Acceleration Of Molecular Dynamics Simulations Research Articles

Heterogeneous parallelization and acceleration of molecular dynamics simulations in GROMACS.

The introduction of accelerator devices such as graphics processing units (GPUs) has had profound impact on molecular dynamics simulations and has enabled order-of-magnitude performance advances using commodity hardware. To fully reap these benefits, it has been necessary to reformulate some of the most fundamental algorithms, including the Verlet list, pair searching, and cutoffs. Here, we present the heterogeneous parallelization and acceleration design of molecular dynamics implemented in the GROMACS codebase over the last decade. The setup involves a general cluster-based approach to pair lists and non-bonded pair interactions that utilizes both GPU and central processing unit (CPU) single instruction, multiple data acceleration efficiently, including the ability to load-balance tasks between CPUs and GPUs. The algorithm work efficiency is tuned for each type of hardware, and to use accelerators more efficiently, we introduce dual pair lists with rolling pruning updates. Combined with new direct GPU-GPU communication and GPU integration, this enables excellent performance from single GPU simulations through strong scaling across multiple GPUs and efficient multi-node parallelization.

A combined BCA-MD method with adaptive volume to simulate high-energy atomic-collision cascades in solids under irradiation

We present a method combining the Binary Collision Approximation (BCA) and Molecular Dynamics (MD) with adaptive volume to simulate high-energy collision cascades in solids under irradiation. The results obtained with the BCA-MD method with adaptive volume are in very good agreement with those obtained with full MD calculations. The BCA-MD predicts very well in a broad range of Primary Knock-on Atom (PKA) energies the different phases of evolution of the cascade, the number of Frenkel pairs, the fraction of point defects in clusters and their size distribution. The BCA-MD method proposed here achieves a considerable acceleration of MD simulations with a speedup factor that increases with the PKA energy. For a PKA energy of 80 keV in Fe, the speedup measured is higher than 30. For a PKA energy of 0.5 MeV in Fe, by comparison with MD simulations performed by other authors, we estimate that the BCA-MD accelerates MD simulations by a factor 312.

Acceleration of molecular dynamics simulation of multiphase systems on GPU

The paper presents results on acceleration of molecular dynamics simulations with the usage of GPUs. A system of water molecules is considered as an example of polar liquid. The intermolecular interaction is modeled with the usage of Coulomb and truncated Lennard-Jones potentials. Results of computational experiments on acceleration and performance of the developed code are presented.

Accelerating Molecular Dynamics Simulations with Reconfigurable Computers

With advances in reconfigurable hardware, especially field-programmable gate arrays (FPGAs), it has become possible to use reconfigurable hardware to accelerate complex applications such as those in scientific computing. There has been a resulting development of reconfigurable computers, that is, computers that have both general-purpose processors and reconfigurable hardware, as well as memory and high-performance interconnection networks. In this paper, we describe the acceleration of molecular dynamics simulations with reconfigurable computers. We evaluate several design alternatives for the implementation of the application on a reconfigurable computer. We show that a single node accelerated with reconfigurable hardware, utilizing fine-grained parallelism in the reconfigurable hardware design, is able to achieve a speedup of about two times over the corresponding software-only simulation. We then parallelize the application and study the effect of acceleration on performance and scalability. Specifically, we study strong scaling, in which the problem size is fixed. We find that the unaccelerated version actually scales better, because it spends more time in computation than the accelerated version does. However, we also find that a cluster of P accelerated nodes gives better performance than a cluster of 2P unaccelerated nodes.

Explicit design of FPGA-based coprocessors for short-range force computations in molecular dynamics simulations

FPGA-based acceleration of molecular dynamics simulations (MD) has been the subject of several recent studies. The short-range force computation, which dominates the execution time, is the primary focus. Here we combine: a high level of FPGA-specific design including cell-lists, systematically determined interpolation and precision, handling of exclusion, and support for MD simulations of up to 256 K particles. The target system consists of a standard PC with a 2004-era COTS FPGA board. There are several innovations: new microarchitectures for several major components, including the cell-list processor and the off-chip memory controller; and a novel arithmetic mode. Extensive experimentation was required to optimize precision, interpolation order, interpolation mode, table sizes, and simulation quality. We obtain a substantial speed-up over a highly tuned production MD code.

Acceleration of Molecular Dynamics Simulation for Proteins on the Earth Simulator

Acceleration of Molecular Dynamics Simulation for Proteins on the Earth Simulator

Acceleration of molecular dynamics simulation of order N with neighbour list

A method for removing data dependency in an indirectly indexed DO loop is presented. Vectorization of such DO loops may, in some applications and on those computers which cannot do it themselves, result in a considerable speed-up of the calculations. Timings for scalar/vector calculations have been performed on an ETP 10P supercomputer and the application of the algorithm for a speed-up of molecular dynamics (MD) simulations of order N, handling short-range interactions, is discussed. The algorithm presented does not use any special calls and, therefore, it can be applied on most vector computers. The method makes it possible to execute an MD program of order N with practically the same efficiency on any supercomputer no matter if such a loop can be automatically vectorized or not.