IEICE TRANSACTIONS on Information
Efficient Parallel Join Processing Exploiting SIMD in Multi-Thread Environments
Summary :
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.
- Publication
- IEICE TRANSACTIONS on Information Vol.E101-D No.3 pp.659-667
- Publication Date
- 2018/03/01
- Publicized
- 2017/12/14
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2017EDP7300
- Type of Manuscript
- PAPER
- Category
- Data Engineering, Web Information Systems
Authors
Gilseok HONG
Korea Univ. of Tech. & Edu.
Seonghyeon KANG
Korea Univ. of Tech. & Edu.
Chang soo KIM
ETRI
Jun-Ki MIN
Korea Univ. of Tech. & Edu.
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Gilseok HONG, Seonghyeon KANG, Chang soo KIM, Jun-Ki MIN, "Efficient Parallel Join Processing Exploiting SIMD in Multi-Thread Environments" in IEICE TRANSACTIONS on Information,
vol. E101-D, no. 3, pp. 659-667, March 2018, doi: 10.1587/transinf.2017EDP7300.
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.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2017EDP7300/_p
Copy
@ARTICLE{e101-d_3_659,
author={Gilseok HONG, Seonghyeon KANG, Chang soo KIM, Jun-Ki MIN, },
journal={IEICE TRANSACTIONS on Information},
title={Efficient Parallel Join Processing Exploiting SIMD in Multi-Thread Environments},
year={2018},
volume={E101-D},
number={3},
pages={659-667},
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.},
keywords={},
doi={10.1587/transinf.2017EDP7300},
ISSN={1745-1361},
month={March},}
Copy
TY - JOUR
TI - Efficient Parallel Join Processing Exploiting SIMD in Multi-Thread Environments
T2 - IEICE TRANSACTIONS on Information
SP - 659
EP - 667
AU - Gilseok HONG
AU - Seonghyeon KANG
AU - Chang soo KIM
AU - Jun-Ki MIN
PY - 2018
DO - 10.1587/transinf.2017EDP7300
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E101-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2018
AB - 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.
ER -
English
