AMD Hawaii R9 290X GPU Specifications ?
Click here to post a comment for AMD Hawaii R9 290X GPU Specifications ? on our message forum
Texter
Why not top 3Dcenter.org forum member's unmitigated optimism by assuming AMD threw in a whole nother column of 16 GCN compute units, totaling 3,072 shader units and can run the new monster at 1 GHz while we're at it...all because the 28nm process has matured in such a nice way, of course...
Rich_Guy
Its only about 5 days till AMD confirm the final specs.
-Tj-
Yes I've heard about possible 2800 cores,
If its really a 2800 core it will definitely destroy through current "high end" market. That 40% faster gap seems very possible
Blackops_2
Edit just saw this was the 290x/dual GPU/onePCB nvm. :3eyes:
Kaerar
R9-290X isn't a dual GPU. Just compare it to the stats of the 7990 at the top of that list of cards and you can see that.
It's looking promising for my next gfx card at least 🙂
Texter
Oh yes it will be, the rumors are about the 280 but they couldn't even get THAT right, apparently lol.
Titan29
My guess is around 2560 cores (more would be nice). But more importantly we need to see how much is GCN 2.0 better than GCN 1.0. Remember 6970 had less cores than 5870 but due to more efficient architecture (VLIW 4 vs VLIW 5), the performance was better even with less cores.
Interesting times ahead...
btw, Hilbert, when can we expect a review for it? around 25th or near the launch in OCT?
Koniakki
Selling my GTX 690 this Saturday. Going for either a new AMD or a Palit SJS GTX 780.
My money goes to the best/fastest product in that price range or lower.
I really hope that AMD suprises me.
Andrew LB
Yeah. But the problem is none of these numbers came from a reputable source, like AMD. They're almost entirely random speculation, wishful thinking, and/or a logical assumption.
example: PCPerspective (formerly AMDMB.com) claimed back in May that it was "rumored" this chip would have 4096 ****** processors.
Now... getting back to the reality that if Hawaii is being released this month, they would without question be using the 28nm manufacturing process because 20nm is not ready for prime-time.
The following quote was made by an AMD executive...
Source
That sounds to me like it's a mid-high card, probably somewhere near between GTX 770 and 780. The fact that he says Kepler is 30% larger in die size actually makes me think AMD isn't releasing a high end card until 20nm is finished. My GTX 680 is 294mm^2, which puts Hawaii's size too small to be high end.
-Tj-
7970Ghz falls between 770GTX and 780GTX, enough said.
5 more days and all will be clear, but I still bet it will be at least 20-30% faster then a GK110 with 14SMX + DoublePrecision (aka Titan), if 2800core then even more 30-40%.
Titan29
I think it will match or slightly exceed Titan at most. That in itself will be a win for AMD as it will kill Titan on perf/price.
The focus this generation seems to be efficiency (perf/watt). I do hope that they dont strip it of compute performance like Kepler.
PS: If Hawaii kills Titan, I will change my name 🙂
ELNIKA
+1
I don't get why nvidia fanboys get so annoying sometimes. And this is coming from a nvidia/AMD user for years, i just buy the best price/performance solution at the time, no matter the brand.
Cheers.
Blackops_2
I'm not a fanboy of either and i bet it doesn't match Titan. They've already stated they're not aiming at competing with Titan. I'm betting slightly behind the 780 or matching it. Not to mention OC room will probably be limited i don't expect these to OC like Tahiti. Matching Titan will be hard enough for their small die strategy on the same 28nm process. Much less exceeding it.
Then again the 7790 with GCN 2.0 cores was able to achieve a 30% increase over it's predecessor.
Koniakki
Hey Hawaii29, I hope they release a great product too. Competition will benefit us greatly.. 😉
-Tj-
Because it carries 1000$ mark or because it supports double precision?
Idk, why so negative, Titan's SP and DP is around the same as 7970Ghz, its only faster because it has more ROPS, higher fillrate and more raster engines; which makes it 15-25% faster then 7970Ghz. Now add all that to R9-290X? with more cores and its min 20% faster for sure.
Laykun
Let hope they fix their horrendous crossfire issues in hardware this time. I believe I read somewhere that was their goal but I'll believe it when I see it. The 7970 was the last straw for me which pushed my back to nvidia.
DP performance is completely irrelevant in the context of gaming. If AMD puts silicone towards DP performance then it'll be sacrificing gaming performance for DP compute performance ( completely irrelevant to 99.99% of all computer users). Not to mention that DP performance is artificially limited at driver level for consumer level cards so they can sell Quadros/FirePros/Teslas at much higher margins.
Blackops_2
To clarify the 290x is the single Hawaii solution right? Or is it the double?
Because it carries the 1000$ mark and all these released specs are speculation. 2800+ cores would undoubtedly beat Titan but that seems like a lot for the same process and the same power envelop/efficiency.
Titan is 30% faster than the 7970GE and 40% faster than the 7970/680. 20% Faster than the 7970GE sounds about right, but it still doesn't match Titan, though would theoretically compete with the 780. I just felt like it would be hard to achieve much more on the 28nm process.
I'm not meaning to be negative per say but when they come out and state they aren't wanting to compete with Titan i just don't think it's about to blow the lid off Titan.
I'm expecting competition against the 780 for 500-550, hopefully it beats the 780 giving us a price war. If it's bundled with BF4 i'll be getting them for sure.
yasamoka
They fixed it in software (still Phase 1 with no Eyefinity support though). It's practically as good as Nvidia's hardware solution. Anyways I cast doubt over the hardware frame-metering in Nvidia's hardware since according to them, it's been there since G80 (8800GTX) but we all know that Nvidia suffered from horrendous microstutter (that improved every generation) until Kepler which finally *eliminated* it in a general sense.
Frame-metering is an algorithm that paces not when the frames are displayed, but when they are rendered (else you'd have frames being repeated). This tells me that it takes effect before the GPU gets to rendering the second, pushed frame. So it's earlier than when the GPU receives what it has to render.
The 7970 did have excellent DP performance compared to the GTX680 and it didn't sacrifice much, if any, gaming performance against the 680. However, it does consume more power.
Why would there be an artificial driver limit on either if they can cripple DP performance straight on the hardware? AMD's GCN is 1/4 DP:SP and it performs as expected, even with the FirePros thrown in.
The workstation cards have specialized tasks that they excel in, but that is not necessarily tied directly to DP performance.
warlord
^AMD never caught up to Nvidia's smoothness since forever, what SLI microstutter i am hearing about? LOL 🙂 even 13.10beta is not making things smooth enough. They should learn something from nvidia's superiority in mgpu solutions. Maybe hardware pacing is better to be done than driver level.
yasamoka
Really? What games are not smooth with the new Frame-Pacing? Everything I've tried till now has been as smooth as a faster single-GPU, especially when FPS hit refresh rate, it felt like VSync was on. If anything, the vast majority of games are now smooth.
Nvidia don't have any driver-level frame metering, you think?
