Performance Analysis of MySQL, Apache Spark on CPU and GPU
Bharath Grandhi, Satyadhyan Chickerur, Mahesh S. Patil · 2018
However, with the huge amount of data that is getting generated every day from various fields, need for the advanced methods for managing and analyzing the big data is very much obvious. One of such platforms, which were developed exclusively for Big Data Analytics, is Apache Spark. Though MySQL is preferred for small amount of Data and Spark is meant for big data(in terms of volume), many of the functionalities are found similar in both and they can be considered for a comparative study. This paper implements execution of Big data on Apache Spark based on the parameters considered and comparing the same work with MySQL on CPU and GPU. The parameters that considered here are Loading Time and Response Time of the queries execution. The execution of queries directly on GPU dramatically reduces the effort required to achieve GPU acceleration by avoiding the need for database programmers to use new programming languages such as CUDA or modify their programs to use non-SQL libraries. This paper focus on accelerating the queries. The obtained results are analyzed with appropriate conclusion. The execution of the data on GPU is faster than the MySQL and Apache Spark. Results on an NVIDIA gtx 650 achieve speedups of 20-70X depending upon the size of the data.