2017 National Conference on Parallel Computing Technologies (PARCOMPTECH)最新文献

{"title":"Accelerated spam filtering with enhanced KMP algorithm on GPU","authors":"Venkata Krishna Pavan Kalubandi, M. Varalakshmi","doi":"10.1109/PARCOMPTECH.2017.8068335","DOIUrl":"https://doi.org/10.1109/PARCOMPTECH.2017.8068335","url":null,"abstract":"Spam filtering is one of the most important applications in email services that has become increasingly sophisticated due to the enormous usage of Internet. Traditionally, spam filters have been implemented on the CPU with a pattern matching algorithm. In this paper, an accelerated spam filtering mechanism that uses GPUs is presented. The filtering process utilizes an enhanced version of Knuth Morris Pratt pattern matching algorithm that outperforms the serial versions up to 12x and also performs more efficiently compared to other parallel versions. The parallel algorithm is to develop and advanced keyword based Naïve Bayesian classifier speeds up the spam filtering up to 2 times compared to CPU.","PeriodicalId":219266,"journal":{"name":"2017 National Conference on Parallel Computing Technologies (PARCOMPTECH)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114954287","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":"An improved firefly algorithm for permutation routing in baseline multistage interconnection network","authors":"Abhay B. Rathod, S. M. Gulhane","doi":"10.1109/PARCOMPTECH.2017.8068332","DOIUrl":"https://doi.org/10.1109/PARCOMPTECH.2017.8068332","url":null,"abstract":"This paper present the parallelization of firefly algorithm for permutation routing in baseline multistage interconnection network. The proposed parallel firefly algorithm employs a self routing approach to route the permutation in baseline network. The objective of this paper is as follows (i) to improve serial firefly algorithm to parallel one for better utilization of multi core/ many core processor. (ii) to use speedup, quality of solution and efficiency as performance metric in improved firefly algorithm for optimal permutation routing in baseline network. (iii) the analysis of the simulation results on firefly algorithm is compared with other algorithms. Simulation results demonstrate that the proposed parallel firefly algorithm for permutation routing in baseline network outperforms known sequential and parallel algorithm in terms of speedup, efficiency and quality solution.","PeriodicalId":219266,"journal":{"name":"2017 National Conference on Parallel Computing Technologies (PARCOMPTECH)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127955091","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":"Identifying pitfalls in automatic parallelization of NAS parallel benchmarks","authors":"S. Prema, R. Jehadeesan, B. K. Panigrahi","doi":"10.1109/PARCOMPTECH.2017.8068329","DOIUrl":"https://doi.org/10.1109/PARCOMPTECH.2017.8068329","url":null,"abstract":"This paper provides an examination of OpenMP based auto-parallelizers and their limitations encountered during parallelization of NAS parallel benchmarks. It also elucidates the issues faced by the parallelizers during parallelization and the resolutions to overcome the problems. Compute-intensive loops are pinpointed using Gprof and the problematic loops within the hotspot area were recognized. Our work concentrates on identifying the pitfalls within the located hotspots and rendering solution in such cases. Analysis on measured speedup and its reasons are well illustrated. This paper underlines the need of a user-interactive environment that highlights the problems evoked during parallelization. It also underscores the obligation for minimal manual intervention concerning coding changes to resolve the problematic code section and make them amenable to parallelization.","PeriodicalId":219266,"journal":{"name":"2017 National Conference on Parallel Computing Technologies (PARCOMPTECH)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117331089","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":"Performance comparison of various STM concurrency control protocols using synchrobench","authors":"Ajay Singh, Sathya Peri, G. Monika, Anila Kumari","doi":"10.1109/PARCOMPTECH.2017.8068330","DOIUrl":"https://doi.org/10.1109/PARCOMPTECH.2017.8068330","url":null,"abstract":"Writing concurrent programs for shared memory multiprocessor systems is a nightmare. This hinders users to exploit the full potential of multiprocessors. STM (Software Transactional Memory) is a promising concurrent programming paradigm which addresses woes of programming for multiprocessor systems. In this paper, we implement BTO (Basic Timestamp Ordering), SGT (Serialization Graph Testing) and MVTO(Multi-Version Time-Stamp Ordering) concurrency control protocols and build an STM(Software Transactional Memory) library to evaluate the performance of these protocols. The deferred write approach is followed to implement the STM. A SET data structure is implemented using the transactions of our STM library. And this transactional SET is used as a test application to evaluate the STM. The performance of the protocols is rigorously compared against the linked-list module of the Synchrobench benchmark. Linked list module implements SET data structure using lazy-list, lock-free list, lock-coupling list and ESTM (Elastic Software Transactional Memory). Our analysis shows that for a number of threads greater than 60 and update rate 70%, BTO takes (17% to 29%) and (6% to 24%) less CPU time per thread when compared against lazy-list and lock-coupling list respectively. MVTO takes (13% to 24%) and (3% to 24%) less CPU time per thread when compared against lazy-list and lock-coupling list respectively. BTO and MVTO have similar per thread CPU time. BTO and MVTO outperform SGT by 9% to 36%.","PeriodicalId":219266,"journal":{"name":"2017 National Conference on Parallel Computing Technologies (PARCOMPTECH)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126341007","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":"Average end-to-end delay of customised ZigBee stack","authors":"A. Narmada, P. S. Rao","doi":"10.1109/PARCOMPTECH.2017.8068333","DOIUrl":"https://doi.org/10.1109/PARCOMPTECH.2017.8068333","url":null,"abstract":"Zigbee protocol supports long range and reliable communication with reasonable data rates suitable for WPAN communication and hence it is chosen for experimentation in the proposed work. But unfortunately, Different devices of a WPAN may use different types of protocols, the zigbee protocol may not be adequate to control all the devices of WPAN. There are different protocols for realising WPAN. It is chosen to modify ZigBee stack in order to incorporate the features of common communication protocol so as to enable the consumer electronics share resources and communicate among themselves leading to a virtual control network. As the internet is most commonly used communication network in the user community, the protocols of internet are studied to find the suitability in channel access and routing strategies in order to implement these protocols in the customised ZigBee stack. After a thorough research ZigBee stack is modified with appropriate protocols at respective layers with the addition of a new layer i.e. adaptation layer between network and application layers. The design of this middleware is presented and the results are published [21]. This work presents the mathematical modelling of the average end-to-end delay of modified ZigBee stack, christened ZI stack. Both the stacks viz., ZI and ZigBee are also compared w.r.t average end-to-end delay.","PeriodicalId":219266,"journal":{"name":"2017 National Conference on Parallel Computing Technologies (PARCOMPTECH)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129572251","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":"BDPGx — A big data platform for graph-based pharmacogenomics data","authors":"P. Alluri, Janaki Chintalapati, Priyanka Sharma, N. Supriya Pal, S. Shekhar, Prahlada Rao B.B.","doi":"10.1109/PARCOMPTECH.2017.8068334","DOIUrl":"https://doi.org/10.1109/PARCOMPTECH.2017.8068334","url":null,"abstract":"Pharmacogenomics studies are widely adopted in clinical practices and it helps in understanding the effect of drug and its dosage based on individual's genetic makeup. The pharmacogenomics data available in open repositories are used to find the molecular associations between genes, pathways, diseases and the drug dosage effects. With the advent of various sequencing projects, the data deposited in the repositories are voluminous, multidimensional and are of different formats. The heterogeneous data need to be integrated and visualized in a graphical format to gain meaningful information. We developed a big data platform for querying and visualization of pharmacogenomics data stored in the form of graphs. Initially, the data related to genes, its related pathways and diseases, drugs and chemicals are integrated using Neo4j graph database. A web application is developed to provide an easy to use interface for querying this integrated database. The results are given back in the form of graphs and downloadable text format. The platform is scalable to integrate new databases and extensible to add more properties.","PeriodicalId":219266,"journal":{"name":"2017 National Conference on Parallel Computing Technologies (PARCOMPTECH)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124063550","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":"Significance of hierarchical and partitioning based clustering in grouping aware data placement for data intensive applications","authors":"S. Vengadeswaran, S. Balasundaram","doi":"10.1109/PARCOMPTECH.2017.8068331","DOIUrl":"https://doi.org/10.1109/PARCOMPTECH.2017.8068331","url":null,"abstract":"Recent development and exponential growth in the field of IT generates large volume of data every day in a variety of domains such as Social networks, Health care, Government sectors etc. These data are voluminous, varied and ever increasing at an unprecedented pace which makes storage and computing a mammoth task. Generally the time taken to execute a query and return the results, increases exponentially as the amount of data increases leading to more waiting times on the user. This processing inability has led to the use of Hadoop to analyze and gain insights from the data. With its distributed processing capability, Hadoop is considered as an efficient solution for query processing but it has its own limitation when the data to be processed exhibit interest locality. Generally it is observed that the data required for any query execution follows grouping behavior wherein only a part of the Big-Data set is utilized more often. Since Hadoop default data placement strategy (HDDPS) does not consider such grouping behavior among the dataset, it does not perform efficiently resulting in lacunas such as decreased local map execution, increased query execution time etc. Hence in this paper we experiment the significance of two most promising Matrix clustering techniques viz. partitioning and hierarchical in grouping aware data placement for improved performance. Both clustering techniques are separately applied over the user history log to obtain independent data groupings. These data groupings are interpreted and validated to extract the optimal data grouping for improved parallel execution. The proposed strategy was tested in 15 node Hadoop cluster. The results show an improved performance for Big-Data sets in heterogeneous distributed environment. It improves the data locality by 25.75% and reduces query execution time by 28% compared to HDDPS. Also Hierarchical based Matrix clustering shows a marginal improved performance over Partitioning based methods for queries exhibiting interest localities.","PeriodicalId":219266,"journal":{"name":"2017 National Conference on Parallel Computing Technologies (PARCOMPTECH)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114547467","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":"Parallel 2D and 3D acoustic modeling application for hybrid computing platform of PARAM Yuva II","authors":"A. Srivastava, A. Londhe, R. Rastogi","doi":"10.1109/PARCOMPTECH.2017.8068328","DOIUrl":"https://doi.org/10.1109/PARCOMPTECH.2017.8068328","url":null,"abstract":"In this paper, we report the performance of in-house developed parallel staggered grid finite-difference based 2D and 3D seismic acoustic modeling application using PARAM Yuva II. Seismic modeling is used for simulation of seismic wave propagation through earth's subsurface for generation of seismic data. The accuracy of the developed scheme is 4th order in space and 2nd order in time. MPI and OpenMP is used for parallelization. Parallelization model is based upon data decomposition strategy. Different optimization techniques are applied for performance enhancement. For 2D, performance gain of 5.25X is recorded using optimization techniques with respect to the baseline code (MPI + OpenMP). Speedup and efficiency of the application are studied using 16 to 1024 cores and results are presented in the paper. The 2D optimized application is also ported on Xeon Phi co-processor in native mode. The OpenMP scaling is performed on Xeon Phi and comparison with Xeon node results are discussed. 2D and 3D synthetic simple to complex geological models are used for applications outcome demonstration.","PeriodicalId":219266,"journal":{"name":"2017 National Conference on Parallel Computing Technologies (PARCOMPTECH)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126592118","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}