3D-Tech News Around The Web / Design Methods and Tools for FPGA-Based Acceleration of Scientific Computing« on: February 04, 2011, 06:13:52 PM »
Field-Programmable Gate Arrays (FPGAs) have been considered as possible implementation platforms for computation since the early 1990's. Over the technology generations, the regularity of FPGA designs has allowed them to stay at the leading edge of each new technology node, with architectural innovations enabling their widespread adoption for embedded applications. The potential of FPGAs for scientific computations is well understood today; nonetheless, long implementation cycles have hindered their faster adoption for numerically intensive scientific applications. We currently stand on a threshold, where various key research contributions and initiatives have the potential for propel FPGA-based computation from the embedded space into scientific computing. At the same time, other "accelerator technologies" such as GPGPU are beginning to make deep inroads into traditional HPC, with the potential for common design capture languages such as OpenCL.
Get dozens of whitepapers from Microsoft