Initialising ...
Initialising ...
Initialising ...
Initialising ...
Initialising ...
Initialising ...
Initialising ...
Abe, Takato*; Sato, Takuto; Boku, Taisuke*; Fujita, Norihisa*; Kusaka, Hiroyuki*
Joho Shori Gakkai Kenkyu Hokoku, p.1 - 11, 2025/05
no abstracts in English
Miyamura, Hiroko; Kawamura, Takuma; Suzuki, Yoshio; Idomura, Yasuhiro; Takemiya, Hiroshi
Joho Shori Gakkai Rombunshi, 55(9), p.2216 - 2224, 2014/09
In numerical simulations, variations of calculation results with respect to a variable axis are often observed. When the target model is given in 3D, the simulation results become 4D. Such a multi-dimensional dataset given in more than 4D space is analyzed by detailed explorations of regions of interest (ROIs) in multi-dimensional space. However, for high-dimensional and large-scale datasets, this approach requires enormous processing time and effort, and may have difficulty in capturing all the ROIs. Therefore, we propose a technique that is based on a concept of spatiotemporal image. In our technique, a space axis is created by octree, a variable axis is defined in the direction perpendicular to the space axis. Our technique is applied to the results of 3D seismic simulations of a nuclear plant, and regions with characteristic frequency responses of each region are analyzed. Through the analyses, it is demonstrated that our technique can effectively capture ROIs from 4D datasets.
Miyamura, Hiroko; Shinano, Yuji*; Miyashiro, Ryuhei*; Saito, Takafumi*
Joho Shori Gakkai Rombunshi; Suri Moderuka To Oyo (Internet), 2(2), p.103 - 112, 2009/03
In branch-and-bound algorithms for integer programming, runtime behavior of the algorithms depends much on branching strategy. However, from a huge computation log of a large program, it is difficult to explore a key factor for effective branching. To analyze which factor of branching strategy is essential, we develop a system for visualization of growing process of a large branch-and-bound tree. The proposed system provides intuitive understanding how branching strategy affects branch-and-bound process.
Tsujita, Yuichi*; Arima, Tatsumi*; Idemitsu, Kazuya*; Suzuki, Yoshio; Kimura, Hideo
Joho Shori Gakkai Kenkyu Hokoku 2008-ARC-177, 2008-HPC-114, p.103 - 108, 2008/03
Recently, many research works for Pu-recycle have been done. We proposed a molecular dynamics method to have deep understandings in nuclear materials. We adopted a parallel computing technique by using an ITBL's computing environment in our simulation program because a huge amount of computations and time steps is required. We received a request from application users to incorporate a user friendly interface in a computing environment for specifying parameters in a simulation program and successive operations of parallel computation and visualization on a user's terminal. So, we have built a GUI computing environment to realize such the functionalities by using an ITBL's client API. In this paper, we report objectives of this development, implementation method of this application, and examples of the computing environment. Finally, we mention its future plan.
Saito, Kimiaki; Saito, Hidetoshi*; Kunieda, Etsuo*; Narita, Yuichiro*; Myojoyama, Atsushi*; Fujisaki, Tatsuya*; Kawase, Takatsugu*; Kaneko, Katsutaro*; Ozaki, Masahiro*; Deloar, H. M.*; et al.
Joho Shori, 48(10), p.1081 - 1088, 2007/10
no abstracts in English
Kashiwagi, Hiroe*; Takata, Masami*; Sasaki, Akira; Jo, Kazuki*
Joho Shori Gakkai Rombunshi; Suri Moderuka To Oyo (Internet), 48(SIG15), p.189 - 198, 2007/10
no abstracts in English
Imamura, Toshiyuki*; Yamada, Susumu; Machida, Masahiko
Joho Shori Gakkai Kenkyu Hokoku 2007-HPC-111, p.167 - 172, 2007/08
no abstracts in English
Yamada, Susumu; Machida, Masahiko; Imamura, Toshiyuki*
Joho Shori Gakkai Rombunshi; Komputeingu Shisutemu (Internet), 45(SIG6(ACS6)), p.161 - 170, 2004/05
no abstracts in English
Ueshima, Yutaka; Kondo, Takao*; Isogai, Kentaro*
Joho Shori Gakkai MPS Shimpojiumu Rombunshu, 2003(14), p.151 - 158, 2003/10
no abstracts in English
Tsujita, Yuichi; Yamagishi, Nobuhiro*; Kimura, Kazuyuki*; Otani, Takayuki; Tsuruoka, Nobuhiko*; Fujita, Naoyuki*
Joho Shori Gakkai Kenkyu Hokoku 2002-HPC-92, p.7 - 12, 2002/10
SCore system has been developed to provide flat computing infrastructure for parallel computing without awareness of each compute host in a PC cluster system. An SCore cluster system can be handled as a single computer. MPICH-SCore, which is an MPI library in SCore, is not available across multiple SCore cluster systems as well as multiple platforms. We have implemented an MPI communication library, Stampi in SCore cluster system to enable MPI communication between SCore cluster systems and measured communication performance of the library using SCore cluster systems.
Itakura, Kenichi; Yokokawa, Mitsuo; Shimizu, Futoshi; Kimizuka, Hajime*; Kaburaki, Hideo
Joho Shori Gakkai Kenkyu Hokoku 2001-HPC-88, p.67 - 72, 2001/10
he Earth Simulator which is under development has 640 processor nodes and its peak performance is 40 Tflop/s. In this study, we have evaluated performance of solid molecular dynamics simulation on an SMP node of the Earth Simulator. In molecular dynamics simulation, each particle is influenced by all particles within a cut-off region and the representation of these pairs of particles is made by a matrix. Two matrix representations, compressed row form and jagged diagonal form, are considered for vectorization. The jagged diagonal form is better than the compressed row form in performance on a vector processor for the force calculation of every pairs, because the vector length of the former is longer than that of the latter. However, computational cost for converting the normal matrix form to the jagged diagonal form is quite expensive and the total performance in using the jagged diagonal form is low. Speedup by parallelization with the compressed row form is 2.4 to 2.7 with 8 vector processors.
Uehara, Hitoshi; Tsuda, Yoshinori*; Yokokawa, Mitsuo
Joho Shori Gakkai Kenkyu Hokoku 2001-HPC-87, 2001(77), p.67 - 72, 2001/07
MPI is one of major message communication interfaces for application programs. The MPI consists of an MPI-1 as a basic specification, and an MPI-2 as extensions.Some benchmark program for MPI-1 had been proposed already. However benchmark programs for MPI-2 are a little and their measurements are limited. We have developed an MPI benchmark program library for MPI-2 (MBL2) which measures the detail performance of MPI-I/O and RMA functions of MPI-2. In this report, we describe the MBL2 and performance data of MPI-2 on VPP5000, which we measured using MBL2.
Moda, Yukimitsu*; Hayashi, Takuya*; Koide, Hiroshi; Kashima, Toru*; Tsutsui, Hiroaki*; Kasahara, Hironori*
Joho Shori Gakkai Dai-62-Kai (Heisei-13-Nen Zenki) Zenkoku Taikai Koen Rombunshu, p.1_131 - 1_132, 2001/03
no abstracts in English
Imamura, Toshiyuki; Muramatsu, Kazuhiro; Kitabata, Hideyuki*; Kaneko, Isamu*; Yamagishi, Nobuhiro*; Hasegawa, Yukihiro*; Takemiya, Hiroshi*; Hirayama, Toshio
Joho Shori Gakkai Kenkyu Hokoku 2001-ARC-142, p.49 - 54, 2001/03
no abstracts in English
Koide, Hiroshi; Yamagishi, Nobuhiro*; Takemiya, Hiroshi*; Kasahara, Hironori*
Joho Shori Gakkai Rombunshi, 42(3), p.65 - 73, 2001/03
no abstracts in English
Isogai, Kentaro*
Joho Shori Gakkai Dai-63-Kai Zenkoku Taikai Hobunshu, p.3_475 - 3_476, 2001/00
no abstracts in English
Tsujita, Yuichi; Imamura, Toshiyuki; Takemiya, Hiroshi*; Yamagishi, Nobuhiro*
Joho Shori Gakkai Kenkyu Hokoku 2000-HPC-84, p.43 - 48, 2000/12
no abstracts in English
Osoda, Tsutomu*; Maruyama, Kunihide*; Washio, Takumi*; Doi, Shun*; Yamada, Susumu
Joho Shori Gakkai Rombunshi, 41(SIG8), p.92 - 100, 2000/11
no abstracts in English
Yokokawa, Mitsuo; Tani, Keiji
Joho Shori, 41(4), p.369 - 374, 2000/04
no abstracts in English
Tani, Keiji; Yokokawa, Mitsuo
Joho Shori, 41(3), p.249 - 254, 2000/03
no abstracts in English
