Hello,

i just wondered about the GPU list: http://setiathome.berkeley.edu/gpu_list.php

For example: The GTX 570 is better than an GTX 580. But WHY??
The GTX 570 got 480 CUDA Cores. The GTX 580 got 512?
Can somebody explain on which detail i have to look for?
Which constellation on a GPU is needed that it will work fast?
Cuda Cores / Graphics Clock / Processor Clock ... etc.

Hope to get an answer soon!
Thanks for helping me so far!

---

Not saying I am an expert, but it looks like the GPU list is outdated since it doesn't have any of the new Kepler GPU's. Generally, the more CUDA cores a GPU has, the more work it can do. So, the GTX580 will perform marginally better than the GTX 570. Also, memory bandwidth can make some small but measurable difference so a card with a 384 or 256 bit memory bus will outperform a GPU with only a 192 or 128 bit bus. Clocking a card higher in graphics or memory always means it will do more work in a given period. So choose the highest clocked card you can get and still live with the noise, heat and instability. The newer card families all use less power than previous so less heat and noise. Also, the newer cards have optimized CUDA drivers and applications so they process more work than previous cards using lesser drivers and applications. Use of an optimized client will often net a better performance enhancement using an older card technology than getting a newer GPU using the stock applications. For Nvidia cards, the newest Kepler family of cards is performing better than the GTX 570 or 580 when using the optimized clients. They also use less energy. The Kepler family of GPU's do have a big performance hit with other projects like MilkyWay@Home which needs double precision math as Kepler only does 1/24 FPU work versus the older Fermi family which does 1/8 FPU work. They do make up some performance lost in the FPU work in their sheer much higher clocking. So, pick a price point you can live with and get a new card for Seti@Home or look for an older GTX 570 or GTX580 if you need real good double precision math performance for other projects.

Cheers, Keith

---

Seti@Home classic workunits:20,676 CPU time:74,226 hours

A proud member of the OFA (Old Farts Association)

There are a unwrited roules for GPU´s:

Roule 1 - Choose the biggest GPU you could buy

Roule 2 - Follow the roule 1

I never see any cruncher who say "my GPU is to big".

But rememeber: bigger GPU = bigger PSU = higher power bill = lot of heat to dissipate. Don´t play with PSU or Heat dissipation, that could easely destroy you expensive GPU. So keep in mind, to use a big GPU you need a Big and guaranted PSU! (leave at least 30% of spare power in the PSU)

My experience: 690 is the best, then 680... 670... etc.

Fermis are cheaper but uses more power 580 is better than 570 ... 560 etc.

Older cards i don´t use any more.

---

rule 1 how much including pc build cost does it cost per wu.

rule 2 can an older card come close for less money check

rule 3 chose the best bang for the buck that suits your need

I guess what i am saying is that 2 hd6870's will do the same as 1 hd5990 or more

than 1, hd6970. You can get 2 hd 6870's for about 200 dollars used 1 hd5990 for

300+ or hd 6970 also 300+.

If you are building gust 1 pc and the case and mb and power supply allow

you can run 3 gpu's, so it is important to know how much your gpu can do verses

cost 2 or 3 lesser cards may cost less use less power and do more.

also a second 500 watt power supply to support the video cards is much cheaper

than upgrading the current 1 to 1000 watts.















=

---

Thanks guys for your help!
I'm working as an IT specialist. But in this case i don't know what's best for SETI@Home. Because i was not sure on which detail i had to look for.
The Cuda Cores or the clock speed or anything else...

Thanks again!

---

Hello,

i just wondered about the GPU list: http://setiathome.berkeley.edu/gpu_list.php

For example: The GTX 570 is better than an GTX 580. But WHY??
The GTX 570 got 480 CUDA Cores. The GTX 580 got 512?
Can somebody explain on which detail i have to look for?
Which constellation on a GPU is needed that it will work fast?
Cuda Cores / Graphics Clock / Processor Clock ... etc.

Hope to get an answer soon!
Thanks for helping me so far!

That GPU list is a raw speed comparison based on the lowest average time per WU. For recent GPUs it's better to run multiple tasks simultaneously, although that slows each task more tasks get done per unit time. The list in http://www.efmer.eu/forum_tt/index.php?topic=981.0 has better statistics for anyone planning to use an NVIDIA GPU efficiently.

                                                                    Joe

I like to make some comments.
The 6xx series has a lot more cudas, but more isn't always better.
6xx series is more power efficient,that's a good thing.
But the cuda cores are a lot lot less powerful.

As you can see some 5xx cards outperform the 6xx series.
But I expect there will be some gain in optimizing for the 6xx series

---

TThrottle Control your temperatures. BoincTasks The best way to view BOINC. Anza Borrego Desert hiking.

I like to make some comments.
The 6xx series has a lot more cudas, but more isn't always better.
6xx series is more power efficient,that's a good thing.
But the cuda cores are a lot lot less powerful.

As you can see some 5xx cards outperform the 6xx series.
But I expect there will be some gain in optimizing for the 6xx series

Hasn't that something todo with the Reg_Size, being twice as big in
the 600 series (KEPLER), as the FERMIs with 32K regsize.

Setiathome_CUDA: Found 1 CUDA device(s):
  Device 1: GeForce GTX 480, 1535 MiB, regsPerBlock 32768
     computeCap 2.0, multiProcs 15 
     clockRate = 1401000 

AstroPulse
Two GPU results, 1 rev.1363 (LUNATICs Optimized), 1 stock app. and CPU.

I'm mistaken, wanted to compaire 400 (FERMI) and 600 (KEPLER) and CPU, but
it's a GTX 550 Ti.
And a result overflow :-/.

---

I like to make some comments.
The 6xx series has a lot more cudas, but more isn't always better.
6xx series is more power efficient,that's a good thing.
But the cuda cores are a lot lot less powerful.

As you can see some 5xx cards outperform the 6xx series.
But I expect there will be some gain in optimizing for the 6xx series

The cuda cores from the 6xx cards are a lot lot less powerfull? is it because of the "power efficient"?! Especially I'm looking for a GTX 650 Ti - but i couldn't find it at the list right here: http://www.efmer.eu/forum_tt/index.php?topic=981.0

Between which GPUs would it be placed at the list!?

Thanks!

---

I do have a 650 Ti installed in my machine alongside a 670.

670
http://setiathome.berkeley.edu/result.php?resultid=2792404193
650 Ti
http://setiathome.berkeley.edu/result.php?resultid=2792404211

---

Has anyone any experience with an EVGA GTX560 Superclocked of one of two types, the 02G-P3-1469-KR or the 02G-P3-2069-KB?

---

The T1 Trust, PRR T1 Class 4-4-4-4 #5550, 1 of America's First HST's