检索结果-内蒙古大学图书馆

International Conference on High Performance Computing and Simulation (HPCS)

作者： Kabir, Upama Goswami, Dhrubajyoti Concordia Univ Dept Comp Sci & Software Engn Montreal PQ Canada

ISBN: (纸本)9781467378130

Checkpoint and recovery cost imposed by coordinated checkpoint/restart (CCP/R) is a crucial performance issue for high performance computing (HPC) applications. In comparison, algorithm based fault tolerance (ABFT) is a promising fault tolerance method with low recovery overhead, but it suffers from inadequacy of universal applicability and user non-transparency. In this paper we address the overhead problem of CCP/R and some of the limitations of ABFT, and propose a solution for ABFT based on algorithmic patterns. The proposed solution is a generic fault tolerance strategy for a group of applications that exhibit similar algorithmic (structural and behavioral) features. These features together with the minimal fault recovery data (critical data) determine the fault tolerance strategy for the group of applications. We call this strategy a fault tolerance pattern (FTP). We demonstrate the idea of FTP with parallel iterative deepening A* (PIDA*) search, a generic search algorithm used to solve a wide range of discrete optimization problems (DOP). Theoretical analysis shows that our proposed solution performs better than CCP/R in terms of checkpoint and recovery time overhead. Furthermore, using FTP helps in separation of concerns, which facilitates user transparency.

关键词： fault tolerant parallel programs algorithm based fault tolerance parallel algorithmic patterns patterns for fault tolerance framework for fault tolerance

来源：评论

学校读者我要写书评

暂无评论

algorithm-based fault tolerant systolic evaluation of polynomials and exponentials of polynomials for equispaced arguments

引用

COMPUTERS & ELECTRICAL ENGINEERING 1997年第1期23卷 1-13页

作者： Murthy, CSR Department of Computer Science Engineering Indian Institute of Technology Madras 600 036 India

Many applications in digital signal processing and computer graphics, which require high speed evaluation of polynomials and exponentials of polynomials can now be implemented in hardware very efficiently because of the advances in VLSI technology. Several fast algorithms have been proposed in the recent past for the efficient evaluation of polynomials and exponentials of polynomials for equispaced arguments on uniprocessor systems. In this paper, we consider the problem of organizing this evaluation on VLSI chips in the form of systolic arrays. We use algorithm-based fault tolerance to detect and correct errors caused by transient failures in the Processing Elements (PEs) of these systolic arrays. This approach of adding fault tolerance is shown to require minimum space and time overheads compared to the other traditional fault tolerance schemes such as space redundancy and time redundancy. The organizations presented here have the main advantage that the interconnections between the PEs are very regular and simple, and hence are very appropriate for VLSI implementation. Copyright (C) 1997 Elsevier Science Ltd

关键词： systolic arrays evaluation of polynomials and exponentials of polynomials for equispaced arguments algorithm based fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Analyzing fault aware collective performance in a process fault tolerant MPI

引用

PARALLEL COMPUTING 2012年第1-2期38卷 15-25页

作者： Hursey, Joshua Graham, Richard L. Oak Ridge Natl Lab Oak Ridge TN 37831 USA

Application developers are investigating algorithm based fault tolerance (ABET) techniques to improve the efficiency of application recovery beyond what traditional techniques alone can provide. Applications will depend on libraries to sustain failure-free performance across process failure to continue to use High Performance Computing (HPC) systems efficiently even in the presence of process failure. Optimized Message Passing Interface (MPI) collective operations are a critical component of many scalable HPC applications. However, most of the collective algorithms are not able to handle process failure. Next generation MPI implementations must provide fault aware versions of such algorithms that can sustain performance across process failure. This paper discusses the design and implementation of fault aware collective algorithms for tree structured communication patterns. The three design approaches of rerouting, lookup avoiding and rebalancing are described, and analyzed for their performance impact relative to similar fault unaware barrier and broadcast collective algorithms. The analysis shows that the rerouting approach causes a significant performance degradation while the rebalancing approach can bring the performance within 1% of the fault unaware performance. This paper also presents the impact of the run-through stabilization prototype on point-to-point communication, and analyzes the time to rebalance the tree while accounting for process failures. Published by Elsevier B.V.

关键词： MPI fault tolerance Collective communication algorithm based fault tolerance Run-through stabilization

来源：评论

学校读者我要写书评

暂无评论

ERASURE CODING FOR fault-OBLIVIOUS LINEAR SYSTEM SOLVERS

引用

SIAM JOURNAL ON SCIENTIFIC COMPUTING 2017年第1期39卷 C48-C64页

作者： Zhu, Yao Gleich, David F. Grama, Ananth Purdue Univ Dept Comp Sci W Lafayette IN 47907 USA

Dealing with faults is an important problem as parallel and distributed systems scale to millions of processing cores. Traditional methods for dealing with faults include checkpoint-restart, active replicas, and deterministic replay. Each of these techniques has associated resource overheads and constraints. In this paper, we propose an alternate approach to dealing with faults based on input augmentation. This approach, which is an algorithmic analog of erasure-coded storage, applies a minimally modified algorithm on the augmented input to produce an augmented output. The execution of such an algorithm proceeds completely oblivious to faults in the system. In the event of one or more faults, the real solution is recovered using a rapid reconstruction method from the augmented output. We demonstrate this approach on the problem of solving sparse linear systems using a conjugate gradient solver, where we present input augmentation and output recovery techniques. Through simulations, we show that our approach can be made oblivious to a large number of faults with low computational overhead. Specifically, we demonstrate cases where a single fault can be corrected with less than 10% overhead in time, and even in extreme cases (fault rates of 20%), our approach is able to compute a solution with reasonable overhead.

关键词： erasure coding linear system solvers fault oblivious computation algorithm based fault tolerance

来源：评论

学校读者我要写书评

暂无评论

A fault tolerant systolic mesh for linear system solution

引用

INTERNATIONAL JOURNAL OF COMPUTER MATHEMATICS 1998年第3-4期67卷 315-332页

作者： Bhuvaneswari, K Murthy, CSR Indian Inst Technol Dept Comp Sci & Engn Madras 600036 Tamil Nadu India

A systolic N x (N + 1) mesh to solve a system of N linear equations, using a variant of Gaussian elimination algorithm (GE), called successive GE (SGE), was presented in [2]. To ensure numerical stability, the authors have incorporated pairwise pivoting in the algorithm. However, they do not address the important issue of handling oversized problems, i.e., their design is not suitable for solving linear systems of arbitrary size. In this paper, in order to add flexibility to their design, we present two problem partitioning techniques so that problems of any size can be solved on the mesh. Further, in order to add robustness to their design, we suggest two fault tolerant schemes for handling processor failures. The first one is based on time redundancy and has 100% time overhead. It can tolerate up to 50% processor failures at no extra hardware cost. The second scheme is based on algorithm based fault tolerance and uses 2N extra processors to tolerate up to N processor failures with very little time overhead.

关键词： linear equations Gaussian elimination pairwise pivoting systolic array problem partitioning fault tolerance time redundancy algorithm based fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Adaptive fault tolerance for reliable LMS adaptive filtering

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS 1997年第12期44卷 1001-1014页

作者： Schnaufer, BA Jenkins, WK Rockwell Collins Av Cedar Rapids IA 52498 USA Univ Illinois Dept Elect & Comp Engn Urbana IL 61801 USA Univ Illinois Coordinated Sci Lab Urbana IL 61801 USA

Adaptive fault tolerance (AFT) is introduced and applied to finite impulse response (FIR) adaptive filters, fault-tolerant adaptive filters (FTAF's) that result from using the principles of AFT are analyzed with respect to convergence rate, computational complexity, and hardware overhead, A practical and useful FTAF based on the discrete Fourier transform (DFT) is developed that can tolerate numerous coefficient failures regardless of the input noise statistics. The aims of this paper are to demonstrate the principles of the AFT approach and to motivate future research in this area by drawing attention to similarities between AFT and other methods of fault tolerance that exploit adaptivity, such as neural networks.

关键词： adaptive filters algorithm based fault tolerance fault tolerant adaptive filters LMS adaptive filters transform domain adaptive filters

来源：评论

学校读者我要写书评

暂无评论

fault tolerant Faddeeva algorithm

引用

JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING 1998年第1期53卷 78-89页

作者： Connolly, MP Fitzpatrick, P Natl Univ Ireland Univ Coll Cork Natl Microelect Res Ctr Cork Ireland

We present an algorithm based fault tolerant scheme suitable for array implementations of the Faddeeva algorithm. Our technique corrects errors due to multiple transient, intermittent, or permanent faults provided these are restricted to a single column of the array. We show how to find the location of the faulty column and to determine the correct Schur complement from the erroneous one. The fault recovery algorithm is of quadratic complexity in the number of rows of the input matrix while the hardware overhead is approximately four times the number of rows. (C) British Crown Copyright 1998.

关键词： algorithm based fault tolerance Faddeeva algorithm

来源：评论

学校读者我要写书评

暂无评论

AN EFFICIENT algorithm-based CONCURRENT ERROR-DETECTION FOR FFT NETWORKS

引用

IEEE TRANSACTIONS ON COMPUTERS 1995年第9期44卷 1157-1162页

作者： OH, CG YOUN, HY RAJ, VK Dept. of Comput. Sci. Eng. Texas Univ. Arlington TX USA

In this brief contribution a new algorithm-based concurrent error detection scheme employing the checksum approach is proposed for FFT networks. Our design allows high error coverage with low false alarm rate by applying the linear weight factors to the checksums. Due to the simplicity, the hardware overhead is relatively small and errors can be quickly detected. The design is also shown to be easily expanded for multidimensional FFT networks.

关键词： algorithm based fault tolerance CHECKSUM SCHEME CONCURRENT ERROR DETECTION FAST FOURIER TRANSFORM fault COVERAGE MULTIDIMENSIONAL FFT NETWORK VLSI

来源：评论

学校读者我要写书评

暂无评论

An algorithm based mesh check-sum fault tolerant scheme for stream ciphers

引用

INTERNATIONAL JOURNAL OF COMMUNICATION NETWORKS AND DISTRIBUTED SYSTEMS 2009年第3期3卷 217-233页

作者： Zhang, C. N. Liu, Xiao Wei Univ Regina TRLabs Dept Comp Sci 3737 Wascana Pkw Regina SK S4S 0A2 Canada

To enhance the security and reliability of the widely-used stream ciphers, a novel mesh check-sum ABFT scheme for stream ciphers is developed. By utilising the ready-made arithmetic unit in stream ciphers, single and multiple errors can be detected and corrected in a cheap way. To meet different requirements in practical applications, 4D mesh check-sum ABFT scheme is proposed which can be applied to RC4 or other stream ciphers. The 2D mesh check-sum ABFT scheme is able to detect and correct single error with high efficiency. The 4D mesh check-sum ABFT scheme is capable of correcting up to three errors located randomly in an N-element matrix with acceptable computation and bandwidth overhead. The workload can be remarkably reduced when most communications are error-free. Our scheme also provides one-to-one mapping between index and check-sum, so that error can be located and recovered by easier logic and simpler operation.

关键词： fault tolerant error detection and correction algorithm based fault tolerance ABFT check-sum parity stream cipher RC4

来源：评论

学校读者我要写书评

暂无评论

Silent Data Corruption Resilient Two-sided Matrix Factorizations 17

Silent Data Corruption Resilient Two-sided Matrix Factorizat...

引用

22nd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP)

作者： Wu, Panruo DeBardeleben, Nathan Guan, Qiang Blanchard, Sean Chen, Jieyang Tao, Dingwen Liang, Xin Ouyang, Kaiming Chen, Zizhong Univ Calif Riverside Dept Comp Sci & Engn Riverside CA 92521 USA Los Alamos Natl Lab Los Alamos NM USA

ISBN: (纸本)9781450344937

This paper presents an algorithm based fault tolerance method to harden three two-sided matrix factorizations against soft errors: reduction to Hessenberg form, tridiagonal form, and bidiagonal form. These two sided factorizations are usually the prerequisites to computing eigenvalues/eigenvectors and singular value decomposition. algorithm based fault tolerance has been shown to work on three main one-sided matrix factorizations: LU, Cholesky, and QR, but extending it to cover two sided factorizations is non-trivial because there are no obvious offline, problem specific maintenance of checksums. We thus develop an online, algorithm specific checksum scheme and show how to systematically adapt the two sided factorization algorithms used in LAPACK and ScaLAPACK packages to introduce the algorithm based fault tolerance. The resulting ABFT scheme can detect and correct arithmetic errors continuously during the factorizations that allow timely error handling. Detailed analysis and experiments are conducted to show the cost and the gain in resilience. We demonstrate that our scheme covers a significant portion of the operations of the factorizations. Our checksum scheme achieves high error detection coverage and error correction coverage compared to the state of the art, with low overhead and high scalability.

关键词： svd eigenvalue decomposition singular value decomposition algorithm based fault tolerance abft

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：