![]() According to representatives from AMD, stream and / or GPU computing are well suited to a number of multimedia-related applications, like sound / music editing and obviously graphics / design applications, as we have seen recently with Adobe's CS4 announcement. With ATI Stream, AMD plans to work with developers in an attempt to leverage the power of the GPU to enhance the functionality of media creation, office productivity, and entertainment applications, among others as well. The goal, as NVIDIA has done to some degree with CUDA and PhysX, is to not only take ATI Stream mainstream, but to also better serve the enterprise and HPC spaces with easier access and standardized programming tools.Īs they have been made more and more programmable over the years, it has become obvious that GPUs are well suited to accelerating more than just graphics. ![]() The new brand is aptly named ATI Stream.ĪTI Stream is essentially a amalgamation of all of ATI's previous initiatives like Close To Metal (CTM), Compute Abstraction Layer (CAL), and Brook+ (AMD’s modified Brook open source compiler), encompassed under a single brand. However, Nvidia makes much about the fact that the ATI GPU does not have error correction on its cores and GDDR memory - and AMD acknowledges that's a feature it needs to add.AMD is revealing a new technology brand today to highlight some recent advances made in the company's stream and GPU computing initiatives. And in this case, the ATI Cypress GPU can hold its own against the best Fermi that Nvidia has. While there are some workloads that can use single-precision just fine (some life sciences and oil and gas exploration apps are fine with single precision), most flop heads care about double-precision. With all of its cores working properly, the Cypress GPU can deliver 2.72 teraflops of single-precision and 544 gigaflops of double-precision floating point performance. The AMD GPU has full support for the DirectCompute 11 and OpenCL 1.0 graphics and number-crunching protocols embedded in its hardware, and also includes 32-bit atomic operations, flexible 32KB local data shares, 64KB global data shares, global synchronization, and append/consume buffers etched onto its silicon. The Cypress chip has 1,600 SIMD engines and a slew of supporting electronics wrapped around them so they can do math with their clothing still intact. ![]() With the FireStream GPU co-processors, the units are equipped with a passive heat sink that allows them to slide into rack and tower servers, creating the hybrid 圆4-GPU systems that many think will soon become the norm in the HPC arena. The Cypress GPU gets the normal fan-cooled packaging for the Radeon HD and FirePro discrete graphics cards, with the major difference being that the FirePro cards has more video memory. The Cypress GPU is no slouch, just like Nvidia's Fermi GPUs - and just like Intel and AMD are fierce competitors that get the best of each other every now and again, the competition between AMD and Nvidia drives innovation forward. Today, the Cypress GPUs will be plunked into the third generation of FireStream GPU coprocessors intended for embedded applications where the GPUs do complex math that an 圆4 can't do without both taking its shoes off and pulling its pants down (if it is male) or lifting its shirt up (if it is female). ![]() The Cypress GPUs already made their way into the ATI Radeon HD 5870 discrete graphics cards ( last October and the ATI FirePro V8800 graphics cards for high-end workstations ( back in April). Keeping pace with Nvidia in the GPU wars, Advanced Micro Devices has not only launched its "Lisbon" Opteron 4100 processors but also released the embedded versions of its "Cypress" family of GPUs, a counterpunch to Nvidia's "Fermi" chips used in its Tesla embedded GPUs. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |