Computing correlation and convolution on bidirectional linear systolic array

Abstract

Recent advances in VLSI technology offer to the user to fabricate thousands of switching elements on a single chip. Computation power can be significantly increased by parallel processing of the algorithms mapped and designed in VLSI technology for applications that require large computational power. These applications include matrix computations, pattern recognition, signal and image processing, etc. Convolution and correlation of agiven sequences form core of many scientific computing, signal and image processing, digital filters, interpolation, etc. Introducing systolic arrays into this area can significantly improve speed of processing. In this paper we describe the procedure for synthesizing a bidirectional linear systolic array (BLSA) for rectangular matrix-vector multiplication. Then we show how this array can be efficiently used for computing convolution and corelation problem. © Dynamic Publishers, Inc.