Embedded floating-point units in FPGAs Export

@inproceedings{citeulike:671495, abstract = {Due to their generic and highly programmable nature, FPGAs provide the ability to implement a wide range of applications. However, it is this nonspecific nature that has limited the use of FPGAs in scientific applications that require floating-point arithmetic. Even simple floating-point operations consume a large amount of computational resources. In this paper, we introduce embedding floating-point multiply-add units in an island style FPGA. This has shown to have an average area savings of 55.0\% and an average increase of 40.7\% in clock rate over existing architectures.}, address = {New York, NY, USA}, author = {Beauchamp, Michael J. and Hauck, Scott and Underwood, Keith D. and Hemmert, K. Scott}, booktitle = {FPGA '06: Proceedings of the 2006 ACM/SIGDA 14th international symposium on Field programmable gate arrays}, citeulike-article-id = {671495}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1117201.1117204}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1117201.1117204}, doi = {10.1145/1117201.1117204}, isbn = {1-59593-292-5}, keywords = {architecture\_comparison, floating\_point, fpga, vlsi\_design}, location = {Monterey, California, USA}, pages = {12--20}, posted-at = {2009-10-13 15:11:08}, priority = {2}, publisher = {ACM}, title = {Embedded floating-point units in FPGAs}, url = {http://dx.doi.org/10.1145/1117201.1117204}, year = {2006} }

TY - CONF ID - citeulike:671495 L3 - citeulike-article-id:671495 N2 - Due to their generic and highly programmable nature, FPGAs provide the ability to implement a wide range of applications. However, it is this nonspecific nature that has limited the use of FPGAs in scientific applications that require floating-point arithmetic. Even simple floating-point operations consume a large amount of computational resources. In this paper, we introduce embedding floating-point multiply-add units in an island style FPGA. This has shown to have an average area savings of 55.0% and an average increase of 40.7% in clock rate over existing architectures. CY - Monterey, California, USA SN - 1-59593-292-5 AD - New York, NY, USA EP - 20 TI - Embedded floating-point units in FPGAs PB - ACM T2 - FPGA '06: Proceedings of the 2006 ACM/SIGDA 14th international symposium on Field programmable gate arrays SP - 12 KW - architecture_comparison KW - floating_point KW - fpga KW - vlsi_design AU - Beauchamp, Michael AU - Hauck, Scott AU - Underwood, Keith AU - Hemmert, Scott PY - 2006/// UR - http://dx.doi.org/10.1145/1117201.1117204 ER -