Out‐of‐core macromolecular simulations on multithreaded architectures

We address the solution of large‐scale eigenvalue problems that appear in the motion simulation of complex macromolecules on multithreaded platforms, consisting of multicore processors and possibly a graphics processor (graphics processing unit). In particular, we compare specialized implementations of several high‐performance eigensolvers that, by relying on disk storage and out‐of‐core techniques, can in principle tackle the large memory requirements of these biological problems, which in general do not fit into the main memory of current desktop machines. All these out‐of‐core eigensolvers, except for one, are composed of compute‐bound (i.e., arithmetically intensive) operations, which we accelerate by exploiting the performance of current multicore processors and, in some cases, by additionally off‐loading certain parts of the computation to a graphics processing unit accelerator. One of the eigensolvers is a memory‐bound algorithm, which strongly constrains its performance when the data is on disk. However, this method exhibits a much lower arithmetic cost compared with its compute‐bound alternatives for this particular application. Experimental results on a desktop platform, representative of current server technology, illustrate the potential of these methods to address the simulation of biological activity. Copyright © 2014 John Wiley & Sons, Ltd.

[1]  Lars Skjærven,et al.  Normal mode analysis for proteins , 2009 .

[2]  Pablo Chacón,et al.  iMod: multipurpose normal mode analysis in internal coordinates , 2011, Bioinform..

[3]  N. Go,et al.  Dynamics of a small globular protein in terms of low-frequency vibrational modes. , 1983, Proceedings of the National Academy of Sciences of the United States of America.

[4]  I. Bahar,et al.  Normal mode analysis of biomolecular structures: functional mechanisms of membrane proteins. , 2010, Chemical reviews.

[5]  Edoardo Di Napoli,et al.  Solving dense generalized eigenproblems on multi-threaded architectures , 2011, Appl. Math. Comput..

[6]  Robert A. van de Geijn,et al.  Using PLAPACK - parallel linear algebra package , 1997 .

[7]  Robert A. van de Geijn,et al.  Parallel out-of-core cholesky and QR factorizations with POOCLAPACK , 2001, Proceedings 15th International Parallel and Distributed Processing Symposium. IPDPS 2001.

[8]  Tosiyuki Noguti,et al.  Dynamics of Native Globular Proteins in Terms of Dihedral Angles , 1983 .

[9]  Gregory A Voth,et al.  Systematic multiscale simulation of membrane protein systems. , 2009, Current opinion in structural biology.

[10]  Robert H. Halstead,et al.  Matrix Computations , 2011, Encyclopedia of Parallel Computing.

[11]  Robert A. van de Geijn,et al.  A Runtime System for Programming Out-of-Core Matrix Algorithms-by-Tiles on Multithreaded Architectures , 2012, TOMS.

[12]  Jack J. Dongarra,et al.  Leading Edge Hybrid Multi-GPU Algorithms for Generalized Eigenproblems in Electronic Structure Calculations , 2013, ISC.

[13]  Enrique S. Quintana-Ortí,et al.  Applying OOC Techniques in the Reduction to Condensed Form for Very Large Symmetric Eigenproblems on GPUs , 2012, 2012 20th Euromicro International Conference on Parallel, Distributed and Network-based Processing.

[14]  Jack Dongarra,et al.  MPI: The Complete Reference , 1996 .

[15]  Nicholas J. Higham,et al.  Stable and Efficient Spectral Divide and Conquer Algorithms for the Symmetric Eigenvalue Decomposition and the SVD , 2013, SIAM J. Sci. Comput..

[16]  Sivan Toledo,et al.  A survey of out-of-core algorithms in numerical linear algebra , 1999, External Memory Algorithms.

[17]  Robert A. van de Geijn,et al.  A Parallel Eigensolver for Dense Symmetric Matrices Based on Multiple Relatively Robust Representations , 2005, SIAM J. Sci. Comput..

[18]  Enrique S. Quintana-Ortí,et al.  Out-of-Core Solution of Eigenproblems for Macromolecular Simulations , 2013, PPAM.

[19]  M. Levitt,et al.  Protein normal-mode dynamics: trypsin inhibitor, crambin, ribonuclease and lysozyme. , 1985, Journal of molecular biology.

[20]  Enrique S. Quintana-Ortí,et al.  Exploring large macromolecular functional motions on clusters of multicore processors , 2013, J. Comput. Phys..

[21]  Lukas Krämer,et al.  Parallel solution of partial symmetric eigenvalue problems from electronic structure calculations , 2011, Parallel Comput..

[22]  B. Parlett,et al.  Multiple representations to compute orthogonal eigenvectors of symmetric tridiagonal matrices , 2004 .

[23]  Chao Yang,et al.  ARPACK users' guide - solution of large-scale eigenvalue problems with implicitly restarted Arnoldi methods , 1998, Software, environments, tools.