next contest?
  1 / 2    
When will the next contest be posted? I'm eager to work on it. B)
When will the next contest be posted? I'm eager to work on it. B)

#1
Posted 08/11/2008 07:48 PM   
[quote name='dpemmons' date='Aug 11 2008, 03:48 PM']When will the next contest be posted? I'm eager to work on it.  B)
[right][snapback]423958[/snapback][/right]
[/quote]
Yeah a contest sounds cool. Were there any before?
[quote name='dpemmons' date='Aug 11 2008, 03:48 PM']When will the next contest be posted? I'm eager to work on it.  B)

[snapback]423958[/snapback]




Yeah a contest sounds cool. Were there any before?

#2
Posted 08/14/2008 02:14 AM   
[quote name='alex_dubinsky' date='Aug 13 2008, 07:14 PM']Yeah a contest sounds cool. Were there any before?
[right][snapback]425306[/snapback][/right]
[/quote]
[url="http://cudacontest.nvidia.com/"]http://cudacontest.nvidia.com/[/url]

We're working on some more, and hopefully we'll have an update in the next few days.
[quote name='alex_dubinsky' date='Aug 13 2008, 07:14 PM']Yeah a contest sounds cool. Were there any before?

[snapback]425306[/snapback]




http://cudacontest.nvidia.com/



We're working on some more, and hopefully we'll have an update in the next few days.

#3
Posted 08/14/2008 03:31 AM   
[quote name='tmurray' date='Aug 13 2008, 10:31 PM'][url="http://cudacontest.nvidia.com/"]http://cudacontest.nvidia.com/[/url]

We're working on some more, and hopefully we'll have an update in the next few days.
[right][snapback]425324[/snapback][/right]
[/quote]

Any news?
[quote name='tmurray' date='Aug 13 2008, 10:31 PM']http://cudacontest.nvidia.com/



We're working on some more, and hopefully we'll have an update in the next few days.

[snapback]425324[/snapback]






Any news?

#4
Posted 08/20/2008 04:27 PM   
[quote name='tmurray' date='Aug 14 2008, 12:31 AM'][url="http://cudacontest.nvidia.com/"]http://cudacontest.nvidia.com/[/url]

We're working on some more, and hopefully we'll have an update in the next few days.
[right][snapback]425324[/snapback][/right]
[/quote]

Aren't old contests available somewhere?

Thanks
[quote name='tmurray' date='Aug 14 2008, 12:31 AM']http://cudacontest.nvidia.com/



We're working on some more, and hopefully we'll have an update in the next few days.

[snapback]425324[/snapback]






Aren't old contests available somewhere?



Thanks

#5
Posted 08/20/2008 06:24 PM   
A contest on x264 CUDA patch maybe great :)
A contest on x264 CUDA patch maybe great :)

#6
Posted 08/29/2008 03:11 AM   
[quote name='cho' date='Aug 28 2008, 07:11 PM']A contest on x264 CUDA patch maybe great :)
[right][snapback]432532[/snapback][/right]
[/quote]

Hmm, I think optimizing codecs is way too specialized to attract a general public. It requires previous experience in the field to have any chance of winning.

My recommendation: Find something that is more attractive to a wider audience.
[quote name='cho' date='Aug 28 2008, 07:11 PM']A contest on x264 CUDA patch maybe great :)

[snapback]432532[/snapback]






Hmm, I think optimizing codecs is way too specialized to attract a general public. It requires previous experience in the field to have any chance of winning.



My recommendation: Find something that is more attractive to a wider audience.

#7
Posted 08/29/2008 09:31 AM   
I posted this in the general forum:
[url="http://forums.nvidia.com/index.php?showtopic=76296&view=getnewpost"]http://forums.nvidia.com/index.php?showtop...view=getnewpost[/url]

Maybe this would be a good contest idea? (It's a post about the MusicBrainz/MusicDNS service, if you don't want to follow the link).

I've also been looking at the GASS .NET bindings for CUDA; they're pretty useful, but a bit...unpolished. I would like to see someone come up with a .NET binding for CUDA that actually fits into the style of the .NET framework, or better yet, come up with a generic interface for doing FFT and Linear-algebra type work, then implement the interface with the CUDA bindings.
I posted this in the general forum:

http://forums.nvidia.com/index.php?showtop...view=getnewpost



Maybe this would be a good contest idea? (It's a post about the MusicBrainz/MusicDNS service, if you don't want to follow the link).



I've also been looking at the GASS .NET bindings for CUDA; they're pretty useful, but a bit...unpolished. I would like to see someone come up with a .NET binding for CUDA that actually fits into the style of the .NET framework, or better yet, come up with a generic interface for doing FFT and Linear-algebra type work, then implement the interface with the CUDA bindings.

GPU.NET: Write your GPU code in 100% pure C#.

Learn more at tidepowerd.com, and download a free 30-day trial of GPU.NET. Follow @tidepowerd for release updates.



GPU.NET example projects

#8
Posted 08/31/2008 02:53 PM   
[quote name='tmurray' date='Aug 13 2008, 10:31 PM'][url="http://cudacontest.nvidia.com/"]http://cudacontest.nvidia.com/[/url]

We're working on some more, and hopefully we'll have an update in the next few days.
[right][snapback]425324[/snapback][/right]
[/quote]

Any updates? It's been a a couple days + weeks and still no word. :(
[quote name='tmurray' date='Aug 13 2008, 10:31 PM']http://cudacontest.nvidia.com/



We're working on some more, and hopefully we'll have an update in the next few days.

[snapback]425324[/snapback]






Any updates? It's been a a couple days + weeks and still no word. :(

#9
Posted 10/02/2008 05:56 AM   
For the next contest, I would like to formally request improving [url="http://www.google.com/search?hl=en&q=libpoker-eval"]libpoker-eval[/url]



/devil.gif' class='bbc_emoticon' alt=':devil:' />
For the next contest, I would like to formally request improving libpoker-eval







/devil.gif' class='bbc_emoticon' alt=':devil:' />

#10
Posted 10/03/2008 09:23 AM   
[quote name='koderpat' date='Oct 3 2008, 01:23 AM']For the next contest, I would like to formally request improving [url="http://www.google.com/search?hl=en&q=libpoker-eval"]libpoker-eval[/url]
/devil.gif' class='bbc_emoticon' alt=':devil:' />
[right][snapback]447216[/snapback][/right]
[/quote]

What makes this library interesting, important, or practical for CUDA implementation?
[quote name='koderpat' date='Oct 3 2008, 01:23 AM']For the next contest, I would like to formally request improving libpoker-eval

/devil.gif' class='bbc_emoticon' alt=':devil:' />

[snapback]447216[/snapback]






What makes this library interesting, important, or practical for CUDA implementation?

#11
Posted 10/04/2008 03:56 AM   
/devil.gif' class='bbc_emoticon' alt=':devil:' /> -- This says it all.
/devil.gif' class='bbc_emoticon' alt=':devil:' /> -- This says it all.

Ignorance Rules; Knowledge Liberates!

#12
Posted 11/03/2008 07:49 AM   
Any update on if/when there will be another contest? How about something to go along with the launch of CUDA 2.1?
Any update on if/when there will be another contest? How about something to go along with the launch of CUDA 2.1?

GPU.NET: Write your GPU code in 100% pure C#.

Learn more at tidepowerd.com, and download a free 30-day trial of GPU.NET. Follow @tidepowerd for release updates.



GPU.NET example projects

#13
Posted 12/01/2008 08:31 PM   
Wait, why can't we just make our own contest?

We can even [size=1]make it interesting throw some money down[/size].

We can think of some good challenges, and I'm sure some us would thoroughly enjoy a competition against fellow forum members.

[spoiler]P.S. NVIDIA probably is still pissed off that in the last contest two people submitted working code. And one of them had to get $5,000. Of course, what'd NVIDIA expect? Encoding MP3s is hard. The kind of hard that's a lot of work, not the kind that's a lot of thinking.[/spoiler]
Wait, why can't we just make our own contest?



We can even make it interesting throw some money down.



We can think of some good challenges, and I'm sure some us would thoroughly enjoy a competition against fellow forum members.



[spoiler]P.S. NVIDIA probably is still pissed off that in the last contest two people submitted working code. And one of them had to get $5,000. Of course, what'd NVIDIA expect? Encoding MP3s is hard. The kind of hard that's a lot of work, not the kind that's a lot of thinking.[/spoiler]

#14
Posted 12/05/2008 03:37 AM   
[quote name='alex_dubinsky' post='472604' date='Dec 4 2008, 08:37 PM']Wait, why can't we just make our own contest?

We can think of some good challenges, and I'm sure some us would thoroughly enjoy a competition against fellow forum members.[/quote]

Actually that's not a bad idea!
Though ideally the actual task should be something small and interesting. Some big huge app is a daunting job, but a small 2-hour side project might get more people to dabble. Ideally there would be a working starting project, similar to the SDK examples, with a "gold" compute to verify correctness, and the goal is to make it faster.

Here's a idea for a contest that's easy to specify, easy to solve, but quite interesting to optimize, and in fact quite hard to perfect: binning.
You have an unsorted list of 5M points. Each point has an XY integer coordinate from 0 to 100. There are therefore 100*100 =10000 possible coordinates. You know that no coordinate has more than 1000 points with that value.
The task: Bin the points into 10000 lists, one list for each coordinate. Do it quickly.

This task is easy to write in just a few lines of code by using global atomics.. but that solution is painfully slow. You can come up with many, many alternatives, but the fastest solution is unclear. So the task is easy to understand.. but actual fast implementation is tricky!
And the question has quite important applications, for example in [url="http://www.ameslab.gov/hoomd/"]HOOMD [/url]where atoms get binned as an important step in neighbor finding.
[quote name='alex_dubinsky' post='472604' date='Dec 4 2008, 08:37 PM']Wait, why can't we just make our own contest?



We can think of some good challenges, and I'm sure some us would thoroughly enjoy a competition against fellow forum members.



Actually that's not a bad idea!

Though ideally the actual task should be something small and interesting. Some big huge app is a daunting job, but a small 2-hour side project might get more people to dabble. Ideally there would be a working starting project, similar to the SDK examples, with a "gold" compute to verify correctness, and the goal is to make it faster.



Here's a idea for a contest that's easy to specify, easy to solve, but quite interesting to optimize, and in fact quite hard to perfect: binning.

You have an unsorted list of 5M points. Each point has an XY integer coordinate from 0 to 100. There are therefore 100*100 =10000 possible coordinates. You know that no coordinate has more than 1000 points with that value.

The task: Bin the points into 10000 lists, one list for each coordinate. Do it quickly.



This task is easy to write in just a few lines of code by using global atomics.. but that solution is painfully slow. You can come up with many, many alternatives, but the fastest solution is unclear. So the task is easy to understand.. but actual fast implementation is tricky!

And the question has quite important applications, for example in HOOMD where atoms get binned as an important step in neighbor finding.

#15
Posted 12/06/2008 12:17 PM   
  1 / 2    
Scroll To Top