Large-scale Parallel Numerical Computing Technology Research Team

Research summary

The Large-scale Parallel Numerical Computing Technology Research Team conducts research and development of a large scale, highly parallel and high-performance numerical software library for the supercomputer Fugaku. Simulation programs require various numerical algorithms for the solution of linear systems, eigenvalue problems, fast Fourier transforms, and non-linear equations. In order to take advantage of the full potential of Fugaku, we must select algorithms and develop a numerical software library based on the concepts of high parallelism, high performance, high precision, resiliency, and scalability. We achieve this through close collaboration among computational science (simulation), computer science (hardware and software) and numerical mathematics. Our goal is to establish a fundamental technique to develop numerical software libraries, called KMATHLIB, for next generation supercomputer systems based on strong cooperation within R-CCS.

Representative papers

Yuki Uchino, Toshiyuki Imamura.:
"High-Performance EigenSolver Combining EigenExa and Iterative Refinement"
SC '24: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, 2024
Takeshi Terao, Toshiyuki Imamura, and Katsuhisa Ozaki.:
"Iterative refinement for an eigenpair subset of a real symmetric matrix"
JSIAM Letters, Vol. 16, pp. 89-92, 2024, doi: 10.14495/jsiaml.16.89
Piotr Luszczek, Ahmad Abdelfattah, Hartwig Anzt, Atsushi Suzuki, Stanimire Tomov.:
"Batched sparse and mixed-precision linear algebra interface for efficient use of GPU hardware accelerators in scientific applications"
Future Generation Computer Systems-The International Journal of Science, Vol.160, pp. 359-374, 2024, doi: 10.1016/j.future.2024.06.004
Yuta Hasegawa, Naoyuki Onodera, Yuuichi Asahi, Takuya Ina, Toshiyuki Imamura, and Yasuhiro Idomura.:
"Continuous data assimilation of large eddy simulation by lattice Boltzmann method and local ensemble transform Kalman filter (LBM-LETKF)"
Fluid Dynamics Research, Vol. 55, Number 6, 2023, doi: 10.1088/1873-7005/ad06bd
Daichi Mukunoki, Satoshi Kawai, and Toshiyuki Imamura.:
"Sparse Matrix-Vector Multiplication with Reduced-Precision Memory Accessor"
2023 IEEE 16th International Symposium on Embedded Multicore/Many-core Systems-on-Chip (MCSoC), pp. 608-615, 2023. doi: 10.1109/MCSoC60832.2023.00094
Atsushi Suzuki.:
"A factorization algorithm for sparse matrix with mixed precision arithmetic"
ECCOMAS Congress 2022, Volume Science Computing, 2022. doi 10.23967/eccomas.2022.006
Hisashi Yashiro, Koji Terasaki, Yuta Kawai, Shuhei Kudo, Takemasa Miyoshi, Toshiyuki Imamura, Kazuo Minami, Hikaru Inoue, Tatsuo Nishiki, Takayuki Saji, Masaki Satoh, and Hirofumi Tomita.:
"A 1024-member ensemble data assimilation with 3.5-km mesh global weather simulations"
Proc. The International Conference for High Performance Computing, Networking, Storage and Analysis (SC '20). IEEE Press, Article 1, 1–10, 2020. doi: 10.1109/SC41405.2020.00005
Daichi Mukunoki, Katsuhisa Ozaki, Takeshi Ogita, Toshiyuki Imamura.:
"DGEMM using Tensor Cores, and Its Accurate and Reproducible Versions"
ISC High Performance 2020, Lecture Notes in Computer Science, Vol.12151, pp. 230-248, 2020. doi.org/10.1007/978-3-030-50743-5_12
Takeshi Fukaya and Toshiyuki Imamura.:
"Performance evaluation of the EigenExa eigensolver on Oakleaf-FX: tridiagonalization versus pentadiagonalization"
Proc. Parallel and Distributed Processing Symposium Workshop (IPDPSW), 2015 IEEE International, pp. 960-969, 2015. doi: 10.1109/IPDPSW.2015.128
Yusuke Hirota and Toshiyuki Imamura.:
"Divide-and-Conquer Method for Banded Generalized Eigenvalue Problems"
Journal of Information Processing Computing System, Vol.52,Nov,20,2015.