Production Floating Point Applications on FPGAs
Computer Architecture and Automated Design Laboratory, Department of Electrical and Computer Engineering, Boston University; Boston, MA 02215
Symposium on Application Accelerators in High Performance Computing, 2009 (SAAHPC’09)
@conference{herbordt2009production,
title={Production Floating Point Applications on FPGAs},
author={Herbordt, M. and Sukhwani, B. and Chiu, M. and Khan, M.A.},
booktitle={Symposium on Application Accelerators in High Performance Computing, SAAHPC},
year={2009}
}
While FPGAs have only one fifth the raw floating point capability of GPUs, other attributes allow them to be surprisingly competitive with respect to a number of critical floating point intensive applications. In the first part we review these FPGA attributes. The bulk of this extended abstract then provides an overview of efficient FPGA implementations of Molecular Dynamics, Molecular Docking, and Molecular Dynamics based on discrete event simulation.
February 22, 2011 by hgpu
