NVIDIA renames two OEM cards, cuts RAM in half
NVIDIA has shaken up its GeForce graphics card lineup, rebranding two budget-priced OEM GT 500-series cards from the Fermi-era architecture into 600-series examples. The GT 520 will now be known as the GT 620 while the GT 510 becomes the GT 605. Other than the name change, there are some slight hardware changes, though mostly not for the better.
NVIDIA GeForce GTX 590 gets Thursday launch, tease
NVIDIA in a quick video teaser (below) gave a hint of the GeForce GTX 590 along with its release date. The company wouldn't give direct clues other than that it's the highest-performing graphics chipset yet, but it did show Crysis 2 running smoothly in the background as a likely sign of how well it would run. The project was two years in the making, NVIDIA's Tom Peterson said.
NVIDIA GeForce GTX 550 Ti official
NVIDIA pushed its second-generation Fermi graphics architecture further into the budget realm on Tuesday through the GeForce GTX 550 Ti. Its card costs just $150 and drops below the $250 of the GTX 560 Ti by cutting back on its parallelism It uses 192 processing cores versus the higher-end chipset's 384, a reduced 192-bit memory bus (versus 256-bit) and has half the texture addressing units at 32, although it partly compensates with a higher 900MHz main clock and faster 1.8GHz GDDR5 memory.
Lenovo outs IdeaPad Y470, Y570 with SSD, HD combos
Lenovo's PC updates on Tuesday were headlined by two IdeaPad notebooks that claim to be more responsive than even the MacBook Air. The 14-inch Y470, as well as the 15.6-inch Y570 and Y570d, each have the option of a 32GB or 64GB SSD for the OS alongside a regular hard drive. Along with Intel's new Sandy Bridge processors and optimizations to the boot process, they can start in as little as 10 seconds, versus Apple's 15 seconds, while still holding as much as 1TB of regular space.
NVIDIA GeForce GTX 570 official at mid-range
NVIDIA today confirmed its second-ever GeForce 500 series chipset in a push to bring its new graphics to the mainstream. The GTX 570 has the exact same 480 cores as the old GTX 480 but, through the refined architecture, runs at a higher 732MHz main clock speed, 1.46GHz clock for each core and a 1.9GHz memory clock. It uses a narrower 320-bit memory interface (down from 384 bits) but, due to the combined improvements, has a higher texture fill rate bumped up from 42 billion to 43.9 billion pixels per second.
NVIDIA GeForce GT 540M ramps up notebook video
NVIDIA overnight quietly brought out its first 500-series GeForce notebook graphics. The GeForce GT 540M like the GTX 580 is primarily a clock speed increase with an increase in its main and effects core clock speeds to 672MHz and 1.34GHz each. It shares the GeForce GT 435M's 96 cores and 128-bit memory bandwidth.
Palit spoils GeForce GTX 570 specs before debut
Video card maker Palit late today spoiled NVIDIA's plans for its next 500-series graphics chipset with details given out days ahead of launch. Sales sheets sent out early have shown the GeForce GTX 570, a more mainstream alternative to the GTX 580, that would potentially outperform the older GTX 480 flagship while still costing less. The design would have a lower 1.28GB of RAM and a narrower 320-bit bus, according to Kitguru's copy, but would boost the main clock speed from 700MHz to 732MHz while also using faster individual shaders and video memory.
GeForce GTX 595 ready, delayed until 2011?
The first dual-chip GeForce 500 graphics card from NVIDIA has been spotted in photos online. The card is said to be the GeForce GTX 595, a high-end, single-board card with two Fermi GPUs. While tech specs are still relatively scarce, it's believed on enet it will have 3GB of total memory split between the two processors.
NVIDIA Quadro 4000 for Mac arrives
NVIDIA today brought its Fermi graphics architecture to the Mac at last by launching the Quadro 4000 for Mac. The workstation-class video supports the same features as its Windows counterpart and focuses heavily on general-purpose computing. It gives a lift to OpenCL in Snow Leopard and can greatly accelerate apps that are using NVIDIA's own CUDA language as well, such as video processing in Adobe Premiere Pro CS5.
NVIDIA GTX 580 debuts at up to 160pc faster
NVIDIA today at last confirmed the existence of the GeForce GTX 580, its new graphics leader. The design jumps from 480 processing cores to 512 and adds 16 PolyMorph (hardware geometry tessellation) units that significantly boost the performance, especially when they can be fully used in DirectX 11 and OpenGL 4.1. In extreme cases, a GTX 580 can be up to 160 percent faster than a Radeon HD 5870 in a game like HAWX 2 and 62 percent faster in a DX9/DX10 game like StarCraft II.
NVIDIA GeForce GTX 580 nears for late November
NVIDIA's next-generation Fermi-based graphics chipset, the GeForce GTX 580, was said today to be shipping in late November or early December. The design is estimated to be about 20 percent faster than a GTX 480. It would be followed by 2011 releases of mainstream cards using the GF112, GF114 and GF119 architectures, which would mostly pare back the GF110 architecture the GTX 580 will use.
NVIDIA Kepler to be 3X more efficient than Fermi
As part of its GPU Technology Conference, NVIDIA today provided a brief glimpse at its future graphics architecture, Kepler. The design will replace the Fermi core of today's GeForce 400 series and should calculate about five gigaflops of per watt, or more than three times the 1.5 gigaflops of Fermi hardware. Both the redesign as well as a shrink in the assembly process from 40 nanometers to 28 should reduce the need for extra cooling and power in notebooks and other hardware in tight spaces.
AMD and NVIDIA focus on mid-range graphics in fall
AMD and NVIDIA may focus their attention on mid-range graphics with new introductions this fall, based on early details divulged this morning. The Radeon HD 6000 series would start with just two models in the 6700 line; their names aren't known by DigiTimes, but they would be the Barts XT and Barts Pro hinted earlier and would be direct replacements for the 5750 and 5770. Both are rumored to get their unveiling in October.
NVIDIA GF GT 425M surfaces in ASUS notebook
NVIDIA's first mainstream GeForce 400 notebook chipset, the GT 425M, has surfaced in leaks earlier this month. Semi-Accurate noted that the graphics core has been listed as showing in a 17-inch ASUS notebook, but with different features. Some list it as only a DirectX 10 chip, implying that it's only a refreshed 300M chip, while others mention DirectX 11 and that it would use a version of the Fermi architecture in the GTX 480M.
NVIDIA revamps Quadro line for new architecture
NVIDIA today began shipping its long promised Fermi-based Quadro workstation graphics cards. They share the same, DirectX 11-capable (and OpenGL 4.1) cores as the GeForce 400 series and are theoretically up to five times faster than the models they replace. At the top, the Quadro 6000 has a large 6GB of GDDR5 video memory and can handle as many as 1.3 billion triangles per second across its 448 processing cores.
GF104 could replace most NVIDIA hardware
NVIDIA's upcoming GF104 architecture, once targeted at just the mainstream, could soon take over virtually all of the company's GeForce graphics chipsets. The GTX 460 and now GTS 455 were the primary targets, but it's now thought that every other mid-range and low-end GeForce 400 card will use the same architecture, which uses about 25 percent less power and should work better for low-end hardware.
GeForce GTX 465 hits mainstream pricing
NVIDIA today launched its first mainstream graphics chipset in the Fermi family with the GeForce GTX 465. The chipset scales back from the GTX 470 with 352 visual effect (stream) processors versus 448, 32 render output processors versus 40, and slightly slower 802MHz GDDR5 memory on a 256-bit bus. It still runs at the same clock speed and carries the full feature set, which gives it DirectX 11 (and OpenGL 4) features as well as higher-performance general computing in CUDA, PhysX and OpenCL.
GeForce GTX 480M shows up in pro notebook
Eurocom inadvertently spoiled NVIDIA's mobile graphics plans today through the description of its X8100 Leopard mobile workstation notebook. The system now has the option of a GeForce GTX 480M that would presumably replace the 280M as NVIDIA's fastest notebook graphics. It doesn't appear to be a typo as it's described using the Fermi architecture, a much larger 2GB of video memory on one chip, and the newer 40 nanometer process used on newer GeForce chipsets.
NVIDIA may have third GTX 400 chipset
NVIDIA is said to be working on a third high-end Fermi-based graphics card, at the bottom part of the GeForce GTX 400-series lineup. An unnamed but historically reliable source says the card will be known as the GTX 460 and have 1GB of GDDR5 RAM along with a 256-bit memory interface. It will use an NVIDIA-reference board design, but third parties are said to have their own design rights.
GeForce GTX 480 and 470 finally official
NVIDIA at PAX East tonight finally released the first video chipsets based on its Fermi architecture. The top-end GeForce GTX 480 leads the group and is billed as the "fastest GPU in the world:" it has 480 visual processing cores, 16 geometry units and four raster units that combined should beat the ATI Radeon HD 5800 series in real-world tests. It also has major optimizations to multi-card SLI that produce a 90 percent speed boost with a second card, making the case for multiple GeForce 400 series cards in high-end systems.
Leak spoils NVIDIA's 2010 mid-range plans
NVIDIA should launch mid-range counterparts to the imminent GeForce GTX 480 in roughly two months' time, according to a new roadmap. Cards based on the new GF104 architecture should ship as early as June and would, as is often the case, scale down the design but keep its feature set. Its fastest variant, the GeForce GTS 450, would have just 256 shader (effect) cores and a 256-bit memory bus versus the 448 cores and 384-bit bus of the GTX 480, but it would theoretically outperform the upper-mid-range Radeon HD 5830 and cost 200 euros ($268).
NVIDIA GeForce GTX not as costly as believed?
NVIDIA's upcoming GeForce GTX 480 graphics hardware will not be as costly as initially expected, according to a Monday Fudzilla rumor. The company is rumored to price the card at 450 euros, which should also mean a roughly $450 price in the US; early estimates and indications had pricing set at closer to $680.
NVIDIA Fermi cards only for loyal firms initially
NVIDIA's GeForce GTX 470 and 480 will only be available in short supply and at very high prices, a leak from within the graphics field claims. Although the company has promised a launch on March 26th at PAX East, boards based on the new architecture will reportedly only be available through the companies most loyal to NVIDIA and don't sell any ATI-branded graphics. The sources allege that "second-tier" third parties that sell both brands will have to wait until sometime in April.
Company's first Fermi-based GPUs
NVIDIA will officially launch the GeForce GTX480 and GTX470 graphics cards next month at the upcoming PAX East gaming conference, according to a Twitter post. The components are the first to integrate the company's Fermi architecture. The technology is said to improve graphics performance while expanding support for other standards such as OpenCL and PhysX
NVIDIA skips to GeForce 400 for Fermi GPUs
NVIDIA in a Twitter update has confirmed the names of the first two graphics chips based on its Fermi architecture. The GeForce GTX 470 and 480 should be the first to ship. Details of their performance weren't given, but the naming scheme positions them as top-end parts for gamers.
NVIDIA Fermi is ultra-general, 68pc faster
NVIDIA edged closed to the formal release of boards based on its Fermi architecture with fuller details about the processor as well as an early test. The 512-core design is now known to also be a high-end graphics design and adds 16 geometry and 4 raster units that weren't present in previous GeForce 200 cards. These newly dedicated units let a Fermi chip better handle tasks out of order.
Flaws push NVIDIA Fermi past CES
NVIDIA's delay for Fermi will put it in March, video card makers said Monday. The company had acknowledged a push back to the first quarter of the year, but tips to DigiTimes now have the launch of cards based on the new chipsets moved to the very end of that period. The first part would be a mid-range chipset known for now as the GF!00 while a true high-end part, the GF104, wouldn't arrive until the spring.
GeForce 300, Tesla may run slower
NVIDIA has quietly scaled back the ambitions of its Fermi-based hardware, a document (PDF) on its own site may have revealed. A specs sheet for the Tesla 20 now shows even the faster hardware using 448 visual processing cores versus the publicly promised 512. It has also ramped down the internal clock for these individual cores to at most 1.4GHz, slightly lower than the current generation.
NVIDIA may claim absolute speed win
NVIDIA's first GeForce 300 series cards may provide it with an unambiguous lead over AMD if purportedly leaked benchmarks are accurate. The tests suggest that the fastest single-chip GeForce card, the GTX 380, would be faster than the dual-chip Radeon HD 5970. They go so far as to suggest that a slightly speed-reduced card, the GTX 360, will often come close and in one case exceed AMD's flagship card.
NVIDIA 20 series Teslas appear
NVIDIA today provided details of the first official hardware to use its upcoming Fermi architecture. The Tesla 20 series is even more optimized for general-purpose computing standards like OpenCL or NVIDIA's own CUDA and handles complex math that previously hasn't been as practical, such as ISO standard double-precision math and C++ code processing. Unlike past models, though, the card model also has a video output and works as a video card rather than just as a companion device.
NVIDIA says GPUs still only focus
NVIDIA chief Jen-Hsun Huang has denied rekindled talk of his company making x86 processors. Speaking after a conference call, the CEO claims that his focus is still "very, very clear" and that the focus is on graphics processors and closely related parallel computing cards like the Tesla line. The only full processors that NVIDIA is making are mobile chips like the ARM-based Tegra series for handhelds, Huang tells CNET.
NVIDIA Fermi details escape
A pair of leaks have revealed NVIDIA's Fermi hardware should both be a dramatic visual upgrade and have a quick release of mobile parts. A post today on a Chinese forum shows samples of the graphics chipset that include 3D rendered faces with both extremely high detail as well as particularly complex visual effects, such as natural-looking facial hair or skin glare. One also shows the level of detail possible with relatively fast raytraced lighting.
NVIDIA Fermi with Snow Leopard in mind
The just-unveiled Fermi graphics architecture will find its way into Macs and play an important role in Mac OS X Snow Leopard, NVIDIA chief scientist Bill Dally said today. While it's expected that NVIDIA would continue to play an important part of future Macs, the researcher drew a particular connection between the new GPU design and Apple's new OS, expecting that it would provide a significant boost for those apps that implement OpenCL. Windows 7 will also get support through DirectX 11 and DirectCompute.
NVIDIA Fermi to start with three models
NVIDIA's Fermi architecture will start with three models if it ships before the end of the year as promised, one leak from Friday claims. A flagship single-chip model would have the 512 cores NVIDIA is advertising, but a second model would, like the GeForce GTX 295, have two slightly less powerful chipsets on one card that combined would be much faster. The slowdown may be necessary as Fudzilla believes the card would have a peak thermal power of 300W.
NVIDIA this evening provided an early look at the next generation of its graphics processors. Nicknamed Fermi, the architecture for future GeForce, Quadro and Tesla chipsets will jump from 240 cores to a much larger 512 and should be much faster in each core courtesy of some industry-first techniques. Fermi chips will be the first GPUs to have a real cache hierarchy, with Level 1 caches to keep specific information on hand and a single, shared Level 2 cache for larger tasks; they will also have a new GigaThread engine that can transfer data in both directions at once and handle "thousands" of tasks at once.