NVIDIA Kepler speculation thread

Only until you actually look at the values on the graph. Sure, it'll fool the Joe Average but anyone with half a brain shouldn't really be all that bothered about it.

Graphs are supposed to be informative based on their appearance. They are literally graphical representations of data. Bar graphs, in particular, are meant to show relative proportion. If you're going to start at a non-zero origin you need to at least add the squigglies showing you've chopped out the middle per CAD, etc.
 
No. Tahiti has a 50% larger bus width than Pitcairn but is over 50% larger. It makes no sense at all to blame the decrease in transistor density to the larger bus. Going by that logic Tahiti should if anything be more dense.
The drivers for the memory interface are significantly larger compared to Pitcairn. IIRC Dave Baumann hinted they are meant to allow higher memory speeds and may be actually overspec'd to get there (it is actually quite easy for Tahiti to reach 7+ Gbps even with the 6 Gbps memory chips used).
Tahiti also has a significantly higher cache/SP ratio, which again should help make it more dense.
???
Where did you get that from? The SRAM per CU is basically the same (registers, LDS, vD$) as long as we don't factor in ECC. Pitcairn even has relatively (to the CU count) slightly more sD$, I$, and L2 cache as well as relatively more (the same in absolute numbers) ROP (color and Z) cache and GDS.
 
Where are you getting the 200 USD less? Oh you mean the 6800 (non-ultra)? Then blame Nvidia for not having something similar. Heck they aren't even planning on launching GTX 670 for a few months. Likely due to trying to get enough GTX 680 chips to satisfy demand at 550 USD or GTX 670 is close enough to GTX 680 that they don't want to cannibalize sales in the first month or so.

Regards,
SB

Yeah I was being nostalgic (and my memory may be spotty), 9500->9700pro, x800 pro-->x800 XT, 6800-->utlra, 6200-->6600. Man that was just great times back then. I miss that. Very good value.
 
Yeah I was being nostalgic (and my memory may be spotty), 9500->9700pro, x800 pro-->x800 XT, 6800-->utlra, 6200-->6600. Man that was just great times back then. I miss that. Very good value.

Definitely. I remember taking a X800 Pro VIVO and converting it to a XTPE for a friend of mine (I foolishly just bought the XTPE). It may be the the 6950 -> 6970 may be the last we see of something like that. But who knows, maybe something will fall through the cracks again in the future. :)

Regards,
SB
 
At least over here the X800 Pro Vivo was almost as expensive as the real X800 XT PE and they often struggled to reach XT PE speeds, mine was one of those, although it ran fine after the pencil mod. 9500/9700np to 9700 Pro and 6950 to 6970 were great stuff.
 
One more guess as to density differences. A larger chip might require an increase in the port count of the on-chip switch(es) connecting everything together. If those are cross-bars, then my guess would be that associated transistor count grows about linearly with port count, but that wiring grows quadratically. Assuming that's not way off, then perhaps the effect is non-negligible?
 
384 CCs, 625 MHz core clock, and 1250 MHz shader clock? So hot clocks are in Kepler?

EDIT: BSN says "unified clock of up to 625MHz."
 
Last edited by a moderator:
So it beats the outgoing Fermi in BF3 too? Suddenly a lot of stuff starts to make sense. Remember the "faster in dx11 titles". BF3 has been mentioned a lot obviously.

The point on the heat is most worrying.

The answer to that question starts to become evident when playing games on this laptop. While the palmrest remains in the mid-80s, the middle of the keyboard becomes extremely warm, reaching temperatures up to 105 degrees.
That’s nothing compared to center-bottom of the laptop, where we read temperatures of up to 128 degrees after playing Battlefield 3 on Ultra. That’s unacceptably warm - it’s hard to imagine using this laptop on anything besides a desk if you want to engage the GPU.
Ivy Bridge is also supposed to be struggling with heat issues so what are both gonna be like together?

When is Nvidia going to learn that these are real issues? I can totally believe that Apple told them to GTF because of too much heat. It's just not acceptable in 2012.
 
jimbo75 said:
So it beats the outgoing Fermi in BF3 too? Suddenly a lot of stuff starts to make sense. Remember the "faster in dx11 titles". BF3 has been mentioned a lot obviously.

The point on the heat is most worrying.

Ivy Bridge is also supposed to be struggling with heat issues so what are both gonna be like together?

When is Nvidia going to learn that these are real issues? I can totally believe that Apple told them to GTF because of too much heat. It's just not acceptable in 2012.

This was an ultrabook review. It seems Acer decided to be aggressive with GPU clocks, but not with their cooling solution. I don't see how that's Nvidia's fault.
This review doesn't evaluate performance per watt directly, which is the key information you'd need to extrapolate to other laptops (including Apple's). An inadequate cooling solution would make any GPU look hot.
 
I doubt Acer was the one deciding the GPU clocks. It was the one responsible for cooling it though.

Still, this is ridiculously hot.
 
So it's up to the OEM to decide final clocks?

One of the tactics used by Nvidia to squeeze maximum performance out of the new Kepler mobile chips is performance scaling. Every laptop has a maximum amount of heat it can cool - so why not make sure all of it is being used?
(...)

I asked an Nvidia rep what they were going to do to ensure that the dynamic performance scaling did not result in high external temperatures. The answer I received was that it’s up to the laptop manufacturer as the thermal capacity of the chassis is often determined before they select a GPU. It appears Acer has been very liberal with the maximum temperatures it will tolerate.
Well, an ultrabook chasis, even if it is 15", might a bit too little to put such a "beast" inside. But it sure looks like a common issue, if cooling isn't adequate.
 
SimBy said:
I doubt Acer was the one deciding the GPU clocks. It was the one responsible for cooling it though.

Still, this is ridiculously hot.

The Nvidia rep said they choose the thermal limit, and the GPU throttles clocks to meet it. Acer decided to be aggressive with the thermal limit on the GPU, but not with the cooling. So, maybe this laptop isn't the one for you, but it's hardly time for overwrought doom and gloom about Kepler's perf/watt.
 
I don't know if anyone else caught this, but did Tim Sweeny just leak kepler floating point spec?

GI: More generally speaking, what are the things you are looking for in next-gen systems, the kinds of things that get you and Epic excited creatively?
TS: Gosh, my list for the next generation; it's really two big things. One is to bring all that's best about other computing devices - the convenience, the access to social media, the connectivity with the internet, Facebook or Twitter - and continue to bring that forward in the console experience. If you look at the console generation previous to this one, these were offline devices. You'd install a game, play it by yourself and you're done. Nowadays you go online, play games, and buy games through XBLA or PSN. I think we've really only seen the tip of the iceberg there. There is a continual challenge for the industry to push forward in order to remain relevant and competitive with the awesome things that are happening on iOS for example.
"If you go into the next generation with a budget of $100 million, you are doing it wrong and are being far too brute force."
Tim Sweeney

Number two is to deliver the maximum amount of computing power that is economically possible. Really, that's the reason consoles exist in the future. They have an enormous amount of graphics processing power that delivers an experience that goes far beyond what you can get on a lighter weight device. Pushing forward, we measure that performance in teraflops, trillions of floating point operations per second. When I started programming, you had about one thousand floating point operations per second. Now we have, on nVidia's fastest hardware, two and a half to three teraflops. To push next-generation up to those levels will really ensure that they will remain relevant for another generation, even as other cool consumer devices like iPads and iPhones become more prevalent.

I can't think of anything else that would line up with that unless hes talking about SLI...
 
33le6f6.jpg


GK104 Transistor Count and Exact Die-Size Revealed
 
Last edited by a moderator:
Of course, NVIDIA is likely able to fit all that shader power into the 640M due to the chip being based on their upcoming Kepler architecture and thus manufactured on TSMC's 28nm process instead of 40nm. It's entirely possible and even likely given what we know of Kepler behind the scenes that these numbers are incorrect; even GPU-Z doesn't accurately detect the 640M.

Hmm.. a bit cryptic.. what numbers are they aluding to? The 384 cores?
 
That's pretty good performance from what I assume is a 30GB/s part. Would be interesting to see how it fares with GDDR5.
 
Back
Top