From the Dynamic Lattice Liquid Algorithm to the Dedicated Parallel Computer – mDLL Machine
Jung Jarosław 1, Kiełbik Rafał 2, Rudnicki Kamil 2, Hałagan Krzysztof 1, Polanowski Piotr 1, Sikorski Andrzej 3*
1 Department of Molecular Physics, Technical University of Łódź
90-924 Łódź, Poland2 Department of Electronics, Technical University of Łódź
90-924 Łódź, Poland3 Department of Chemistry, University of Warsaw Pasteura 1
02-093 Warsaw, Poland*E-mail: sikorski@chem.uw.edu.pl
Received:
Received: 13 November 2018; revised: 03 December 2018; accepted: 05 December 2018; published online: 24 December 2018
DOI: 10.12921/cmst.2018.0000054
Abstract:
The designing, production and testing of the mDLL machine led to the development of such a structure in which operational cells (e.g. KDLL) were located in the nodes of a three-dimensional torus network and the device was scalable. Thus, the future expansion of this device with additional Printed Circuit Boards (PCB) will not result in lengthened wire connections between Field-Programmable Gate Arrays (FPGA) or slow down the operation of the machine. The conducted tests confirmed the correctness of the adopted design assumptions and showed that by using mDLL one can effectively perform molecular simulations. Despite some structural shortcomings, the mDLL machine was a prototype that has already been sufficiently tested to allow the technology used in it to be used to build a device with a number of 1 million to 5 million KDLL cells. Such a device would already be suitable for simulating multi-particle systems with unprecedented speed.
Key words:
Field Programmable Gate Array, molecular simulations, parallel data processing, topology of the network connections
References:
[1] B.G.Fitch,A.Rayshubsky,M.Elftheriou,T.J.C.Ward,M.E. Giampapa, M.C. Pitman, J.W. Pitera, W.C. Swope, R.. Ger- main, Blue Matter: Scalling of N-body simulations to one atom per node, IBM J. Res & Dev, 52 145 (2008).
[2] X. Hu, L. Hong, M.D. Smith, T. Neusius, X. Cheng, J.C. Smith J., The Dynamics of Single Protein Molecules Is Non- Equilibrium and Self-Similar over Thirteen Decades in Time, Nature Physics 12, 171–174 (2016).
[3] W. Chen, E. De Schutter, Parallel STEPS: Large Scale Stochastic Spatial Reaction-Diffusion Simulation with High Performance Computers, Frontiers in Neuroinformatics,11:13, doi: 10.3389/fninf.2017.00013 (2017)
[4] P. Polanowski, Implementacja sieciowych modeli cieczy i polimerów w symulacjach opartych na obliczeniach równoległych, Rozprawa doktorska, Politechnika Łódzka, (2002).
[5] R.D. Jackson, A.J. Hoane Jr., Modular Infinitely Ex- tendable Three Dimensional Torus Packing Scheme for Parallel Processing, US Patent no. US005715391A, http://www.google.ch/patents/US5715391 (1998).
[6] T. Pakula, Collective dynamics in simple supercooled and polymer liquids, J. Mol. Liq. 86, 109-121 (2000).
[7] P. Polanowski, J.K. Jeszka, K. Krysiak, K. Matyjaszewski, Influence of intramolecular crosslinking on gelation in liv- ing copolymerization of monomer and divinyl cross-linker. Monte Carlo simulation studies, Polymer, 79, 171-178 (2015).
[8] P. Polanowski, J. Jung, R. Kiełbik, A. Napieralski, K. Lichy, Od algorytmu dynamicznej cieczy sieciowej do dedykowanego komputera równoległego, Przegla ̨d Elek- trotechniczny, 84, 69-73 (2008).
[9] J. Jung, Od wybranych zagadnien ́ elektroniki organicznej do uniwersalnej maszyny przeznaczonej do analizy zjawisk zachodza ̨cych w ge ̨stych układach wieloskładnikowych, Rozprawa habilitacyjna, Politechnika Łódzka (2016).
[10] J. Jung, P. Polanowski, R. Kiełbik, Special state machine based on Dynamic Lattice Liquid model, International Jour- nal of Engineering Science and Innovative Technology (IJE- SIT), 3, 360-367 (2014).
[11] J.Jung,P.Polanowski,R.Kiełbik,K.Hałagan,W.Zatorski, J. Ulan ́ski, A. Napieralski, T. Pakuła, A parallel machine with reduced number of connections between logical cir- cuits, (2016), EP Patent Application no. EP3079073A1,https://www.google.com/patents/EP3079073A1?cl=un (2016).
[12] G.G. Pachanek, N.P. Pitsianis, E.F. Barry, T.L. Draben- stott, Method and Apparatus for Manifold Array Processing, US Patent no. US6167502A, https://www.google.tl/patents/ US6167502 (2000).
[13] H.W. Daniel, Parallel Processor, EP Patent no. EP0501524A2.
[14] www.google.com.na/patents/EP0501524A2?cl=un (1992).
[15] R.S. Passint, G. Thorson, M.B. Galles, Hybrid Hyper- cube/Torus Architecture, US Patent no. US6230252B1, http:// www.google.ch/patents/US6230252 (2001).
[16] J. Jung, P. Polanowski, R. Kiełbik, K. Hałagan, W. Zatorski, J. Ulan ́ski, A. Napieralski, T. Pakuła, Panel z układami elektronicznymi i zestaw paneli, RP Patent no. P.405479, http://regserv.uprp.pl/register/application?number=P.405479 (2016).
[17] J. Jung, P. Polanowski, R. Kiełbik, K. Hałagan, W. Za- torski, J. Ulan ́ski, A. Napieralski, T. Pakuła, A panel with electronic circuits and a set of panels, EP Patent Application no. EP3079071A1, https://google.com/patents/ EP3079071A1?cl=en (2016).
[18] J. Jung, P. Polanowski, R. Kiełbik, K. Hałagan, W. Za- torski, J. Ulan ́ski, A. Napieralski, T. Pakuła, A parallel machine having operational cells located at nodes of a face centered lattice, EP Patent Application no. EP3079072A1, https://www.google.com.na/patents/EP3079072A1?cl=en (2016).
The designing, production and testing of the mDLL machine led to the development of such a structure in which operational cells (e.g. KDLL) were located in the nodes of a three-dimensional torus network and the device was scalable. Thus, the future expansion of this device with additional Printed Circuit Boards (PCB) will not result in lengthened wire connections between Field-Programmable Gate Arrays (FPGA) or slow down the operation of the machine. The conducted tests confirmed the correctness of the adopted design assumptions and showed that by using mDLL one can effectively perform molecular simulations. Despite some structural shortcomings, the mDLL machine was a prototype that has already been sufficiently tested to allow the technology used in it to be used to build a device with a number of 1 million to 5 million KDLL cells. Such a device would already be suitable for simulating multi-particle systems with unprecedented speed.
Key words:
Field Programmable Gate Array, molecular simulations, parallel data processing, topology of the network connections
References:
[1] B.G.Fitch,A.Rayshubsky,M.Elftheriou,T.J.C.Ward,M.E. Giampapa, M.C. Pitman, J.W. Pitera, W.C. Swope, R.. Ger- main, Blue Matter: Scalling of N-body simulations to one atom per node, IBM J. Res & Dev, 52 145 (2008).
[2] X. Hu, L. Hong, M.D. Smith, T. Neusius, X. Cheng, J.C. Smith J., The Dynamics of Single Protein Molecules Is Non- Equilibrium and Self-Similar over Thirteen Decades in Time, Nature Physics 12, 171–174 (2016).
[3] W. Chen, E. De Schutter, Parallel STEPS: Large Scale Stochastic Spatial Reaction-Diffusion Simulation with High Performance Computers, Frontiers in Neuroinformatics,11:13, doi: 10.3389/fninf.2017.00013 (2017)
[4] P. Polanowski, Implementacja sieciowych modeli cieczy i polimerów w symulacjach opartych na obliczeniach równoległych, Rozprawa doktorska, Politechnika Łódzka, (2002).
[5] R.D. Jackson, A.J. Hoane Jr., Modular Infinitely Ex- tendable Three Dimensional Torus Packing Scheme for Parallel Processing, US Patent no. US005715391A, http://www.google.ch/patents/US5715391 (1998).
[6] T. Pakula, Collective dynamics in simple supercooled and polymer liquids, J. Mol. Liq. 86, 109-121 (2000).
[7] P. Polanowski, J.K. Jeszka, K. Krysiak, K. Matyjaszewski, Influence of intramolecular crosslinking on gelation in liv- ing copolymerization of monomer and divinyl cross-linker. Monte Carlo simulation studies, Polymer, 79, 171-178 (2015).
[8] P. Polanowski, J. Jung, R. Kiełbik, A. Napieralski, K. Lichy, Od algorytmu dynamicznej cieczy sieciowej do dedykowanego komputera równoległego, Przegla ̨d Elek- trotechniczny, 84, 69-73 (2008).
[9] J. Jung, Od wybranych zagadnien ́ elektroniki organicznej do uniwersalnej maszyny przeznaczonej do analizy zjawisk zachodza ̨cych w ge ̨stych układach wieloskładnikowych, Rozprawa habilitacyjna, Politechnika Łódzka (2016).
[10] J. Jung, P. Polanowski, R. Kiełbik, Special state machine based on Dynamic Lattice Liquid model, International Jour- nal of Engineering Science and Innovative Technology (IJE- SIT), 3, 360-367 (2014).
[11] J.Jung,P.Polanowski,R.Kiełbik,K.Hałagan,W.Zatorski, J. Ulan ́ski, A. Napieralski, T. Pakuła, A parallel machine with reduced number of connections between logical cir- cuits, (2016), EP Patent Application no. EP3079073A1,https://www.google.com/patents/EP3079073A1?cl=un (2016).
[12] G.G. Pachanek, N.P. Pitsianis, E.F. Barry, T.L. Draben- stott, Method and Apparatus for Manifold Array Processing, US Patent no. US6167502A, https://www.google.tl/patents/ US6167502 (2000).
[13] H.W. Daniel, Parallel Processor, EP Patent no. EP0501524A2.
[14] www.google.com.na/patents/EP0501524A2?cl=un (1992).
[15] R.S. Passint, G. Thorson, M.B. Galles, Hybrid Hyper- cube/Torus Architecture, US Patent no. US6230252B1, http:// www.google.ch/patents/US6230252 (2001).
[16] J. Jung, P. Polanowski, R. Kiełbik, K. Hałagan, W. Zatorski, J. Ulan ́ski, A. Napieralski, T. Pakuła, Panel z układami elektronicznymi i zestaw paneli, RP Patent no. P.405479, http://regserv.uprp.pl/register/application?number=P.405479 (2016).
[17] J. Jung, P. Polanowski, R. Kiełbik, K. Hałagan, W. Za- torski, J. Ulan ́ski, A. Napieralski, T. Pakuła, A panel with electronic circuits and a set of panels, EP Patent Application no. EP3079071A1, https://google.com/patents/ EP3079071A1?cl=en (2016).
[18] J. Jung, P. Polanowski, R. Kiełbik, K. Hałagan, W. Za- torski, J. Ulan ́ski, A. Napieralski, T. Pakuła, A parallel machine having operational cells located at nodes of a face centered lattice, EP Patent Application no. EP3079072A1, https://www.google.com.na/patents/EP3079072A1?cl=en (2016).
