A massive GPU that’ll be hard to find, and even harder to beat
Today Nvidia is pulling the wraps off the GK110-based GeForce GTX Titan, a single-GPU card that is expected to easily capture the title of Baddest Ass GPU in the world when benchmarks are released this Thursday, February 21st. The Titan is Nvidia’s “Big Kepler” GPU, and has double the transistors and almost double the CUDA cores of the mid-range GK104 chip found in its flagship GeForce GTX 680 GPU. Though it runs at a lower clock speed in stock trim, it should still offer a sizable performance improvement over the already capable GTX 680.
The GTX 660 is the first 28nm Kepler board based on a new GPU dubbed GK106, and the final 6-series card to support high-performance features like GPU Boost and SLI. Compared to the GTX 660 Ti, the GTX 660 offers the same 2GB of DDR5 memory, the same 192-bit memory interface, and the same number of ROP units, but loses two SMX units compared to the GTX 660 Ti, giving it just 960 CUDA cores compared to 1,344 in the previous cards (and the 1,536 in the GTX 680). At $230 it’s our new favorite GPU in the price-to-performance category.
When is a GTX 560 Ti not really a GTX 560 Ti? When it’s almost a GTX 570.
Nvidia’s latest GPU, the GTX 560 Ti 448 is really a GTX 580 (originally dubbed the GF110) with two functional blocks disabled, reducing its CUDA Core count from 512 to 448. The GTX 570 is a GF110 with one functional block disabled, endowing it with 480 CUDA Cores. The original GTX 560 Ti is a completely different chip, with different power requirements, but all 384 of its cores are fully functional.
Does a paltry 256MB of RAM matter? Apparently, it does, if you’re talking about Nvidia’s GF104-based GTX 460 cards.
In the October issue, we took a long look at Asus’s sweet GTX 460 768MB card. While that card impressed us for the most part, it did seem a little weak in a few areas, especially when you turned up antialiasing. This 1GB version isn’t just the same chip with another 256MB of GDDR5 memory slapped on.
The memory bus is actually wider than the 768MB card, at 256 bits wide instead of 192 bits wide. That extra bus width is managed by a fourth memory controller on board the chip (the 768MB card has only three memory controllers.) If you’re thinking that the 1GB version of the GeForce GTX 460 should have had its own model—perhaps GTX 463—you’re not alone. A lot of people have wondered why Nvidia would use the same nomenclature for these two different beasts. The chip itself is the same. The 1GB chip is based on TSMC’s 40nm process technology, and has the same 1.95-billion transistor count as the 768MB version.
GPUs that cost $500 are all well and good, but the sweet spot for high-end graphics cards is in the $350–$400 range. That’s still a good chunk of change, but it can get you a card with close to 90 percent of the performance of high-end cards.
That’s certainly true of EVGA’s GTX 470 SC. Built on a cut-down version of Nvidia’s high-end, DirectX 11 GPU, this card posted eyebrow-raising benchmarks, pretty much putting it into a class of its own.
EVGA’s super-clocked GTX 470 GPU ships with 448 shader processors, running at 625MHz, with a shader clock of 1,280MHz. That’s a 3 percent faster core clock and 2.5 percent faster memory frequencies than the stock GTX 470. (The GTX 480 uses 480 shader processors at 700MHz). The 320-bit-wide memory interface pumps data to 1,280MB of GDDR5 running at 850MHz (3,400MHz effective.) Of course, the card supports the usual set of Nvidia features, including hardware SLI, PhysX acceleration, and 3D Vision Surround video.
More than a few early GTX 280 and GTX 260 adopters are catching a break thanks to vendors stepping up to the plate with cash back offers. XFX announced it would give its qualified customers up to $120 back in the wake of Nvidia's aggressive price cuts, and Evga has opened up a similar program. Evga customers must have purchased their GTX 280 or 260 videocard between June 16, 2008 and July 7, 2008 to be eligible for the kickback, and those eligible can choose between $75 in Evga bucks or $60 cash back (GTX 260), or $150 in Evga Bucks or $125 cash back (GTX 280). Other terms and conditions include:
Must be a new purchase from an authorized Evga reseller. Step-ups do not qualify
You have 14 days to register and upload a qualified invoice to claim your Evga Bucks
Only customers who purchased the Evga GTX 280 or GTX 260 at the full Manufactured Suggested Retail Price (MSRP) will qualify for the Reimbursement Program
So far this marks two Nvidia partners (that we know of) offering relief to early adopters affected by the quick price cuts, and it's anyone's guess if more will follow. Who thinks BFG will be next?
Being an early adopter doesn't always net you bragging rights. Just ask your neighbor how his HD-DVD player is working out for him, or your co-worker what he bought with his Apple gift card after being one of the first to own an iPhone. And in the world of PCs, being the first to own a Geforce GTX 280 means you're stuck watching others pay $499 for the same videocard you plopped down $649 for just weeks ago.
It's because of this that XFX's latest announcement comes as an epic win for its customers. The company says it wants to "thank you for your loyalty and believing in the XFX brand," and to prove it, XFX is issuing up to $120 cash back for anyone who purchased an XFX-brand Geforce GTX 280 or 260 videocard between June 16, 2008 and July 11, 2008. This from the same company that offers a double-lifetime warranty on all its videocards.
If you’re already gaming with a G92-based 8800 GTS, there’s very little reason to move up to a G92-based 9800 GTX such as PNY’s XLR8. The architecture in both GPUs is nearly the same, with 128 stream processors, a 256-bit interface, and 512MB of GDDR3. Slightly faster clock speeds yield only a modest bump in performance. That’s not to say the 9800 brings nothing to the table, but you’ll have to decide for yourself whether its offerings are worth the price.
Watching the ongoing race between AMD and Nvidia to build the ultimate graphics processor reminds us of the tale of the tortoise and the hare. AMD has played the hare, aggressively bounding ahead of Nvidia in terms of process size, number of stream processors, frame buffer size, memory interface, die size, and even memory type. Yet Nvidia always manages to snag the performance crown. The GeForce 200 series is but the latest example. We lay hands on the smokin’-fast GeForce GTX 280. Could this be the graphics processor to finally tame Crysis? We reveal what makes the card unique and how its architectural advances translate in the benchmarks!