News Posts matching #CUDA

Return to Keyword Browsing

Sparkle Adds 1GB GeForce 9600 GSO to its Lineup

As NVIDIA celebrates the launch of its two new flagship products: the GeForce GTX 295 and GeForce GTX 285, Sparkle made an addition to its mainstream graphics lineup with a 1 GB variant its GeForce 9600 GSO accelerator (model: SX96SO1024D3-HM). Traditionally, the G92 graphics processor in the 8800 GS, 9600 GSO should have a 192-bit memory bus, but with this particular card, Sparkle chose a 128-bit memory bus and added 1 GB of GDDR3 memory.

The card features a dual-slot cooler for the GPU. Its core is clocked at 550 MHz. Its 96 stream processors are clocked at 1375 MHz. The memory runs at 800 MHz (1600 MHz DDR). It supports NVIDIA CUDA and PhysX technologies and is SLI capable. It will be priced around US $100.

NVIDIA Releases Graphics Plus Power Pack #2

NVIDIA adopted the marketing strategy of Graphics Plus, meaning that they intend to show their products as something more than just graphics hardware. The introduction of the CUDA GPGPU platform, and the subsequent introduction of GPU-acceleration physics in the form of NVIDIA PhysX helped the cause. The company released the Power Pack software delivery system back in August, which served as a mode for delivering not only system drivers, but also related content such as free games, technology demos, game demos, free software and software trials. The user can choose what to download, by customizing the Power Pack.

NVIDIA released Power Pack #2, the second major iteration, consisting of changes to the list of things that can be downloaded. The pack now includes Warmonger (full free game) with two new levels: Tombstone & Asylum. It includes three new tech demos, a PhysX accelerated screensaver, and most notably, trial versions of Power Director 7, TMPGENC XPRESS and Badaboom media converter, all of which take advantage of GPU acceleration. Apart from these, the usual contents of Power Pack #1 are also included. At any point in time, the Power Pack includes the latest system drivers of NVIDIA Forceware, and PhysX system software. For more, please visit this page.

NVIDIA Launches Quadro FX 4800 Professional Graphics Accelerator

Today, mechanical computer-aided design (MCAD), digital content creation (DCC) and broadcast applications received a major performance boost with the introduction of the NVIDIA Quadro FX 4800 ultra-high-end professional graphics card. With advances in GPU architecture, added graphics memory and 30-bit color, the Quadro FX 4800 gives professionals the right toolset to dramatically push the boundaries of realism, performance and quality.

"In this increasingly competitive landscape, it's imperative that professionals deliver better, faster and more cost-effective results," said Jeff Brown general manager, Professional Solutions, NVIDIA. "NVIDIA is not only addressing this challenge, but is raising the ultra-high-end visualization bar by creating specialized solutions to meet the direct needs of professionals - whether it be a geophysicists or MCAD designer."

NVIDIA Makes a Tesla Personal Supercomputer

Today, scientific research is carried out on supercomputing clusters, a shared resource that consumes hundreds of kilowatts of power and costs millions of dollars to build and maintain. As a result, researchers must fight for time on these resources, slowing their work and delaying results. NVIDIA and its worldwide partners today announced the availability of the GPU-based Tesla Personal Supercomputer, which delivers the equivalent computing power of a cluster, at 1/100th of the price and in a form factor of a standard desktop workstation.

NVIDIA Brings the World's First Quadro FX 5800 4GB Graphics Card to Market

Professionals searching for oil, diagnosing illness or styling the next high-performance luxury vehicle all have one thing in common, the need for advanced visual computing solutions. NVIDIA Corporation, the world leader in visual computing technologies, today unveiled the most powerful professional graphics card in graphics history - the NVIDIA Quadro FX 5800.
"The size and complexity of data is growing at an exponential rate. The challenge for today's professional is to make sense of the mountain of data by distilling it into a form they can comprehend, analyze and use to make impactful decisions," said Jeff Brown, general manager, Professional Solutions, NVIDIA. "At stake can be billions of investment dollars, or even people's lives. The Quadro FX 5800 has advanced features to allow massive
datasets to be viewed beyond traditional 3D enabling professionals to make fast and accurate decisions."

ASUS Unveils its Most Powerful DirectX 10 Motherboard

ASUS is proud to announce an exclusive partnership with NVIDIA in the creation of the most powerful DirectX (DX) 10 motherboard-the ASUS P5N7A-VM motherboard. A showcase of intelligent and innovative motherboard design, the P5N7A-VM features an LGA775 socket for Intel Core 2 Extreme / Core 2 Quad / Core 2 Duo processors and supports the GeForce 9300 / nForce 730i chipset and memory expansion of up to a maximum of 16 GB with four DDR2 800/667 dual channel memory slots. With support for Hybrid SLI, CUDA and PhysX graphics acceleration, the P5N7A-VM promises to be the most powerful DX10 motherboard in the consumer market today.

EVGA Announces the nForce 730i Motherboard with Integrated GeForce 9300 GPU

Following a news article about the launch of the 730i which we covered here, EVGA has launched its first motherboard based on the Nvidia 730i Chipset with onboard graphics. You can find out more information on EVGA's Product Page, and a video overview is available here.
EVGA is proud to announce the latest product to the EVGA Motherboard family; the EVGA nForce 730i. With support for DirectX 10 and NVIDIA GeForce Boost Technology, the EVGA nForce 730i represents the latest in graphics technology and can provide up to a 70% increase in overall visual performance! All of these innovations are combined to make the EVGA nForce 730i the best single GeForce Graphics platform available.

Get it all with from The Force Within: With support for NVIDIA PhysX and CUDA Technology, the EVGA nForce 730i will provide you a full spectrum of visual nirvana and unsurpassed graphics processing power.

NVIDIA Announces Strategic Partnership with MotionDSP

NVIDIA Corporation today announced a strategic partnership with MotionDSP, an emerging leader in digital video software applications and a new NVIDIA CUDA ecosystem partner. MotionDSP relies heavily on the computation power of NVIDIA CUDA technology to accelerate its breakthrough video enhancement software that significantly improves the visual quality of consumer-created videos. As proof that NVIDIA GPUs deliver more than just graphics rendering horsepower, MotionDSP engineers were able to achieve a 500% increase in numerical software performance after porting to CUDA. MotionDSP's revolutionary video enhancement technology-shown with CUDA acceleration for the first time at last month's NVISION 08 conference-allows users to clean up videos from cell phones, still cameras, camcorders, or the Internet. By tapping into the many parallel cores of NVIDIA GeForce GPUs, and utilizing NVIDIA CUDA technology, MotionDSP's software can immediately achieve real-time performance, something not attainable with today's CPUs.

NVIDIA PhysX System Software Version 8.09.04 Released

NVIDIA released today the latest WHQL version of its NVIDIA PhysX System Software. Version 8.09.04 supports both Windows XP and Windows Vista (32-bit and 64-bit).

Release Highlights:
  • Supports for NVIDIA PhysX acceleration on all GeForce 8-series, 9-series and 200-series GPUs with a minimum of 256MB dedicated graphics memory.
  • Experience GPU PhysX acceleration in several full games and demos today by downloading the GeForce Power Pack.
  • Supports AGEIA PhysX processors and software runtimes (no change to PPU driver support).
  • Includes the latest PhysX runtimes used in the latest game titles.
  • Supports the following NVIDIA PhysX runtime engines: 2.8.1, 2.8.0, 2.7.4, 2.7.3, 2.7.2, 2.7.1, 2.7.0, 2.6.x, 2.5.x, 2.4.x and 2.3.x
  • Supports NVIDIA PhysX acceleration on GeForce via CUDA 2.0 for SDK versions 2.7.3, 2.7.2, 2.8.0 and 2.8.1 (requires graphics driver v177.81 or later).
  • The PhysX control panel can be found in the Windows Start Menu under NVIDIA Corporation.
DOWNLOAD: NVIDIA PhysX System Software Version 8.09.04

NVIDIA CUDA Delivers 446% Speed Increase to Pegasys Video Processing Solution

Today, at the NVISION 2008 conference, NVIDIA Corporation in conjunction with Pegasys Inc., makers of TMPGEnc 4.0 XPress multi-format video encoding software, showcased a technology demonstration to optimize video processing with the massively parallel architecture of the GPU.

Using NVIDIA CUDA technology (a C-like programming language programming for the GPU), Pegasys is taking advantage of the parallel processing capabilities of an NVIDIA GeForce GPU to create a GPU-enabled beta version of TMPGEnc 4.0 XPress software. The software is used to dramatically increase video decode and processing speed by as much as 446% on a GeForce GPU.

NVIDIA to Showcase its x86 Plans this NVISION?

Team R21 of FiringSquad studied the credibility of a rumor on NVIDIA materializing its long-term processor plans. They said they would be surprised if NVIDIA didn't have an x86 plan chalked out at least at a very interior level. The Inquirer speculated earlier that NVIDIA could lift the covers from its x86 plans as early as some time this week, during the ongoing NVISION event. The credibility of this rumor is based purely on who's breeding it. Many point it to have been doing rounds during IDF.

Reality bites: NVIDIA lacks a regularized x86 license which has to be issued by Intel to be able to use x86 in their products. Any mass announcement at this point could cost them. NVISION however looks to be an ideal substrate for discussions on CUDA and NVIDIA's SoC (System on a Chip) plans.

Point of View releases GeForce 9800 GTX+

POINT OF VIEW, well known for its range of NVIDIA based Graphics cards, is launching today the GeForce 9800GTX+, an upgraded version of one of the fastest single GPU graphics card on the market, the GeForce 9800 GTX.

The GeForce 9800GTX+ has major improvements compared to its predecessor. The GPU has been down-sized to 55nm, which offering a major improvement to its power consumption efficiency, operating temperature and core speed. Its 512 MB DDR3 memory is running on 2200 MHz whilst the GPU core has a speed of 738 MHz. The speed of the internal processors has been increased with almost 250 MHz to an impressive speed of 1836 MHz.

GeForce 9800M, 9700M Offer Performance and Energy Savings in a Broad Range

NVIDIA has released two lines of high performance graphics processors (GPU) for the notebook PC market, the GeForce 9800M series and the 9700M series. These are sub-classified into GT and GTS for the 9700M and GT, GTS and GTX for the 9800M. These new GPUs provide a wide range of options for manufacturers to choose from and design high-performance gaming and multimedia notebooks.

These 9800M GTX GPU is based on the same G92 core, and will outperform its previous generation 8800M GTX that also happens to be based on the same core. The rest are based on the G94 and the newer G96 cores. These GPUs are CUDA compliant and will be able to accelerate game physics using the PhysX API. They support NVIDIA Hybrid Power technology. Simply put, on notebooks with integrated graphics processors (IGP) along with these GPUs, the system will be able to switch over to the IGP when not gaming, and switch over to the GPU when heavy graphics tasks are running (such as gaming, 3D rendering, HD Video acceleration, etc.). Speaking of video, these GPUs support Powervideo HD technology, includes VP2 acceleration. There's no information on these GPUs' fabrication technology yet. Specifications provided below.

AMD to PhysX: 'Acceptable Under Conditions'

Following the NGOHQ episode with devising software that lets users accelerate GPU-based NVIDIA PhysX API on Radeon accelerators, and with NVIDIA coming in support of such an effort, a general opinion was made that NVIDIA sought an industry-wide domination of CUDA as the de-facto general purporse graphics processing (GPGPU) architecture, with putting their investment of acquiring Ageia Technologies to good use by pushing the PhysX API. Although it comes as a good news for AMD that their graphics cards that are already optimized for Havoc physics could now support PhysX acceleration, it's not in the best interests of the company that they allow the growth of CUDA and components based on it to this extent, since AMD has its own FireStream line of products and a GPGPU architecture in the making.

TG Daily spoke with Richard Huddy, Manager of Worldwide Developer Relations, and Godfrey Cheng, Director of Product Marketing, two key individuals with AMD. When it comes to the most interesting question of PhysX implementation on Radeon, Mr. Cheng says that AMD has no problems encouraging the use of feature-enhancing 'middleware', and that they have no arguments in NVIDIA going ahead with propogating their PhysX middleware as long as they don't put Radeon accelerators into a unfair disadvantage.

Radeon PhysX Creator: 'NVIDIA Offered To Help Us', 'Expected More From AMD'

In a dramatic turnaround of events,, the creators of a special system software that allowed users of the ATI Radeon graphics accelerators to use proprietary features of NVIDIA graphics accelerators such as GPU-accelerated version of the NVIDIA PhysX game physics API, claim that in fact NVIDIA wanted to help them with this effort. On June, the 26th we had covered reports of the said outfit improvising a driver after proving that NVIDIA's proprietary GPGPU architecture, CUDA was flexible enough to work on a ATI RV670 graphics processor.

Intel Downplays the Growing Popularity of NVIDIA CUDA

The co-general manager of Intel's Digital Enterprise Group, Pat Gelsinger told Custom PC that NVIDIA's CUDA programming model would be nothing more than an interesting footnote in the annals of computing history.

Gelsinger says that programmers simply don't have enough time to learn how to program for new architectures like CUDA. Says Gelsinger: "The problem that we've seen over and over and over again in the computing industry is that there's a cool new idea, and it promises a 10x or 20x performance improvement, but you've just got to go through this little orifice called a new programming model. Those orifices have always been insurmountable as long as the general purpose computing models evolve into the future.". The Sony CELL and the fact that it didn't live up to all its hype as something superior to current computing architectures proves his point.

Gelsinger tells that Intel's Larrabee graphics chip will be entirely based on Intel Architecture x86 cores, and the reason for that is so developers can program for the graphics processor without having to learn a new language. Larrabee will have full support for APIs like DirectX and OpenGL.

NVIDIA Appoints First CUDA Center of Excellence

NVIDIA Corporation and the University of Illinois at Urbana-Champaign (UIUC) today announced that UIUC has been named as the world's first CUDA Center of Excellence. In addition to the appointment, NVIDIA has donated $500,000 to UIUC for the development of parallel computing facilities and the continuation of its research programs.

PhysX Runs On RV670, Scores 22,000 CPU Marks in 3DMark Vantage

Eran Badit of successfully modified NVIDIA CUDA (Compute Unified Device Architecture) to operate on an ATI GPU and has been able to run the NVIDIA PhysX layer on an RV670, the Radeon HD 3850.

He tells that enabling PhysX support on Radeon cards is not particularly difficult, leading us to believe that physics on graphics cards may not so much be a technology problem but an issue of corporate dynamics.

On his first run, Eran got a 22,606 CPU score in 3D Mark Vantage, enhancing the overall score to P4262. A comparable system without PhysX-support will cross the finish line at about P3800.

NVIDIA GeForce GTX 280/260 WHQL Driver Version 177.41 Released

I hope you haven't already installed the beta driver we reported earlier today, because a new one is now available for download. Not that the betas are bad, but have in mind that the newer 177.41 WHQL driver is already here. Here are some of the highlights for this release:
  • Supports GeForce GTX 280 and GeForce GTX 260 GPUs.
  • Supports single GPU and NVIDIA SLI technology on DirectX 9, DirectX 10, and OpenGL, including 3-way SLI Technology with GeForce GTX 280 and GeForce GTX 260 GPUs.
  • Supports CUDA Technology.
  • Supports Folding@home distributing computing application.
DOWNLOAD: Windows XP 32-bit|64-bit,
Windows Vista 32-bit|64-bit

NVIDIA CUDA PhysX Engine Almost Complete

Although NVIDIA bought AGEIA Technologies only two months ago (on February 13, 2008), the GeForce creator informed recently that the conversion of AGEIA's PhysX API engine to CUDA programming language that interfaces with the GPUs is almost complete. Upong completeion of CUDA, owners of GeForce 8 and 9 series graphics cards will be able to play PhysX-enabled games without the need of an additional AGEIA PhysX PCI card. The big question here is, how much will this PhysX addition worse the frame rate in games. Well for now we only know that NVIDIA showed off a particle demo at its recent analysts day that was apparently similar to Intel's Nehalem physics demo from IDF 2008. For the record, the Nehalem demo managed 50,000 - 60,000 particles at 15-20 fps (without a GPU), while NVIDIA's demo on a GeForce 9800 card achieved the same level of particles at an amazing 300 fps, quite a boost. NVIDIA's next-gen parts (G100: GT100/200) in theory can double this score to top 600 fps. Manju Hegde, co-founder and former CEO of AGEIA added that in-game physics will be the "second biggest thing" in 2008.
Return to Keyword Browsing