In-Depth Analysis of OLAP Query Performance on Heterogeneous Hardware

Abstract

Classical database systems are now facing the challenge of processing high-volume data feeds at unprecedented rates as efficiently as possible while also minimizing power consumption. Since CPU-only machines hit their limits, co-processors like GPUs and FPGAs are investigated by database system designers for their distinct capabilities. As a result, database systems over heterogeneous processing architectures are on the rise. In order to better understand their potentials and limitations, in-depth performance analyses are vital. This paper provides interesting performance data by benchmarking a portable operator set for column-based systems on CPU, GPU, and FPGA – all available processing devices within the same system. We consider TPC‑H query Q6 and additionally a hash join to profile the execution across the systems. We show that system memory access and/or buffer management remains the main bottleneck for device integration, and that architecture-specific execution engines and operators offer significantly higher performance.

Audit Data and Management Platform Based on Intelligent Algorithm

“…[10][11]. The main characteristics of online analytical processing are: fast speed, and the ability to respond to the analysis requests of most users in very little time; Users do not need a program to determine specific new operations in the way that users expect, and perform different logic and statistical analysis related to the application in the way that users expect; Multidimensional, providing users with multi-dimensional observation and analysis; Timeliness, no matter how large the number of data is or where it is stored, you can get timely information and manage these large amounts of information [12][13]. The use of OLAP technology has greatly expanded the ability of data warehouse to process data, but in this era of information explosion, the limitations of OLAP technology have also become increasingly prominent.…”