Data processing system and data processing method

Abstract

The invention provides a data processing system and a data processing method. The data processing system comprises a host processor, a coprocessor and a control module, wherein the host processor is used for sending to-be-processed data to the control module; the control module is used for receiving the to-be-processed data sent by the host processor and sending the to-be-processed data to the coprocessor; the coprocessor is used for receiving the to-be-processed data sent by the control module, processing the to-be-processed data to obtain a processing result of the to-be-processed data and sending the processing result of the to-be-processed data to the host processor through the control module; and the host processor is used for receiving the processing result, sent by the coprocessor through the control module, of the to-be-processed data. Through the data processing system and the data processing method, system design can be simplified, and the workload of the host processor can be lowered.

Description

technical field [0001] The invention relates to the field of databases, in particular to a data processing system and a data processing method. Background technique [0002] The hybrid platform architecture in which the main processor and coprocessors assist in data processing usually consists of 1-2 central processing units (English: central processing unit, referred to as: CPU) and 1-8 integrated cores (English: many integrated cores, referred to as: MIC) coprocessor, the coprocessor processor is often used as an online analytical processing (English: online analytical processing, abbreviation: OLAP) query accelerator, and mainly handles computationally intensive tasks in OLAP queries. From the perspective of computing characteristics, coprocessors are especially used for time-consuming independent operations such as data connection processing or aggregation processing that are suitable for parallel completion. [0003] In the process of processing data in the existing CP...

AI Technical Summary

Problems solved by technology

[0004] However, when a large amount of data processing is required, all the data cannot be stored on the MIC side at one time. At this time, it is necessary to partition the two data on the CPU side, and then perform the above data processing process on each partition on the MIC side. , in this way, all data processing, data transmission and memory access management work is performed by the main processor, resulting in a heavy workload on the main processor, and it is necessary to integrate data transmission, data processing and memory in the system code design The function of access management, the code is more complicated

Images