Popcount computations are widely used in such areas as combinatorial search, data processing, statistical analysis, and bio- and\nchemical informatics. In many practical problems the size of initial data is very large and increase in throughput is important.\nThe paper suggests two types of hardware accelerators that are (1) designed in FPGAs and (2) implemented in Zynq-7000\nall programmable systems-on-chip with partitioning of algorithms that use popcounts between software of ARM Cortex-A9\nprocessing system and advanced programmable logic. A three-level system architecture that includes a general-purpose computer,\nthe problem-specific ARM, and reconfigurable hardware is then proposed. The results of experiments and comparisons with\nexisting benchmarks demonstrate that although throughput of popcount computations is increased in FPGA-based designs\ninteracting with general-purpose computers, communication overheads (in experiments with PCI express) are significant and\nactual advantages can be gained if not only popcount but also other types of relevant computations are implemented in\nhardware. The comparison of software/hardware designs for Zynq-7000 all programmable systems-on-chip with pure software\nimplementations in the same Zynq-7000 devices demonstrates increase in performance by a factor ranging from 5 to 19 (taking\ninto account all the involved communication overheads between the programmable logic and the processing systems).
Loading....