RIKEN Center for Computational Science Application Tuning Development Unit
Unit Leader: Kazuo Minami (Ph.D.)
The application tuning development team work to develop outstanding infrastructure of application development that will take full advantage of the capabilities of the supercomputer Fugaku.
In particular, performance evaluation and performance optimization of the applications developed by R-CCS research teams will be carried out.
We establish the performance analysis method and carry out the following tasks in order to optimize the applications.
- 1.Analysis of applications information such as performance, function and usage status.
- 2.Single CPU performance tuning and high parallelization.
- 3.Improvement for efficiency of operational resources by performance optimization of applications.
Our goal is to systematize the technology for performance optimization of applications through these tasks.
Main Research Fields
Related Research Fields
- Parallel processing
- High performance application
- Numerical analysis
- Distributed processing
- 1.K. Kumahata, K. Minami, Y. Yamade and C. Kato.:
"Performance improvement of the general-purpose CFD code FrontFlow/blue on the K computer"
Proceedings of the International Conference on High Performance Computing in Asia-Pacific Region (HPC Asia), Tokyo, Japan, pp.171-182. (2018).
- 2.M. Hashimoto, M. Terai, T. Maeda, K. Minami.:
"An Empirical Study of Computation-Intensive Loops for Identifying and Classifying Loop Kernels"
Proceedings of the 8th ACM/SPEC on International Conference on Performance Engineering, L'Aquila, Italy, pp.361-372. (2017).
- 3.T. Yamasaki, A. Kuroda, T. Kato, J. Nara, J. Koga, T. Uda, K. Minami and T. Ohno.:
"Multi-axis decomposition of density functional program for strong scaling up to 82,944 Nodes on the K Computer: Compactly folded 3D-FFT communicators in the 6D torus network"
Computer Physics Communications, in press, DOI:10.1016/j-cpc.2019.04.008. (2019).
- 4.A. Kuroda, K. Kumahata, S. Chiba, K. Takashina and K. Minami.:
"Performance Tuning of Deep Learning Framework Chainer on the K computer"
ISC High Performance 2019 (ISC2019) Research Poster, Frankfurt Messe, Germany, PR-28. (2019).
- 5.K.Minami et al.:
"Performance Estimation of Programs by an Extension of the RoofLine Model Considering Cache Effects"
IPSJ Transactions on Advanced Computing System (ACS) Vol.9 No.2, 1–14 (2016).
- 6.Akiyoshi Kuroda et al.:
"Analysis of the Correlation between Application Performance and Power Consumption on the K Computer (in Japanese)"
IPSJ Transactions on Advanced Computing System (ACS) Vol.8, No.4, 1-12 (2015).
- 7.Kiyoshi Kumahata, Kazuo Minami, Naoya Maruyama.:
"High-performance conjugate gradient performance improvement on the K computer"
International Journal of High Performance Computing Applications Vol.30, No.1, 55-70 (2016).
- 8.Hasegawa, Y., Iwata, J.I., Tsuji, M., Takahashi, D., Oshiyama, A.,Minami, K., Boku, T., Inoue, H., Kitazawa,Y.,Miyoshi, I., Yokokawa,M.:
"Performance evaluation of ultra-large-scale first-principles electronic structure calculation code on the K computer"
The International journal of High Performance Computing Applications Vol.28(3), 335-355 (2014).
- 9.Y.Hasegawa,K.Minami et al.:
"First-principles calculations of electron states of a silicon nanowire with 100,000 atoms on the K computer"
Proc. of 2011 Int. Conf. for High Performance Computing, Networking, Storage and Analysis (SC’11), November 12-18, Seattle, USA, 1-11 (2011).
- Kazuo Minami
- Unit Leader
- Akiyoshi Kuroda
- Research & Development Scientist
- Kiyoshi Kumahata
- Research & Development Scientist
- Keigo Nitadori
- Technical Scientist
- Kazuto Ando
- Technical Staff I
7-1-26 Minatojima-minami-machi , Chuo-ku,
Email: minami_kaz [at] riken.jp