ProHos-1 — A vector processor for the efficient estimation of higher-order moments.pdfVIP

P r o H o s - 1 - A V e c t o r P r o c e s s o r for t h e Efficient E s t i m a t i o n of H i g h e r - O r d e r M o m e n t s J. C. Alves, A. Puga, L. Corte-Real and J. S. Matos FEUP - Faculdade de Engenharia da Universidade do Porto/INESC, Praga da Repfiblica 93, 4007 Porto CODEX, PORTUGAL Abstract. Higher-order statistics (HOS) are a powerful analysis tool in digital signal processing. The most difficult task to use it effectively is the estimation of higher-order moments of sampled data taken from real systems. For applications that require real-time processing, the perfor- mance achieved by common microprocessors or digital signal processors is not good enough to carry out the large number of calculations needed for their estimation. This paper presents ProHosq, an experimental vec- tor processor for the estimation of the higher-order moments up to the fourth-order. The processors architecture exploits the structure of the algorithm, to process in parMlel four vectors of the input data in a pipe- lined fashion, executing the equivalent to 11 operations in each clock cycle. The design of dedicated control circuits led to high clock rate and small hardware complexity, thus suitable for implementation as an ASIC (Application Specific Integrated Circuit). 1 I n t r o d u c t i o n Higher-order statistics (HOS--higher-order cumulants and higher-order spectra) are powerful tools for the analysis and