Procedia Computer Science

Volume 80, 2016, Pages 1416-1417

ICCS 2016. The International Conference on Computational ELSEVIER Science

Workshop on Large Scale Computational Physics

LSCP 2016

1 12 O. Olagbemi , E. de Doncker and F. Yuasa

1 Western Michigan University, Kalamazoo MI 49008, U. S.A. omofolakunmiel. olagbemi@wmich. edu, elise. dedoncker@wmich. edu 2 High Energy Accelerator Research Organization (KEK), Tsukuba, Ibaraki, 305-0801, Japan

fukuko.yuasa@kek.jp

Abstract

The LSCP workshop focuses on symbolic and numerical methods and simulations, algorithms and tools (software and hardware) for developing and running large-scale computations in physical sciences. Special attention goes to parallelism, scalability and high numerical precision. System architectures are also of interest as long as they are supporting physics-related calculations, such as: massively parallel systems, GPUs, many-integrated-cores, distributed (cluster, grid/cloud) computing, and hybrid systems. Topics this year are from theoretical physics (high energy physics and lattice gauge theory/QCD). The effects of transformations in obtaining numerical results for Feynman loop integrals, and the deployment of a novel architecture to achieve large computational power with low electric power consumption are presented.

Keywords: Preface, Workshop overview, Workshop organization, Large Scale Computational Physics

Preface

The LSCP Workshop has been held under the ICCS conference since 2011. In LSCP 2016, the following papers are presented:

- "First application of lattice QCD to Pezy-SC processor", Tatsumi Aoyama, Ken-Ichi Ishikawa, Yasuyuki Kimura, Hideo Matsufuru, Atsushi Sato, Tomohiro Suzuki and Sunao Torii [AIKMSST16]

1416 Selection and peer-review under responsibility of the Scientific Programme Committee of ICCS 2016

(gi The Authors. Published by Elsevier B.V.

doi:10.1016/j.procs.2016.05.452

Preface LSCP 2016 workshop

O. Olagbemi, E. de Doncker and F. Yuasa

- "Adaptive Integration and Singular Boundary Transformations", Elise de Doncker, Fukuko Yuasa, Tadashi Ishikawa, John Kapenga and Fola Olagbemi [dDYIKO16]

In the first paper, the Pezy-SC processor, a novel architecture developed by Pezy Computing K. K. is used on a hybrid parallel system (Suiren) in the simulation of lattice QCD. In varying scenarios, the sustained performance is measured for matrix multiplications and a BiCGStab solver. An attractive feature of the Pezy-SC processor (an accelerator device similar to GPGPUs) is the desirable combination of large computational power and low electric power consumption by the processor. The authors examine how the data access patterns affect the performance of the processor, and present their results along with their observations pertaining to the Pezy-SC processor.

The second paper applies multivariate adaptive integration combined with a variety of transformations to integrals plagued with singularities at the boundaries of the integration domain. The transformations are compared with respect to their acceleration of convergence and the resulting computation time. The integration is performed with the ParInt parallel software package, which is written in C and layered over MPI. In addition, the effects of using higher precision are presented for double and long double precision. An application is given to Feynman loop integrals.

Acknowledgements

The LSCP chairs appreciate the help of the Workshop Program Committee, all reviewers of the LSCP papers, and the organizers of the ICCS conference. We also acknowledge the support of the National Science Foundation under Award Number 1126438, and of Grant-in-Aid for Scientific Research (24540292 and 25400284) of JSPS, and the Large Scale Simulation Program No. 14/15-06, No. 15/1606, No. 14/15-T01 and No. 15/16-T01 of KEK.

References

[AIKMSST16] Tatsumi Aoyama, Ken-Ichi Ishikawa, Yasuyuki Kimura, Hideo Matsufuru,

Atsushi Sato, Tomohiro Suzuki and Sunao Torii. First application of lattice QCD to Pezy-SC processor. Procedia Computer Science, 2016. Workshop on Large Scale Computational Physics (LSCP), ICCS 2016.

[dDYIKO16] Elise de Doncker, Fukuko Yuasa, Tadashi Ishikawa, John Kapenga and

Fola Olagbemi. Adaptive Integration and Singular Boundary Transformations. Procedia Computer Science, 2016. Workshop on Large Scale Computational Physics (LSCP), ICCS 2016.