Asus has been coming on strong in graphics cards for several years now, though it never offers quite the variety of versions as companies like XFX and EVGA. Typically, Taiwan-based Asus will ship a reference card under its main brand, and then a custom-built, high-end card under its DirectCU brand. At a later date, the company might ship a super-high-end card using the company’s Matrix or Mars sub-brands. Price differences between Asus’s high-end and standard versions are wider, too, so it’s a little easier to figure out which card really is the premium version.
Consider the bog-standard reference-card design. Enthusiasts often sneer at the thought, but the GTX 680 reference design is efficient, quiet, and fast. You often have to spend extra for higher clocks and more fans—and more moving parts and heat often equate to a higher probability of failure.
The EVGA GTX 680 we’re reviewing here is a standard reference card, but EVGA equips it with one of the best overclocking software tools we’ve tested.
You can use Precision to tweak the base clock, Boost clock, voltage, fan settings, and more. The GTX 680 GPU itself offers good overclocking headroom, so a few quick tweaks using Precision should get you 5–10 percent pretty easily.
Unpacking the XFX HD 7950 Black Edition caused a bit of déjà vu. The card bears a strong resemblance to its big brother, the HD 7970 Black Edition (reviewed April 2012), clad in svelte brushed aluminum. If graphics cards dressed up for black tie galas, then the XFX Black Edition is ready to attend.
XFX pushes the reference clocks higher than stock, hitting 900MHz for the core clock and 1,375MHz for the memory clock. The additional memory cycles translate to a peak memory bandwidth of 5.5 gigabytes per second—the same as the HD 7970, and higher than the 5GB/s of the stock 7950. The question is: Can the GPU keep up? There’s always a balance between memory bandwidth and how much of that bandwidth the GPU cores can actually use. Plus, as more games become shader- and tessellation-intensive, bandwidth isn’t as big a part of the equation.
AMD’s reference HD 7950 board sets its core clock at 800MHz and memory at 1,250MHz, using the default cooling system. Sapphire takes this reference board, adds dual 12cm fans, and juices the core clock to 900MHz. The memory clock remains at 1,250MHz—but that’s 3GB of 1,250MHz GDDR5. Priced at around $480, it’s worth seeing how the card compares with Nvidia’s GTX 580. Note that we’ve also included results from the XFX Radeon HD 7970 for your reference, but excluded that card from the direct comparisons.
For direct comparison we turned to two different versions of the GTX 580—the slightly overclocked EVGA GTX 580 SC with 1.5GB of GDDR5 and the ultra-beefed-up EVGA GTX 580 Classified with 3GB of video RAM—as well as the XFX Radeon HD 7950 Black Edition reviewed next.
The Sapphire card ships with a slight memory bandwidth disadvantage compared with the XFX card (5GB per second versus 5.5GB/s) due to running its GDDR5 frame buffer at the reference clock speed. This shows up in a few benchmarks, where the Sapphire card places just a little behind the XFX card, but the differences are pretty small.
‘We don’t need no stinkin’ reference design!’ says XFX
It's not unusual to see factory-overclocked videocards ship with custom cooling solutions a few months after a GPU launches. But XFX didn’t waste any time with its Radeon HD 7970 Black Edition—a factory-overclocked card with a custom cooling solution that aims to take the performance crown. Based on what we’ve seen to date, XFX has delivered the fastest single-GPU card on the planet.
The Radeon HD 7970 is AMD’s latest GPU, with support for DirectX 11.1 and OpenCL 1.2. It’s a brand-new architecture—completely different from past AMD GPUs—built on TSMC’s 28nm manufacturing process and sporting a staggering 4.3 billion transistors. In AMD’s reference design, the 7970’s core runs at 925MHz, and its GDDR5 memory is clocked at 1,375MHz. XFX ups the ante significantly, pushing the core clock speed to a whopping 1GHz and running its 3GB of memory at 1,425MHz.
As you might imagine, the results are nothing short of amazing. We’re seeing genuine performance milestones here, including a 3DMark 11 performance score higher than 8,000 (for a single GPU), Far Cry 2 hitting 100fps at 2560x1600 with 4x AA, and Batman: Arkham City heading north of 50fps at the same resolution and AA settings. On top of that, the idle system power is just 124 watts, and a dark idle (when Windows 7 blanks the screen) draws 110 watts. Push the card and you’ll see system power consumption climb to 349 watts, but that merely puts its overall power draw into Fermi territory. XFX’s Radeon HD 7970 Black Edition is substantially faster than EVGA’s super-overclocked 3GB GeForce GTX 580 Classified, and it’s outfitted with just two PCIe power connectors (one 8-pin and one 6-pin). EVGA’s card requires three power connectors.
Nvidia’s new Kepler-based graphics cards are still fairly new on the scene, but a fairly serious new bug has emerged that started out as a forum rant, and has evolved into an official acknowledgement from the green team. The problem in question seems to be limited to GTX 670, 680, & 690 customers who enable v-sync though the Nvidia control panel, and by most accounts, is pretty infuriating.
Ruh-roh! Being an early adopter of technology often means putting up with headaches while a product's kinks get worked out, and it seems that's holding true for at least some early GTX 670 buyers. EVGA apparently forgot to quality test a small batch of GTX 670 Superclock cards and is recalling them as a result.
After the GTX 670 launched to pretty much universal applause last Friday, a mini-controversy began brewing almost immediately: did it support 4-way SLI or not? The card uses the same GPU as the quad-enabled GTX 680, the PCB sports two SLI connectors, reviews from prominent online enthusiast sources listed the card as supporting quad-SLI, and heck, Asus photos for the GTX670 DirectCU II TOP even show it in a quad setup. Lots of other reviewers said 4-way SLI wasn't available, however. What gives? Does the GTX 670 support 4 card setups or what?
Nvidia President and Chief Financial Officer Jen-Hsun Huang gleefully indicated that "Kepler GPUs are accelerating our business" when reporting revenue of $924.9 million for the company's first quarter of fiscal 2013 ended April 29, 2012. The irony there is that Kepler cards are in short supply and extremely difficult to find in stock, save for the GeForce GTX 670, which just went on sale yesterday. But despite GPU shortages (courtesy of TSMC's inability to produce chips fast enough), Nvidia was able to best analysts' expectations.
Nvidia's Kepler unveiling essentially amounted to a paper launch, but that doesn't mean the company's GPU partners are sitting around twiddling their collective thumbs. New derivatives of the GeForce GTX 680 graphics card are coming out all the time, the newest ones being a pair of FTW cards from EVGA with overclocked specs, a sturdier design, and even twice the amount of memory.