A Comparison of Linear Processor Arrays for Image Processing

This paper describes a comparison of the performance and usability of three Linear Processor Arrays for image processing purposes. The study covered the NEC IMAP-VISION card [I], the AS1 CNAPS card [2] and the SYMPHONIE of the CEA-LETI[3]. The manufacturers of these card have made different design decisions regarding the number of processing elements (PEs) and their complexity. It was found that for image processing many simple PEs are more useful than few powerful processors.

[1]  Shorin Kyo,et al.  Efficient Implementation of Image Processing Algorithms on Linear Processor Arrays Using the Data Parallel Language IDC , 1996, MVA.

[2]  E. R. Komen,et al.  Low-level image processing architectures: Compared for some non-linear recursive neighbourhood operations , 1990 .

[3]  Y. Fujita,et al.  A parallelizing method for implementing image processing tasks on SIMD linear processor arrays , 1997, Proceedings Fourth IEEE International Workshop on Computer Architecture for Machine Perception. CAMP'97.

[4]  Dan Hammerstrom,et al.  Image processing using one-dimensional processor arrays , 1996, Proc. IEEE.

[5]  P.P. Jonker,et al.  Bucket processing: a paradigm for image processing , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[6]  Y. Fujita,et al.  A 10 GIPS SIMD processor for PC-based real time vision applications -architecture, algorithm implementation and language support , 1997, Proceedings Fourth IEEE International Workshop on Computer Architecture for Machine Perception. CAMP'97.