The GTX 680 is priced at $499, $50 lower than the AMD Radeon
HD 7970, and I'm sure everyone is hoping for killer performance and
price drops on other cards to come out of this launch. In a nutshell,
the GTX 680 features eight SMX units, each containing 192 CUDA cores -
that's a total of 1536 cores. The Kepler core also has eight geometry
units, four raster units, 128 texture units, and 32 ROP units. The GTX
680 comes with 2048MB of 6GHz 256-bit, 192.26 GB/s memory as well. So,
what does that mean in terms of performance?
OCC: I hope by now, after seeing
these results, that everyone can come to an agreement with, or at least
partially accept, NVIDIA's claim that the GTX 680 is the
fastest and most efficient GPU on the market. In nearly every test, the
NVIDIA GTX 680 beats the AMD HD 7970. In some cases, the
performance numbers of the GTX 680 actually top the dual-GPU card from
NVIDIA. So not only is the NVIDIA GTX 680 the fastest single-GPU card
on the market, it's bordering the edge of the fastest GPU on the
market, period! That's a huge statement, but the numbers don't lie. Not
only does it have more juice than pretty much every other card out
there, it does the amount of work that those cards can do and more,
with less power consumption across the board. The Kepler architecture
is clearly very impressive and I can't wait for what's next from NVIDIA.
TechReport:Also,
the GeForce GTX 680 is a massive generational improvement, extracting
roughly twice the performance of the GeForce GTX 560 Ti from a similar
class of GPU. Still, we're a little disappointed Nvidia isn't
passing along more of those gains to consumers in the form of higher
performance per dollar, as has happened in the past. Half a grand is a
lot to ask for a mid-sized chip on a card with a 256-bit memory
interface. We had a similar complaint when AMD introduced the Radeon HD
7970, and at that time, we expressed the hope that competition from
Nvidia would drive prices down. Now, we're having to face the reality
that the problem isn't really lack of competitive fire at the GPU
companies, it's the limited number of 28-nm wafers coming out of TSMC,
who makes the chips for both firms. The number of good chips per wafer
is likely an issue, too. AMD and Nvidia will probably be able to sell
all of the chips they can get at current prices for a while, simply
because of supply constraints. PCPer: What is maybe even more
impressive and more surprising, is that NVIDIA was able to do
this while actually using less power than the Radeon HD 7970 3GB card
under a peak load. NVIDIA has usually had the fastest
single-GPU option going back to the days of the GTX 285, GTX 480 and
GTX 580, but they always had the caveat of being hot and power hungry.
The new Kepler GPU balances things out in a way that previously only
AMD had the will to do and we found that with features like GPU Boost,
the GTX 680 can balance power consumption with performance across a
wide range of games efficiently.
BenchMarkReviews: Construction
is the one area NVIDIA continually shines, and thanks in part to
extremely quiet operation paired with more efficient cores that consume
less energy and emit less heat, I'm confident that GeForce
GTX 680 will continue this tradition. Reducing the flagship model to
use two 6-pin PCI-E power connections is a step in the right direction,
while tweaking heatsink and fan placement to optimize cooling
performance proves there are still ways to improve on a commonplace
technology. Even better yet, now consumers have a single-GPU solution
capable of driving three monitors in 3D Vision Surround with the
inclusion of two DL-DVI ports with supplementary HDMI and DisplayPort
output.