Using analog computers in today's largest computational challenges

Abstract. Analog computers can be revived as a feasible technology platform for low precision, energy efficient and fast computing. We justify this statement by measuring the performance of a modern analog computer and comparing it with that of traditional digital processors. General statements are made about the solution of ordinary and partial differential equations. Computational fluid dynamics are discussed as an example of large scale scientific computing applications. Several models are proposed which demonstrate the benefits of analog and digital-analog hybrid computing.

[1]  ShuChi-Wang.  High order WENO and DG methods for time-dependent convection-dominated PDEs , 2016 .

[2]  Michael Dumbser,et al.  A unified framework for the construction of one-step finite volume and discontinuous Galerkin schemes on unstructured meshes , 2008, J. Comput. Phys..

[3]  David P. Rodgers,et al.  Improvements in multiprocessor system design , 1985, ISCA '85.

[4]  Luis Ceze,et al.  General-purpose code acceleration with limited-precision analog computation , 2014, 2014 ACM/IEEE 41st International Symposium on Computer Architecture (ISCA).

[5]  E. F. Toro,et al.  Primitive, Conservative and Adaptive Schemes for Hyperbolic Conservation Laws , 1998 .

[6]  C. Hirsch,et al.  Numerical Computation of Internal and External Flows. By C. HIRSCH. Wiley. Vol. 1, Fundamentals of Numerical Discretization. 1988. 515 pp. £60. Vol. 2, Computational Methods for Inviscid and Viscous Flows. 1990, 691 pp. £65. , 1991, Journal of Fluid Mechanics.

[7]  W. Munro,et al.  Quantum analogue computing , 2010, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[8]  R. Jeltsch,et al.  Generalized disks of contractivity for explicit and implicit Runge-Kutta methods , 1979 .

[9]  Bruce J. MacLennan,et al.  Analog Computation , 2009, Encyclopedia of Complexity and Systems Science.

[10]  John L. Gustafson,et al.  Reevaluating Amdahl's law , 1988, CACM.

[11]  Gerhard Wellein,et al.  LIKWID: Lightweight Performance Tools , 2011, CHPC.

[12]  V. E. Bukhman,et al.  Analogues for the solution of boundary-value problems , 1967 .

[13]  Wu-chun Feng,et al.  Trends in energy-efficient computing: A perspective from the Green500 , 2013, 2013 International Green Computing Conference Proceedings.

[14]  Barry Koren,et al.  Numerical methods in fluid dynamics, initial and initial boundary-value problems , 1987, Acta Applicandae Mathematicae.

[15]  Chi-Wang Shu,et al.  High order WENO and DG methods for time-dependent convection-dominated PDEs: A brief survey of several recent developments , 2016, J. Comput. Phys..

[16]  Amaury Pouly,et al.  A Survey on Analog Models of Computation , 2018, Theory and Applications of Computability.

[17]  Yiqing Zhou,et al.  What limits the simulation of quantum computers , 2020 .

[18]  Connor Schenck,et al.  SPNets: Differentiable Fluid Dynamics for Deep Neural Networks , 2018, CoRL.

[19]  PROCEEDINGS OF THE WESTERN JOINT COMPUTER CONFERENCE , 2006 .

[20]  Robert Vichnevetsky.  Hybrid methods for partial differential equations , 1971 .

[21]  D. Durran.  Numerical Methods for Fluid Dynamics , 2010 .

[22]  Don W. Green,et al.  Hybrid computer implementation of the alternating direction implicit procedure for the solution of two‐dimensional, parabolic, partial‐differential equations , 1970 .

[23]  Rui Paulo Martins,et al.  A 5.35-mW 10-MHz Single-Opamp Third-Order CT $\Delta\Sigma$ Modulator With CTC Amplifier and Adaptive Latch DAC Driver in 65-nm CMOS , 2018, IEEE Journal of Solid-State Circuits.

[24]  Robert Vichnevetsky,et al.  A new stable computing method for the serial hybrid computer integration of partial differential equations , 1968, AFIPS '68 (Spring).

[25]  Michael Dumbser,et al.  ADER discontinuous Galerkin schemes for general-relativistic ideal magnetohydrodynamics , 2018, 1801.02839.

[26]  Catherine D. Schuman,et al.  A Survey of Neuromorphic Computing and Neural Networks in Hardware , 2017, ArXiv.

[27]  S. Barnett,et al.  Philosophical Transactions of the Royal Society A : Mathematical , 2017 .

[28]  Gerhard Wellein,et al.  LIKWID Monitoring Stack: A Flexible Framework Enabling Job Specific Performance monitoring for the masses , 2017, 2017 IEEE International Conference on Cluster Computing (CLUSTER).

[29]  A. Harten.  High Resolution Schemes for Hyperbolic Conservation Laws , 2017 .

[30]  R. I. Issa,et al.  Numerical computation of internal and external flows, volume 2: Computational methods for inviscid and viscous flows , 1991 .

[31]  Martin Ziegler,et al.  Novel hardware and concepts for unconventional computing , 2020, Scientific Reports.

[32]  Bruce J. MacLennan,et al.  Natural computation and non-Turing models of computation , 2004, Theor. Comput. Sci..

[33]  Eleuterio F. Toro,et al.  ADER schemes for three-dimensional non-linear hyperbolic systems , 2005 .

[34]  F. Browder,et al.  Partial Differential Equations in the 20th Century , 1998 .

[35]  F. Nori,et al.  Quantum Simulation , 2013, Quantum Atom Optics.

[36]  Walter J. Karplus,et al.  Increasing Digital Computer Efficiency with the Aid of Error-Correcting Analog Subroutines , 1971, IEEE Transactions on Computers.

[37]  G.E.R. Cowan,et al.  A VLSI analog computer/math co-processor for a digital computer , 2005, ISSCC. 2005 IEEE International Digest of Technical Papers. Solid-State Circuits Conference, 2005..

[38]  Todd A. Oliver,et al.  Solving differential equations using deep neural networks , 2020, Neurocomputing.

[39]  Simha Sethumadhavan,et al.  Hybrid Analog-Digital Solution of Nonlinear Partial Differential Equations , 2017, 2017 50th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO).

[40]  Stéphane Clain,et al.  The Multidimensional Optimal Order Detection method in the three‐dimensional case: very high‐order finite volume method for hyperbolic systems , 2013 .

[41]  Chi-Wang Shu,et al.  Runge–Kutta Discontinuous Galerkin Methods for Convection-Dominated Problems , 2001, J. Sci. Comput..

[42]  Yi Wang,et al.  Modern numerical methods and their applications in mechanical engineering , 2019 .

[43]  Eleuterio F. Toro,et al.  ADER: Arbitrary High Order Godunov Approach , 2002, J. Sci. Comput..

[44]  Stéphane Clain,et al.  The MOOD method in the three-dimensional case: Very-High-Order Finite Volume Method for Hyperbolic Systems. , 2012 .

[45]  Bernd Ulmann,et al.  Analog and Hybrid Computer Programming , 2020 .

[46]  Sven Köppel.  Towards an exascale code for GRMHD on dynamical spacetimes , 2018 .

[47]  H T Siegelmann,et al.  Dating and Context of Three Middle Stone Age Sites with Bone Points in the Upper Semliki Valley, Zaire , 2007 .