ARUZ - Large-scale, massively parallel FPGA-based analyzer of real complex systems

被引：14

作者：

Kielbik, Rafal ^{[1
]}

Halagan, Krzysztof ^{[2
]}

Zatorski, Witold ^{[3
]}

Jung, Jaroslaw ^{[2
]}

Ulanski, Jacek ^{[2
]}

Napieralski, Andrzej ^{[1
]}

Rudnicki, Kamil ^{[1
]}

Amrozik, Piotr ^{[1
]}

Jablonski, Grzegorz ^{[1
]}

Stozek, Dominik ^{[4
]}

Polanowski, Piotr ^{[2
]}

Mudza, Zbigniew ^{[1
]}

Kupis, Joanna ^{[1
]}

Panek, Przemyslaw ^{[5
]}

机构：

[1] Lodz Univ Technol, Dept Microelect & Comp Sci, Ul Wolczanska 221-223, PL-90924 Lodz, Poland

[2] Lodz Univ Technol, Dept Mol Phys, Ul Zeromskiego 116, PL-90924 Lodz, Poland

[3] Forel Witold Zatorski, Ul Ejsmonda 3 M 44, PL-93249 Lodz, Poland

[4] Blue Brick, Ul POW 25, PL-90248 Lodz, Poland

[5] Bionanopark Sp Zoo, Ul Dubois 114-116, PL-93465 Lodz, Poland

来源：

COMPUTER PHYSICS COMMUNICATIONS | 2018年 / 232卷

关键词：

Parallel processing; Reconfigurable systems; Molecular simulations; MOLECULAR-DYNAMICS SIMULATIONS; LIVING COPOLYMERIZATION; GELATION; MONOMER; DLL; INTERDIFFUSION; DIFFUSION;

D O I：

10.1016/j.cpc.2018.06.010

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

This paper presents general information about ARUZ, a scalable, fully parallel data processing system equipped with low-latency communication channels, designed for simulations of interactions among huge number of relatively simple elements. ARUZ consists of approximately 26 000 FPGAs and it can represent a system composed of several million elements consuming barely tens of kilowatts of power. It can be seen as a powerful machine for a wide range of applications. Currently, it implements the Dynamic Lattice Liquid algorithm, which enables studies of dynamic processes and phenomena in dense macromolecular systems. A performance estimation for liquid water shows that in one day ARUZ can model the diffusion of 1.5 million water molecules ongoing in reality for approximately 0.7 ms. (C) 2018 Elsevier B.V. All rights reserved.

引用

页码：22 / 34

页数：13

共 55 条

[21] Jung J., 2017, Patent RP PAT, Patent No. 223795
[22] Jung J., 2017, Patent RP PAT, Patent No. 227249
[23] Jung J., 2016, EP Patent App., Patent No. [EP20,150,163,078, 20150163078]
[24] Parallel Processor Design and Implementation for Molecular Dynamics Simulations on a FPGA-Based Supercomputer
Kasap, Server
Benkrid, Khaled
[J]. JOURNAL OF COMPUTERS, 2012, 7 (06) : 1312 - 1328
[25] Diffusive properties of solvent molecules in the neighborhood of a polymer chain as seen by Monte-Carlo simulations
Kozanecki, M.
Halagan, K.
Saramak, J.
Matyjaszewski, K.
[J]. SOFT MATTER, 2016, 12 (25) : 5519 - 5528
[26] CUBE: A 512-FPGA CLUSTER
Mencer, Oskar
Tsoi, Kuen Hung
Craimer, Stephen
Todman, Timothy
Luk, Wayne
Wong, Ming Yee
Leong, Philip Heng Wai
[J]. 2009 5TH SOUTHERN CONFERENCE ON PROGRAMMABLE LOGIC, PROCEEDINGS, 2009, : 51 - +
[27] Bluehive - A Field-Programable Custom Computing Machine for Extreme-Scale Real-Time Neural Network Simulation
Moore, Simon W.
Fox, Paul J.
Marsh, Steven J. T.
Markettos, A. Theodore
Mujumdar, Alan
[J]. 2012 IEEE 20TH ANNUAL INTERNATIONAL SYMPOSIUM ON FIELD-PROGRAMMABLE CUSTOM COMPUTING MACHINES (FCCM), 2012, : 133 - 140
[28] MDGRAPE-4: a special-purpose computer system formolecular dynamics simulations
Ohmura, Itta
Morimoto, Gentaro
Ohno, Yousuke
Hasegawa, Aki
Taiji, Makoto
[J]. PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES, 2014, 372 (2021):
[29] Collective dynamics in simple supercooled and polymer liquids
Pakula, T
[J]. JOURNAL OF MOLECULAR LIQUIDS, 2000, 86 (1-3) : 109 - 121
[30] PAKULA T, 2004, SIMULATION METHODS P, P147, DOI DOI 10.1201/9780203021255.CH5

← 1 2 3 4 5 6 →