Beyond3D Featured ContentNVIDIA Fermi GPU and Architecture Analysis
The timing could barely be better! ATI launch a new line of graphics processors and what do we do? We finally get round to looking at Fermi. Alex was at the controls again for this one, beating GF100 in GeForce GTX 470 form up with a new suite of software and a very deep, in-depth analysis of how the majority of the chip and architecture work. It's the de-facto public analysis and a must read.
IBM announced earlier this week the introduction of the BladeCenter QS21, the newest iteration of the Cell-based QS20 blade server released last year.
ZDNet's Technical Director, George Ou, has called the latest round of pre-release Barcelona performance data by AMD, blatantly deceptive, cherry-picked and simply wrong.
Being able to witness the earnest birth of a new computing industry is a special thing. In the last few years, efforts to use programmable commodity graphics hardware for things other than graphics have gained pace, and now there's a legit multi-million dollar industry surrounding it.
GPGPU middleware developer PeakStream has been acquired by Google, according to The Register. Where this leaves the GPGPU development platform is unclear, although it has stopped selling the product for the moment.
NVIDIA has released the Quadro Plex VCS model IV today, which they had hinted at earlier this year during the launch of the Quadro FX 4600 and 5600, both based on the G80 architecture. Unsurprisingly, the new Quadro Plex model is actually two FX 5600 GPUs in a standalone box,…
NVIDIA has announced the release of a sample CUDA plug-in for Matlab that accelerates single-precision FFTs by up to 14x.
NVIDIA has released version 1.0 of its CUDA programming framework, with a number of new features including asynchronous kernel calls and 64-bit Linux support.
Figures released by Jon Peddie Research for Q1 this year in the workstation market hold some surprises, not least that the share for 2P workstation by AMD Opteron has fallen to levels AMD last experienced back in Q3 and Q3 2005.
Intel is currently researching data-parallel languages, reports EETimes. These languages would most likely be for massively parallel architectures, such as Larrabee and Terascale, putting them in direct competition with NVIDIA and AMD in the GPGPU market.
The Street is reporting that NVIDIA will launch a brand, similar to its GeForce and Quadro brands of cards, specifically for GPGPU apps. This follows AMD's launch of its Stream Computing line, based on its R580 chipset.