FPGA (Field Programmable Gate Array) parallel sorting method and system based on index tree and data linked list

Abstract

The invention provides an FPGA (Field Programmable Gate Array) parallel sorting method and system based on an index tree and a data linked list. The method comprises the following steps of reading a characteristic value and an identification value to be sorted and recorded from a memory in sequence; creating an identification value node in a data linked list storage area, and storing the recorded identification value in the identification value node; according to the recorded characteristic value, establishing a characteristic value node on the index tree of an index tree storage area; after all records are read and processed, traversing the characteristic value node of each layer on the index tree in sequence, and recovering the characteristic value according to a path of the characteristic value node; according to an identification value node address recorded in the obtained characteristic value node, finding the corresponding identification value in the data linked list storage area; finally, according to a traversing sequence, outputting all the recorded characteristic values and identification values. According to the FPGA parallel sorting method and system based on the index tree and the data linked list, data is coded / decoded through the FPGA to realize data sorting so as to carry out data sorting while data is read.

Description

technical field

[0001] The invention relates to a data sorting method, in particular to an FPGA parallel sorting method and system based on an index tree and a data linked list. Background technique

[0002] Sorting is an important data operation and an important operation in computer technology and information systems. Traditional sorting algorithms include bubble method, selection method, counting method, address sorting method and so on. Most of these algorithms use cyclic comparison, which has the disadvantages of time-consuming calculation, poor real-time performance, and processing space resource occupancy, which is the sorting algorithm of "space for time".

[0003] In the era of big data, industry / enterprise big data that can easily reach hundreds of terabytes or even tens to hundreds of petabytes has far exceeded the processing capabilities of existing traditional computing technologies and information systems. Therefore, finding an effective data sorting method h...

Images