Yeah hopefully within the next week or two we'll have an alpha CUDA application for you guys to crash :D

Well, I have one GTX 280 and 2 GTX 295s ... start your engines ...

Of course we will need a setting on the site to get only CPU work, only CUDA work ... or both ...

It's effectively important to have both options.

I'm hoping that eventually we can get an OpenCL implementation that will work on both ATI and Nvidia cards... we'll see how that whole thing pans out :P

---

My HD4830 times have been going up steadily in the last day or so. Running almost 30 seconds now.

My HD4830 times have been going up steadily in the last day or so. Running almost 30 seconds now.

There are quite some dual stream work units out there. They take about 50% longer but are also giving 50% more credits (~ 18.5 credits).
I would say your crunch times appear to be completely okay.

Awesome, thank you for all your help.

Earlier you mentioned leaving the max_ncpus at 1, is there any harm in having it higher? I set it back to 5 and the times are immediately back to 2-3 seconds. Just bad timing I suppose, or could it be bottlenecked and needing some extra CPU power?

Awesome, thank you for all your help.

Earlier you mentioned leaving the max_ncpus at 1, is there any harm in having it higher? I set it back to 5 and the times are immediately back to 2-3 seconds. Just bad timing I suppose, or could it be bottlenecked and needing some extra CPU power?

It won't help as the MW app is single threaded and it may have the negative side effect of blocking other applications to run concurrently. So I would leave it at 1.
And don't take the CPU time you see too serious. Now, with the disappered credit limit it doesn't matter anyhow. The important thing is just the throughput, i.e. how many WUs are you crunching per minute/hour/day wall clock time.

How big of an impact does amount of memory on the card (ie 512MB vs 1GB 4870) have on crunch times?

How big of an impact does amount of memory on the card (ie 512MB vs 1GB 4870) have on crunch times?

None.
Also the speed of the memory does not have a pronounced effect (cache hit rates are quite high). The advantage of a HD4870 compared to a HD4850 stems only from the higher clockrate (+20%). The almost doubled memory bandwidth of the HD4870 (GDDR5 vs GDDR3) does not help in case of MW. The algorithm is dominated by computations, not memory accesses. One has only one memory access every eleven instructions or so. And as most of these accesses can be cached quite well it doesn't need much memory bandwidth. Actually it is the same behaviour as one sees with the CPU version.

More memory on the card would only enable the possibility to crunch more WUs concurrently (think of 30+ on a 1 GB card). But as more WUs in flight does not help the througput, it is only an esoterical advantage.

How big of an impact does amount of memory on the card (ie 512MB vs 1GB 4870) have on crunch times?

None.
Also the speed of the memory does not have a pronounced effect (cache hit rates are quite high). The advantage of a HD4870 compared to a HD4850 stems only from the higher clockrate (+20%). The almost doubled memory bandwidth of the HD4870 (GDDR5 vs GDDR3) does not help in case of MW. The algorithm is dominated by computations, not memory accesses. One has only one memory access every eleven instructions or so. And as most of these accesses can be cached quite well it doesn't need much memory bandwidth. Actually it is the same behaviour as one sees with the CPU version.

More memory on the card would only enable the possibility to crunch more WUs concurrently (think of 30+ on a 1 GB card). But as more WUs in flight does not help the througput, it is only an esoterical advantage.

Interesting- thanks for that info... ummm, 32 bit XP version in the works?? ;)

32 bit XP version in the works?? ;)

Will be the next thing I do.
It's now a higher priority than to fiddle around with multi GPU or linux support.

Regarding Multi-GPU: does that mean that at the moment you can run only GPU or only one card per PC ? What should one look for: an 4870X2 or an 4870 ?

Regarding Multi-GPU: does that mean that at the moment you can run only GPU or only one card per PC ? What should one look for: an 4870X2 or an 4870 ?

In the moment it uses only one GPU per machine. I hope I can extend it to arbitrary values in the future. Just have to find some time (and two cards to test) for it ;)

Thanx, that did save me some money... :)

I noticed something strange of the website (zslip.com) : the link for the ATI GPU app is labeled "Windows optimized apps (0.17 - latest, cuda)".

Cuda ?

---

Star Wars BOINC Team

I noticed something strange of the website (zslip.com) : the link for the ATI GPU app is labeled "Windows optimized apps (0.17 - latest, cuda)".

Cuda ?

I guess nvidias marketing has done its job ;)

I noticed something strange of the website (zslip.com) : the link for the ATI GPU app is labeled "Windows optimized apps (0.17 - latest, cuda)".

Cuda ?

I guess nvidias marketing has done its job ;)

lol. They probably want to change that :)

---

So is there currently a WU/credit limit on the GPU app, and if so, what is it?

I noticed something strange of the website (zslip.com) : the link for the ATI GPU app is labeled "Windows optimized apps (0.17 - latest, cuda)".

Cuda ?

I guess nvidias marketing has done its job ;)

lol. They probably want to change that :)

Haha, sorry about that. I'll get it changed later today when I can get to the site(s). I meant to put 'gpu' not 'cuda'.

---

I noticed something strange of the website (zslip.com) : the link for the ATI GPU app is labeled "Windows optimized apps (0.17 - latest, cuda)".

Cuda ?

I guess nvidias marketing has done its job ;)

lol. They probably want to change that :)

Haha, sorry about that. I'll get it changed later today when I can get to the site(s). I meant to put 'gpu' not 'cuda'.

Might want to put ATI because I think it will only work for certain ATI cards. You might want to mention which ones as well.

---

I noticed something strange of the website (zslip.com) : the link for the ATI GPU app is labeled "Windows optimized apps (0.17 - latest, cuda)".

Cuda ?

I guess nvidias marketing has done its job ;)

lol. They probably want to change that :)

Haha, sorry about that. I'll get it changed later today when I can get to the site(s). I meant to put 'gpu' not 'cuda'.

Might want to put ATI because I think it will only work for certain ATI cards. You might want to mention which ones as well.

Yes, you are right. It needs to be differentiated from the 'general' Windows versions. I'll probably put the whole info; Windows optimized apps (0.17 - latest, Win64 GPU app for ATI HD38x0 or HD48x0 card and Catalyst 8.12 or 9.1 driver)

---

It's my personal opinion, but I think that a full list of compatible GPUs might be great, because I can read here and there some questions about the compatibility of cards. Maybe the label "HD38x0 or HD48x0" isn't clear for all people. Maybe something like this :

Compatible Cards :

- ATI Radeon HD 3840
- ATI Radeon HD 4850
- ATI Radeon HD 4870

Cluster > do not be offensed by my next question : do you want a simple html/css code to present your different pages ? With some nice tables, colors, etc. ?

---

Star Wars BOINC Team