Výsledky vyhledávání - "Fujita, Norihisa"

Report

White Paper from Workshop on Large-scale Parallel Numerical Computing Technology (LSPANC 2020): HPC and Computer Arithmetic toward Minimal-Precision Computing

Autor: Iakymchuk, Roman, Mukunoki, Daichi, Podobas, Artur, Jézéquel, Fabienne, Imamura, Toshiyuki, Fujita, Norihisa, Huthmann, Jens, Kudo, Shuhei, Tan, Yiyu, Domke, Jens, Ohlhus, Kai Torben, Fukaya, Takeshi, Hoshi, Takeo, Murakami, Yuki, Nakata, Maho, Ogita, Takeshi, Sano, Kentaro, Boku, Taisuke

In numerical computations, precision of floating-point computations is a key factor to determine the performance (speed and energy-efficiency) as well as the reliability (accuracy and reproducibility). However, precision generally plays a contrary ro

Externí odkaz: http://arxiv.org/abs/2004.04628

Zobrazit plný text záznamu

Optimizing Precision for High-Performance, Robust, and Energy-Efficient Computations

Autor: Iakymchuk, Roman, Graillat, Stef, Jézéquel, Fabienne, Mukunoki, Daichi, Imamura, Toshiyuki, Tan, Yiyu, Koshiba, Atsushi, Huthmann, Jens, Sano, Kentaro, Fujita, Norihisa, Boku, Taisuke

Publikováno v: International Conference on High Performance Computing in Asia-Pacific Region
International Conference on High Performance Computing in Asia-Pacific Region, Jan 2020, Fukuoka, Japan

International audience; In numerical computations, precision of floating-point computations is a key factor to determine the performance (speed and energy-efficiency) as well as the reliability (accuracy and reproducibility). However, precision gener

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::d7e44a1e05f18e94dc7b1dcc8f525988
https://hal.archives-ouvertes.fr/hal-02401813

Zobrazit plný text záznamu

Minimal-Precision Computing for High-Performance, Energy-Efficient, and Reliable Computations

Autor: Mukunoki, Daichi, Toshiyuki, Imamura, Tan, Yiyu, Koshiba, Atsushi, Huthmann, Jens, Sano, Kentaro, Jézéquel, Fabienne, Graillat, Stef, Iakymchuk, Roman, Fujita, Norihisa, Boku, Taisuke

Publikováno v: International Conference on High Performance Computing, Networking, Storage and Analysis (SC19)
International Conference on High Performance Computing, Networking, Storage and Analysis (SC19), Nov 2019, Denver, United States
France-Japan-Germany trilateral workshop: Convergence of HPC and Data Science for Future Extreme Scale Intelligent Applications
France-Japan-Germany trilateral workshop: Convergence of HPC and Data Science for Future Extreme Scale Intelligent Applications, Nov 2019, Tokyo, Japan
2nd R-CCS international symposium, K to Fugaku: Simulation, Big Data and AI supporting Society 5.0
2nd R-CCS international symposium, K to Fugaku: Simulation, Big Data and AI supporting Society 5.0, Feb 2020, Kobe, Japan

International audience; We have recently started a research collaboration to explore the possibility of a new computing system with precision-tuning, in collaboration with RIKEN CCS, Sorbonne University, and University of Tsukuba. Our proposal, "mini

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::592139b10c3f98f19b7c4064996cb16e
https://hal.archives-ouvertes.fr/hal-02401757

Zobrazit plný text záznamu