A GPU solvent–solvent interaction calculation accelerator for biomolecular simulations using the GROMOS software

During the past few years, graphics processing units (GPUs) have become extremely popular in the high performance computing community. In this study, we present an implementation of an acceleration engine for the solvent–solvent interaction evaluation of molecular dynamics simulations. By careful optimization of the algorithm speed‐ups up to a factor of 54 (single‐precision GPU vs. double‐precision CPU) could be achieved. The accuracy of the single‐precision GPU implementation is carefully investigated and does not influence structural, thermodynamic, and dynamic quantities. Therefore, the implementation enables users of the GROMOS software for biomolecular simulation to run the solvent–solvent interaction evaluation on a GPU, and thus, to speed‐up their simulations by a factor 6–9. © 2010 Wiley Periodicals, Inc. J Comput Chem, 2010     

A real-time infrared imaging simulation method with physical effects modeling of infrared sensors

Infrared imaging simulation technology can provide infrared data sources for the development, improvement and evaluation of infrared imaging systems under different environment, status and weather conditions, which is reusable and more economic than physical experiments. A real-time infrared imaging simulation process is established to reproduce a complete physical imaging process. Our emphasis is put on the modeling of infrared sensors, involving physical effects of both spatial domain and frequency domain. An improved image convolution method is proposed based on GPU parallel processing to enhance the real-time simulation ability with ensuring its simulation accuracy at the same time. Finally the effectiveness of the above methods is validated by simulation analysis and result comparison.     

Benchmarking JPEG 2000 implementations on modern CPU and GPU architectures

The use of graphics hardware for non-graphics applications has become popular among many scientific programmers and researchers as we have observed a higher rate of theoretical performance increase than the CPUs in recent years. However, performance gains may be easily lost in the context of a specific parallel application due to various both hardware and software factors. JPEG 2000 is a complex standard for data compression and coding, that provides many advanced capabilities demanded by more specialized applications. There are several JPEG 2000 implementations that utilize emerging parallel architectures with the built-in support for parallelism at different levels. Unfortunately, many available implementations are only optimized for a certain parallel architecture or they do not take advantage of recent capabilities provided by modern hardware and low level APIs. Thus, the main aim of this paper is to present a comprehensive real performance analysis of JPEG 2000. It consists of a chain of data and compute intensive tasks that can be treated as good examples of software benchmarks for modern parallel hardware architectures. In this paper we compare achieved performance results of various JPEG 2000 implementations executed on selected architectures for different data sets to identify possible bottlenecks. We discuss also best practices and advices for parallel software development to help users to evaluate in advance and then select appropriate solutions to accelerate the execution of their applications.     

Acceleration of coarse grain molecular dynamics on GPU architectures

Coarse grain (CG) molecular models have been proposed to simulate complex systems with lower computational overheads and longer timescales with respect to atomistic level models. However, their acceleration on parallel architectures such as graphic processing units (GPUs) presents original challenges that must be carefully evaluated. The objective of this work is to characterize the impact of CG model features on parallel simulation performance. To achieve this, we implemented a GPU‐accelerated version of a CG molecular dynamics simulator, to which we applied specific optimizations for CG models, such as dedicated data structures to handle different bead type interactions, obtaining a maximum speed‐up of $14$ on the NVIDIA GTX480 GPU with Fermi architecture. We provide a complete characterization and evaluation of algorithmic and simulated system features of CG models impacting the achievable speed‐up and accuracy of results, using three different GPU architectures as case studies. © 2012 Wiley Periodicals, Inc.     

SU (2) lattice gauge theory simulations on Fermi GPUs

In this work we explore the performance of CUDA in quenched lattice SU (2) simulations. CUDA, NVIDIA Compute Unified Device Architecture, is a hardware and software architecture developed by NVIDIA for computing on the GPU. We present an analysis and performance comparison between the GPU and CPU in single and double precision. Analyses with multiple GPUs and two different architectures (G200 and Fermi architectures) are also presented. In order to obtain a high performance, the code must be optimized for the GPU architecture, i.e., an implementation that exploits the memory hierarchy of the CUDA programming model.     

Data assimilation using a GPU accelerated path integral Monte Carlo approach

The answers to data assimilation questions can be expressed as path integrals over all possible state and parameter histories. We show how these path integrals can be evaluated numerically using a Markov Chain Monte Carlo method designed to run in parallel on a graphics processing unit (GPU). We demonstrate the application of the method to an example with a transmembrane voltage time series of a simulated neuron as an input, and using a Hodgkin–Huxley neuron model. By taking advantage of GPU computing, we gain a parallel speedup factor of up to about 300, compared to an equivalent serial computation on a CPU, with performance increasing as the length of the observation time used for data assimilation increases.     

GPU-enhanced DEM analysis of flow behaviour of irregularly shaped particles in a full-scale twin screw granulator

During twin screw granulation (TSG), small particles, which generally have irregular shapes, agglomerate together to form larger granules with improved properties. However, how particle shape impacts the conveying characteristics during TSG is not explored nor well understood. In this study, a graphic processor units (GPUs) enhanced discrete element method (DEM) is adopted to examine the effect of particle shape on the conveying characteristics in a full scale twin screw granulator for the first time. It is found that TSG with spherical particles has the smallest particle retention number, mean residence time, and power consumption; while for TSG with hexagonal prism (Hexp) shaped particles the largest particle retention number is obtained, and TSG with cubic particles requires the highest power consumption. Furthermore, spherical particles exhibit a flow pattern closer to an ideal plug flow, while cubic particles present a flow pattern approaching a perfect mixing. It is demonstrated that the GPU-enhanced DEM is capable of simulating the complex TSG process in a full-scale twin screw granulator with non-spherical particles.     

Parallelization and improvements of the generalized born model with a simple sWitching function for modern graphics processors

Two fundamental challenges of simulating biologically relevant systems are the rapid calculation of the energy of solvation and the trajectory length of a given simulation. The Generalized Born model with a Simple sWitching function (GBSW) addresses these issues by using an efficient approximation of Poisson–Boltzmann (PB) theory to calculate each solute atom's free energy of solvation, the gradient of this potential, and the subsequent forces of solvation without the need for explicit solvent molecules. This study presents a parallel refactoring of the original GBSW algorithm and its implementation on newly available, low cost graphics chips with thousands of processing cores. Depending on the system size and nonbonded force cutoffs, the new GBSW algorithm offers speed increases of between one and two orders of magnitude over previous implementations while maintaining similar levels of accuracy. We find that much of the algorithm scales linearly with an increase of system size, which makes this water model cost effective for solvating large systems. Additionally, we utilize our GPU‐accelerated GBSW model to fold the model system chignolin, and in doing so we demonstrate that these speed enhancements now make accessible folding studies of peptides and potentially small proteins. © 2016 Wiley Periodicals, Inc.     

Accelerating electrostatic interaction calculations with graphical processing units based on new developments of ewald method using non‐uniform fast fourier transform

We present new algorithms to improve the performance of ENUF method (F. Hedman, A. Laaksonen, Chem. Phys. Lett. 425, 2006, 142) which is essentially Ewald summation using Non‐Uniform FFT (NFFT) technique. A NearDistance algorithm is developed to extensively reduce the neighbor list size in real‐space computation. In reciprocal‐space computation, a new algorithm is developed for NFFT for the evaluations of electrostatic interaction energies and forces. Both real‐space and reciprocal‐space computations are further accelerated by using graphical processing units (GPU) with CUDA technology. Especially, the use of CUNFFT (NFFT based on CUDA) very much reduces the reciprocal‐space computation. In order to reach the best performance of this method, we propose a procedure for the selection of optimal parameters with controlled accuracies. With the choice of suitable parameters, we show that our method is a good alternative to the standard Ewald method with the same computational precision but a dramatically higher computational efficiency. © 2015 Wiley Periodicals, Inc.     

基于GPU加速的磁共振血管造影图像的并行分割与追踪算法

在应用磁共振血管造影图像进行临床诊断时,临床医生往往需要提取感兴趣区域(Region Of Interest,ROI)的部分血管.这个工作传统上需要手工进行,费时费力.该文提出一种并行的血管分割与追踪算法,利用现代图形处理器(Graphics Processing Unit,GPU)所具备的大规模并行计算能力进行快速的血管分割.首先将三维图像网格化为共面的立方体,并行处理每个立方体,确定立方体中哪些表面有血管通过,以及立方体中哪些体素包含血管.之后再将该结果用于串行的全局分割与血管追踪处理.实验结果表明,利用这种先并行后串行的方法,可以在1 s之内完成全脑血管的分割,分割的结果也更准确.