arXiv subjects

JCS Kadupitiya

Publications and source records attributed to JCS Kadupitiya.

6 recordsLinked to original sources

arXiv2021

Solving Newton's Equations of Motion with Large Timesteps using Recurrent Neural Networks based Operators

Classical molecular dynamics simulations are based on solving Newton's equations of motion. Using a small timestep, numerical integrators such as Verlet generate trajectories of particles as solutions to Newton's equations. We introduce operators derived using recurrent neural networks that accurately solve Newton's equations utilizing sequences of past trajectory data, and produce energy-conserving dynamics of particles using timesteps up to 4000 times larger compared to the Verlet timestep. We demonstrate significant speedup in many example problems including 3D systems of up to 16 particles.

physics.comp-ph↗

arXiv2020

Integrating Machine Learning with HPC-driven Simulations for Enhanced Student Learning

We explore the idea of integrating machine learning (ML) with high performance computing (HPC)-driven simulations to address challenges in using simulations to teach computational science and engineering courses. We demonstrate that a ML surrogate, designed using artificial neural networks, yields predictions in excellent agreement with explicit simulation, but at far less time and computing costs. We develop a web application on nanoHUB that supports both HPC-driven simulation and the ML surrogate methods to produce simulation outputs. This tool is used for both in-classroom instruction and for solving homework problems associated with two courses covering topics in the broad areas of computational materials science, modeling and simulation, and engineering applications of HPC-enabled simulations. The evaluation of the tool via in-classroom student feedback and surveys shows that the ML-enhanced tool provides a dynamic and responsive simulation environment that enhances student learning. The improvement in the interactivity with the simulation framework in terms of real-time engagement and anytime access enables students to develop intuition for the physical system behavior through rapid visualization of variations in output quantities with changes in inputs.

physics.ed-ph↗

arXiv2020

Designing Surface Charge Patterns for Shape Control of Deformable Nanoparticles

Designing reconfigurable materials based on deformable nanoparticles (NPs) hinges on an understanding of the energetically-favored shapes these NPs can adopt. Using simulations, we show that hollow, deformable patchy NPs tailored with surface charge patterns such as Janus patches, stripes, and polyhedrally-distributed patches differently adapt their shape in response to changes in patterns and ionic strength, transforming into capsules, hemispheres, variably-dimpled bowls, and polyhedra. The links between anisotropy in NP surface charge, shape, and the elastic energy density are discussed.

cond-mat.soft↗

arXiv2020

Modeling The Temporally Constrained Preemptions of Transient Cloud VMs

Transient cloud servers such as Amazon Spot instances, Google Preemptible VMs, and Azure Low-priority batch VMs, can reduce cloud computing costs by as much as $10\times$, but can be unilaterally preempted by the cloud provider. Understanding preemption characteristics (such as frequency) is a key first step in minimizing the effect of preemptions on application performance, availability, and cost. However, little is understood about temporally constrained preemptions---wherein preemptions must occur in a given time window. We study temporally constrained preemptions by conducting a large scale empirical study of Google's Preemptible VMs (that have a maximum lifetime of 24 hours), develop a new preemption probability model, new model-driven resource management policies, and implement them in a batch computing service for scientific computing workloads. Our statistical and experimental analysis indicates that temporally constrained preemptions are not uniformly distributed, but are time-dependent and have a bathtub shape. We find that existing memoryless models and policies are not suitable for temporally constrained preemptions. We develop a new probability model for bathtub preemptions, and analyze it through the lens of reliability theory. To highlight the effectiveness of our model, we develop optimized policies for job scheduling and checkpointing. Compared to existing techniques, our model-based policies can reduce the probability of job failure by more than $2\times$. We also implement our policies as part of a batch computing service for scientific computing applications, which reduces cost by $5\times$ compared to conventional cloud deployments and keeps performance overheads under $3\%$.

cs.DC↗

arXiv2019

Machine Learning for Parameter Auto-tuning in Molecular Dynamics Simulations: Efficient Dynamics of Ions near Polarizable Nanoparticles

Simulating the dynamics of ions near polarizable nanoparticles (NPs) using coarse-grained models is extremely challenging due to the need to solve the Poisson equation at every simulation timestep. Recently, a molecular dynamics (MD) method based on a dynamical optimization framework bypassed this obstacle by representing the polarization charge density as virtual dynamic variables, and evolving them in parallel with the physical dynamics of ions. We highlight the computational gains accessible with the integration of machine learning (ML) methods for parameter prediction in MD simulations by demonstrating how they were realized in MD simulations of ions near polarizable NPs. An artificial neural network based regression model was integrated with MD simulation and predicted the optimal simulation timestep and optimization parameters characterizing the virtual system with $94.3\%$ success. The ML-enabled auto-tuning of parameters generated accurate dynamics of ions for $\approx 10$ million steps while improving the stability of the simulation by over an order of magnitude. The integration of ML-enhanced framework with hybrid OpenMP/MPI parallelization techniques reduced the computational time of simulating systems with thousands of ions and induced charges from thousands of hours to tens of hours, yielding a maximum speedup of $\approx 3$ from ML-only acceleration and a maximum speedup of $\approx 600$ from the combination of ML and parallel computing methods. Extraction of ionic structure in concentrated electrolytes near oil-water emulsions demonstrates the success of the method. The approach can be generalized to select optimal parameters in other MD applications and energy minimization problems.

physics.comp-ph↗

arXiv2019

Learning Everywhere: Pervasive Machine Learning for Effective High-Performance Computation

The convergence of HPC and data-intensive methodologies provide a promising approach to major performance improvements. This paper provides a general description of the interaction between traditional HPC and ML approaches and motivates the Learning Everywhere paradigm for HPC. We introduce the concept of effective performance that one can achieve by combining learning methodologies with simulation-based approaches, and distinguish between traditional performance as measured by benchmark scores. To support the promise of integrating HPC and learning methods, this paper examines specific examples and opportunities across a series of domains. It concludes with a series of open computer science and cyberinfrastructure questions and challenges that the Learning Everywhere paradigm presents.

cs.DC↗