BROWSE
Detail
Journal Article
Efficient Parallel Join Processing Exploiting SIMD in Multi-Thread Environments
Cited 3 time in 
Download 5 time
Share 
Download 5 time
Share
- Authors
- Gilseok Hong, Seonghyeon Kang, Chang soo Kim, Jun-Ki Min
- Issue Date
- 2018-03
- Citation
- IEICE Transactions on Information and Systems, v.E101-D, no.3, pp.659-667
- ISSN
- 1745-1361
- Publisher
- 일본, 전자정보통신학회 (IEICE)
- Language
- English
- Type
- Journal Article
- Project Code
- 17HS7600, Development of an Unified Data Engineering Technology for Large-scale Transaction Processing and Real-time Complex Analytics, Chang Soo Kim
- Abstract
- In this paper, we study parallel join processing to improve the performance of the merge phase of sort-merge join by integrating all parallelism provided by mainstream CPUs. Modern CPUs support SIMD instruction sets with wider SIMD registers which allows to process multiple data items per each instruction. Thus, we devise an efficient parallel join algorithm, called Parallel Merge Join with SIMD instructions (PMJS). In our proposed algorithm, we utilize data parallelism by exploiting SIMD instructions. And we also accelerate the performance by avoiding the usage of conditional branch instructions. Furthermore, to take advantage of the multiple cores, our proposed algorithm is threaded in multi-thread environments. In our multi-thread algorithm, to distribute workload evenly to each thread, we devise an efficient workload balancing algorithm based on the kernel density estimator which allows to estimate the workload of each thread accurately.
- KSP Keywords
- Instruction sets, Join algorithm, Join processing, Multi-thread, Multiple data, SIMD instruction, Sort-merge Join, Workload Balancing, balancing algorithm, data parallelism, kernel density estimator