Message boards :
Number crunching :
Why doesn\'t LHC@home use CUDA?
Message board moderation
| Author | Message |
|---|---|
 Send message Joined: 16 Sep 08 Posts: 1 Credit: 576 RAC: 0 |
In case you may not know, CUDA is NVIDIA\'s SDK environment for allowing applications such as LHC@HOME to use the GPU to process chunks of data. The performance gains can be up to 100 times faster than using a CPU. Folding@home (not a boinc project) uses it, and Seti@home is working on a beta version (it may have already been released). Boinc also supports CUDA now as well. More info on CUDA can be found here: http://www.tomshardware.com/reviews/nvidia-cuda-gpu,1954.html http://www.criticalmasses.info |
|
Send message Joined: 27 Aug 05 Posts: 1 Credit: 3,104 RAC: 0 |
In case you may not know, CUDA is NVIDIA\\\'s SDK environment for allowing applications such as LHC@HOME to use the GPU to process chunks of data. The performance gains can be up to 100 times faster than using a CPU. there are hundreds of similar threads ... |
|
Send message Joined: 19 Feb 08 Posts: 708 Credit: 4,336,249 RAC: 43  
|
See also the David Anderson article posted on the BOINC home page. Tullio |
|
Send message Joined: 12 Sep 08 Posts: 10 Credit: 2,747 RAC: 0 |
Wow those Tesla\'s aren\'t cheap are they! I have seen the nVidia Tesla C870 GPU for £363 + vat, but they are usually nearer the £600 mark. Check out the Tesla D870 Deskside Supercomputer here, which comes with 2 of them installed for a cool 5k: http://www.kikatek.com/product_info.php?products_id=66210 Here\'s the brief of the card: NVIDIA Tesla C870 GPU computing processor is the first to bring a massively multi-threaded architecture to high performance computing (HPC) applications for scientists, engineers, and other technical professionals. The Tesla C870 GPU computing processor transforms a standard system into a personal supercomputer with over 500 gigaflops of peak floating point performance. With a 128-processor computing core, a C-language development environment for the GPU, a suite of developer tools, and the world’s largest ISV development community for GPU computing, the Tesla C870 GPU computing processor enables professionals to develop applications faster and to deploy them across multiple generations of processors. The Tesla C870 GPU computing processor can be used in tandem with multi-core CPU systems to create a flexible solution for personal supercomputing. Main Features: * Tesla GPU\'s: 1 * Memory: 1.5GB GDDR3 * Memory Interface: 384-bit * Memory Bandwidth: 76.8 GB/sec * Maximum Power: 170W * System Interface: PCI Express x16 * Auxillary Power Connectors: 2 * Thermal Solution: Active Fansink Rob |
©2023 CERN