Reading this thread is so entertaining. There are so many butt hurt AMD fanboys right now. Just face it, the 680 beats the 7970 where it matters, which is 1080p gaming. Nobody cares about the 1600p performance except for the miniscule amount of people who actually own an extremely high res monitor, so stop using this one and only performance comparison where the 7970 actually has a chance to show that the 680 "is a let down".
Go Premiums!
Why do you insist on this becoming the new meme? :\
I missed where they removed the compute parts out. Hey! I called that too! Make a beefy gaming card, sell it just for gaming at the usual price points, make a giant GPU for the HPC sector and sell it at those prices.
No crossing over, nothing but pure profits! Damn I'm good
Go Premiums!
I can already tell Nvidia is going to mess up the pricing on this great card...It's suppose to fill the shoes of the GTX 560 and GTX 570, and so it should be priced around there. I would say $359 would be a completely reasonable price for a card like this. We all know that the only reason the 79xx cards are so expensive is because there wasn't much competition from Nvidia, they should have been priced $400-499. If Nvidia was smart, they would realize that this isn't fast enough for the people who already bought a 7970 to upgrade, and the 7970 may very well be faster in "enthusiast" scenarios of eye candy, mutliple monitors, high resolutions and so on. People may say 1600p doesn't matter, or 8x MSAA doesn't matter, or multiple GB's of textures doesn't matter, but if you are shelling out $500 for a video card, some of that probably does matter. If Nvidia was smart, they would realize that this card absolutely excels in the high-mid range, maxed out settings 1080P, and they would price it accordingly. If Nvidia was smart, they would realize that this card needs to make a really good impression to get people excited. Selling a card that just falls in line with pricing doesn't really tend to do that. This card would sell so much more and be so much more popular if it was around the $359 mark, at least then theres room to go up with the real Kepler high end cards. Did either company learn nothing from ATI and the 4870?
Prety much. I'm sure on Thursday when all the reviews are out we'll be hearing the exact same complaints we heard at the 7970's launch - that nvidia is ripping people off on the 680 with a premium price not justified by its performance.
It may be even worse since the 680 looks to be less of an increase over the 580 than the 7970 was over the 6970.
Go Premiums! Indeed :sneaky:
I don't have any numbers, but I suspect compute workloads are an extremely small slice of what end users do with their graphics cards.I, for one, am disappoint in their compute performance.
Looks like I will be skipping the GK104 generation.
I occasionally play games, however, the primary focus of my rigs are distributed computing.
That's a lot of questions. I'll answer with more questions. Was AMD trying to gain back marketshare with Evergreen? Were the dev and material costs on 40nm as high as they are with 28nm?Ares, the people who bought 7970's are the same people who bought 4870s, 5870s, and 6970s regardless of what the other team had to offer. The same thing will happen with Kepler. No matter what AMD had to offer, there are still people who waited explicitly for Kepler. No different from gens past. And do you recall what 5870 launch price was? Nvidia's only competition when that launched was the GTX285. No competition to the 5870, but what was the launch price?
Prety much. I'm sure on Thursday when all the reviews are out we'll be hearing the exact same complaints we heard at the 7970's launch - that nvidia is ripping people off on the 680 with a premium price not justified by its performance.
It may be even worse since the 680 looks to be less of an increase over the 580 than the 7970 was over the 6970.
Go Premiums! Indeed :sneaky:
Dude, the 6970 was even slower than the 580 to begin with. False comparison if your only metric is overall price/perf. Price/perf does not care about architectural improvements by the same company. Price/perf means price/perf.
And yes 28nm price/perf are lackluster compared to 40nm price/perf. Maybe prices will fall once TSMC satisfies its backlog of 28nm orders, if it ever does.
This is the smallest perf. increase in a flagship from one node/arch to the next I have ever seen nvidia deliver. It sucks for me personally, as a typical 50% nv increase would give me more perf. from 2 cards than from the ones I have now. These cards are just like 7970s to me, I'd need to overclock 2 stock cards for more perf. Without any guarantees of getting the clocks I'd want, it's not worth it. Never mind that the perf. increase at 1600P for the 680 is looking to be lower than it is at 1080P.
This smells like NV took a GTX460/560 style chip, spent a quarter waiting until 28nm yields improved so they could launch a "factory pre-overclocked" version (hence initial clocks of 706mhz -> 1006mhz), rebadged it as a GTX480, scrapped the real GTX480 entirely since they couldn't get it out on time and because AMD failed to deliver this generation got away with selling a GTX460 at $500!
AMD is abysmally behind Nvidia in the workstation/professional market. They have no software infrastructure to speak of and are no threat to Nvidia. That may change at some point, but I would not hold my breath AMD has been historically weak on the software support side. I never said Nvidia is not going to make a compute based Kepler, I'm saying it all likely hood such a part is a far ways away, think 8 months at best. I base this on the rumored tape out dates among other things.
True. GTX680 is a disappointing flagship generational increase for NV. I still think this is a re-badged GTX660Ti/GTX670. As I noted many times already, Nvidia's next generation mid-range card has always either matched or beaten its previous high-end. In this regard, GTX680 is much faster than a historical mid-range next generation NV card (so it prob. should have been called GTX670Ti in fairness).
Having said that, it was obvious starting with the entire HD7000 series that 1st 'half' of 28nm generation is likely going to be an expensive generation. HD7770 was the biggest pile of **** I've seen since GTX550Ti launch. We have heard for months that 28nm yields were poor, TSMC was wafer supply constrained due to lack of Fab capacity, that they weren't expected to ramp up production volume significantly until Q3 2012, and that the concurrent demand from other customers (Qualcomm, Apple) meant much higher prices per wafer than during 40nm transition, etc.
If we stop focusing on GTX680 vs. HD7970 for a minute, take a look at GTX680 vs. HD7950. GTX680 is beating HD7950 by 30-40% and the 7950 is a $450 card. That in itself tells us the entire HD7000 series generation is mispriced. HD7950/HD7970 were overpriced to begin with from a technological price/performance curve (i.e., improvement would have been HD7970 performance replacing HD6970 at $369). From a business case, their pricing made perfect sense though since AMD just took advantage of early adopters, enthusiasts or people who don't follow GPU cycles.
NV is really laughing here. They are about to sell us a $500+ 294mm^2 die chip with 256-bit memory interface and 2GB of VRAM. No wonder NV breathed a sigh of relief when they said Tahiti's performance was underwhelming. Think about it, if NV's mid-range tends to topple their previous high-end chips, then prob. NV intended GK104 to be a mid-range card at $300-350 or so. If GK104 was meant to be high-end, where is the rest of the desktop Kepler line-up? Nowhere. It's not launching this week. That's because GK104 is just a mid-range card and it was never intended to be cut into 5-6 SKUs; that's why they aren't ready. Could you cut GTX460 into 5 smaller SKUs? It's no wonder NV has none of them ready for launch. Where is the GTX660, GTX660Ti, GTX670Ti, etc.?
This smells like NV took a GTX460/560 style chip, spent a quarter waiting until 28nm yields improved so they could launch a "factory pre-overclocked" version (hence initial clocks of 706mhz -> 1006mhz), rebadged it as a GTX480, scrapped the real GTX480 entirely since they couldn't get it out on time (for whatever reason) and because AMD basically failed to deliver this generation, NV is about to get away with selling a GTX460 at $500!
Now the "real GTX480" will become a rebadged GTX780 sometime later (maybe even Q1 2013), and because GK104 was meant to be mid-range all this time, NV has no choice but to use GTX560Ti/570/580 cards as their new mid-range and upper mid-range cards. Perhaps that's why they are still not EOL. If Nvidia launched 2-3 cards based on GK104 this week, didn't neuter GPGPU compute and outperformed GTX580 by an average of 50%+, I would have believed that GK104 was the real flagship.
That's just my wild theory.
Your second point is interesting, if indeed the original specs have it at 706mhz. That's a huge OC and if theres any headroom
LOL, this is probably a little overstated. The 7970 handily beat a card selling for $500. The generational thing isn't a significant factor when somebody needs a video card. How much better does it perform vs what else I can get and at what price premium? Also how long can we expect the die shrinks to keep giving us the same percentage performance gains as we've had in the past? We're going to start hitting a wall eventually.From a business case, their pricing made perfect sense though since AMD just took advantage of early adopters, enthusiasts or people who don't follow GPU cycles.
True. GTX680 is a disappointing flagship generational increase for NV. I still think this is a re-badged GTX660Ti/GTX670. As I noted many times already, Nvidia's next generation mid-range card has always either matched or beaten its previous high-end. In this regard, GTX680 is much faster than a historical mid-range next generation NV card (so it prob. should have been called GTX670Ti in fairness).
Having said that, it was obvious starting with the entire HD7000 series that 1st 'half' of 28nm generation is likely going to be an expensive generation. HD7770 was the biggest pile of **** I've seen since GTX550Ti launch. We have heard for months that 28nm yields were poor, TSMC was wafer supply constrained due to lack of Fab capacity, that they weren't expected to ramp up production volume significantly until Q3 2012, and that the concurrent demand from other customers (Qualcomm, Apple) meant much higher prices per wafer than during 40nm transition, etc.
If we stop focusing on GTX680 vs. HD7970 for a minute, take a look at GTX680 vs. HD7950. GTX680 is beating HD7950 by 30-40% and the 7950 is a $450 card. That in itself tells us the entire HD7000 series generation is mispriced. HD7950/HD7970 were overpriced to begin with from a technological price/performance curve (i.e., improvement would have been HD7970 performance replacing HD6970 at $369). From a business case, their pricing made perfect sense though since AMD just took advantage of early adopters, enthusiasts or people who don't follow GPU cycles.
NV is really laughing here. They are about to sell us a $500+ 294mm^2 die chip with 256-bit memory interface and 2GB of VRAM. No wonder NV breathed a sigh of relief when they said Tahiti's performance was underwhelming. Think about it, if NV's mid-range tends to topple their previous high-end chips, then prob. NV intended GK104 to be a mid-range card at $300-350 or so. If GK104 was meant to be high-end, where is the rest of the desktop Kepler line-up? Nowhere. It's not launching this week. That's because GK104 is just a mid-range card and it was never intended to be cut into 5-6 SKUs; that's why they aren't ready. Could you cut GTX460 into 5 smaller SKUs? It's no wonder NV has none of them ready for launch. Where is the GTX660, GTX660Ti, GTX670Ti, etc.?
This smells like NV took a GTX460/560 style chip, spent a quarter waiting until 28nm yields improved so they could launch a "factory pre-overclocked" version (hence initial clocks of 706mhz -> 1006mhz), rebadged it as a GTX480, scrapped the real GTX480 entirely since they couldn't get it out on time (for whatever reason) and because AMD basically failed to deliver this generation, NV is about to get away with selling a GTX460 at $500!
Now the "real GTX480" will become a rebadged GTX780 sometime later (maybe even Q1 2013), and because GK104 was meant to be mid-range all this time, NV has no choice but to use GTX560Ti/570/580 cards as their new mid-range and upper mid-range cards. Perhaps that's why they are still not EOL. If Nvidia launched 2-3 cards based on GK104 this week, didn't neuter GPGPU compute and outperformed GTX580 by an average of 50%+, I would have believed that GK104 was the real flagship.
That's just my wild theory.
what a big imagination.
we will be getting more answers soon enough. The more ppl keeps saying this though, the worse it makes AMD look.
I am more incline to believe this card is gk104 because it was genetically engineered from the GF104 genes. Internally it would seem that more would go into names than what us common folk think. We are thinking like consumers and using that line of thinking to make internal code names for architectures mean nothing more than the product name. Since the gf104 made a gtx 460 then the gk104 should make a 660? I guess if its that simple and thats all thats in the internal code names then why have them at all???? It just cannot possibly be that simple for multiple reasons. On is that we are not seeing any leaks with a gk100 name. Another is that we have seen gk112 as a name for a part. These numbers have purpose, but i highly doubt its any 104 is a midgrade and any 100 is the big cersion. Cause we have seen zero leaks from the beginning of such a part as gk100. Even if it were scrapped, we shouldve seen it on some outdated leak. Also nothing makes sense when you see the gk112. how does this fit inot the logic??? it doesnt add up!!!
a lot doesnt add up. There is no gk100, no leaks of one ever being in existence. and the first chip from Nvidia is the GK104 and its carrying the 680 name. If you look at the leaked internal schedule from last year (2011) you will see that the gk104 was always there and first, with no sign of a gk100. This has caused a lot of confusion, including the nvidia will launch its midgrade first. But the big deal is that leak was right. Also in that leak the dual card was their top card for the year and it even had its own GK number. Nvidia did not follow a simple predictable path at all.
Look its too much your not looking at.
LOL, this is probably a little overstated. The 7970 handily beat a card selling for $500. The generational thing isn't a significant factor when somebody needs a video card. How much better does it perform vs what else I can get and at what price premium? Also how long can we expect the die shrinks to keep giving us the same percentage performance gains as we've had in the past? We're going to start hitting a wall eventually.
AnandTech Forum Guidelines said:3) No sharing or requesting pirated software. Discussions addressing piracy are allowed, but using the Forums as a hub or a school for pirates is not.
4) No posting of other's copyrighted material. Discussions of copyright are becoming increasingly important, but we will not allow the Forums to be used to violate any US law.