You should, he was mostly right about the 4xx series. He said hot, it was hot. He said expensive, huge, it was both in spades. http://semiaccurate.com/2010/02/17/nvidias-fermigtx480-broken-and-unfixable/ Show me where he was significantly off. First, we knew he was right about yields, that's why Fermi wasn't being shown anywhere, and was extremely late. Specifics he was correct about. 1. Correct specs for the GTX 470. He inaccurately labeled it as the flagship card, but it was close. 2. Correct die-size measurements. 3. Correct power figures. 4. Correct that the entire Fermi core would be unusable without a respin (GTX 500) 5. Correct measurement of performance vs Cypress (112% http://www.guru3d.com/article/geforce-gtx-470-480-review/24 ) 6. Correct prediction of extremely extremely limited availability for months following release. The guy has a troll writing style that really pisses off the fanboys, and he embellishes to get some readers as trolls do. But in the past his articles have been pretty accurate, accounting for some minor flaws in his information (Like calling the GTX 470 the flagship) Which, who knows, it may have been until the last minute.
Yes its only mid-range gpu, nothing shocking there From Mr Fudd. lol http://www.fudzilla.com/home/item/25636-nvidia-28nm-gk104-gpu-specs-revealed
Lol, I've always wondered why nVidia is called the dark side, when the dark side is RED, red light sabers and everything (Ati)... The good side is green, green light sabers (nVidia), so it's the other way around...LOL regards, RagDoll.
It's already been pointed out, quite correctly, that this guy's writing style is intentionally biased almost to the point of spitting bile/venom at times so any opinions offered have to be taken with that in mind. It is entirely possible that in the month since he wrote that that he's seen the GK104 card for himself and changed his mind about what he wrote earlier. I'm willing to give him the benefit of the doubt but we'll know soon enough once the new card or cards are unveiled officially and the reviews are out.
It could also still be a misinformation rumor to see who doesn't name S|A as a source when spreading the FUD as their own. They've spread nonsense before.
Honestly though, I don't know what the big deal with the guy is. He works for a website called Semiaccurate. What the hell do you people expect except semi-accurate information?
yeah but that was after he said 4xx could not be done,so as pointed out above he tends to change up his story as he goes along or how about when he plays up the lack of fermi but he did not harp on it when amd makes a few 1000 cards for a paper launch. but he pissed me off when he said that dfi was going out before the workers were told that instance he should have kept his mouth shut. i dont get caught up in speculation thats for fools
If a new NVIDIA card due to be released in April 2012, over two and half months from now, wasn't faster than the HD 7970 then I'd be very disappointed. It's interesting that they're releasing a mid-range card first as that is unusual for NVIDIA but, if those rumours are true, it may be because they're confident that it's an HD 7950/7970 beater. And being a mid-range GTX 560 Ti replacement with just 2 GB of memory it would surely be cheaper than the HD 7970, possibly between £250 and £300 (the HD 7970 is £450 here in the UK)? If the card is faster and cheaper then it would be win, win, win for NVIDIA and perhaps that is why Semi-Accurate have changed their tune?
Well nVidia have a strong habit of nearly doubling performance with each new architecture so what should make Kepler any different? The GTX480 may have struggled with that and wasn't running 100% but the 580 is twice as fast as a 285. ATM nVidia need about 30% over the GTX580 to beat the 7970 in just about any title...
If Nvidia's mid range can even come within I would say 10% of AMD's top card then I believe AMD is in a world of ****. Both companies releasing a new architecture at the same time (well close enough anyway) is really interesting. I think one or the other is going to be a clear winner. AMD is not in a strong position right now either so this could be really bad for them IF Nvidia hits one out of the park.
I'd say the new Nvidia performance rumours are just that, rumours. Realistically being a reviewer, being biased towards Nvidia or AMD, and reporting either directly, or indirectly (due to settings, hidden settings etc) that your biased card is superior can only be considered an act of lunacy. Increased demand, increased prices. Why would you want to be stupid enough to promote or validate a price rise?!
Lets give equal billing http://www.fudzilla.com/home/item/25636-nvidia-28nm-gk104-gpu-specs-revealed Nvidia's next-generation 28nm GPU architecture, codenamed Kepler, is officially expected to launch in early Q2 2012 according to the latest schedule we have seen from the company. Although the company will technically be launching one quarter behind AMD, we can still expect to see a few noteworthy design wins in the enthusiast and performance segments, beginning with GK110 in April and following up with GK104, GK107 and GK108. The latest report from sources overseas claims that Nvidia's GK104 GPU, the successor to 40nm GF114 (see: Geforce GTX 560, Geforce GTX 560 Ti), will feature a 256-bit memory interface, will pack 2GB of memory capacity and should have a 225W TDP. Nevertheless, the GK104 will most likely be branded as Geforce GTX 660 and may very well have a Geforce GTX 660 Ti variant later down the release roadmap. Many analysts are expecting 28nm GK104 to get a big boost in CUDA cores. Some estimates are projecting as many as 768 CUDA cores or "well above 2 teraflops" of raw performance, which roughly equates to 50-percent more compute power than the current flagship Geforce GTX 580 single-GPU card with its 1.56 teraflops. While we don't have exact information on these specifications yet, we expect more information on the exact details of CUDA cores, texture units and ROPs in the very near future. more fud GK104 impressively doubles up on GF114's core count to 768 CUDA cores - although Kepler shaders will be different from Fermi counterparts. Single precision performance is rated at above 2 Teraflops, twice that of GTX 560 Ti and over 50% higher than GTX 580. GK104 will continue to feature a 256-bit memory interface, but with frame buffer doubled to 2GB presumably at higher clocks. With everything increasing, unfortunately so does power consumption, to a TDP of 225W. A GTX 660 Ti variant is also expected in the future. While the remaining details remain unknown, including Kepler's architectural peculiarities, GK104 or GTX 660 will most likely end up competing with AMD's Radeon HD 7970. NVIDIA is expected to start releasing its Kepler parts in early Q2 2012, as we had previously reported, with GK110 releasing first - presumably going up against AMD's New Zealand dual-Tahiti flagship http://vr-zone.com/articles/report-...cifications-revealed/14589.html#ixzz1k2y38WiA just give us a $350 card that is 50% faster then a 580 that be a nice start
That would make it faster than a 550 7970 forcing ati to lower the price on that. Competition is good
Competition is good, but AMD is the underdog and really needs to be a good percentage better to be considered an equivalent for any given card. Also look at the games they are reviewing. Some are favourable to one brand or the other. If you remember back to Bioshock 1, it originally had DirectX 10.1 support, and the performance on ATI cards was far better than on Nvidia cards running DirectX 10. They removed support for DirectX 10.1 which put Nvidia back in front. Nvidia then were too slack to add Direct 10.1 to their cards for a LOOONNNG time, meaning game developers were relunctant to go to the poor performing DirectX 10 (too much effort, not enough benefit), and now they don't bother at all since consoles are too easy. That was probably the tipping point, since PC was still ahead of consoles then. Game developers could have been using DirectX 10.1, which would be an easier step to using 11 now, instead of using crappy old DirectX 9. In this scenario, a mainstream game developer wouldn't have risked releasing a DirectX 9 only game. but they 'get away' with it because its expected. DirectX 11.1 games should start to show once the new Xbox comes out. Then it will be a very common thing (but stuck on crappy console textures on 'consolified' games...
