PDA

View Full Version : ATI GPU2 Client limited to only 320 shaders?


wingless
02-01-09, 03:00 PM
Apparently current GPU2 WUs just happen to be fast on Nvidia's less complex hardware at the moment. ATI GPUs are currently heavily limited in performance, all according to this guy from TR:

Okay about ATI Vs. Nvidia.

For low end cards, get Nvidia, they definitely out do anything that is currently offered by ATI, mainly because they aren't much improvement compared to the 3850 which is used for benchmarking, and thus sit around the 1.5k ppd area.

However, if you did have the money, it might be best to think twice about choosing Nvidia over ATI. Sure the GTX 260 gets 7-9k ppd, and the HD 4870 only gets 4-5k, but its important to understand how points are assigned.

The benchmark machine is a Radeon HD 3850, points are determined so that no matter what WU the 3850 does, it will get 1.5k ppd per day. For instance all those 511 point WU's the 3850 will do three per day or so. Pretty basic, yes?

Now, Nvidia does well because the current range of WU's are in-efficient on ATI gpus. All gpu work units are very small at the moment, (You know how when you select WU size, you have the option of small, medium, or large? There only are small WU's and a few medium ones out yet) this is due to the GPU client still being early days. So Nvidia cards are essentially optimized for this kind of WU, they have a smaller amount of fast shaders. This is compounded by the fact that the ATI client has huge in-efficiencies so that it can't use any more shaders than were on the HD 3870.

So where am I going with this.

1. Once larger WUs are released, ATI gpus will do much better as they are more suited to this with the greater amount of shaders. Nvidia gpus will actually slow down and earn less points because the benchmark 3850 will do better.
2. The ATI client still has a lot of optimization to do. I have a HD 4870, its ppd has gone from around 3k to about 5k with the newest client and the largest WU. CPU usage has dropped from maxing out a core to using only 25%. Nvidia has already done pretty much all the optimization they can do client wise. (Remember how much they marketed CUDA with folding, they put in a lot more effort than ATI did with folding) Basically this is the idea, the HD 4870 has 800 shader processors, the HD 3870 has only 320. Thats about 2.5k performance if it can all be accessed. So do the math, 4 or 5 times 2.5 is 10-12.5k ppd! Of course this is over optimistic but it obviously shows there is more power in the HD 4870 for folding than is recognized.
3. Theoretically ATI gpus have much greater number crunching power, 1.2 t flops for the 4870, compared to 500-600 g flops for the GTX 260-280.

Thats about it, now all we have to do is wait for new ATI clients to get their job done...

Since you OCF boys seem to be "in-the-know", are these statements truthful? Are ATI GPUs that highly underutilized with the current client (Only 320 of my 800 shaders being use)?!

Honestly, this would explain the tiny increase in PPD going from my 2900XT to a 4870. If anything that is proof that something is unoptimized right now in the ATI client.

the_cultie
02-01-09, 04:06 PM
I can't say yes this is true but it sounds very plausible. Hopefully GPU2 will get optimized for ATi and we can see some real folding from them :)

Burninate35
02-01-09, 04:14 PM
I do not agree, let me explain my understanding of this.

All of Nvidias stream processors can be assigned to any task. Most of ati's stream processors can only do specific tasks. I think it is 1 out of every 5 stream processor on an ati card is like nvidias stream processors.

I think this is why nvidia cards are so much quicker.

Also this would explain why even though many ATI cards have way more stream processors than nvida cards, nvidia cards outperform then in F@H.

I remember reading this somewhere. It could be totally wrong though...

wingless
02-01-09, 11:24 PM
http://foldingforum.org/viewtopic.php?f=51&t=8245&p=81548#p81548

Mike Houston gave us some clarification over at the F@H forums. Us ATI boys are in for some serious performance, when they eventually get around to optimizing for the 4XXX series....

orion456
02-02-09, 12:31 AM
[QUOTE=wingless;5967531Us ATI boys are in for some serious performance, when they eventually [/QUOTE]

IF...is the operative word. I sure wouldn't go with ATI again unless they actually produce some performance better than NVidia.

Firestrider
02-06-09, 12:37 AM
I say we better get an improved core/driver by Q1'09. We have been promised this too long, and the only way AMD can show the true power of "Stream" is by demonstrating it with Folding@home. People would then get more interested and make GPU applications for other things (BOINC clients are largely CUDA now)

Mr.Guvernment
02-06-09, 01:09 AM
has been some time since they said they had / were, to optmize the ATI clients, so long so i am losing hope.

WonderingSoul
02-06-09, 06:34 AM
This is true. I have a HD4870 and I can get maybe 3k a day, no matter the WU. My 8800GTs can get anywhere from 3.5-6k a day.

It needs to be optimized.