Items tagged with Fermi
Just before the end of 2017, NVIDIA dropped a bit of a bombshell: it'd be soon dropping support for 32-bit OSes with its GeForce GPU drivers. Admittedly, such a move was inevitable, as x64 OSes have been available to mainstream audiences for at least 13 years, with Windows XP Professional x64 Edition having released on April 25, 2005. The end is now nigh, and NVIDIA has laid out all of the details on its support website. First and foremost, NVIDIA plans to drop all 32-bit GPU driver support on the GeForce side effective this month. Security releases will continue to be issued until January 2019. What this means for those stuck on 32-bit OSes is that they will lose access to Game Ready updates,...
Read more...
When we evaluated NVIDIA’s Maxwell-based GeForce GTX 750 and 750 Ti a few weeks back, we lauded the GPUs for their competitive performance and class-leading power efficiency. The GeForce GTX 750 and 750 Ti are mainstream products that didn’t tear up the benchmark charts like a bleeding-edge high-end GPU would, but their Maxwell-based GPUs competed well with similarly priced products and they did so at much lower power levels. The power efficiency of NVIDA’s Maxwell architecture make it ideal for mobile applications, so today’s announcement by NVIDIA of a new top-to-bottom line-up of mobile GPUs—most of them featuring the Maxwell architecture—should...
Read more...
If you've paid attention to quarterly earnings reports from the major computer OEMs, you've likely noticed that the hard drive shortage this fall had an impact, but not a disastrous one. Companies like Intel reported that manufacturer inventories were substantially affected as company's held off on restocking to see what prices would do, but net sales only fell modestly. The GPU market, on the other hand, seems to have taken a hit. Nvidia has stated that its Q4 results were hurt by the hard drive shortage, something AMD also mentioned in its Q4 results. We didn't break it out initially -- AMD's overall GPU results were fairly decent -- but in the wake of NV's statements it's worth revisiting....
Read more...
At its Fusion Development Summit this week, AMD discussed the concepts and capabilities it's targeting for future generations of AMD graphics cards. The company isn't sharing any specific architectural features, but even the general information it handed out is interesting. Demers began by talking about the history of ATI's graphics card and the evolution of the company's GPU design. When ATI originally designed its DX9 hardware, it designed its vertex shaders to use a VLIW5 (Very Long Instruction Word) implementation. Back in such halcyon days of yore, Nvidia's programmable G80 was scarcely a twinkle in David Kirk's eye. Pixel and vertex shaders were two different animals. ATI's VLIW5 approach...
Read more...
Larrabee, Intel's once-vaunted, next-generation graphics card died years ago, but the CPU technology behind the would-be graphics card has lived on. Intel discussed the future of MIC/Knight's Corner today. After Larrabee was officially canceled, Intel repurposed the design and seeded development kits to appropriate market segments. MIC cards won't start shipping until the 22nm Knight's Corner chip is launched, but even the Knight's Ferry prototypes offer tantalizing hints at what future performance might be resemble. Like Larrabee, Knight's Corner (and future MIC products in general) utilize a CPU based on Intel's original Pentium architecture (P54C). Modifications include complete cache coherency,...
Read more...
Heather Mackey of Nvdia has written a new blog post discussing the company's hardware emulation equipment, thus affording us an opportunity to discuss a little-mentioned aspect of microprocessor development. Although we'll be discussing Nvidia products in particular, both software tools (aka, simulation) and hardware emulation are vital to all microprocessor design firms, including Intel, AMD, Via/Centaur, and ARM. There's a significant difference between software simulation and hardware emulation. In simulation, software tools are used to simulate the logic of a new design or product respin. The advantage to simulation is that most such tools are mature, flexible, and inexpensive. The...
Read more...
When we published our analysis of JPR's Q1 2011 GPU market share yesterday, we noted that Nvidia's share of the entire market had dropped significantly due to declining sales in their integrated graphics business. We also discussed how the rise of 'Fusion' hardware from both AMD and Intel will inevitably squeeze NV's share of the lower-end GPU market in years to come. This follow-up is a more detailed look at Nvidia's performance in discrete GPU sales. Nvidia doesn't contest the JPR article as such, but is concerned that the expected decline of their integrated chipset business could confuse readers into thinking that the company's share of the discrete market is slumping badly. Hence, this article....
Read more...
Last week, Futuremark released the latest version of 3DMark. We've taken the new benchmark for a spin using CPUs from Intel and AMD as well as GPUs from AMD and NVIDIA. The new version, dubbed 3DMark 11 (in reference to its level of DirectX support, not the upcoming year) includes a fresh set of tests, a game demo sequence, and measures CPU performance rather differently than its predecessor, 3DMark Vantage. We ran the benchmark through multiple tests, comparing it across AMD and Intel CPUs as well as AMD vs NVIDIA GPUs....
Read more...
Last week, Futuremark released the latest version of 3DMark. We've taken the new benchmark for a spin using CPUs from Intel and AMD as well as GPUs from AMD and NVIDIA. The new version, dubbed 3DMark 11 (in reference to its level of DirectX support, not the upcoming year) includes a fresh set of tests, a game demo sequence, and measures CPU performance rather differently than its predecessor, 3DMark Vantage. 3DMark 11: Now with additional oceanic encrustations. We've run the benchmark through multiple tests, comparing it across AMD and Intel CPUs as well as AMD vs NVIDIA GPUs. According to Futuremark, 3DMK11 was designed meet four specific goals. These are: Produce consistent results that...
Read more...
NVIDIA's been in the news quite often this week, primarily due to the release of the newest GPU in the GeForce Fermi desmtop series. Now, ZOTAC is offering another new graphics card: the GeForce GTX 580 AMP! Edition. As with all of the AMP! cards, this one is also turbocharged and ready to crank through today's latest titles. It is overclocked from the factory, and it fully supports DirectX 11. There's an 815MHz clock speed, 512 unified shaders, a 1630MHz shader clock, 1536MB of GDDR5 memory, a 384-bit memory interface, 4100MHz memory clock and a PCIe 2.0 interface. Of course, NVIDIA's 3D Vision is supported, and there's HDMI 1.4 compliance and a fully copy of Prince of Persia: The Forgotten...
Read more...
If you're a fan of GPGPU computing this is turning out to be an interesting week. At SC10 in New Orleans, Intel has been demoing and discussing its Knights Ferry development platform. Knights Ferry, which Intel refers to as a MIC (Many Integrated Core) platform, is the phoenix rising rising from the ashes of Larrabee. Future MIC products (Knights Ferry is a development prototype, the first commercial product will be called Knights Corner) will mesh x86 compatibility with a level of parallelism typically found only in cluster nodes. Intel's Knights Ferry Knights Ferry contains 32 indepedent x86 cores with quad HyperThreading, fits into a PCIe 2.0 slot, and offers up to 2GB of DDR5 memory per card....
Read more...
Mac graphic gurus users rejoice -- Nvidia today announced the expansion of its Quadro professional videocard line to the Mac platform, finally giving Mac OS X Snow Leopard users access to the Fermi architecture. "Adobe Premiere Pro CS5 and the Adobe Mercury Playback Engine, accelerated by NVIDIA Quadro GPUs, have redefined the non-linear editing workflow, delivering huge productivity gains," said Ginna Baldassarre, senior product manager at Adobe. "Adobe looks forward to working with NVIDIA to help more Mac users reap the benefits of real-time performance and the ability to create compelling, multi-layer projects with multiple HD or higher resolution video clips, all while instantly viewing results."...
Read more...
Futuremark hasn't told anyone when it plans to launch 3DMark 11, but the video and screenshots the company has released thus far point towards a gorgeous application. It's arguably timely; the three-year-old 3DMark Vantage doesn't support DirectX 11. This could probably be fixed via an update, the same way 3DMark 2005 was rebuilt as 3DMark 2006, but Futuremark apparently has enough changes in mind to justify a new program. These tidings are virtually guaranteed to kick off a fresh round of debate over whether or not 3DMark is a "real" test, or whether it deserves to be considered a benchmark at all. In addition to providing news of the actual video, we've decided to tackle this question. It's...
Read more...
It's nothing new to see AMD and NVIDIA arguing over benchmarks, but news that came across our desk today put a new twist on a very old battle. A few days ago, NVIDIA contacted us and inquired if we'd be interested in testing HAWX 2's stand-alone benchmark for evaluation, noting that tessellation effects were employed for better terrain realism. We said sure—a number of DX11-enabled games and/or test programs make use of the effect currently. Synthetic benchmarks aren't much better at this point; Unigine might as well be called TesselationMark. NVIDIA's Reviewer's Guide also put great emphasis on the game's use of tessellation and Fermi's superior performance in that area. We read...
Read more...
NVIDIA's Fermi has made a huge splash lately. Particularly with gamers, Fermi has proven to be a real gem, and the benchmarks are here to prove that it's a serious contender in the gaming world. But what about the pros? NVIDIA has an eye out for them as well, and today they too are feeling the Fermi love with a pair of Quadro GPUs. The new Quadro 2000 (with 192 CUDA processing cores) and the Quadro 600 (with 96 CUDA cores) are both based on Fermi, with the 2000 delivering 1.5 times the geometry performance of the previous Quadro graphics processing unit in the mid-range sector. It also utilizes the new NVIDIA Scalable Geometry Engine technology to deliver dramatically higher performance across...
Read more...
If you've read our review of NVIDIA's new GTS 450 and are hungry for additional information, we've rounded up some of the other coverage online for your perusing pleasure. Tech Report has information on stock and overclocked cards with SLI tossed in, as do our lovable, polite Canadian brothers. Hexus.net has its own review on some single card matchups, Over at Legit Reviews, Nathan Kirsch goes into some detail on NVIDIA's target market for the GTS 450, and tests a few games other sites didn't. If you're curious about numbers for Batman: Arkham Asylum, Stalker: Call of Pripyat, or FurMark 1.8.2, he's got the goods. Similarly, Tweaktown has performance data on Resident Evil 5, HAWX, Lost Planet...
Read more...
Asus, meet NVIDIA. NVIDIA, meet Asus. We know you two have a long history of working together, but this particular union seems more important than ever before. The G53 and G73 gaming notebooks were powerful before, but the newest versions are even more potent. These two machines have just been upgraded with NVIDIA's GTX 460M (Fermi) graphics engine, meaning that DirectX 11 support and high-end 3D gaming are both included. Both machines also enjoy a rear vented cooling system, ergonomic keyboard layout, 1.5GB of GDDR5 memory and plenty of screen real estate. The G73 has an eye-popping 17" panel, while the G53 steps it back to 15". Also, both machines are cut out for 3D gaming, and the HDMI 1.4...
Read more...
NVIDIA has just taken the wraps off an entire line-up of Fermi-based GeForce GT and GTX 400M mobile GPUs—seven in total---and revealed a number of notebook design wins from major OEMs using the GPUs. Like their desktop-targeted counterparts, the mobile GeForce GT and GTX 400M series GPUs leverage technology from NVIDIA’s Fermi architecture, which debuted in the GF100 GPU at the heart of the company’s flagship GeForce GTX 480. GeForce GT and GTX 400M series GPUs are DirectX 11 compatible and support all of NVIDIA’s “Graphics Plus” features, including PhysX, 3D Vision, CUDA, Verde drivers, and 3DTV Play. All of the GeForce GT and GTX 400M GPUs support NVIDIA’s...
Read more...
Zotac's GeForce GTX 480 Amp! Edition was designed to address some of the issues found in NVIDIA’s reference design. One look and it's easy to see that this is an extreme graphics card, made for hardcore enthusiasts. What makes us say that? With a core frequency of 756MHz, 1512MHz shaders, and 950MHz memory, this is the fastest GTX 480 on the market currently. And the preinstalled, triple slot Zalman VF3000 cooler also makes it one of the largest cards you can buy. Nevertheless, it’s obvious to us that Zotac made no compromises in designing this bad boy, which caters to hardcore gamers who won't settle for stock... Zotac GTX 480 Amp Edition Video Card Review...
Read more...
By now, we all know that NVIDIA's flagship GeForce GTX 480 is a powerful graphics card. For most systems, it provides a lot more GPU muscle than is even necessary, but that's OK with us. We're sure there are many enthusiasts out there that consider overkill a good thing. Unfortunately, the card in its reference form is not perfect and has its own set of flaws that might turn off some consumers, namely excessive heat and noise. Roughly $500 is a lot of money to spend on a single PC component. And if a product commands such a high price, any perceived drawbacks can be a tough pill to swallow. Without a doubt, if you happen to have that much disposable income to spend on a video card upgrade,...
Read more...
NVIDIA has never been a company to shy away from a fight, even if that fight is very public. The company has been battling with Intel off and on again over the past couple of years, with comics and harsh words from NVIDIA's CEO leading the way. But for as confident as NVIDIA is about their company, their hardware and their software, we have always heard that there's nothing quite like getting a taste of one's own medicine. AMD's processors haven't exactly been the coolest bunch; the Neo platform in particular can warm an ultraportable up in rapid fashion, but the company has nicely dodged that in a new short film aimed directly at NVIDIA's graphics business. AMD vs. NVIDIA has been another longstanding...
Read more...
The International Trade Commission has announced its findings in the NVIDIA/Rambus patent infringement lawsuit and it's not the sort of ruling Team Green would've preferred. The commission found NVIDIA to be in violation of three Rambus patents. The trade panel also granted an injunction Rambus had requested, which theoretically prevents NVIDIA and the various companies attached to the lawsuit (Asus, HP, Palit, and MSI among others) from selling products that contain the infringing IP. This last bit sounds more ominous than it actually is; there's a 60-day window before the injunction takes effect and NVIDIA believes it has other options. "There will be no impact on our customers or our business...
Read more...
