检索结果-内蒙古大学图书馆

IEEE 27th international parallel and distributed Processing symposium (IPDPS)

作者： Pennycook, S. J. Hughes, C. J. Smelyanskiy, M. Jarvis, S. A. Univ Warwick Dept Comp Sci Coventry CV4 7AL W Midlands England Intel Corp Parallel Comp Lab Santa Clara CA USA

ISBN: (纸本)9780769549712

We analyse gather-scatter performance bottle-necks in molecular dynamics codes and the challenges that they pose for obtaining benefits from SIMD execution. this analysis informs a number of novel code-level and algorithmic improvements to Sandia's miniMD benchmark, which we demonstrate using three SIMD widths (128-, 256- and 512-bit). the applicability of these optimisations to wider SIMD is discussed, and we show that the conventional approach of exposing more parallelism through redundant computation is not necessarily best. In single precision, our optimised implementation is up to 5x faster than the original scalar code running on Intel (R) Xeon (R) processors with 256-bit SIMD, and adding a single Intel (R) Xeon Phi (TM) coprocessor provides up to an additional 2x performance increase. these results demonstrate: (i) the importance of effective SIMD utilisation for molecular dynamics codes on current and future hardware;and (ii) the considerable performance increase afforded by the use of Intel (R) Xeon Phi (TM) coprocessors for highly parallel workloads.

关键词： scientific computing accelerator architectures parallel programming performance analysis high performance computing

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization of Data Caching and Task Scheduling based on Information Entropy for Mobile Edge computing 19

Joint Optimization of Data Caching and Task Scheduling based...

引用

19th IEEE international symposium on parallel and distributed Processing with Applications (IEEE ISPA)

作者： Wang, Pengwei Zhao, Yajun Zhang, Zhaohui Donghua Univ Sch Comp Sci & Technol Shanghai 201620 Peoples R China Minist Educ Engn Res Ctr Digitalized Text & Fash Technol Shanghai 201620 Peoples R China

ISBN: (纸本)9781665435741

the rise of 5G technology has prompted the emergence of mobile edge computing (MEC), which deploys edge servers at the edge of networks to process task requests. Most work on MEC considers either data caching or task scheduling, but not their combination. However, the two are related, and should be considered together. We do so in this work, with the aim to reduce the average response delay of user task requests. A multi-index collaborative cache replacement (MCCR) algorithm based on the theory of information entropy is proposed, which considers the priority, replacement cost, and size of cached data, so as to replace data with low caching value. An effective task scheduling algorithm, NHSA-MCCR, based on the nearest hierarchical scheduling strategy (NHSA) and MCCR, is then proposed. Experiments are conducted to evaluate the performance of our proposed algorithms, whose results show that MCCR is superior to other caching algorithms in terms of cache hit rate, and that NHSA-MCCR can achieve lower response delay and energy consumption than other scheduling algorithms.

关键词： Mobile edge computing Data caching Task scheduling Information entropy

来源：评论

学校读者我要写书评

暂无评论

Optimization of Multi-level Checkpoint Model for Large Scale HPC Applications

Optimization of Multi-level Checkpoint Model for Large Scale...

引用

IEEE 28th international parallel & distributed Processing symposium (IPDPS)

作者： Di, Sheng Bouguerra, Mohamed Slim Bautista-gomez, Leonardo Cappello, Franck INRIA Paris France Argonne Natl Lab Argonne IL USA

ISBN: (纸本)9780769552071

HPC community projects that future extreme scale systems will be much less stable than current Petascale systems, thus requiring sophisticated fault tolerance to guarantee the completion of large scale numerical computations. Execution failures may occur due to multiple factors with different scales, from transient uncorrectable memory errors localized in processes to massive system outages. Multi-level checkpoint/restart is a promising model that provides an elastic response to tolerate different types of failures. It stores checkpoints at different levels: e.g., local memory, remote memory, using a software RAID, local SSD, remote file system. In this paper, we respond to two open questions: 1) how to optimize the selection of checkpoint levels based on failure distributions observed in a system, 2) how to compute the optimal checkpoint intervals for each of these levels. the contribution is threefold. (1) We build a mathematical model to fit the multilevel checkpoint/restart mechanism with large scale applications regarding various types of failures. (2) We theoretically optimize the entire execution performance for each parallel application by selecting the best checkpoint level combination and corresponding checkpoint intervals. (3) We characterize checkpoint overheads on different checkpoint levels in a real cluster environment, and evaluate our optimal solutions using both simulation with millions of cores and real environment with real-world MPI programs running on hundreds of cores. Experiments show that optimized selections of levels associated with optimal checkpoint intervals at each level outperforms other state-of-the-art solutions by 5-50 percent.

关键词： Checkpoint/Restart model Resilience exascale High Performance computing Checkpoints Cell Cycle Checkpoints Resilience High Performance computing core Scale formation

来源：评论

学校读者我要写书评

暂无评论

Dynamic Computation Offloading for Green things-Edge-Cloud computing with Local Caching 36

Dynamic Computation Offloading for Green Things-Edge-Cloud C...

引用

36th IEEE international parallel and distributed Processing symposium (IEEE IPDPS)

作者： Tian, Xianzhong Meng, Huixiao Li, Yanjun Miao, Pingting Xu, Pengcheng Zhejiang Univ Technol Sch Comp Sci & Technol Hangzhou Peoples R China

ISBN: (纸本)9781665481069

With the increasing popularity of the internet of things (IoT) and 5G, emerging things-edge-cloud computing (TEC) paradigm provides a flexible way for execution of delay-sensitive and computation-intensive applications running on the user equipment (UE). By offloading these workloads to the mobile edge computing (MEC) or mobile cloud computing (MCC) server, the quality of experience, e.g., the execution delay, could be greatly improved. Nevertheless, conventional battery-powered devices face the challenge of battery exhaustion for task offloading. Using renewable energy via energy harvesting (EH) technologies has become a promising way to power these devices. In this paper, we investigate a multi-user green TEC system with EH UEs, each has a task buffer with limited capacity. A joint offloading decision and resource allocation problem is formulated, which addresses the long-term average execution delay, the task dropping and the long-term average energy cost constraint. A low-complexity online algorithm is proposed leveraging Lyapunov optimization framework and matroid theory, which jointly decides the offloading decision, the MEC server CPU frequencies and the transmit power for computation offloading. A unique advantage of this algorithm is that the decisions depend only on the current system state without requiring distribution information of the arrival tasks, wireless channel state, and EH processes. the implementation of the algorithm only requires to solve a deterministic problem in each time slot. Simulation results show that our proposed algorithm makes a best trade-off between minimizing the long-term average generalized delay and satisfying the long-term average energy cost constraint. Impacts of various parameters on the delay and energy cost performance are also discussed.

关键词： thing-edge-cloud computing energy harvesting online offloading Lyapunov optimization matroid theory

来源：评论

学校读者我要写书评

暂无评论

Portable runtime support for graph-oriented parallel and distributed programming 5

Portable runtime support for graph-oriented parallel and dis...

引用

5th international symposium on parallel Architectures, Algorithms and Networks (I-SPAN 2000)

作者： Cao, J Liu, Y Xie, L Mao, B Zhang, K Nanjing Univ Natl Key Lab Novel Software Technol Nanjing 21008 Peoples R China

ISBN: (纸本)0769509363

In this paper, we describe the design and implementation of a portable run-time system for GOP, a graph-oriented programming framework aiming at providing high-level abstractions for configuring and programming cooperative parallel processes. the runtime system provides an interface with a library of programming primitives to the low-level facilities required to support graph-oriented communications and synchronization. the implementation is on top of the parallel Virtual Machine (PVM) in a local area network of Sun workstations. Issues related to the implementation of a graph operations in a distributed environment are discussed. Performance of the runtime system is evaluated by estimating the overheads associated with using GOP primitives as opposed to PVM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PRESHAK: A generic tool to implement application-specific message-passing communication kernels for concurrent machines 5

PRESHAK: A generic tool to implement application-specific me...

引用

5th international parallel Processing symposium, IPPS 1991

作者： Srivastava, Alok K. Kshetramade, Sanjay C. Centre For Development of Advanced Computing Pune411007 India

ISBN: (纸本)0818691670

PRESHAK is a software tool that will relieve the application developers from designing and developing the communication layer for their parallel algorithms. It can be used to tailor a system-wide message-passing communication structure with high throughput and low delay across the application spectrum. In this paper we discuss the design philosophy and the key features of PRESHAK. At present it is implemented on C-DAC's PARAM [1] series of parallel processing machines supporting upto 64 transputers configurable via a programmable cross-bar switch. © 1991 IEEE.

关键词： Transputers

来源：评论

学校读者我要写书评

暂无评论

Simulating the evolution of localization based on the diffusion of damage

引用

international JOURNAL OF SOLIDS AND STRUCTURES 2000年第48-50期37卷 7465-7479页

作者： Chen, Z Univ Missouri Dept Civil & Environm Engn Fac Struct Engn Columbia MO 65211 USA

Based on the failure mechanisms of brittle solids under dynamic loading conditions, a strain-based damage diffusion model is proposed to simulate the evolution of localization due to microcracking. A three-dimensional diffusion equation is formulated with local rate-independent and rate-dependent damage evolution laws, respectively. the diffusion equation governing the evolution of damage is incorporated into the hyperbolic equation governing the wave propagation in a parallel setting. A parametric study is performed to investigate the effects of model parameters on the diffusion of damage. One- and two-dimensional sample problems are considered to illustrate how the dynamic evolution of localization can be simulated without using nonlocal models in the strain-stress space. the relationship between the proposed approach and the existing ones for localization problems is also discussed based on the preliminary results obtained in this paper. It appears that the proposed approach might be an effective numerical procedure to simulate the evolution of localization, with parallel computing, in a single computational domain involving different lower-order governing differential equations. (C) 2000 Elsevier Science Ltd. All rights reserved.

关键词： localization diffusion multi-physics parallel computing

来源：评论

学校读者我要写书评

暂无评论

Heuristic Prefetching Caching Strategy to Enhance QoE in Edge computing 16

Heuristic Prefetching Caching Strategy to Enhance QoE in Edg...

引用

16th IEEE ISPA / 17th IEEE IUCC / 8th IEEE BDCloud / 11th IEEE SocialCom / 8th IEEE SustainCom

作者： Sun, Meng Chen, Haopeng Shu, Buqing Hu, Fei Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn Shanghai Peoples R China China Aeronaut Radio Elect Res Inst Shanghai Peoples R China

ISBN: (纸本)9781728111414

the emergence of mobile devices and wireless services brings unprecedented traffic demand, which causes the bad quality of experience arises in traditional reactive networks, such as long loading time and loss of responsiveness. this paper presents the heuristic prefetching caching strategy in 5G networks, which prefetches content based on its historical frequency in order to improve the quality of experience. the cache of the base station is split into the proactive one and the reactive one. the proactive cache prefetches the popular content within the limit of capacity for a sum total maximum of frequency, while the reactive one caches others with the ordinary caching algorithm. At each period, we adjust the proportion of the proactive cache to minimize latency based on the idea of Simulated Annealing. Under the circumstances where all the content is predictable, our caching strategy improves hit ratio by 20%. And it reduces latency by 15% in the architecture of 400MB small base stations and even 52% with 200MB small base stations, which could enhance the quality of experience to a great degree.

关键词： popularity of content prediction heuristic prefetching caching strategy proportion

来源：评论

学校读者我要写书评

暂无评论

Experiences in a distributed, real-time avionics domain - Weapons system open architecture 5

Experiences in a distributed, real-time avionics domain - We...

引用

5th IEEE international symposium on Object-Oriented Real-Time distributed computing (ISORC 2002)

作者： Gossett, J Noll, D Corman, D Boeing Co St Louis MO USA

ISBN: (纸本)0769515584

Weapons System Open Architecture (WSOA) utilizes a distributed object computing foundation as a "bridge" to enable communication between disparate real-time systems in the redirection of strike assets. this open systems "bridge" connects legacy embedded mission systems and off-board C3I (Command, Control, Communication and Information) sources and systems. WSOA will establish the potential gains in warfighting capability due to the enabling technologies of collaborative planning, information mining, and adaptive embedded resource management. this paper focuses on the experiences and lessons learned in the WSOA demonstration program with CORBA middleware, pluggable protocols and Quality of Service (QoS) enforcement, management and verification.

关键词： Aerospace electronics Bridges Communication system control Computer architecture Control systems distributed computing Open systems Quality of service Real time systems Weapons

来源：评论

学校读者我要写书评

暂无评论

A data allocation method for efficient content-based retrieval in parallel multimedia databases

A data allocation method for efficient content-based retriev...

引用

5th international symposium on parallel and distributed Processing and Applications/ISPA 2007 international Workshops

作者： Manjarrez-Sanchez, Jorge Martinez, Jose Valduriez, Patrick Univ Nantes INRIA F-44035 Nantes France

ISBN: (纸本)9783540747666

Scaling up to large multimedia databases with high dimensional metadata descriptions while providing fast content-based retrieval (CBR) is getting increasingly important for many applications. To address this objective, we strive to exploit the popular parallel shared-nothing architecture. In this context, a major problem is data allocation on the different nodes in order to yield efficient parallel content-based retrieval. In this paper, assuming a clustering process and based on a complexity analysis of CBR, we propose a data allocation method with an optimal number of clusters and nodes. We validated our method through experiments with different high dimensional synthetic databases and implemented a query processing algorithm for full k nearest neighbors.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：