GPUs
Latest
AMD's mid-range Radeon 500-series video cards are here
With last year's Radeon RX 480, AMD wowed us with a $200 video card that could tackle VR and 1,440p gaming. But with its 500-series cards, it's aiming to make an even bigger leap. How does 1,440p gaming beyond 60 frames per second sound? That's what AMD is promising with the RX 580, the most powerful option in this new mid-range lineup. At the same time, the company is also unveiling cheaper cards, the RX 570, 560 and 550, which cater to gamers who might want to save a few more bucks, or want something that could fit into a tiny case.
NVIDIA's GeForce GTX 1060 gives you gaming power on a budget
After debuting the fastest high-end and mid-range video cards ever seen, the GTX 1080 and 1070, we expected a lot from NVIDIA's new lower-tier entry, the $249 GeForce GTX 1060. And the stakes were raised even higher after AMD launched the Radeon RX 480, a $200 GPU that's fast enough to power VR headsets (and manage some decent 1440p gaming). NVIDIA claims the GTX 1060 is even faster than the GTX 980, its premium video card from 2014. That says quite a bit about how far we've come in the GPU world: You no longer have to break the bank for a decent amount of gaming muscle.
NVIDIA's GTX 1070 is a mid-range GPU that feels high-end
As impressive as NVIDIA's GeForce GTX 1080 GPU is, its high price of $599 is tough to stomach for even the most dedicated gamers. That's where the mid-range GTX 1070 comes in: It's almost as fast as its more powerful sibling, but it starts at a more reasonable $379. That's still a hefty chunk of change, but for the money it can tackle pretty much every game today (and likely for the next year or two) without breaking much of a sweat. That's not too shabby for a mid-range video card.
NVIDIA's GeForce GTX 1060 delivers GTX 980 speeds for $249
If you haven't noticed by now, 2016 is shaping up to be a killer year for PC gaming hardware. We've already seen two major new video cards from NVIDIA, the powerhouse GeForce GTX 1080 and the mid-range 1070, as well as a supremely capable budget GPU in AMD's $200 Radeon RX480. Now, NVIDIA has a cheap new option of its own: the GTX 1060, a $249 card that it claims is just as fast as 2014's flagship GTX 980 (which initially sold for $549). It's launching on July 19 from partners like ASUS, EVGA and Gigabyte. And, just like with its past two cards, NVIDIA is offering a "Founders Edition" for a slight premium of $299.
AMD's Radeon RX 480 is the new king of budget video cards
Instead of trying to build the biggest and most powerful video card on the market, AMD aimed at the low end with the Radeon RX 480. But that doesn't make it any less exciting than NVIDIA's recent powerhouse GeForce GTX 1080 and 1070 GPUs. AMD's pitch for the RX 480 is simple: It's a $200 card that's VR ready. That's huge, especially since the current batch of GPUs that meet minimum VR specs cost around $350. I'll admit I was skeptical when AMD announced the RX 480 at Computex last month. But after putting one through its paces over the past few days, I feel like Han Solo in The Force Awakens. It's true. All of it.
NVIDIA GeForce GTX 1080 video review: Behold, the GPU king
As far as video card upgrades go, there's a lot to love with NVIDIA's GeForce GTX 1080. We called it "the upgrade you've been waiting for" in our full review. The GTX 1080 blows away last year's high-end cards, and even though it's $599 ($699 for the Founders Edition we tested), it's well worth the cost for serious gamers. In our video review above, check out some gameplay footage from the new Doom remake, as well as Quantum Break.
NVIDIA's got a new GPU monster, and it's called Titan X
NVIDIA just announced the Titan X, its latest powerhouse graphics card, at Epic Game's GDC session this morning. And boy, it sounds like a monster: According to NVIDIA CEO Jen-Hsun Huang, it's now the world's most powerful GPU with more than 8 billion transistors (a bit of a jump from the 7 billion in last year's Titan Z). Titan X is powered by the company's new Maxwell architecture, and it packs in 12 gigabytes of VRAM, just like the Titan Z. NVIDIA isn't revealing much else about the new GPU yet -- it has its own conference in a few weeks, after all -- but at this point it sounds like the video card we'll all be pining for this year.
Cray's Jaguar supercomputer upgraded with NVIDIA Tesla GPUs, renamed Titan
Cray's Jaguar (or XK7) supercomputer at Oak Ridge National Laboratory has been loaded up with the first shipping NVIDIA Tesla K20 GPUs and renamed Titan. Loaded with 18,688 of the Kepler-based K20s, Titan's peak performance is more than 20 petaflops. Sure, the machine has an equal number of 16-core AMD Opteron 6274 processors as it does GPUs, but the Tesla hardware packs 90 percent of the entire processing punch. Titan is roughly ten times faster and five times more energy efficient than it was before the name change, yet it fits into the same 200 cabinets as its predecessor. Now that it's complete, the rig will analyze data and create simulations for scientific projects ranging from topics including climate change to nuclear energy. The hardware behind Titan isn't meant to power your gaming sessions, but the NVIDIA says lessons learned from supercomputer GPU development trickle back down to consumer-grade cards. For the full lowdown on the beefed-up supercomputer, hit the jump for a pair of press releases.
NVIDIA Quadro K5000 GPU for Mac offers significant Premiere Pro performance boost, we go hands-on
NVIDIA just announced that its new Quadro K5000 GPU will be available on Mac Pros, offering 4K display compatibility and support for up to four displays, not to mention 4GB of graphics memory and about 2x faster performance than the Fermi-based Quadro 4000. While the Kepler-powered chip won't actually hit Apple systems till later this year, we got a first look at the K500 on a Mac here at IBC. NVIDIA demoed Adobe After Effects and Premiere Pro CS6 on a Mac Pro with dual K5000 GPUs. As you'll see in the video below, with 11 streams of 1080p video at 30 fps in Premiere Pro (and one overlay of the NVIDIA logo), GPU acceleration handles the workload seamlessly, letting us add effects in real time without any processing delay. Switching to software rendering mode in the editing program shows a night-and-day difference: video playback is extremely choppy, and processing moves at a crawl. Even with two K5000 chips in this desktop, Premiere Pro utilizes just one, but After Effects takes advantage of both GPUs. In this program, NVIDIA showed us ray-tracing, a computationally intensive 3D imaging feature, which only became available in After Effects with the release of CS6. Like in Premiere Pro, the program runs smoothly enough to let us edit images in real time. Take a look for yourself by heading past the break.
AMD bares all with Southern Islands GPU shots
AMD's been showing off its forthcoming wares at Hot Chips, and has taken the rare step of releasing detailed die shots for its Southern Islands GPUs. According to AnandTech, the company's shy about releasing such details, since it's aiming to beat rival NVIDIA to the punch by several months. Still, it's letting us humble members of the public peer inside the gallery we've got for you below, just as long as you pinkie-swear that you won't be selling the secrets to the boys in Santa Clara, okay? %Gallery-163817%
AMD announces Radeon HD 7000M series with Enduro graphics-switching technology
AMD kicked off 2012 by refreshing its desktop graphics, and now it's back, giving its mobile GPUs the same treatment. The company just announced its third generation of DirectX 11 mobile chips, the Radeon HD 7000 family. All told, the collection includes three 28nm GPUs: the high-end 7900M, the mainstream 7800M and, last but not least, the 7700M, a darling little chip intended for AMD's thin and light Ultrabook competitors. Across the board, the series ushers in a new feature AMD is calling Enduro, a graphics-switching technology that takes direct aim at NVIDIA Optimus. Building on older AMD technologies like PowerXpress, it doesn't require you to close apps, reboot your system or manually specify which apps will trigger the GPU. Additionally, it's designed to work with both Intel CPUs and AMD's own application processing units, so presumably you'll find this inside some Ivy Bridge machines too. With this generation, too, the two higher-end chips support the PCI Express 3.0 interface, and all three make use of AMD's existing ZeroCore Power and Power Gating battery-saving features. That's the abridged version, but we also have a full breakdown of the specs awaiting you past the break.
Zalman reportedly entering the graphics card market, merging GPUs with cooling solutions
Recently leaked slides suggest Korean computer outfit Zalman will soon jump into the ever-expanding graphics card market, initially partnering with AMD on its Radeon series. Known best for its quiet computing technologies, the company's move to infuse GPUs with cooling solutions could enhance the performance of the cards, making overclocking a lesson in simplicity. The slides only show the AMD 6870, 6850, and 6770, but it's feasible more models will appear when official news is released. Given AMD's many board partners, differentiation is important to remain competitive and on their payroll -- graphics cards and their overheating habits is Zalman's cup of tea. Hopefully this brings more innovative products in the coming future (heck, we've already got GPU / NIC hybrids), perhaps as early as CES. Check past the break to view the specifications breakdown for the aforementioned cards.
NVIDIA announces special edition GTX 560 Ti with 448 CUDA cores, available now for $289
Now that we're officially in the throes of holiday shopping season, NVIDIA's rolling out a promotion of its own, though sadly it doesn't involve any steep discounts. The outfit just announced a special edition GPU: the GTX 560 Ti with 448 CUDA cores, running at 1.46GHz, a 732MHz graphics clock and 1.25GB of GDDR5 memory charging ahead at an effective rate of 3.8GHz. Other features include support for three-way SLI, DisplayPort, HDMI and DVI. Those specs place it snugly between the current GTX 560 Ti with 384 CUDA cores, and the higher-end GTX 570, which packs 480. If this seems like a puzzling move, it is indeed the first time NVIDIA's bothered with a limited holiday edition card, though in conversations with reporters the company made it clear its new hardware is meant to dovetail with the arrival of games like The Elder Scrolls V: Skyrim, Battlefield 3 and Batman: Arkham City. If you're shopping for a gamer (or, you know, yourself), it's available now for $289 in the US, Canada, UK, France, Germany, Russia and Nordic countries through companies like ASUS, MSI and Gigabyte, among others. Update: Looks like the reviews are rolling in! We've linked a handful of 'em below.
Switchable graphics solutions duel it out, AMD ends up looking like a chump
At this point, NVIDIA's Optimus switchable graphics are old hat, but AMD is relatively new to the game of packing dual GPUs in a single laptop. AnandTech decided to pit the two solutions against each other and, well, lets just say AMD doesn't come out looking so great. The biggest problem appears to be stability. While performance is acceptable (though, not quite as good as it should be) the site had trouble getting four of the supposedly 16 supported games to switch between the integrated and discrete GPUs as advertised. Regular driver updates, not to mention a bit more testing, could solve the issues, but for now NVIDIA's Optimus simply outclasses its AMD counterpart. Check out the video after the break and don't forget to hit up the source link for all the details.
ASUS MARS II gets reviewed, deemed the fastest single graphics card on the market
Well, that insane ASUS MARS II card we got to feast our eyes on back in June has finally started rolling off the assembly line. That means it's time for the hardware fanatics and gaming freaks to start putting them through their paces. HotHardware said the dual GTX 580-packing card was "quite simply the fastest single graphics card we have ever tested, bar none." And everyone else seemed to agree. Now, obviously there are drawbacks -- the 3GB card is an absolute power hog (requiring 600-watts all by itself) and insanely pricey at $1,499. You could even buy three separate GTX 580 cards for slightly less, use the same number of slots and get better performance, but the MARS II has one other thing going for it -- status. Only 999 of these beasts will be made. After they're all snatched up you'll have to head to eBay, and pay a hefty premium over it's already absurd price. But, if you absolutely have to have the best performance you can out of a single card solution, this is the clear choice. If you need more detail about just how badly this spanks the competition check out the reviews below. Read - HotHardware Read - PC Perspective Read - techPowerUp Read - TweakTown
NVIDIA's Kepler GPU still (kinda, sorta) on schedule for 2011 debut
Back in September of last year NVIDIA pledged that the successor to Fermi, Kepler, would arrive in 2011. Since then, things have been rather quiet on the next-gen GPU front. In fact, rumors have started to circulate that the 28nm-based chip would be pushed back to 2012. Turns out those rumblings aren't entirely inaccurate. While the latest polygon pushing silicon will start being churned out before it's time to buy a new calendar, final products won't start shipping until next year, as a company rep told TechSpot. Kepler's descendent, Maxwell, is still expected to land sometime in either 2013 or 2014, but there's plenty of time for that timetable to slide back a bit too.
NVIDIA pops out five new mobile GPUs to fill invisible gaps in its 200M series lineup
NVIDIA is filling in what it presumes to be holes in its next-generation GPU lineup, adding the 40nm G210M, GT 230M, GT 240M and GTS 250M, with GDDR3 memory ranging from 512MB to 1GB, to its existing GTX 280M, GTX 260M and GTS 160M laptop graphics cards. Apparently the new cards sport "double the performance" and "half the power consumption" over the last generation of discrete GPUs they're replacing. The cards are SLI, HybridPower, CUDA, Windows 7 and DirectX 10.1 compatible, and all support PhysX other than the low-end G210M. Of course, with integrated graphics like the 9400M starting to obviate discrete graphics in the mid range -- even including Apple's latest low-end 15-inch MacBook Pro -- we're not sure what we'll do with eight different GPU options, but we suppose NVIDIA's yet-to-be-announced price sheet for these cards will make it all clear in time.
More integrated graphics from Apple
Apple released the MacBook, its new consumer laptop, today. The full tech specs -- which are over at Apple's site -- mention that the MacBook features an Intel GMA950: in other words, an integrated graphics chip identical to the Mac mini. Previously we've summarized the disadvantages of integrated graphics and we've moaned about the poor graphics performance of Apple's line-up in an attempt to force someone at Apple to listen, but it was all in vain. Apple's supposed "gaming solution" (Windows) is hardly a solution now that Apple's consumer line-up (MacBook, Mac mini) doesn't have a dedicated graphics card, the prosumer line-up (MacBook Pro, iMac) features a low- to mid-range mobile chip and the remaining top-of-the-range machine (PowerMac) is stuck with PowerPC processors, crappy default GPUs (GeForce 6600s, yuck!) and a largely unobtainable price.If Apple one days wakes up and realizes that there are a load of potential gaming switchers sitting on the fence it would either: tell, no, force Intel to make some integrated chips that aren't "virtually unplayable for anybody that cares about gaming" or provide the option of dedicated graphics cards for gamers, even if it costs us more.
