Robust Query Processing in Co-Processor-accelerated Databases

被引:31
作者
Bress, Sebastian [1 ,3 ]
Funke, Henning [2 ]
Teubner, Jens [2 ]
机构
[1] German Res Ctr Artificial Intelligence, Kaiserslautern, Germany
[2] TU Dortmund Univ, Dortmund, Germany
[3] TU Dortmund, Dortmund, Germany
来源
SIGMOD'16: PROCEEDINGS OF THE 2016 INTERNATIONAL CONFERENCE ON MANAGEMENT OF DATA | 2016年
关键词
HASH JOINS;
D O I
10.1145/2882903.2882936
中图分类号
TP [自动化技术、计算机技术];
学科分类号
080201 [机械制造及其自动化];
摘要
Technology limitations are making the use of heterogeneous computing devices much more than an academic curiosity. In fact, the use of such devices is widely acknowledged to be the only promising way to achieve application-speedups that users urgently need and expect. However, building a robust and efficient query engine for heterogeneous co-processor environments is still a significant challenge. In this paper, we identify two effects that limit performance in case co-processor resources become scarce. Cache thrashing occurs when the working set of queries does not fit into the co-processor's data cache, resulting in performance degradations up to a factor of 24. Heap contention occurs when multiple operators run in parallel on a co-processor and when their accumulated memory footprint exceeds the main memory capacity of the co-processor, slowing down query execution by up to a factor of six. We propose solutions for both effects. Data-driven operator placement avoids data movements when they might be harmful; query chopping limits co-processor memory usage and thus avoids contention. The combined approach data driven query chopping achieves robust and scalable performance on co-processors. We validate our proposal with our open-source GPU-accelerated database engine CoGaDB and the popular star schema and TPC-H benchmarks.
引用
收藏
页码:1891 / 1906
页数:16
相关论文
共 38 条
[1]
Abadi D.J., 2008, P 2008 ACM SIGMOD IN, P967, DOI DOI 10.1145/1376616.1376712
[2]
[Anonymous], 2015, PROC EDBT 15 WORKSHO
[3]
[Anonymous], 2011, CUDA by Example: An Introduction to General-Purpose GPU Programming
[4]
[Anonymous], 2014, CUDA C PROGR GUID CU, P77
[5]
Arumugam S., 2010, P ACM SIGMOD INT C M, P519, DOI DOI 10.1145/1807167.1807224
[6]
MIL primitives for querying a fragmented world [J].
Boncz, PA ;
Kersten, ML .
VLDB JOURNAL, 1999, 8 (02) :101-119
[7]
Boncz PA., 2005, CIDR, V5, P225
[8]
The Future of Microprocessors [J].
Borkar, Shekhar ;
Chien, Andrew A. .
COMMUNICATIONS OF THE ACM, 2011, 54 (05) :67-77
[9]
Ocelot/HyPE: Optimized Data Processing on Heterogeneous Hardware [J].
Bress, Sebastian ;
Heimel, Max ;
Saecker, Michael ;
Koecher, Bastian ;
Markl, Volker ;
Saake, Gunter .
PROCEEDINGS OF THE VLDB ENDOWMENT, 2014, 7 (13) :1609-1612
[10]
Load-aware inter-co-processor parallelism in database query processing [J].
Bress, Sebastian ;
Siegmund, Norbert ;
Heimel, Max ;
Saecker, Michael ;
Lauer, Tobias ;
Bellatreche, Ladjel ;
Saake, Gunter .
DATA & KNOWLEDGE ENGINEERING, 2014, 93 :60-79