New NVIDIA compiler lets developers offload math functions to GPU

Message boards : Number crunching : New NVIDIA compiler lets developers offload math functions to GPU

To post messages, you must log in.

AuthorMessage
Profile RedQueen

Send message
Joined: 15 Jun 06
Posts: 9
Credit: 163,610
RAC: 0
Message 37029 - Posted: 20 Feb 2007, 19:53:26 UTC
Last modified: 20 Feb 2007, 19:53:40 UTC

http://www.developer.nvidia.com/object/cuda.html

"GPU computing with CUDA technology is an innovative combination of computing features in next generation NVIDIA GPUs that are accessed through the standard ‘C’ language. Where previous generation GPUs were based on “streaming shader programs”, CUDA programmers use ‘C’ to create programs called kernels that use many threads to operate on large quantities of data in parallel. In contrast to multi-core CPUs, where only a few threads execute at the same time, NVIDIA GPUs featuring CUDA technology process thousands of threads simultaneously enabling high computational throughput across large amounts of data."



This is good to hear. Maybe someday BOINC will be coded to allow the use of CPUs AND GPUs. The GeForce 8800 cards and the new ATI R600 cards launching in March have a lot of processing power.
ID: 37029 · Rating: 0 · rate: Rate + / Rate - Report as offensive    Reply Quote

Message boards : Number crunching : New NVIDIA compiler lets developers offload math functions to GPU



©2024 University of Washington
https://www.bakerlab.org