AMD’S MARKETING pitch for the new Radeon 7800‑series GPUs suggests that “serious gaming starts here.” Built on AMD’s Graphics Core Next, the 7800 series, previously code-named “Pitcairn,” offers impressive performance for less than the price of AMD’s 7900 series. Let’s take a quick look at key features, as compared to the Radeon HD 6870 and 6950 GPUs, AMD’s previous players in the midrange.
The 7870 has 1,280 stream processors—more than the 6870, but fewer than the 1,408 in the Radeon HD 6950. The 7870’s 1,000MHz stock clock speed is 11 percent higher than the 900MHz of the 6870, and twice the 6950’s 500MHz clock. In the Black Edition HD 7870, XFX boosts the core clock an additional 5 percent to 1,050MHz. The 7870 ships with the same 2GB of 256-bit GDDR5 as the 6950—double the 1GB of the 6870.
The Black Edition ships with XFX’s semi-custom dual-fan cooling solution. As with past cards in this class, the HD 7870 requires two 6-pin power connectors. One disappointment: XFX is continuing its policy of leaving out monitor adapter connectors, so if you don’t have a DVI, HDMI, or DisplayPort connector on your monitor, then you’ll need to shell out a little extra for one. It’s mostly not a problem for single-display users, but people with multiple monitors may need to acquire adapters.
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.
ASUS HAS GOTTEN a lot of mileage out of its beefy DirectCU II GPU-cooling technology. It has brought some serious overclocking chops to the GeForce GTX 580 in the form of Asus’s Matrix-branded edition, for example. The DirectCU II versions of the GeForce GTX 560 Ti and the Radeon HD 6870 also sport serious overclocks, and those cards perform well in their respective classes. What’s even better is that the company doesn’t charge much of a price premium for its best cooling tech on cards below the Matrix GTX 580.
We’re scratching our heads, however, over Asus’s decision to offer this GTX 570 card in a three-slot configuration similar to its Matrix GTX 580, but running at Nvidia’s reference clock speeds. The beefy cooler delivers plenty of DIY overclocking potential, but you must assume all the risk. Since we review cards based on out-of-the-box performance, we had to benchmark this one with its 742MHz core clock and 3,800MHz (effective) memory clock.
One good thing the new cooler does provide is fewer decibels. This card isn’t whisper-quiet under load, but it generates much less noise than many of the cards in its class—particularly the Radeon HD 6970, which can get fairly loud under heavy loads.
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.
The Internet's abuzz with yesterday's launch of Nvidia's dual-Kepler GeForce GTX 690 graphics card with two potent GPUs underneath the hood, and if you haven't done so already, be sure to check out our preliminary benchmarks leading up to a full-on review. Following the official launch, EVGA announced it's raring to go with a Signature Edition bundle that packs in a few limited edition extras for a $50 premium.
Nvidia today officially launched its GeForce GTX 690 (see some of our preliminary benchmark results here) dual-GPU graphics card, which arrives a little less than six weeks after the official unveiling of Kepler in the form of the GeForce GTX 680 (see our benchmarks of that card here). Both are formidable graphics cards capable of driving a high-end gaming PC, provided you can find one in stock.
It's still a challenge finding one of Nvidia's Kepler infused GeForce GTX 680 graphics cards in stock and ready to ship, but one thing the new GPU series doesn't lack is third-party variation. Nvidia's GPU partners are putting their own stamp on the GTX 680 with custom coolers and, in some cases like the new DirectCU II TOP edition from Asus, custom designed PCBs as well.
Overclocking a graphics card isn't terribly difficult, and if you're careful, it's not all that dangerous either. But there's always that risk of taking things too far or ending up with components that just don't respond well to faster clockspeeds. Factory overclocked cards get around both problems, and one of the newest on the market is TUL Corporation's PowerColor PCS+ HD7850, a spiffy looking hunk of hardware with a power friendly design.