 986 - Posted: 15 Mar 2014, 16:04:34 UTC - in response to Message 985.  

Hi Eric,

Any news on the GPU front? I found this:http://geraldine.fjfi.cvut.cz/mmg/index.php?page=cuda

CUDA-expert from the "Department of Mathematics at the Czech Technical University in Prague" can help us. They have an CUDA-Research-Center.

The group-site by NVIDIA: http://research.nvidia.com/content/ctu-crc-summary
Take a look at it, if you want help. ;)
I think they will help this project.


Hi Aurel,

Sorry, no news. I've just been too busy to take a look at it. A while back, one of our volunteers (Erno) got something that worked but it offered little speed improvement. If I recall, some of the number field calculations were still being done on the cpu side due to the complication of CUDA-fying the pari libraries.

When I get a chance later, I will take a look at the link. Thanks!
ID: 986 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile Crunch3r
Avatar

Send message
Joined: 13 Sep 11
Posts: 5
Credit: 5,004,016
RAC: 0
Message 998 - Posted: 8 Apr 2014, 17:03:39 UTC - in response to Message 986.  

... A while back, one of our volunteers (Erno) got something that worked but it offered little speed improvement. ...


How about realeasing the apps source for the CPU app ?

ID: 998 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile Aurel
Avatar

Send message
Joined: 25 Feb 13
Posts: 216
Credit: 9,899,302
RAC: 0
Message 999 - Posted: 8 Apr 2014, 19:39:32 UTC

Hi all,

I was today an the Hannover Fair 2014. I meet some interesting persons, I´ll explain it on a single thread. ;)

To the GPU_App:

We all know, MATLAB supports GPU_Computing and Pari not. [Thats the problem...]
We only need an little part from the MATLAB-programm, the mathematical part. With look I´ll become an one-year-testing-lizenz for COMSOL.
[COSMOL is an physical_mathematical computing programm; one lizenz costs ~50.000€] COMSOL is written in C++ and a little bit Java. [I understand C++] I can copy the code and write an single version.

Some other ways? Yes. Using "R". [An spezial programming language] No experince about "R", but I have an open-source programm for "R". [I don´t know who to programm it...]

Thats just some small informations. My test-version will come in 2-3 weeks. ;)

Greets,
Aurel
ID: 999 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile Crunch3r
Avatar

Send message
Joined: 13 Sep 11
Posts: 5
Credit: 5,004,016
RAC: 0
Message 1005 - Posted: 12 Apr 2014, 18:58:46 UTC - in response to Message 999.  

Hi all,

I was today an the Hannover Fair 2014. I meet some interesting persons, I´ll explain it on a single thread. ;)

To the GPU_App:

We all know, MATLAB supports GPU_Computing and Pari not. [Thats the problem...]
We only need an little part from the MATLAB-programm, the mathematical part. With look I´ll become an one-year-testing-lizenz for COMSOL.
[COSMOL is an physical_mathematical computing programm; one lizenz costs ~50.000€] COMSOL is written in C++ and a little bit Java. [I understand C++] I can copy the code and write an single version.

Some other ways? Yes. Using "R". [An spezial programming language] No experince about "R", but I have an open-source programm for "R". [I don´t know who to programm it...]

Thats just some small informations. My test-version will come in 2-3 weeks. ;)

Greets,
Aurel


I don't care about Pari NOR MATLAB at ALL!
I just need the source code of the cpu app that's all..


ID: 1005 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile Aurel
Avatar

Send message
Joined: 25 Feb 13
Posts: 216
Credit: 9,899,302
RAC: 0
Message 1006 - Posted: 12 Apr 2014, 21:02:59 UTC - in response to Message 1005.  

Hi Crunch3r,

please read the PM I´ve written to you. ;)

Pari has an compilation problem, they can´t fix it. This problem is only at Windows OS. I don´t know, if an GPU-App would run with an Pari libary.
ID: 1006 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile Crunch3r
Avatar

Send message
Joined: 13 Sep 11
Posts: 5
Credit: 5,004,016
RAC: 0
Message 1021 - Posted: 25 Apr 2014, 18:52:23 UTC - in response to Message 1006.  
Last modified: 25 Apr 2014, 18:53:10 UTC

Hi Crunch3r,

please read the PM I´ve written to you. ;)

Pari has an compilation problem, they can´t fix it. This problem is only at Windows OS. I don´t know, if an GPU-App would run with an Pari libary.


Yes, that's caused by some stupid pointer arithmetic...
Ten years ago that was a common issue, but the NumberFields app tops it,with what i'd call "code retards in practice"....

Anyway, i have not had the time to fix this garbage code(getting rid of the pari crap etc.)...

Had to fix DistRTGens OCL MD5 code for my own AMD GPUs first...(Yes, credits matter to me!!! Fuck yourself, science whores!!!)

Soooooo... to be continued.
ID: 1021 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote

Message boards : Number crunching : OpenCL/GPU app?


Main page · Your account · Message boards


Copyright © 2024 Arizona State University