Parallel implementation of 3D FFT with volumetric decomposition schemes for efficient molecular dynamics simulations

Jung, Jaewoon; Kobayashi, Chigusa; Imamura, Toshiyuki; Sugita, Yuji

doi:10.1016/j.cpc.2015.10.024

Cited by 27 publications

(23 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This creates additional computational costs compared to explicit solvent simulations where 10–12 Å are the typical cut-off distance for van der Waals interactions and the real space for the particle mesh Ewald (PME) method [143] for electrostatic interactions. Furthermore, the PME method can be efficiently parallelized via domain decomposition schemes for accurate and fast electrostatic calculations [144]. As a result, the calculation of the GB energy and forces can be more expensive than those in the explicit solvent model for large systems like the ribosome.…”

Section: Molecular Models For Membranes and Membrane Proteinsmentioning

confidence: 99%

Molecular dynamics simulations of biological membranes and membrane proteins using enhanced conformational sampling algorithms

Mori

Miyashita²,

et al. 2016

Biochimica et Biophysica Acta (BBA) - Biomembranes

Self Cite

123

108

View full text Add to dashboard Cite

This paper reviews various enhanced conformational sampling methods and explicit/implicit solvent/membrane models, as well as their recent applications to the exploration of the structure and dynamics of membranes and membrane proteins. Molecular dynamics simulations have become an essential tool to investigate biological problems, and their success relies on proper molecular models together with efficient conformational sampling methods. The implicit representation of solvent/membrane environments is reasonable approximation to the explicit all-atom models, considering the balance between computational cost and simulation accuracy. Implicit models can be easily combined with replica-exchange molecular dynamics methods to explore a wider conformational space of a protein. Other molecular models and enhanced conformational sampling methods are also briefly discussed. As application examples, we introduce recent simulation studies of glycophorin A, phospholamban, amyloid precursor protein, and mixed lipid bilayers and discuss the accuracy and efficiency of each simulation model and method. This article is part of a Special Issue entitled: Membrane Proteins. Guest Editors: J.C. Gumbart and Sergei Noskov.

show abstract

Section: Molecular Models For Membranes and Membrane Proteinsmentioning

confidence: 99%

Molecular dynamics simulations of biological membranes and membrane proteins using enhanced conformational sampling algorithms

Mori

Miyashita²,

et al. 2016

Biochimica et Biophysica Acta (BBA) - Biomembranes

Self Cite

123

108

View full text Add to dashboard Cite

show abstract

“…MPI_alltoall communications among four subdomains are done to obtain the global data in the FFT direction. For the reciprocal‐space interaction, we developed two parallelization schemes of FFT; 1d_alltoall and 2d_alltoall 20 . In the 1d_alltoall scheme, five one‐dimensional (1D) MPI_alltoall are applied in forward and backward FFTs.…”

Section: Methodsmentioning

confidence: 99%

New parallel computing algorithm of molecular dynamics for extremely huge scale biological systems

et al. 2020

Self Cite

View full text Add to dashboard Cite

In this paper, we address high performance extreme-scale molecular dynamics (MD) algorithm in the GENESIS software to perform cellular-scale molecular dynamics (MD) simulations with more than 100,000 CPU cores. It includes (1) the new algorithm of real-space nonbonded interactions maximizing the performance on ARM CPU architecture, (2) reciprocal-space nonbonded interactions minimizing communicational cost, (3) accurate temperature/pressure evaluations that allows a large time step, and (4) effective parallel file inputs/outputs (I/O) for MD simulations of extremely huge systems. The largest system that contains 1.6 billion atoms was simulated using MD with a performance of 8.30 ns/day on Fugaku supercomputer. It extends the available size and time of MD simulations to answer unresolved questions of biomacromolecules in a living cell.

show abstract

“…The CPU data point N = 512 is from P3DFFT on 262144 cores of the BlueGene/Q at the Julich Research Center (Pippig, 2013). The CPU data point N = 1024 is from 262152 cores on the K computer (Jung et al, 2016).…”

Section: D Fft Models For Catapult Ii and Novo-g#mentioning

confidence: 99%

High Performance Communication on Reconfigurable Clusters

Sheng

Yang

Herbordt

2018

2018 28th International Conference on Field Programmable Logic and Applications (FPL)

View full text Add to dashboard Cite

High Performance Computing (HPC) has matured to where it is an essential third pillar, along with theory and experiment, in most domains of science and engineering. Communication latency is a key factor that is limiting the performance of HPC, but can be addressed by integrating communication into accelerators. This integration allows accelerators to communicate with each other without CPU interactions, and even bypassing the network stack. Field Programmable Gate Arrays (FPGAs) are the accelerators that currently best integrate communication with computation. The large number of Multi-gigabit Transceivers (MGTs) on most high-end FPGAs can provide high-bandwidth and low-latency inter-FPGA connections. Additionally, the reconfigurable FPGA fabric enables tight coupling between computation kernel and network interface. Our thesis is that an application-aware communication infrastructure for a multi-FPGA system makes substantial progress in solving the HPC communication bottleneck. This dissertation aims to provide an application-aware solution for communication infrastructure for FPGA-centric clusters. Specifically, our solution demonstrates application-awareness across multiple levels in the network stack, including low-level vii link protocols, router microarchitectures, routing algorithms, and applications. We start by investigating the low-level link protocol and the impact of its latency variance on performance. Our results demonstrate that, although some link jitter is always present, we can still assume near-synchronous communication on an FPGAcluster. This provides the necessary condition for statically-scheduled routing. We then propose two novel router microarchitectures for two different kinds of workloads: a wormhole Virtual Channel (VC)-based router for workloads with dynamic communication, and a statically-scheduled Virtual Output Queueing (VOQ)-based router for workloads with static communication. For the first (VC-based) router, we propose a framework that generates application-aware router configurations. Our results show that, by adding application-awareness into router configuration, the network performance of FPGA clusters can be substantially improved. For the second (VOQbased) router, we propose a novel offline collective routing algorithm. This shows a significant advantage over a state-of-the-art collective routing algorithm. We apply our communication infrastructure to a critical strong-scaling HPC kernel, the 3D FFT. The experimental results demonstrate that the performance of our design is faster than that on CPUs and GPUs by at least one order of magnitude (achieving strong scaling for the target applications). Surprisingly, the FPGA cluster performance is similar to that of an ASIC-cluster. We also implement the 3D FFT on another multi-FPGA platform: the Microsoft Catapult II cloud. Its performance is also comparable or superior to CPU and GPU HPC clusters. The second application we investigate is Molecular Dynamics Simulation (MD). We model MD on both FPGA clouds and clusters. We find ...

show abstract

Parallel implementation of 3D FFT with volumetric decomposition schemes for efficient molecular dynamics simulations

Cited by 27 publications

References 23 publications

Molecular dynamics simulations of biological membranes and membrane proteins using enhanced conformational sampling algorithms

Molecular dynamics simulations of biological membranes and membrane proteins using enhanced conformational sampling algorithms

New parallel computing algorithm of molecular dynamics for extremely huge scale biological systems

High Performance Communication on Reconfigurable Clusters

Contact Info

Product

Resources

About