News Posts matching #CUDA

Return to Keyword Browsing

Acer Announces Aspire Predator Gaming PC with GeForce GTX 470

Acer, the world's second largest vendor in the PC market, today announced its newest Acer Aspire "Predator" gaming desktop PC is armed for combat and ready to do battle in the U.S. A force to be reckoned with, the power-packed AG7750-U2222 gaming rig harnesses the pinnacle of processor, graphics and memory technologies for conquering the fiercest opponents.

Taking bold style and performance to a killer level, the Aspire Predator is designed for avid gamers with a "take no prisoners" attitude. It's a monster machine outfitted with plenty of ammo, including Intel Core i7 quad-core processors, NVIDIA GeForce GTX 470 graphics with 3-way SLI support and a whopping 12GB DDR3 memory for blowing away the competition.

New NVIDIA GF100 Board Surfaces, Suggests New High-End SKU

Sources in the hardware industry leaked some interesting pictures of a new, supposedly reference-design NVIDIA GF100 GPU graphics card PCB, watermarked by board partner Little Tiger. The pictures reveal a PCB that's similar to that of the GeForce GTX 480, but with a stronger VRM that makes use of better high-C surface-mount capacitors (completely doing away with cylindrical capacitors), and draws power from two 8-pin PCI-Express power inputs. The design can deliver up to 375W of power (that's not the board power we're talking about).

This also opens up speculation about what NVIDIA would do with this design. The most talked about theory as of now points to a new high-end SKU by NVIDIA based on the GF100, that enables all streaming multiprocessors (SMs) physically present on the GF100, taking the CUDA core count up to 512, and ROP count to 64. The most likely marketing name for this SKU is GeForce GTX 485. Apart from higher CUDA core and ROP count than that of the GTX 480, slightly higher clock-speeds for the GPU are also on the cards. The memory subsystem remains untouched, at 1536 MB of GDDR5 memory clocked at 924 MHz (effective 3.7 GHz), over a 384-bit wide memory interface. NVIDIA could release this SKU this fall.

NVIDIA GF104 Package Pictured

One of the first pictures of NVIDIA's upcoming GF104 graphics processor has come to light, with a Chinese source picturing a GF104 qualification sample. The sample is based on the A1 silicon. The GPU package is similar to that of the GF100, it makes use of an integrated heat-spreader (IHS) to disperse heat from the die underneath it. The package is rectangular rather than square (probably a move to reduce board footprint, translating into more compact boards) The GPU is built on TSMC's 40 nm process, and is said to have significantly lower TDP compared to the GF100. One of the first SKUs built around it is the GeForce GTX 460.

Contrary to older reports, Expreview's report suggests that the GeForce GTX 460 will have 336 CUDA cores (instead of 256), and 768 MB of memory across a 192-bit GDDR5 memory interface. Its TDP is expected to be around the 150W mark, similar to that of a GeForce GTS 250. It will target price-point slightly above the $200 mark, while other SKUs carved out of this silicon will be lesser.

NVIDIA Releases GeForce 257.21 WHQL Driver Suite

NVIDIA today released GeForce 257.21 WHQL driver suite for GeForce series graphics cards and NVIDIA ION platforms, this is the first WHQL-signed driver in its 256 series of drivers, which archives two main goals as far as driver packaging goes: unifying desktop and mobile GeForce drivers; and unifying GeForce 400 series drivers with that which supports GeForce 6 thru GeForce 300 series into one package (NVIDIA initially had a separate package for GeForce 400 series). GeForce 257.21 also packs a boatload of changes, including a large number of game-specific performance increments, new technologies, updates key extra components, and fixes bugs.

DOWNLOAD: NVIDIA GeForce 257.21 WHQL for Windows 7/Vista 64-bit, Windows 7/Vista 32-bit, Windows XP 32-bit, Windows XP 64-bit
A complete list of changes follows.

Galaxy Designs GeForce GTX 480 with Dedicated PhysX GPU

While every NVIDIA GPU since GeForce 8 series, with over 256 MB of memory supports the CUDA GPU compute technology, and with it PhysX GPU acceleration, the prospect of dedicated GPUs for computing PhysX interests many, especially enthusiasts, after NVIDIA stopped production of the PhysX processor from erstwhile Ageia. EVGA first devised a graphics card that has a high-end GPU processing graphics, and a mainstream GPU dedicated to PhysX processing, with its GeForce GTX 275 Co-op. Building on the same principle, Galaxy designed an enthusiast-grade graphics card that uses an NVIDIA GeForce GTX 480 for DirectX 11 compliant graphics processing, while its sidekick on board is a 40 nm GeForce GT 240 GPU.

The GeForce GTX 480 sticks to specifications, complete with 1536 MB of GDDR5 memory across a 384-bit wide, while the GT 240 has its own 512 MB of GDDR5 memory across a 128-bit wide interface. Both GPUs share the system bus over an NVIDIA nForce 200 bridge chip, which gives both GPUs a PCI-Express 2.0 x16 link. The GTX 480 GPU packs 480 CUDA cores, and features the latest GPU technologies, including 3D Vision surround. Since it is independent from the GT 240, the GTX 480 can pair with three more of its kind for 4-way SLI, without affecting the functionality of the GT 240 in any way.

Gigabyte Rolls Out Twin-Fan GeForce GTX 465

Gigabyte rolled out its first graphics card based on NVIDIA's newest GPU, the GeForce GTX 465. The card features Gigabyte's own design, which makes use of the Ultra Durable VGA construction, a combination of PCB with 2 oz thick copper layers, Japanese solid-state capacitors, grade 1 memory chips, ferrite-core chokes and low RDS on MOSFETs. The cooler uses a large aluminum fin block which is cooled by two 80 mm fans. Though geared for overclocking, the card comes with NVIDIA reference clock speeds of 607/1215/3206 MHz (core/shader/memory). The GTX 465 SKU is derived from the GF100 die, it features 352 CUDA cores, and 1 GB of GDDR5 memory across a 256-bit wide interface. It is priced at a standard $279.

Gainward Intros GeForce GTX 470 Golden Sample

Gainward released a new custom-design GeForce GTX 470 graphics card, which is based on the Gainward GTX 470 GOOD Edition that was launched a month ago, replicated as Palit GTX 470 Dual-Fan. The factory-overclocked model is designated with the Golden Sample (GS) identifier. It packs clock speeds of 650/1301/850(3400) MHz (core/shader/memory), against reference speeds of 607/1215/837(3348) MHz.

As with the GOOD Edition design, it features a slightly longer PCB at 10.5 inches, custom dual-fan GPU cooler, and display outputs which include two DVI-D, and one each of HDMI and DisplayPort (though only two displays can be connected at a time). The DirectX 11 compliant GeForce GTX 470 packs 448 CUDA cores, and 1280 MB of GDDR5 memory across a 320-bit wide memory interface. It is expected to be priced at a slight premium of the GOOD Edition.

AMD Appoints Manju Hegde to Lead Fusion Experience Program

AMD today announced the appointment of Manju Hegde as corporate vice president, Fusion Experience Program. A renowned parallel and visual computing innovator, Hegde previously served as vice president of CUDA Technical Marketing at NVIDIA before joining AMD to lead the AMD Fusion Experience Program, an initiative focused on identifying innovative computing solutions and applications poised to take full advantage of the forthcoming AMD Fusion family of Accelerated Processing Units (APU). Hegde reports to Rick Bergman, senior vice president and general manager, AMD Products Group.

"We are thrilled to be able to attract an experienced industry leader like Manju Hegde to the AMD team, a sign of the quality of talent we are able to attract to AMD on the strength of our Fusion roadmap," said Bergman. "Manju brings prized expertise in developing the ecosystem for enabling breakthrough and heightened experiences on new architectures to AMD. As Manju and his team work with the ecosystem to usher in a new era of visual computing, we expect a wide range of industry leaders to embrace the future of accelerated computing through the combination of the GPU and CPU -- a combination only AMD can deliver with its AMD Fusion technology."

Latest Folding@Home GPU3 Core Extends Support to GeForce 400 Series

The latest Folding@Home GPU client core released by Pande Group adds support for NVIDIA's latest GeForce 400 Series GPUs, using the NVIDIA CUDA GPU compute technology. Dubbed GPU3 core, this beta release of the Folding@Home client core packs several optimizations to harness the new GPUs. Apart from GeForce 400 Series, the core supports the full range of GPUs, although the developers don't recommend using it with ATI GPUs, as the software doesn't offer any advantage, and could instead be buggy. They are, however, working on improving the software for ATI GPUs. The graphical and console clients using this core can be downloaded from here.

NVIDIA Reports Financial Results for First Quarter Fiscal 2011

NVIDIA reported revenue of $1.0 billion for the first quarter of fiscal 2011 ended May 2, 2010, up 2 percent from the prior quarter and up 51 percent from $664.2 million in the same period a year earlier. On a GAAP basis, the company recorded net income of $137.6 million, or $0.23 per diluted share, for the first quarter of fiscal 2011. That compares with $131.1 million, or $0.23 per diluted share, in the previous quarter and a net loss of $201.3 million, or $0.37 per share, in the same period a year earlier.

Gross margin increased to 45.6 percent for the first quarter fiscal 2011 from 44.7 percent in the previous quarter and 28.6 percent in the same period a year earlier.
  • Revenue grew 2 percent quarter-on-quarter to $1.0 billion
  • GAAP net income increased to $137.6 million, or $0.23 per diluted share
  • GAAP gross margin improved to 45.6 percent

Inno3D Releases GTX 470 Hawk Graphics Card

Inno3D released the non-reference design GeForce GTX 470 Hawk graphics card. The card is characterized by the large iChill heatsink which uses a large aluminum fin array that's cooled by three fans. Despite its proportions, the company claims the cooler's noise level to be only around 18 - 29 dBA (max), compared to the up to 38 dBA of the reference cooler. As far as performance goes, Inno3D claims the cooler keeps temperatures up to 22 °C lower than what the reference cooler manages, around the 70 °C mark on load.

Apart from the cooler, the Inno3D GTX 470 Hawk uses a fairly standard NVIDIA reference design PCB that is green in color, and comes with reference clock speeds of 608/1215/837 MHz (core/shader/memory). Like any other GTX 470, the card has 448 CUDA cores, and 1280 MB of GDDR5 memory installed on a 320-bit wide memory interface.

Galaxy GTX 470 GC Version Graphics Card Unveiled

Galaxy is ready with its 100% non-reference design graphics card based on the NVIDIA GeForce GTX 470 GPU, the Galaxy GTX 470 GC Version. The card makes use of Galaxy engineering with both the PCB and cooler designs. The card features a blue PCB, which is 0.5 inch shorter than the reference design (at 9 inches), and pushes the two 6-pin power connectors to the rear-end of the card. The cooling assembly uses a large aluminum fin array cooling all vital parts, covered with a silvery plastic found on action figures. Galaxy innovated a little with the fan, which can be partly detached from the rest of the cooler to help clean it and the heatsink under it.

The card is overclocked out of the box, with speeds of 625 MHz / 1250 MHz / 837 or 3348 MHz (effective), for the core, shader, and memory, respectively. Like every other GTX 470 based card, it is DirectX 11 compliant, and has 448 CUDA cores, 1280 MB of GDDR5 memory across a 320-bit wide interface, and is 2/3/4-way SLI capable. Display connectivity includes two DVI-D, and HDMI with integrated audio. A test by the source shows that with this cooling solution, the GTX 470 GC Version manages to keep the GPU at around 88 degrees Celsius with Furmark load. It is expected that the card will be available in the US as early as by tomorrow.

Zotac Readies GeForce GTX 480 Amp! Edition Graphics Card

Zotac is ready with one of the first non-reference design GeForce GTX 480 graphics card, the Zotac GTX 480 amp! Edition. At the center of its design is the Zalman VF3000 GPU cooler sitting atop an NVIDIA reference design PCB. Overclocked out of the box, the amp! Edition card has clock speeds of 750 MHz (core), 1512 MHz (shader), and 950 MHz / 3800 MHz effective (memory), against reference speeds of 700/1401/924(3700) MHz.

The gigantic VF3000 cooler makes the card require three expansion slots. As with every other GTX 480, the GTX 480 Amp! Edition packs 480 CUDA cores, is DirectX 11 compliant, and has 1536 MB of GDDR5 memory across a 384-bit wide interface. Zotac has not let out any more information, particularly pricing and availability.

NVIDIA Posts GeForce 197.41 WHQL Drivers for GeForce 400 Series

NVIDIA released version 197.41 of its GeForce driver suite, specifically for the DirectX 11 compliant GeForce 400 series GPUs. These drivers are WHQL-signed, and come in time for the market-availability of GeForce GTX 480 and GTX 470 graphics cards. Although NVIDIA didn't mark out any significant changes to this version, it bundles PhysX system software v9.10.0129, and on-chip HD audio driver v1.0.9.1. These drivers enable support for CUDA 3.0 and OpenGL 3.2. A proper release-notes document from the company is awaited for more details.

DOWNLOAD: NVIDIA GeForce 197.41 WHQL for GeForce GTX 400 series

NVIDIA CUDA Emulator for every PC

NVIDIA's CUDA GPU compute API could be making its way to practically every PC, with an NVIDIA GPU in place, or not. A chinese freelance developer has coded a means to get CUDA work as a middleware on OpenCL. This move lets CUDA work on ATI Radeon GPUs that support OpenCL, as well as x86 CPUs, since OpenCL specs allow the API to run on CPUs for development purposes. The implications of these are many:
  • Letting CUDA-accelerated software such as Badaboom make use of ATI GPUs
  • Letting PhysX run on ATI GPUs as PhysX middleware uses CUDA for GPU acceleration
  • Possibly better scaling of PhysX on multi-core CPUs (over OpenCL), as the regular PhysX CPU acceleration is infamous for bad multi-core scaling in performance
The software works as a translation layer, exchanging calls between CUDA and OpenCL or the CPU if OpenCL is not available. It comes in the form of a loader application that injects itself into the executing process. To get PhysX to run, one needs to install older versions of PhysX System Software (version 8.09.04 WHQL being the latest) from its standalone installer (installs PhysX libraries without looking for NVIDIA GPUs).

DOWNLOAD: CUDA Emulator Loader

Inno3D Readies First ''Non-Reference'' GeForce GTX 470 Graphics Card

Inno3D seems to be in a bit of a hurry to bag the title of "first to come out with a non-reference GeForce GTX 400 graphics card," and is working tirelessly to get there. The company is readying a new "non-reference" graphics card, put in quotes because for the most part it is in fact a reference design. Traditionally, NVIDIA disallows its board partners from designing their own non-reference graphics cards based on newly-launched high-end GPUs, with a few concessions made for designs with factory-fitted water-blocks, or minor cosmetic changes, apart from letting their own sticker design, box design, bundle, and to an extant, pricing.

Inno3D's concession comes in the form of two things: 1. an NVIDIA reference-design PCB, which is now green instead of black, and 2. looking at the pictures, possibly a different cooler shroud design, although internally the cooling assembly remains reference design. Inno3D may roll out graphics cards with reference NVIDIA clock speeds, and also those with higher clock speeds. As with every other GTX 470 made so far, Inno3D's card is based on the GF100 GPU, it is DirectX 11 compliant, packs 448 CUDA cores, and 1.25 GB (1280 MB) of GDDR5 memory across a 320-bit wide interface. It supports 3-way SLI. At this point, there is no word on when exactly the card comes out, or pricing.

SPARKLE Announces GeForce GTX 480/470 Graphics Accelerators

SPARKLE Computer Co., Ltd., the professional VGA card manufacturer and supplier, today proudly announced the SPARKLE GeForce GTX 480/470 Graphics Cards, which are the most powerful single chip graphics cards on the planet for gaming and beyond. Packing in 3 billion transistors, double the CUDA cores of previous generation GPUs, a high speed GDDR5 memory interface, and full DirectX 11 support, the SPARKLE GeForce GTX 480/470 Graphics Cards are designed for groundbreaking graphics performance. With a revolutionary new scalable geometry pipeline and enhanced anti-aliasing capabilities, the SPARKLE GeForce GTX 480/470 Graphics Cards are the world's most powerful single GPU graphics cards solution, delivering up to 3 times faster performance than previous GTX 285 single GPU solutions.

With the power of GF100 GPUs, the SPARKLE GeForce GTX 480/470 Graphics Cards bring ultimate DX11 HD gaming experience to high-end gamers. The SPARKLE GeForce GTX 480/470 Graphics Cards place gamers in the center of the action and experience true DirectX 11 gaming cinema in extreme HD (2560x1600) resolutions-all enabled by GF100's revolutionary compute architecture, NVIDIA 3-way SLI technology, and incredible performance in the latest DX11 games including Dirt 2, Stalker:OCP, Alien VS. Predator, Metro 2033 and so on. With 1.5~3 times more performance than prior generation GPUs, the SPARKLE GeForce GTX 480/470 Graphics Cards tear through complex DirectX 10 environments and cinematic effects at blazing frame rates in extreme HD resolutions.

ZOTAC Unleashes Next-Generation Graphics Cards

ZOTAC International, the world's largest manufacturer of graphics cards, motherboards and mini-PCs in the channel, today unleashes the world's most powerful graphics cards capable of delivering a phenomenal gaming experience and unmatched processing power - the new ZOTAC GeForce GTX 480 and GeForce GTX 470 graphics cards. The ZOTAC GeForce GTX 480 and GeForce GTX 470 graphics cards take gaming to uncharted levels with new Microsoft DirectX 11, 32x anti-aliasing, NVIDIA 3D Vision Surround and HDMI 1.3a technologies.

The new ZOTAC GeForce GTX 480 and GeForce GTX 470 deliver exceptional performance and visuals with an enhanced unified architecture that features hundreds of programmable unified shaders ready to process all GPU needs for extreme high-definition 3D gaming and everyday tasks. The unified architecture combines with a large 1536MB frame buffer on the ZOTAC GeForce GTX 480 and 1280MB frame buffer on the ZOTAC GeForce GTX 470 to deliver high-quality details and breathtaking performance.

NVIDIA Announces the GeForce GTX 480 and GeForce GTX 470 Graphics Cards

NVIDIA finally released the graphics cards it made many wait for: the DirectX 11 compliant GeForce GTX 480 and GeForce GTX 470. The two were unveiled at the PAX East gaming event, in the United States, as publications were allowed to post reviews right away. The two are based on the NVIDIA GF100 GPU, built on the 40 nm process. The higher-end GeForce GTX 480 packs 480 shader units (now referred to by NVIDIA as "CUDA cores"), branched geometry processing along with multiple tessellation units, and a 384-bit wide GDDR5 memory interface to connect to 1536 MB (1.5 GB) of memory.

The GeForce GTX 470 is the more affordable part, it packs 448 CUDA cores, and a 320-bit GDDR5 memory interface to connect to 1280 MB (1.25 GB) of memory. Both models support new features by NVIDIA, such as CUDA 3.0, faster PhysX acceleration, Stereoscopic 3D, 3D Vision surround multi display technology, as well as support for OpenCL and DirectCompute 5.0. While the GeForce GTX 480 has a suggested retail price of US $499, the GTX 470 is suggested to be priced at $349, although final pricing set by board partners could vary. NVIDIA is initially making tens of thousands of these cards, which should be available worldwide a little after April 12th.

MSI Shows off N480GTX Graphics Card

Here's MSI with its GeForce GTX 480 offering, the MSI N480GTX. While it's clear that all GeForce GTX 400 series graphics cards, at least initially, will adhere to NVIDIA's reference designs, each manufacturer is throwing in a little something unique. MSI's offering speaks of "Military-class" components, though it's likely that NVIDIA's own choice of components fit MSI's definition of military-class, and the MSI Afterburner software. The software is advertised to work with the card to provide voltage control, advertising up to 15% of performance gains using it. Usual features include DirectX 11 support, support for PhysX, CUDA, 3D Vision Surround, 480 CUDA cores, 1536 MB of GDDR5 memory across a 384-bit memory interface, and connectivity which includes two DVI-D and a mini HDMI.

Leadtek Ready with GeForce GTX 400 Series Graphics Cards

Leadteak is one of the many NVIDIA partners ready with its offering of GeForce GTX 470 and GeForce GTX 480 graphics cards, pictured ahead of its launch. As with every other GeForce 400 series SKU in the making, these cards stick to NVIDIA's reference design. The Leadtek GeForce GTX 480 is DirectX 11 compliant, has 480 CUDA cores, and 1536 MB of GDDR5 memory across a 384-bit memory interface, while the GeForce GTX 470 has 448 CUDA cores, and 1280 MB of GDDR5 memory across a 320-bit memory interface. Both are 3-way SLI capable. The two are expected to be launched later this week.

SPARKLE Announces GeForce 210 1GB Graphics Card With 128-bit Video Memory Design

SPARKLE Computer Co., Ltd., the professional VGA card manufacturer and supplier, today announced the SPARKLE GeForce 210 1GB Graphics Card with 128-bit video memory design, bringing impressive graphics processing power to your PC at an incredible value.

Based on NVIDIA's next generation G210 architecture, the SPARKLE GeForce 210 1GB Graphics Card adopts innovative unified architecture, dynamically allocates processing power to geometry, vertex, physics, or pixel shading operations, delivering up to 2x the gaming performance of prior generation GPUs. Built upon technologies such as NVIDIA Lumenex Engine, providing support for DirectX 10.1 Shader Model 4.0, NVIDIA Quantum Effects technology for physics computation and GigaThread Technology for extreme processing efficiency in advanced, next generation shader programs.

GeForce GTX 400 Series Clock Speeds and Other Details Surface

Exactly a week ahead of releasing its GeForce GTX 400 series accelerators, NVIDIA held meetings with the press discussing the company's newest technologies, including GeForce GTX 400 series. Some lesser known details about the GeForce GTX 480 and GeForce GTX 470 surfaced, among more known and established ones. To begin with, the GeForce GTX 480 is confirmed to have a CUDA core (shader core) count of 480. The GF100 core operates at 700 MHz, its shader domain at 1401 MHz, and the memory operates at 924 MHz (actual, 1848 MHz DDR, 3700 MHz effective). With a GDDR5 memory bus width of 384-bit, the effective memory bandwidth would be 173.4 GB/s.

The GeForce GTX 470, on the other hand, has 448 CUDA cores, clock speeds of 607 MHz core, 1215 MHz shader domain, and 837 MHz memory (actual, 1674 MHz DDR, 3348 MHz effective). With a GDDR5 memory bus width of 320-bit, the effective memory bandwidth would be 130.7 GB/s. While the GTX 480 has a board power of 295W, the GTX 470 has a board power of 225W. Another piece of information the source reveals is that internal testing by NVIDIA showed that the performance level to expect from the GeForce GTX 470 should be 5-10% higher than that of the ATI Radeon HD 5850. The GeForce GTX 480 should be expected to be just that much faster than the ATI Radeon HD 5870. It is also expected that the target price of the GeForce GTX 480 should be typically US $499, while the GTX 470 should go typically for US $349. Detailed reviews of the two should be up by this time, next week.

ZOTAC Unleashes World’s First ION Upgrade Kits

ZOTAC International, the world's largest manufacturer graphics cards, mini-ITX motherboards and mini-PCs in the channel, today unveils the world's first ION Upgrade Kits featuring a ZOTAC small form factor motherboard and ZOTAC ION graphics card for a combination that delivers phenomenal value with premium graphics and outstanding user experience.

A ZOTAC ION graphics card with 16 unified shaders and 512MB of DDR3 memory empowers the ZOTAC ION Upgrade Kits with high-end features such as NVIDIA CUDA and PureVideo HD technologies, DirectX 10.1, DirectCompute, OpenGL and OpenCL compatibility for a high-performance and feature rich experience.

GeForce GTX 480 has 480 CUDA Cores?

In several of its communications about Fermi as a GPGPU product (Next-Gen Tesla series) and GF100 GPU, NVIDIA mentioned the GF100 GPU to have 512 physical CUDA cores (shader units) on die. In the run up to the launch of GeForce 400 series however, it appears as if GeForce GTX 480, the higher-end part in the series will have only 480 of its 512 physical CUDA cores enabled, sources at Add-in Card manufacturers confirmed to Bright Side of News. This means that 15 out of 16 SMs will be enabled. It has a 384-bit GDDR5 memory interface holding 1536 MB of memory.

This could be seen as a move to keep the chip's TDP down and help with yields. It's unclear if this is a late change, because if it is, benchmark scores of the product could be different when it's finally reviewed upon launch. The publication believes that while the GeForce GTX 480 targets a price point around $449-499, while the GeForce GTX 470 is expected to be priced $299-$349. The GeForce GTX 470 has 448 CUDA cores and a 320-bit GDDR5 memory interface holding 1280 MB of memory. In another report by Donanim Haber, the TDP of the GeForce GTX 480 is expected to be 298W, with GeForce GTX 470 at 225W. NVIDIA will unveil the two on the 26th of March.
Return to Keyword Browsing