{"title":"A Heuristic Speculative Execution Strategy in Heterogeneous Distributed Environments","authors":"Huicheng Wu, Kenli Li, Zhuo Tang, Longxin Zhang","doi":"10.1109/PAAP.2014.29","DOIUrl":"https://doi.org/10.1109/PAAP.2014.29","url":null,"abstract":"MapReduce is a distributed parallel computing framework for large-scale data processing with extensive applications. Hadoop MapReduce is the most widely employed open-source implementation of MapReduce framework for its flexible customization and simple usage. To avoid the relatively slow running task, called a straggler task, slowing down the job, MapReduce speculatively backups the straggler task on another node to execute aiming to reduce the job's finish time. Although there have been many speculative execution strate-gies in heterogeneous environments, they all do not consider the impact of dynamic system load on the running time of tasks. They may make mistakes in determining stragglers. In our paper, we propose a novel speculative execution strategy in heterogeneous environments, ERUL, to im-prove the estimation of tasks' rest time. ERUL also overcomes some drawbacks of LATE that mislead the speculative execution in some cases. The experimental result indicates that, our Hadoop-ERUL strategy not only works more accurately in the estimation of running tasks' remaining execution time, but also reduces 26% job's running time compared to Hadoop-LATE.","PeriodicalId":235467,"journal":{"name":"2014 Sixth International Symposium on Parallel Architectures, Algorithms and Programming","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130360920","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Wide Area Power System Fault Detection Using Compressed Sensing to Reduce the WAN Data Traffic","authors":"Bei Li, Jinghan He, T. Yip, Jiangchen Li","doi":"10.1109/PAAP.2014.28","DOIUrl":"https://doi.org/10.1109/PAAP.2014.28","url":null,"abstract":"With the increasingly complex power system, wide area protection, using global data obtained from different substations through communications, has been a hot research topic for some time. However, the overall transmission of large amounts of data will cause communication network congestion, which will lead to delay and loss of data. Therefore building an algorithm which can make use of a reduced number of global data to identify the fault area is very useful. This paper proposes a down-sampling matrix to reduce the original data. For example, a protection system requiring 240 feature points of voltage data, if using the down-sampling matrix, will need only a minimum of 24 points, and still has a high probability to identify the fault zone. Simulation results show that when the data size M > 0.3, the result of classifying adjacent bus fault point is credible (greater than 60%), and when the data size M > 0.05, the result of classifying the non-adjacent bus fault point is credible (greater than 72%).","PeriodicalId":235467,"journal":{"name":"2014 Sixth International Symposium on Parallel Architectures, Algorithms and Programming","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123808017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Runtime Framework for GPGPU","authors":"Shang-Chieh Lin, Yarsun Hsu","doi":"10.1109/PAAP.2014.18","DOIUrl":"https://doi.org/10.1109/PAAP.2014.18","url":null,"abstract":"A runtime framework for GPGPU is proposed. It provides a unified interface for applications to easily take advantage of the various computation powers on a heterogeneous environment. Multiple devices and platforms, such as CUDA and OpenCL can be utilized at the same time to achieve a better performance.","PeriodicalId":235467,"journal":{"name":"2014 Sixth International Symposium on Parallel Architectures, Algorithms and Programming","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127770990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Notice of Violation of IEEE Publication PrinciplesEfficient FPGA-mapping of 1024 point FFT Pipeline SDF Processor","authors":"I. Qureshi, F. Qureshi, Ghulam Muhammad Shaikh","doi":"10.1109/PAAP.2014.70","DOIUrl":"https://doi.org/10.1109/PAAP.2014.70","url":null,"abstract":"In this paper the efficient mapping of pipeline single path delay feedback (SDF) fast Fourier transform (FFT) processors to FPGAs is considered. By paying special attention to how the design can efficiently be mapped to the course grained hardware structure of a target field programmable gate array (FPGA) better implementation results can be obtained.This is illustrated by mapping a R22 SDF FFT processor, targeted towards Virtex-4 .The FPGA mapping of these designs have been explored in detail. Algorithmic transformations that provide a better mapping is proposed, resulting in implementation achievements that by far outperform earlier published work.For Virtex-4 the results show a better throughput per slice and lesser latency , still not using more memory or DSP48 resources.","PeriodicalId":235467,"journal":{"name":"2014 Sixth International Symposium on Parallel Architectures, Algorithms and Programming","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131344417","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Design and Implementation for File Monitor System Based on Windows Driver","authors":"Xiao-Jun Tang, Ying Lu, Na Liu","doi":"10.1109/PAAP.2014.31","DOIUrl":"https://doi.org/10.1109/PAAP.2014.31","url":null,"abstract":"Security access of enterprise production data file and design file is critical to ensure the enterprise interests. This paper puts forward the method of using windows driver combined with API function to write the virtual equipment articulated driver. The method can track the enterprise internal file access, at the same time make detailed monitoring records to the server. The administrator can monitor file operation through records. Practice shows that the file monitoring system has characteristics of low overhead, security and effectively.","PeriodicalId":235467,"journal":{"name":"2014 Sixth International Symposium on Parallel Architectures, Algorithms and Programming","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131949703","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Efficient Parallelization of a Two-List Algorithm for the Subset-Sum Problem on a Hybrid CPU/GPU Cluster","authors":"Letian Kang, Lanjun Wan, Kenli Li","doi":"10.1109/PAAP.2014.44","DOIUrl":"https://doi.org/10.1109/PAAP.2014.44","url":null,"abstract":"Recently, hybrid CPU/GPU cluster has been widely used to deal with compute-intensive problems, such as the subset-sum problem. The two-list algorithm is a well known approach to solve the problem. However, a hybrid MPI-CUDA dual-level parallelization of the algorithm on the cluster is not straightforward. The key challenge is how to allocate the most suitable workload to each node to achieve good load balancing between nodes and minimize the communication overhead. Therefore, this paper proposes an effective workload distribution scheme which aims to reasonably assign workload to each node. According to this scheme, an efficient MPI-CUDA parallel implementation of a two-list algorithm is presented. A series of experiments are conducted to compare the performance of the hybrid MPI-CUDA implementation with that of the best sequential CPU implementation, the single-node CPU-only implementation, the single-node GPU-only implementation, and the hybrid MPI-OpenMP implementation with same cluster configuration. The results show that the proposed hybrid MPI-CUDA implementation not only offers significant performance benefits but also has excellent scalability.","PeriodicalId":235467,"journal":{"name":"2014 Sixth International Symposium on Parallel Architectures, Algorithms and Programming","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134622258","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Algorithmic Aspects for Bi-Objective Multiple-Choice Hardware/Software Partitioning","authors":"Wenjun Shi, W. Jigang, S. Lam, T. Srikanthan","doi":"10.1109/PAAP.2014.42","DOIUrl":"https://doi.org/10.1109/PAAP.2014.42","url":null,"abstract":"Designing embedded systems has become a challengingprocess due to the increasing complexity of the applications. In addition, there is a need to meet multiple conflicting constraints such as speed, power and cost. These factors have led to an explosion in the design space as each task in the application can have various implementation options (software and a range of hardware customizations), where each implementation option is associated with different speed, power and cost. In this paper, we propose hardware-software (HW/SW) partitioning algorithms that are capable of managing the large design space by taking into account the multiple implementation choices. In particular, we focus on multiple-choice HW/SW partitioning with the following objectives: minimizing execution time and power consumption, while meeting the area constraint. Two algorithms will be presented: 1) a heuristic method that is based on the bi-objective knapsack problem to rapidly generate an approximate solution, 2) a dynamic programming algorithm to calculate the exact solution. Simulation results show that the heuristic method produces results that are very close to the exact ones.","PeriodicalId":235467,"journal":{"name":"2014 Sixth International Symposium on Parallel Architectures, Algorithms and Programming","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116314604","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A DAG Task Scheduling Scheme on Heterogeneous Computing Systems Using Invasive Weed Optimization Algorithm","authors":"Kenli Li, Shuai Li, Yuming Xu, Zhaoxin Xie","doi":"10.1109/PAAP.2014.34","DOIUrl":"https://doi.org/10.1109/PAAP.2014.34","url":null,"abstract":"Efficient task scheduling is crucial to heterogeneous cluster performance. And various scheduling methods based on random search technique have been proposed for both homogeneous and heterogeneous cluster systems. However, most of these methods have high computational overhead and poor convergence. Invasive weed optimization algorithm (IWO) is a novel bionic intelligent optimization algorithm that has fast convergence rate and easier implementation than traditional genetic algorithm (GA) based algorithm. In this paper, an IWO task scheduling (IWOTS) algorithm is proposed for heterogeneous cluster system. To the best of our knowledge, this study is the first time to apply IWO to discrete task scheduling problems. Extensive simulation experiment results show that IWOTS generally exhibits outstanding convergence performance and could produce an optimal scheduling strategy.","PeriodicalId":235467,"journal":{"name":"2014 Sixth International Symposium on Parallel Architectures, Algorithms and Programming","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128441173","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yongrui Cui, Hang Zhao, Jun Wu, Zhiyuan Su, Mingchu Li
{"title":"A Sensitive and Robust Grid Reputation System Based on Rating of Recommenders","authors":"Yongrui Cui, Hang Zhao, Jun Wu, Zhiyuan Su, Mingchu Li","doi":"10.1109/PAAP.2014.15","DOIUrl":"https://doi.org/10.1109/PAAP.2014.15","url":null,"abstract":"In this paper, we propose a sensitive and robust reputation system for service grid environments. A punishment factor is introduced to express the subjective opinion of evaluators and destroy the reputation of bad performers rapidly, which improves the sensitivity of the reputation system. By evaluating the reputation of recommenders, our solution filters out dishonest recommendations during the process of trust evaluation, thus making the reputation system more robust against vicious attacks launched by dishonest recommenders. Moreover, the introduction of inter-organizational trust enables the proposed reputation system to be more suitable for grid environments that span multiple autonomous organizations. Experimental results show that the proposed reputation system copes with changing behaviors of grid participants with high sensitivity and accuracy and works well even in extremely harsh environments full of dishonest recommenders.","PeriodicalId":235467,"journal":{"name":"2014 Sixth International Symposium on Parallel Architectures, Algorithms and Programming","volume":"203 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121717270","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Two-Step Similarity Ranking Scheme for Image Retrieval","authors":"Di Wu, Jun Wu, Mingyu Lu, Chun-Li Wang","doi":"10.1109/PAAP.2014.26","DOIUrl":"https://doi.org/10.1109/PAAP.2014.26","url":null,"abstract":"similarity ranking is one of the keys of a content-based image retrieval (CBIR) system. Among various methods, manifold ranking (MR) is popular for its application to relevance feedback in CBIR. Most existing MR methods only take the visual features into account in the similarity ranking, however, which is not accurate enough to reflect the intrinsic semantic structure of a given image database. In this paper, we propose a two-step similarity ranking scheme that aims to preserve both visual and semantic resemblance in the similarity ranking. Concretely, in the first step it derives an initial visual-based similarity rank through a self-tuning MR solution. In particular, the Gaussian kernel used in our scheme is refined by using a point-wise bandwidth. In the second step, the rank of each database image is further adjusted to achieve semantic consistency by mining the query log. An empirical study shows that using two-step similarity ranking in CBIR is beneficial, and the proposed scheme is more effective than some existing MR approaches.","PeriodicalId":235467,"journal":{"name":"2014 Sixth International Symposium on Parallel Architectures, Algorithms and Programming","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121395302","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}