Toward GPU-accelerated Database Optimization

Abstract

For over three decades, research investigates optimization options in DBMSs. Nowadays, the hardware used in DBMSs become more and more heterogeneous, because processors are bound by a fixed energy budget leading to increased parallelism. Existing optimization approaches in DBMSs do not exploit parallelism for a single optimization task and, hence, can only benefit from the parallelism offered by current hardware by batch-processing multiple optimization tasks.Since a large optimization space often allows us to process sub-spaces in parallel, we expect large gains in result quality for optimization approaches in DBMSs and, hence, performance for query processing on modern (co-)processors. However, parallel optimization on CPUs is likely to slow down query processing, because DBMSs can fully exploit the CPUs computing resources due to high data parallelism. In contrast, the communication overhead of co-processors such as GPUs typically lead to plenty of compute resources unused.In this paper, we motivate the use of parallel co-processors for optimization in DBMSs, identify optimization problems benefiting from parallelization, and show how we can design parallel optimization approaches on the example of the operator placement problem.A. Meister ( ) · G. Saake

Online Sketch-based Query Optimization

“…Leis et al [28,30] evaluate the influence of several plan enumeration algorithms and the impact of considering bushy trees. Several recent approaches have been proposed to optimize the plan enumeration phase by using GPUs [37,38] and deep reinforcement learning models [34,35]. In this work, we propose an adaptive graph traversal algorithm that efficiently explores the search space.…”

The New Hardware Development Trend and the Challenges in Data Management and Analysis

“…Academics and industry are beginning to explore some new ways to accelerate the performance of data processing through software/hardware co-design. Instructionlevel optimization [16], coprocessor query optimization [17,18], hardware customization [19], workload hardware migration [20], increasing hardware-level parallelism [21], hardware-level operators [22], and so on are used to provide hardware-level performance optimization. However, the differences between the new processor and x86 processor fundamentally change the assumptions of traditional database software design on hardware.…”

“…Nowadays, the processor technology moves from multi-core to many-core which greatly differs from the multi-core processor in terms of core integration, number of threads, cache structure, and memory access. The object that should be optimized has been turned into SIMD [84,85], GPUs, APUs, Xeon Phi coprocessors, and FPGAs [18,[86][87][88]. The query optimization is becoming more and more dependent on the underlying hardware.…”

GridTables: A One-Size-Fits-Most H2TAP Data Store

“…A good overview about this topic can be found in a recent survey by Özcan et al [45]. A key enabling factor for HTAP systems is modern hardware: modern hardware promises novel ways for data process-Marcus Pinnecke pinnecke@ovgu.de 1 Institute of Technical and Business Information Systems, Database and Software Engineering Group, University of Magdeburg, Magdeburg, Germany ing of relational [14,25] and non-relational data [42,49], as well as benefits for several database system components, such as query optimization [26,41]. Appuswamy et al even suggested to use the term H 2 TAP whenever hybridization of workloads is combined with heterogeneity of hardware [6], effectively emphasizing the role of modern hardware.…”