Fast iterative circuits and RAM-based mergers to accelerate data sort in software/hardware systems; pp. 323–335

Estonian Academy of Sciences. Proceedings

Valery Sklyarov¹ 

关键词: arallel data processing;    merging;    iterative networks;    communication-time processing;    Field-Programmable Gate Array (FPGA);    Peripheral Component Interconnect (PCI)expressbus.;   

DOI  :  10.3176/proc.2017.3.07

学科分类：化学（综合）

来源: Teaduste Akadeemia Kirjastus

【 摘 要 】

The paper suggests and describes two architectures for parallel data sort. The first architecture is applicable to large data sets and it combines three stages of data processing data sorting in hardware (in a Field-Programmable Gate Arrays – FPGA), merging preliminary sorted blocks in hardware (in the FPGA), and merging large subsets received from the FPGA in general-purpose software. Dataexchange between the FPGA anda general-purpose computeris organized throughafast Peripheral Component Interconnect (PCI) expressbus.The second architectureis applicabletosmalldatasetsandit enablessortingtobedoneatthetimeofdata acquisition,i.e.as soon as the last data item is received, the sorted items can be transferred immediately. The results of experiments clearly demonstrate the advantages of the proposed architectures that permit the reduction of the required hardware resources and increasing throughput compared to the results reported in publications and software functions targeted to data sorting.

【 授权许可】

CC BY-NC