Performance improvement for matrix calculation on CP-PACS node processor

CP-PACS (Computational Physics by Parallel Array Computer System) is a massively parallel processing system with 2048 node processors for large scale scientific calculations. On a node processor of CP-PACS, there is a special hardware feature called PVP-SW (Pseudo Vector Processor based on Slide Window), which realizes an efficient vector processing on a superscalar processor without depending on the cache. The authors present the effectiveness of PVP-SW by performance measurement on a single node processor for the LINPACK benchmark. Utilizing loop unrolling techniques and the block-TLB feature, the PVP-SW function improves the basic performance up to 3.5 times faster for 1000/spl times/1000 LINPACK. This performance corresponds to the 73% of theoretical peak.