A Library of Parameterized Floating-Point Modules and Their Use

@inproceedings{citeulike:2642887, abstract = {We present a parameterized floating-point library for use with reconfigurable hardware. Our format is both general and flexible. All IEEE formats are a subset of our format, as are all previously published floating-point formats for reconfigurable hardware. We have developed a library of fully parameterized hardware modules for format control, arithmetic operations and conversion to and from any fixed-point format. The format converters allow for hybrid implementations that combine both fixed and floating-point calculations. This permits the designer to choose between the increased range of floating-point and the increased precision of fixed-point within the same application. We illustrate the use of this library with a hybrid implementation of the K-means clustering algorithm applied to multispectral satellite images.}, author = {Belanovi\'{c}, Pavle and Leeser, Miriam }, citeulike-article-id = {2642887}, doi = {http://dx.doi.org/10.1007/3-540-46117-5\_68}, journal = {Field-Programmable Logic and Applications: Reconfigurable Computing Is Going Mainstream}, keywords = {floating\_point, fpga, fpgasupercomputing}, pages = {657--666}, posted-at = {2008-04-08 22:34:17}, priority = {2}, title = {A Library of Parameterized Floating-Point Modules and Their Use}, url = {http://dx.doi.org/10.1007/3-540-46117-5\_68}, year = {2002} }

TY - CONF ID - citeulike:2642887 L3 - citeulike-article-id:2642887 TI - A Library of Parameterized Floating-Point Modules and Their Use JF - Field-Programmable Logic and Applications: Reconfigurable Computing Is Going Mainstream SP - 657 EP - 666 N2 - We present a parameterized floating-point library for use with reconfigurable hardware. Our format is both general and flexible. All IEEE formats are a subset of our format, as are all previously published floating-point formats for reconfigurable hardware. We have developed a library of fully parameterized hardware modules for format control, arithmetic operations and conversion to and from any fixed-point format. The format converters allow for hybrid implementations that combine both fixed and floating-point calculations. This permits the designer to choose between the increased range of floating-point and the increased precision of fixed-point within the same application. We illustrate the use of this library with a hybrid implementation of the K-means clustering algorithm applied to multispectral satellite images. KW - floating_point KW - fpga KW - fpgasupercomputing AU - Belanović, Pavle AU - Leeser, Miriam PY - 2002/// UR - http://dx.doi.org/10.1007/3-540-46117-5_68 ER -