The NEXT LAST R600 Rumours & Speculation Thread

I hate to say it, but I agree. I had much higher hopes for this card...

 

The inquirer comments sure did add some spice!

 

Is there any possibility of the R600 supporting double precision math - for the GPGPU folks?

 

Since we haven't heard anything yet I seriously doubt it.

 

After reading that inquirer article. And their comments almost make me think they take offense to it all.

 

From what I've seen, that mostly mirrors my thoughts too, except for the IQ part. As for the AA modes, I have yet to see narrow-tent and edge-enhanced modes. I haven't seen any AF comparisons that do not also use wide-tent AA at the same time.

I'm rather disappointed with the performance and price. It would be different if it traded performance with the 8800GTX or it soundly bests the GTS.

 

and another one bites the dust!

 

Even if it do so, it won't be at full speed (think of Cell).

TweakTown == TweakDown

 

Yes, but it would be a first then - even with much lower performance. NV has a DP part in the works - and I guess the first DP chip to hit the GPGPU market would stir it up a little bit.

 

And what did they expect

 

It's been always like that due the AA sample patterns, 6xAA on ATI was a bit better since it has sparse pattern.

 

I was actually somewhat impressed with the benches on this card, it seems to beat a GTS and approach a GTX in many cases. For $399 it seemed worthy.

However, once you factor in the lame IQ and high power requirments, it's probably a no sale.

BTW, I like how the Vr-Zone article several times blames poor results on X2900XT's "bandwidth", when it has more bandwidth than any other card. Clearly they mean texture capabilities, but apparantly dont understand it. I expect to see most sites not understanding the extremely low texture abilities of R600 are clearly responsible for it's poor performance.

And I was jumped all over for suggesting the card was a power hog a ways back..

Too bad for ATI R600 contains over 700 million transistors, and engaging in mid-range sub $300 price wars is not where they really want to be with the product. But hey, that's their own fault for not engineering performance.

I suppose in a bizzare way, R600 is probably more efficient than than R580. R580 was about twice as big IIRC for nominal perfomance over G70, this is probably roughly size parity for maybe 80% performance as G81. Could probably be considered an improvement. It's just that, performance is far more paramount in these sectors than anything else, so it's probably actually better to be in R580's shoes.

 

Ok, so it consumes lot's of power, reintroduces crappy AA blur modes just to be able to say "we also got 16X AA". Performs like crap in some games, really good in some games. Can't keep up with the GTX.

Hmm, i must say that it's currently very underwhelming. But i guess we'll see what happens in a month or so.

Might add that AMD's first explanation that they could have released the card much earlier seems pretty laughable considering the performance with the current drivers.

 

I'm a little dissapointed, so far.. though hard to tell really with the results we're seeing seemingly all over the place, some show it with a comfortable advantage over the GTS, closing on the GTX, others show it trailing the GTS (and 1950XTX..)

But re. the IQ, as somebody said earlier (either here or at AT), the AF tests seem to have the tent thing going on too.. which would kinda defeat the purpose of testing just the AF, wouldn't it?

I think I'll hold my breath for B3D, Xbitlabs and FS' pieces

 

Ok PNG lossless versions.

8800GTX vs 2900XT




All four frames in a zip file here.

http://www.sharebigfile.com/file/168282/pics-zip.html

 

Hmm.. Perhaps Kombatant's comments about 'a lot of people being very happy' did in fact refer to all those who had bought an 8 series card already.

 

Yeah they didn't twist much, if anything at all. I guess there's no need for FUD when the truth does the job.

 

I can't remember if I've posted this already, but is R600 another case of ATI needing time to fully optimize its memory controller (as it seems to have taken a step beyond the R500 series' one)? Are these app-specific optimizations, with the MC tuned for specific games or engines, or just generically for various AA loads? Or is this just a cover for app-specific optimizations (not specific to the MC)? It does seem like they've got some tweaking to do, given how non-AA framerates are decent but drop like a stone with AA in some games.

That NV comparo that The Inq published claims R600 can filter INT16 at full speed but FP16 at half. Don't they require the same amount of info, both being 16bit? I mean, those fillrate #s NV published look crazy. Then again, R600XT spots G80GTS double the fillrate but benches even with it. So, WTF? Don't tell me NV's "wasting" die space with excess filtering power, b/c it seems a lot easier to tout "eleventy billion shaders!" than "eleventy billion bilinear filtered floating point pixels per clock, kids!"--IOW, that can't be for marketing alone.

Ignoring cache (but continuing with my ignorance), how much bandwidth would an FP16 bilinear filtered pixel require per clock? Is it the same as a single FP32 unfiltered pixel? Or do we have to go one step further and consider the minimum bytes per RAM chip access (e.g., a single FP32 fetch might be more efficient than two FP16 ones)? I'd like to know how each card's theoretical fetching/filtering ability matches up with its physical bandwidth (i.e., if a GPU has more filter/fetch hardware than its bandwidth can support b/c it assumes a certain level of cache hits).

I'll wait for more comprehensive reviews before clucking about IQ (though ATI does seem to have blur in full effect in some modes), but how did NV's PR dept get sshots of R600 in action before NDA lift? I know it's all a grey area, and they probably got a card as soon as anyone else simply b/c they must have better contacts than any of us enthusiasts/reviewers, but it seems a little weird that they're presenting sshots. (Weirder still is that they obviously ran some fillrate tests and their presenting that didn't make me blink an eye.)

And did Google cache Tt's review, ffs?

 

Hardly seeing any differences..

the first ATi pic, is lighter than the GTX.. could that account for the more defined lines on the roof? (bottom right - almost looks like the contrast has been bumped up a notch to make the edge stand out more?)

and in the second pics, the pointy rod on the front of the airship is ever so slightly more obvious - not seeing anything else that is different tbh..

 

Btw, my first impressions on CFAA is not very good. Getting rid of jaggies is one thing, but blurring out the images? Cant wait til i read some more indepth review based on the IQ of R600.