10/02, 5:35pm
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.
more
09/30, 5:35pm
NVIDIA Fermi
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.
more
09/29, 3:15pm
Translates for supporting video cards
NVIDIA has announced that a public beta release of the PGI CUDA-enabled Fortran compiler is now available for download. The compiler was developed by NVIDIA and the Portland Group, and is billed as the first Fortran compiler that works with CUDA-enabled GPUs. The compiler translates the Fortran programming language into binary code that CUDA GPUs can interpret.
more
07/01, 2:30pm
NVIDIA Ion Sequel Speedup
The sequel to NVIDIA's Ion platform could be much faster than its predecessor when it ships, leaks today would show. While the current graphics and chipset combo is based on the GeForce 9400M and has just 16 visual effects cores, Fudzilla now hears that it will have 32 cores, potentially doubling the amount of simultaneous effects it can handle at once. The difference will have the most dramatic effect on 3D but could also impact general-purpose computing tasks that need CUDA or OpenCL.
more
05/21, 10:10am
Apple ARM Cortex Job
Apple has posted a job listing that hints at the company's future hardware direction for the iPhone, iPod touch and possible other devices. The position for a High Perform/Low Level Programmer asks for someone familiar not only for programming assembly-level code for ARM processors, which Apple already uses in its handhelds, but for the NEON vector math units used in the newer Cortex architecture for the mobile chips. Apple is especially concerned about experience with vector math and particularly values anyone with additional knowledge of vector units through general CPUs, such as Intel's SSE or the AltiVec units found on PowerPC G4 and G5 cores.
more
01/15, 4:35pm
Mac mini NVIDIA Ion Rumor
Apple's Mac mini desktop will switch to NVIDIA's Ion platform and Intel's Atom chip as a result, an alleged confirmation by an NVIDIA partner asserts. The Cupertino company is believed to be using the combination graphics and system chipset in an updated computer that would also use the 1.6GHz, dual-core Atom 330. While slower in processing power than the existing Core 2 Duo, the mini system would have video performance close to if not exactly like the GeForce 9400M currently found in all aluminum MacBooks.
more
11/21, 3:20pm
Apple OpenCL trademark
Apple has filed for a trademark on OpenCL technology, documents from the US Patent and Trademark Office show. The standard is intended to better distribute processing power on a computer, by using the normally segregated processing on a video card to help with tasks unrelated to graphics. Video cards can be extremely powerful, Apple notes, but only tend to maximize their use in certain applications, such as games.
more
11/17, 4:45pm
PGI 8.0 compiler released
The Portland Group has released PGI 8.0, the latest version of its compiling and development suite for Mac, Linux and Windows software. The v8.0 edition introduces support for the OpenMP 3.0 multi-core programming standard, which lets coders exploit multiple cores in C or Fortran. Concurrent with this is the ability to create and debug OpenMPI apps in Linux and the Mac OS, and build and deploy multi-core apps to any "major" desktop or cluster OS.
more
11/10, 8:30am
NVIDIA Quadro FX 5800
NVIDIA on Monday established a new flagship video card for its workstation line. The Quadro FX 5800 is a major improvement over the earlier 5600 that brings 240 visual effects cores, or nearly double the old model's 128, but stands out as the first-ever video card with 4GB of onboard memory. The capacity allows for extremely large textures and geometry and also enables apps with CUDA general-purpose computing support to feed very large data sets: 4D modeling that factors in time is now more realistic.
more
09/25, 11:40am
NVIDIA, MotionDSP team up
NVIDIA on Thursday announced it has partnered up with digital video software creator MotionDSP to provide users with a way to enhance the quality of personal videos created by their cellphone cameras, point-and-shoot digicams, camcorders or video captured from the Internet. Written using NVIDIA’s CUDA general-purpose computing technology to take advantage of the GPUs’ abiilities to handle non-graphics tasks, MotionDSP’s codenamed Carmel software tracks every pixel from tens of video frames before reconstructing high-quality video from low-res sources.
more
08/22, 12:50pm
NVIDIA CUDA 2.0 Final
NVIDIA today formally released the finished version of CUDA 2.0. The second generation of the company's general-purpose programming language for its video chipsets supports 64-bit versions of Mac OS X and Windows Vista and adds support for instructions that can help offload more specific tasks from the main processor to the video card, such as 3D textures and hardware-accelerated interpolation of information.
more
08/20, 9:05pm
Apple adds CUDA dev kit
Apple has updated its download site with the latest version of the NVIDIA CUDA development kit. CUDA (Compute Unified Device Architecture) allows users to crunch mathematical formulas using the GPU resident inside a computer, speeding up otherwise lengthy tasks, such as encoding video or other rich media, as well as scientific and design uses. The kit will allow developers to tweak their code to run optimally on systems such as the MacBook Pro, and its GeForce 8600M graphics chipset.
more
07/30, 8:40pm
NVIDIA Candidate for Mac
Apple's rumored non-Intel mainboard platform may primarily involve a change of suppliers to NVIDIA rather than any kind of custom development, PCPer suggests. The enthusiast site notes that Santa Clara, California-based NVIDIA has been developing its first nForce mainboard chipset for Intel-based notebooks, currently codenamed MCP79, with the aim of improving several weaknesses that have affected Intel's own designs and thus Apple as well. The architecture would support all the necessary components for Intel's just-announced Core 2 processors, including a 1,066MHz system bus and the option of DDR3 memory.
more
06/06, 4:35pm
Apple to adopt CUDA?
Apple may be looking to adopt proprietary Nvidia code for Macs, an interview reveals. The latter company's CEO, Jen-Hsun Huang, has proposed that Apple is extremely interested in his company's CUDA programming language, which simplifies the coding process for Nvidia graphics hardware and can in theory improve performance. In February, an early Mac SDK for CUDA was released in the form of a beta.
more
05/23, 2:40pm
Adobe CS4 GPU Use
(Update with corrections) The version of Photoshop included with Adobe's future Creative Suite 4 will include fuller acceleration both for dedicated video hardware as well as the first support for physics processing, TGDaily has been told as part of an early demonstration. While CS3 has already had limited support for graphics processing units (GPUs) for certain filters, the new version will use video hardware to improve performance across much of the image editor's pipeline. It will also enable new editing techniques: users can bring in a 3D image and paint it with changes applied immediately.
more
05/22, 1:10am
NVIDIA GeForce GTX coming?
NVIDIA plans on refreshing its GPU line-up next month with two new graphics card that will feature its next-generation CUDA-enabled graphics core, codenamed D10U. The company is expected to deliver both the GeForce GTX 260 (D10U-20) and GeForce GTX 280 (D10U-30) on June 18th as part of its summer refresh, according to DailyTech. The report claims that the GTX 260 will be a "significantly" scaled down version of the GTX 280, which will enable all 240 unified stream processors designed into the processor. These second-generation unified shaders perform 50 percent better than the shaders than its previous-generation offering, the company claims in its documentation; however, the new NVIDIA cards will only support GDDR3 memory and DirectX 10, while AMD focuses on faster GDDR5-based cards due early this summer.
more
02/20, 11:55am
Nvidia CUDA for Macs
Nvidia today announced the release of CUDA beta (12.9MB) for the Mac, a developer's kit that allows users to create derivative works for academic, commercial, or personal purposes. In addition to Nvidia's cards being used for gaming, some research firms use CUDA to do molecular modeling using parallel processing implementations, according to The Enquirer. The CUDA developers kit beta is available from Nvidia's website.
more
02/04, 7:25pm
Nvidia to acquire Ageia
Nvidia today announced an official acquisition of Ageia Technologies, the company behind the PhysX software and hardware components. The acquisition will give Nvidia a physics element for its Cuda parallel processing systems. The PhysX technology is currently in use in many Xbox 360, Playstation 3 and Nintendo Wii games, as well as many gaming PCs worldwide. Nvidia will be hosting a quarterly conference call on February 13th to provide more information about the acquisition in its final stages.
more
