Optimization Techniques for GPU-Based Parallel Programming Models in High-Performance Computing

This study embarks on a comprehensive examination of optimization techniques within GPU-based parallel programming models,pivotal for advancing high-performance computing(HPC).Emphasizing the transition of GPUs from graphic-centric processors to versatile computing units,it delves into the nuanced optimization of memory access,thread management,algorithmic design,and data structures.These optimizations are critical for exploiting the parallel processing capabilities of GPUs,addressingboth the theoretical frameworks and practical implementations.By integrating advanced strategies such as memory coalescing,dynamic scheduling,and parallel algorithmic transformations,this research aims to significantly elevate computational efficiency and throughput.The findings underscore the potential of optimized GPU programming to revolutionize computational tasks across various domains,highlighting a pathway towards achieving unparalleled processing power and efficiency in HPC environments.The paper not only contributes to the academic discourse on GPU optimization but also provides actionable insights for developers,fostering advancements in computational sciences and technology.

Towards Auction-Based HPC Computing in the Cloud

Cloud computing is expanding widely in the world of IT infrastructure. This is due partly to the cost-saving effect of economies of scale. Fair market conditions can in theory provide a healthy environment to reflect the most reasonable costs of computations. While fixed cloud pricing provides an attractive low entry barrier for compute-intensive applications, both the consumer and supplier of computing resources can see high efficiency for their investments by participating in auction-based exchanges. There are huge incentives for the cloud provider to offer auctioned resources. However, from the consumer perspective, using these resources is a sparsely discussed challenge. This paper reports a methodology and framework designed to address the challenges of using HPC （High Performance Computing） applications on auction-based cloud clusters. The authors focus on HPC applications and describe a method for determining bid-aware checkpointing intervals. They extend a theoretical model for determining checkpoint intervals using statistical analysis of pricing histories. Also the latest developments in the SpotHPC framework are introduced which aim at facilitating the managed execution of real MPI applications on auction-based cloud environments. The authors use their model to simulate a set of algorithms with different computing and communication densities. The results show the complex interactions between optimal bidding strategies and parallel applications performance.

MatDEM-fast matrix computing of the discrete element method

Discrete element method can effectively simulate the discontinuity,inhomogeneity and large deformation and failure of rock and soil.Based on the innovative matrix computing of the discrete element method,the highperformance discrete element software MatDEM may handle millions of elements in one computer,and enables the discrete element simulation at the engineering scale.It supports heat calculation,multi-field and fluidsolid coupling numerical simulations.Furthermore,the software integrates pre-processing,solver,postprocessing,and powerful secondary development,allowing recompiling new discrete element software.The basic principles of the DEM,the implement and development of the MatDEM software,and its applications are introduced in this paper.The software and sample source code are available online(http://matdem.com).

Creep experimental test and analysis of high-performance concrete in bridge

Factors that have effect on concrete creep include mixture composition,curing conditions,ambient exposure conditions,and element geometry.Considering concrete mixtures influence and in order to improve the prediction of prestress loss in important structures,an experimental test under laboratory conditions was carried out to investigate compression creep of two high performance concrete mixtures used for prestressed members in one bridge.Based on the experimental results,a power exponent function of creep degree for structural numerical analysis was used to model the creep degree of two HPCs,and two series of parameters of this function for two HPCs were calculated with evolution program optimum method.The experimental data was compared with CEB-FIP 90 and ACI 209(92) models,and the two code models both overestimated creep degrees of the two HPCs.So it is recommended that the power exponent function should be used in this bridge structure analysis.

Experimental study on creep of high-performance concretes

In order to investigate the compression creep of two kinds of high-performance concrete mixtures used for prestressed members in a bridge,an experimental test under laboratory conditions was carried out.Based on the experimental results,a power exponent function was used to model the creep degree of these high-performance concretes(HPCs) for structural numerical analysis,and two series parameters of this function for the HPCs were given with the optimum method of evolution program.The experimental data were compared with CEB-FIP 90 and ACI 92 models.Results show that the two code models both overestimate the creep degree of two HPCs,so it is recommended that the power exponent function should be used for the creep analysis of bridge structure.

Evaluation of the Application Benefit of Meteorological High Performance Computing Resources

The meteorological high-performance computing resource is the support platform for the weather forecast and climate prediction numerical model operation. The scientific and objective method to evaluate the application of meteorological high-performance computing resources can not only provide reference for the optimization of active resources, but also provide a quantitative basis for future resource construction and planning. In this paper, the concept of the utility value B and index compliance rate E of the meteorological high performance computing system are presented. The evaluation process, evaluation index and calculation method of the high performance computing resource application benefits are introduced.

API Development Increases Access to Shared Computing Resources at Boston University

Within the last few decades, increases in computational resources have contributed enormously to the progress of science and engineering (S & E). To continue making rapid advancements, the S & E community must be able to access computing resources. One way to provide such resources is through High-Performance Computing (HPC) centers. Many academic research institutions offer their own HPC Centers but struggle to make the computing resources easily accessible and user-friendly. Here we present SHABU, a RESTful Web API framework that enables S & E communities to access resources from Boston University’s Shared Computing Center (SCC). The SHABU requirements are derived from the use cases described in this work.

广域网协议在PC集群系统HPC中的应用分析

鉴于绝大多数PC集群系统都使用了TCP/IP协议,着重分析了作为分布式进程间通信手段的socket通信机制在Linux中的实现以及传统通信开销中影响性能的主要因素,并针对通信瓶颈,对传统的通信协议栈进行了改进,对广域网协议在PC集群系统中应用的不足之处,提出了改进集群网络性能的方法.

HPCC:面向存储访问模型的基准测试—一种可能替代TOP500 HPL的测试方法

高性能计算机系统的性能评价历来是本领域所关注的重要问题.TOP500排名所采用的标准测试HPL(HigPerformanceLinpack)并不能真实的反映系统各方面的性能,尤其是存储访问方面.HPCChallenge基准测试则着重于各种存储访问模型,在HPL的基础之上又整合了多个有代表性的核心测试程序,很有可能在未来取代现在TOP500采用的的HPL测试.本文首先简单介绍HPCChallenge诞生的背景,解释基准测试的基本概念和原理,从存储访问模型的角度对各项测试进行了描述,并根据实际的测试结果进行比较和分析.最后给出结论以及将来的工作.

HPC海量存储系统Pass-Through访问策略研究

为了解决海量信息处理中实时访问中的"I/O墙"的问题,提高海量信息分布式存储系统的性能,提出了一种基于高性能计算(high performance computing,HPC)的存储部件新型访问策略.首先,分析传统访问模型存在的问题;其次,研究存储部件直通路模式的工作机理,建立存储系统分解为多层次、分布式的模型,根据不同的层次和映射策略实现存储空间物理地址、缓存地址、存储系统逻辑空间地址的连续映射;第三,分析直通路访问模式下的存储路径时间开销;第四,在模拟环境下存储部件访问的性能测试,在实际采用该策略的应用系统中进行验证.通过验证测试结果表明,该方法能有效提高存储系统的性能,能够不断满足海量信息处理实时需要.

HPC的最新发展情况及发展趋势

本文介绍了高性能计算机在国际和国内的最新发展情况,对目前比较热门的计算机机群和网格计算机进行了理性分析和客观评价,并对以后高性能计算机的发展进行了前瞻性探讨,以期对我国高性能计算的发展有所借鉴。

基于64位的HPC应用研究

针对64位高性能计算,本文简述了如何配置64位编程环境,并对64位SIMD指令作了介绍。通过一个实例验证了利用64位SIMD指令可以较好地提高任务处理速度。

New prospects for computational hydraulics by leveraging high-performance heterogeneous computing techniques

In the last two decades, computational hydraulics has undergone a rapid development following the advancement of data acquisition and computing technologies. Using a finite-volume Godunov-type hydrodynamic model, this work demonstrates the promise of modern high-performance computing technology to achieve real-time flood modeling at a regional scale. The software is implemented for high-performance heterogeneous computing using the OpenCL programming framework, and developed to support simulations across multiple GPUs using a domain decomposition technique and across multiple systems through an efficient implementation of the Message Passing Interface （MPI） standard. The software is applied for a convective storm induced flood event in Newcastle upon Tyne, demonstrating high computational performance across a GPU cluster, and good agreement against crowd- sourced observations. Issues relating to data availability, complex urban topography and differences in drainage capacity affect results for a small number of areas.

The use of high-performance and high-throughput computing for the fertilization of digital earth and global change studies

The study of global climate change seeks to understand:(1)the components of the Earth’s varying environmental system,with a particular focus on climate;(2)how these components interact to determine present conditions;(3)the factors driving these components;(4)the history of global change and the projection of future change;and(5)how knowledge about global environmental variability and change can be applied to present-day and future decision-making.This paper addresses the use of high-performance computing and high-throughput computing for a global change study on the Digital Earth(DE)platform.Two aspects of the use of high-performance computing(HPC)/high-throughput computing(HTC)on the DE platform are the processing of data from all sources,especially Earth observation data,and the simulation of global change models.The HPC/HTC is an essential and efficient tool for the processing of vast amounts of global data,especially Earth observation data.The current trend involves running complex global climate models using potentially millions of personal computers to achieve better climate change predictions than would ever be possible using the supercomputers currently available to scientists.

基于Microsoft HPC的Magic迭代计算软件的并行化

Magic软件可以通过馈入参数仿真计算输出功率。为了确定最优的参数,实际工作中通过采用Magic迭代计算软件中的遗传算法迭代计算确定参数,但每代计算需要同时启动多个Magic程序,耗时长、单机计算效率低。本文提出了基于Windows环境,使用现有的工作站,利用Microsoft HPC工具包搭建一个并行计算集群,实现将每代启动的Magic程序放到多台计算机上进行并行计算的解决方案。首先利用HPC Pack进行集群的搭建,然后设置共享文件夹进行数据的存储与访问,最后使用Microsoft HPC Pack SDK中的API改写Magic迭代计算软件,实现将每代启动的Magic程序放到多台计算机上进行并行计算。通过测试表明加速比大约为2,能够有效提高计算速度。

一种全面高效的HPCS监控体系

分析了以超级计算中心联想深腾6800为主的HPCS监控需求,比较了大量的监控实现技术,给出监控系统评估特征和指标,提出了一种集系统、性能、应用程序、进程监控于一体的改进策略,讨论了利用信息流水、过滤、双重传输模式减少监控数据传输量,减轻监控资源消耗,提高综合监控的性能和效率。

Ad Hoc File Systems for High-Performance Computing

Storage backends of parallel compute clusters are still based mostly on magnetic disks,while newer and faster storage technologies such as flash-based SSDs or non-volatile random access memory(NVRAM)are deployed within compute nodes.Including these new storage technologies into scientific workflows is unfortunately today a mostly manual task,and most scientists therefore do not take advantage of the faster storage media.One approach to systematically include nodelocal SSDs or NVRAMs into scientific workflows is to deploy ad hoc file systems over a set of compute nodes,which serve as temporary storage systems for single applications or longer-running campaigns.This paper presents results from the Dagstuhl Seminar 17202"Challenges and Opportunities of User-Level File Systems for HPC"and discusses application scenarios as well as design strategies for ad hoc file systems using node-local storage media.The discussion includes open research questions,such as how to couple ad hoc file systems with the batch scheduling environment and how to schedule stage-in and stage-out processes of data between the storage backend and the ad hoc file systems.Also presented are strategies to build ad hoc file systems by using reusable components for networking and how to improve storage device compatibility.Various interfaces and semantics are presented,for example those used by the three ad hoc file systems BeeOND,GekkoFS,and BurstFS.Their presentation covers a range from file systems running in production to cutting-edge research focusing on reaching the performance limits of the underlying devices.

GCSS:a global collaborative scheduling strategy for wide-area high-performance computing

Wide-area high-performance computing is widely used for large-scale parallel computing applications owing to its high computing and storage resources.However,the geographical distribution of computing and storage resources makes efficient task distribution and data placement more challenging.To achieve a higher system performance,this study proposes a two-level global collaborative scheduling strategy for wide-area high-performance computing environments.The collaborative scheduling strategy integrates lightweight solution selection,redundant data placement and task stealing mechanisms,optimizing task distribution and data placement to achieve efficient computing in wide-area environments.The experimental results indicate that compared with the state-of-the-art collaborative scheduling algorithm HPS+,the proposed scheduling strategy reduces the makespan by 23.24%,improves computing and storage resource utilization by 8.28%and 21.73%respectively,and achieves similar global data migration costs.

Mochi: Composing Data Services for High-Performance Computing Environments

Technology enhancements and the growing breadth of application workflows running on high-performance computing(HPC)platforms drive the development of new data services that provide high performance on these new platforms,provide capable and productive interfaces and abstractions for a variety of applications,and are readily adapted when new technologies are deployed.The Mochi framework enables composition of specialized distributed data services from a collection of connectable modules and subservices.Rather than forcing all applications to use a one-size-fits-all data staging and I/O software configuration,Mochi allows each application to use a data service specialized to its needs and access patterns.This paper introduces the Mochi framework and methodology.The Mochi core components and microservices are described.Examples of the application of the Mochi methodology to the development of four specialized services are detailed.Finally,a performance evaluation of a Mochi core component,a Mochi microservice,and a composed service providing an object model is performed.The paper concludes by positioning Mochi relative to related work in the HPC space and indicating directions for future work.