Expanding on this post I made a while back:
[url]http://www.mersenneforum.org/showpost.php?p=176635&postcount=21[/url]

Here are some performance figures for various high end graphics cards (all units are GFLOPs). I have coloured pairs of cards as there are comparable in terms of the role they have in each companies line-up:[code]

Card SP DP

GTX 275 673.92 84.24
[color=green]GTX 285 708.48 88.56[/color]
[color=blue]GTX 295 1192.32 149.04[/color]
[color=red]GTX 480 1344.96 168.12[/color]

[color=blue]HD 4870 X2 2400 480[/color]
[color=green]HD 4890 1360 272[/color]
[color=red]HD 5870 2720 544[/color]
HD 5970 4640 928

[color=green]Previous generations highest spec single GPU card.[/color]
[color=blue]Previous generations highest spec dual GPU card.[/color]
[color=red]Current generations highest spec single GPU card.[/color]
nVidia does not yet have a dual GPU 400 series card to compete with the 5970.[/code]To work out the performance of any recent nVidia or ATI graphics card, here is the formula:
SP performance = shaders (aka cores) * frequency / 500

To get the DP performance, divide by 8 for nVidia GPUs, and divide by 5 for ATI GPUs. Note that for dual GPU graphics cards such as the 5970, there are 1600 cores per GPU, so it is usually listed as 3200 cores.

Hands down the ATI cards take the performance crowns for single and dual precision performance.

Too bad that my code doesn't depend much on FP performance.

You can't compare those numbers directly between both vendors execpt you're a marketing guy. :razz:
Look at gaming performance, the HD 4890 isn't able to beat the GTX 480.

From my feeling the ATI cores are smaller, simpler and slower than the Nvidia cores. On the other hand ATI has more cores.

Do you have performance numbers for GPU-computing for the same application on both, ATI and Nvidia?

---
personally I don't own a recent ATI card (I've some "Xpert-98" and one ES-1000 here). The Linux drivers from Nvidia are less evil than the ATI ones (for me).

Oliver

[quote=TheJudger;214382]

Do you have performance numbers for GPU-computing for the same application on both, ATI and Nvidia?


Oliver[/quote]

Oliver,

You can find [url=http://n0cgi.distributed.net/speed/]here[/url] some benches for distributed.net GPU client for ATI and Nvidia applications. Hope this helps you in anyway.

Carlos

Lol, way to go ET_, lots more factors, including one that was missed, 107 unfactored candidates left in the current pile.

And of absolutely course, way to go Judger for writing the code.

This page is suddenly pretty big now:
[url]http://2721.hddkillers.com/compare/live/[/url]

Hi,

I'll run some doublechecks from 2^71 to 2^75 (factored and unfactored exponents). Using this list ([url]http://home.earthlink.net/~elevensmooth/Billion.html[/url]).
I'll start at the top and we'll se how far I go. :smile:

Oliver

Taking 3321929411 from 75 bits to 79 bits

Luigi

Taking 3321929987 from 75 bits to 79 bits

Luigi

Taking 3321931381 from 75 bits to 79 bits.

Luigi

finished [B]all[/B] OBD exponents from 2^71 to 2^75.

I've "verified" all 4 known factors within this range and found 11 new factors. :smile:

[CODE]
M3321928097 has a factor: 7771207163883536443921
M3321929357 has a factor: 6350799856004899669463
M3321929759 has a factor: 4103086300931724495689 <-- old
M3321929843 has a factor: 21231759207812485313329
M3321929843 has a factor: 2947492197366428673583
M3321929959 has a factor: 16147234168816040969113
M3321930893 has a factor: 9539022928074431524207
M3321931051 has a factor: 15671269871631418605889
M3321931061 has a factor: 29833158347165530570273 <-- old
M3321931637 has a factor: 28475025393798152885081 <-- old
M3321932473 has a factor: 5768855748580684424359
M3321932897 has a factor: 21421097980873876521463
M3321933073 has a factor: 23731540314540450112807
M3321933281 has a factor: 20842680057158059318249
M3321933893 has a factor: 36285087986156170392041 <-- old
[/CODE]

---

I'll take [B]3321928417, 3321928483 and 3321928601[/B] next (from 2^75 to 2^79)

Oliver

Good luck for a new[COLOR="Red"][SIZE="4"] BIG[/SIZE][/COLOR] factor! :smile:

Luigi

[QUOTE=TheJudger;217223]
[CODE]
M3321929843 has a factor: 21231759207812485313329
[/CODE]
[/QUOTE]
This factor is composite. It is the product of the two smallest already known factors, 6643859687 * 3195696508967