Pub Date : 2008-10-31DOI: 10.1109/CLUSTR.2008.4663793
N. Trebon, P. Beckman
Scientific simulation and modeling often aid in making critical decisions in such diverse fields as city planning, severe weather prediction and influenza modeling. In some of these situations the computations operate under strict deadlines, after which point the results may have very little value. In these cases of urgent computing, it is imperative that these computations begin execution as quickly as possible. The special priority and urgent compute environment (SPRUCE) is a framework designed to enable these high priority computations to quickly access computational grid resources through elevated batch queue priority. However, participating resources are allowed to decide locally how to respond to urgent requests. For instance, some may offer next-to-run status while others may preempt currently executing jobs to clear off the necessary nodes. However, the user is still faced with the problem of resource selection - namely, which resource (and corresponding urgent computing policy) provides the best probability of meeting a given deadline? This paper introduces a set of methodologies and heuristics aimed at generating an empirical-based probabilistic upper bound on the total turnaround time for an urgent computation. These upper bounds can then be used to guide the user in selecting a resource with greater confidence that their deadline will be met.
{"title":"Empirical-based probabilistic upper bounds for urgent computing applications","authors":"N. Trebon, P. Beckman","doi":"10.1109/CLUSTR.2008.4663793","DOIUrl":"https://doi.org/10.1109/CLUSTR.2008.4663793","url":null,"abstract":"Scientific simulation and modeling often aid in making critical decisions in such diverse fields as city planning, severe weather prediction and influenza modeling. In some of these situations the computations operate under strict deadlines, after which point the results may have very little value. In these cases of urgent computing, it is imperative that these computations begin execution as quickly as possible. The special priority and urgent compute environment (SPRUCE) is a framework designed to enable these high priority computations to quickly access computational grid resources through elevated batch queue priority. However, participating resources are allowed to decide locally how to respond to urgent requests. For instance, some may offer next-to-run status while others may preempt currently executing jobs to clear off the necessary nodes. However, the user is still faced with the problem of resource selection - namely, which resource (and corresponding urgent computing policy) provides the best probability of meeting a given deadline? This paper introduces a set of methodologies and heuristics aimed at generating an empirical-based probabilistic upper bound on the total turnaround time for an urgent computation. These upper bounds can then be used to guide the user in selecting a resource with greater confidence that their deadline will be met.","PeriodicalId":198768,"journal":{"name":"2008 IEEE International Conference on Cluster Computing","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127252238","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}
Pub Date : 2008-10-31DOI: 10.1109/CLUSTR.2008.4663773
Matthew J. Koop, J. K. Sridhar, D. Panda
A significant component of a high-performance cluster is the compute node interconnect. InfiniBand, is an interconnect of such systems that is enjoying wide success due to low latency (1.0-3.0 musec) and high bandwidth and other features. The Message Passing Interface (MPI) is the dominant programming model for parallel scientific applications. As a result, the MPI library and interconnect play a significant role in the scalability. These clusters continue to scale to ever-increasing levels making the role very important. As an example, the ldquoRangerrdquo system at the Texas Advanced Computing Center (TACC) includes over 60,000 cores with nearly 4000 InfiniBand ports. Previous work has shown that memory usage simply for connections when using the Reliable Connection (RC) transport of InfiniBand can reach hundreds of megabytes of memory per process at that level. To address these scalability problems a new InfiniBand transport, eXtended Reliable Connection, has been introduced. In this paper we describe XRC and design MPI over this new transport. We describe the variety of design choices that must be made as well as the various optimizations that XRC allows. We implement our designs and evaluate it on an InfiniBand cluster against RC-based designs. The memory scalability in terms of both connection memory and memory efficiency for communication buffers is evaluated for all of the configurations. Connection memory scalability evaluation shows a potential 100 times improvement over a similarly configured RC-based design. Evaluation using NAMD shows a 10% performance improvement for our XRC-based prototype for the jac2000 benchmark.
{"title":"Scalable MPI design over InfiniBand using eXtended Reliable Connection","authors":"Matthew J. Koop, J. K. Sridhar, D. Panda","doi":"10.1109/CLUSTR.2008.4663773","DOIUrl":"https://doi.org/10.1109/CLUSTR.2008.4663773","url":null,"abstract":"A significant component of a high-performance cluster is the compute node interconnect. InfiniBand, is an interconnect of such systems that is enjoying wide success due to low latency (1.0-3.0 musec) and high bandwidth and other features. The Message Passing Interface (MPI) is the dominant programming model for parallel scientific applications. As a result, the MPI library and interconnect play a significant role in the scalability. These clusters continue to scale to ever-increasing levels making the role very important. As an example, the ldquoRangerrdquo system at the Texas Advanced Computing Center (TACC) includes over 60,000 cores with nearly 4000 InfiniBand ports. Previous work has shown that memory usage simply for connections when using the Reliable Connection (RC) transport of InfiniBand can reach hundreds of megabytes of memory per process at that level. To address these scalability problems a new InfiniBand transport, eXtended Reliable Connection, has been introduced. In this paper we describe XRC and design MPI over this new transport. We describe the variety of design choices that must be made as well as the various optimizations that XRC allows. We implement our designs and evaluate it on an InfiniBand cluster against RC-based designs. The memory scalability in terms of both connection memory and memory efficiency for communication buffers is evaluated for all of the configurations. Connection memory scalability evaluation shows a potential 100 times improvement over a similarly configured RC-based design. Evaluation using NAMD shows a 10% performance improvement for our XRC-based prototype for the jac2000 benchmark.","PeriodicalId":198768,"journal":{"name":"2008 IEEE International Conference on Cluster Computing","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114888009","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}
Pub Date : 2008-10-31DOI: 10.1109/CLUSTR.2008.4663801
Takeshi Fukaya, Yusaku Yamamoto, Shaoliang Zhang
In this paper, we present a new approach to optimizing the blocking strategy for the householder QR decomposition. In high performance implementations of the householder QR algorithm, it is common to use a blocking technique for the efficient use of the cache memory. There are several well known blocking strategies like the fixed-size blocking and recursive blocking, and usually their parameters such as the block size and the recursion level are tuned according to the target machine and the problem size. However, strategies generated with this kind of parameter optimization constitute only a small fraction of all possible blocking strategies. Given the complex performance characteristics of modern microprocessors, non-standard strategies may prove effective on some machines. Considering this situation, we first propose a new universal model that can express a far larger class of blocking strategies than has been considered so far. Next, we give an algorithm to find a near-optimal strategy from this class using dynamic programming. As a result of this approach, we found an effective blocking strategy that has never been reported. Performance evaluation on the Opteron and Core2 processors show that our strategy achieves about 1.2 times speedup over recursive blocking when computing the QR decomposition of a 6000 times 6000 matrix.
{"title":"A dynamic programming approach to optimizing the blocking strategy for the Householder QR decomposition","authors":"Takeshi Fukaya, Yusaku Yamamoto, Shaoliang Zhang","doi":"10.1109/CLUSTR.2008.4663801","DOIUrl":"https://doi.org/10.1109/CLUSTR.2008.4663801","url":null,"abstract":"In this paper, we present a new approach to optimizing the blocking strategy for the householder QR decomposition. In high performance implementations of the householder QR algorithm, it is common to use a blocking technique for the efficient use of the cache memory. There are several well known blocking strategies like the fixed-size blocking and recursive blocking, and usually their parameters such as the block size and the recursion level are tuned according to the target machine and the problem size. However, strategies generated with this kind of parameter optimization constitute only a small fraction of all possible blocking strategies. Given the complex performance characteristics of modern microprocessors, non-standard strategies may prove effective on some machines. Considering this situation, we first propose a new universal model that can express a far larger class of blocking strategies than has been considered so far. Next, we give an algorithm to find a near-optimal strategy from this class using dynamic programming. As a result of this approach, we found an effective blocking strategy that has never been reported. Performance evaluation on the Opteron and Core2 processors show that our strategy achieves about 1.2 times speedup over recursive blocking when computing the QR decomposition of a 6000 times 6000 matrix.","PeriodicalId":198768,"journal":{"name":"2008 IEEE International Conference on Cluster Computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122509338","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}
Pub Date : 2008-10-31DOI: 10.1109/CLUSTR.2008.4663781
Shin'ichi Miura, Takayuki Okamoto, T. Boku, T. Hanawa, M. Sato
Although recent high-end interconnection network devices and switches provide a high performance/cost ratio, most of the small to medium sized PC clusters are still built on the commodity network, Ethernet. To enhance performance on commonly used gigabit Ethernet networks, link aggregation or binding technology is used. Currently, a Linux kernel is equipped with a software solution named linux channel bonding (LCB), which is based on IEEE802.3ad Link Aggregation technology. However, standard LCB has the problem of mismatching with the commonly used TCP protocol, which consequently implies several problems of both large latency and instability on bandwidth improvement. The fault-tolerant feature is also supported, but the usability is not sufficient. We have developed a new implementation similar to LCB named RI2N/DRV (redundant interconnection with inexpensive network with driver) for use on a gigabit Ethernet with a complete software stack that is very compatible with the TCP protocol. Our algorithm suppresses unnecessary ACK packets and retransmission of packets even in imbalanced network traffic and link failures on multiple links. It provides both high-bandwidth and fault-tolerant communication on multi-link gigabit Ethernet. We confirmed that this system improves the performance and reliability of the network, and our system can be applied to ordinary UNIX services such as NFS, without any modification of other modules.
{"title":"RI2N: High-bandwidth and fault-tolerant network with multi-link Ethernet for PC clusters","authors":"Shin'ichi Miura, Takayuki Okamoto, T. Boku, T. Hanawa, M. Sato","doi":"10.1109/CLUSTR.2008.4663781","DOIUrl":"https://doi.org/10.1109/CLUSTR.2008.4663781","url":null,"abstract":"Although recent high-end interconnection network devices and switches provide a high performance/cost ratio, most of the small to medium sized PC clusters are still built on the commodity network, Ethernet. To enhance performance on commonly used gigabit Ethernet networks, link aggregation or binding technology is used. Currently, a Linux kernel is equipped with a software solution named linux channel bonding (LCB), which is based on IEEE802.3ad Link Aggregation technology. However, standard LCB has the problem of mismatching with the commonly used TCP protocol, which consequently implies several problems of both large latency and instability on bandwidth improvement. The fault-tolerant feature is also supported, but the usability is not sufficient. We have developed a new implementation similar to LCB named RI2N/DRV (redundant interconnection with inexpensive network with driver) for use on a gigabit Ethernet with a complete software stack that is very compatible with the TCP protocol. Our algorithm suppresses unnecessary ACK packets and retransmission of packets even in imbalanced network traffic and link failures on multiple links. It provides both high-bandwidth and fault-tolerant communication on multi-link gigabit Ethernet. We confirmed that this system improves the performance and reliability of the network, and our system can be applied to ordinary UNIX services such as NFS, without any modification of other modules.","PeriodicalId":198768,"journal":{"name":"2008 IEEE International Conference on Cluster Computing","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123985606","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}
Pub Date : 2008-10-31DOI: 10.1109/CLUSTR.2008.4663767
K. Fürlinger, S. Moore
Several performance analysis tools support hybrid applications. Most originated as MPI profiling or tracing tools and OpenMP capabilities were added to extend the performance analysis capabilities for the hybrid parallelization case. In this paper we describe our experience with the other path to support both programming paradigms. Our starting point is a profiling tool for OpenMP called ompP that was extended to handle MPI related data. The measured data and the method of presentation follow our focus on the OpenMP side of the performance optimization cycle. For example, the existing overhead classification scheme of ompP was extended to cover time in MPI calls as a new type of overhead.
{"title":"OpenMP-centric performance analysis of hybrid applications","authors":"K. Fürlinger, S. Moore","doi":"10.1109/CLUSTR.2008.4663767","DOIUrl":"https://doi.org/10.1109/CLUSTR.2008.4663767","url":null,"abstract":"Several performance analysis tools support hybrid applications. Most originated as MPI profiling or tracing tools and OpenMP capabilities were added to extend the performance analysis capabilities for the hybrid parallelization case. In this paper we describe our experience with the other path to support both programming paradigms. Our starting point is a profiling tool for OpenMP called ompP that was extended to handle MPI related data. The measured data and the method of presentation follow our focus on the OpenMP side of the performance optimization cycle. For example, the existing overhead classification scheme of ompP was extended to cover time in MPI calls as a new type of overhead.","PeriodicalId":198768,"journal":{"name":"2008 IEEE International Conference on Cluster Computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126432411","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}
Pub Date : 2008-10-31DOI: 10.1109/CLUSTR.2008.4663758
J. Tilson, Mark S. C. Reed, R. Fowler
We report our experiences with using high-throughput techniques to run large sets of performance experiments on collections of grid accessible parallel computer systems for the purpose of deploying optimally compiled and configured scientific applications. In these environments, the set of variable parameters (compiler, link, and runtime flags; application and library options; partition size) can be very large, so running the performance ensembles is labor intensive, tedious, and prone to errors. Automating this process improves productivity, reduces barriers to deploying and maintaining multi-platform codes, and facilitates the tracking of application and system performance over time. We describe the design and implementation of our system for running performance ensembles and we use two case studies as the basis for evaluating the long term potential for this approach. The architecture of a prototype benchmarking system is presented along with results on the efficacy of the workflow approach.
{"title":"Workflows for performance evaluation and tuning","authors":"J. Tilson, Mark S. C. Reed, R. Fowler","doi":"10.1109/CLUSTR.2008.4663758","DOIUrl":"https://doi.org/10.1109/CLUSTR.2008.4663758","url":null,"abstract":"We report our experiences with using high-throughput techniques to run large sets of performance experiments on collections of grid accessible parallel computer systems for the purpose of deploying optimally compiled and configured scientific applications. In these environments, the set of variable parameters (compiler, link, and runtime flags; application and library options; partition size) can be very large, so running the performance ensembles is labor intensive, tedious, and prone to errors. Automating this process improves productivity, reduces barriers to deploying and maintaining multi-platform codes, and facilitates the tracking of application and system performance over time. We describe the design and implementation of our system for running performance ensembles and we use two case studies as the basis for evaluating the long term potential for this approach. The architecture of a prototype benchmarking system is presented along with results on the efficacy of the workflow approach.","PeriodicalId":198768,"journal":{"name":"2008 IEEE International Conference on Cluster Computing","volume":"70 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132150299","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}
Pub Date : 2008-10-31DOI: 10.1109/CLUSTR.2008.4663792
Kazuki Ohta, Hiroya Matsuba, Y. Ishikawa
Multiple processors or multi-core CPUs are now in common, and the number of processes running concurrently is increasing in a cluster. Each process issues contiguous I/O requests individually, but they can be interrupted by the requests of other processes if all the processes enter the I/O phase together. Then, I/O nodes handle these requests as non-contiguous. This increases the disk seek time, and causes performance degradation. To overcome this problem, a node-level request reordering architecture, called gather-arrange-scatter (GAS) architecture, is proposed. In GAS, the I/O requests in the same node are gathered and buffered locally. Then, those are arranged and combined to reduce the I/O cost at I/O nodes, and finally they are scattered to the remote I/O nodes in parallel. A prototype is implemented and evaluated using the BTIO benchmark. This system reduces up to 84.3% of the lseekO calls and reduces up to 93.6% of the number of requests at I/O nodes. This results in up to a 12.7% performance improvement compared to the non-arranged case.
{"title":"Gather-arrange-scatter: Node-level request reordering for parallel file systems on multi-core clusters","authors":"Kazuki Ohta, Hiroya Matsuba, Y. Ishikawa","doi":"10.1109/CLUSTR.2008.4663792","DOIUrl":"https://doi.org/10.1109/CLUSTR.2008.4663792","url":null,"abstract":"Multiple processors or multi-core CPUs are now in common, and the number of processes running concurrently is increasing in a cluster. Each process issues contiguous I/O requests individually, but they can be interrupted by the requests of other processes if all the processes enter the I/O phase together. Then, I/O nodes handle these requests as non-contiguous. This increases the disk seek time, and causes performance degradation. To overcome this problem, a node-level request reordering architecture, called gather-arrange-scatter (GAS) architecture, is proposed. In GAS, the I/O requests in the same node are gathered and buffered locally. Then, those are arranged and combined to reduce the I/O cost at I/O nodes, and finally they are scattered to the remote I/O nodes in parallel. A prototype is implemented and evaluated using the BTIO benchmark. This system reduces up to 84.3% of the lseekO calls and reduces up to 93.6% of the number of requests at I/O nodes. This results in up to a 12.7% performance improvement compared to the non-arranged case.","PeriodicalId":198768,"journal":{"name":"2008 IEEE International Conference on Cluster Computing","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133761549","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}
Pub Date : 2008-10-31DOI: 10.1109/CLUSTR.2008.4663804
D. Ren, D. Giannacopoulos, R. Suda
A new Dynamic Load Balancing (DLB) method for automatic performance tuning in parallel, adaptive, 3-D mesh refinement is developed based on study of characteristics of Finite Element Method (FEM) on electromagnetics with tetrahedra. On the top of existing DLB algorithms, the new design optimized the task pool location of each processing element (PE) and the initial data assignments in multiprocessor parallel architecture. To accomplish our method, we investigate it by applying the algorithm in implementations of parallel 3-D Hierarchical Tetrahedra and Octahedra (HTO) mesh refinement. By comparing the benchmark results derived from the performance measures of the new method with the performance results from other two existing DLB algorithms running the same HTO example geometric mesh refinement model and on the same parallel architecture, the benefits of the new method for achieving high performance parallel mesh refinement are demonstrated.
{"title":"An optimized Dynamic Load Balancing method for parallel 3-D mesh refinement for finite element electromagnetics with Tetrahedra","authors":"D. Ren, D. Giannacopoulos, R. Suda","doi":"10.1109/CLUSTR.2008.4663804","DOIUrl":"https://doi.org/10.1109/CLUSTR.2008.4663804","url":null,"abstract":"A new Dynamic Load Balancing (DLB) method for automatic performance tuning in parallel, adaptive, 3-D mesh refinement is developed based on study of characteristics of Finite Element Method (FEM) on electromagnetics with tetrahedra. On the top of existing DLB algorithms, the new design optimized the task pool location of each processing element (PE) and the initial data assignments in multiprocessor parallel architecture. To accomplish our method, we investigate it by applying the algorithm in implementations of parallel 3-D Hierarchical Tetrahedra and Octahedra (HTO) mesh refinement. By comparing the benchmark results derived from the performance measures of the new method with the performance results from other two existing DLB algorithms running the same HTO example geometric mesh refinement model and on the same parallel architecture, the benefits of the new method for achieving high performance parallel mesh refinement are demonstrated.","PeriodicalId":198768,"journal":{"name":"2008 IEEE International Conference on Cluster Computing","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114717134","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}
Pub Date : 2008-10-31DOI: 10.1109/CLUSTR.2008.4663785
K. Nakajima
In this work, parallel preconditioning methods based on ldquoHierarchical Interface Decomposition (HID)rdquo and hybrid parallel programming models were applied to finite-element based simulations of linear elasticity problems in media with heterogeneous material properties. Reverse Cuthill-McKee reordering with cyclic multicoloring (CM-RCM) was applied for parallelism through OpenMP. The developed code has been tested on the ldquoT2K Open Super Computer (Todai Combined Cluster)rdquo using up to 512 cores. Preconditioners based on HID provide a scalable performance and robustness in comparison to conventional localized block Jacobi preconditioners. Performance of Hybrid 4x4 parallel programming model is competitive with that of Flat MPI.
{"title":"Parallel multistage preconditioners by Hierarchical Interface Decomposition on “T2K Open Super Computer (Todai Combined Cluster)” with Hybrid parallel programming models","authors":"K. Nakajima","doi":"10.1109/CLUSTR.2008.4663785","DOIUrl":"https://doi.org/10.1109/CLUSTR.2008.4663785","url":null,"abstract":"In this work, parallel preconditioning methods based on ldquoHierarchical Interface Decomposition (HID)rdquo and hybrid parallel programming models were applied to finite-element based simulations of linear elasticity problems in media with heterogeneous material properties. Reverse Cuthill-McKee reordering with cyclic multicoloring (CM-RCM) was applied for parallelism through OpenMP. The developed code has been tested on the ldquoT2K Open Super Computer (Todai Combined Cluster)rdquo using up to 512 cores. Preconditioners based on HID provide a scalable performance and robustness in comparison to conventional localized block Jacobi preconditioners. Performance of Hybrid 4x4 parallel programming model is competitive with that of Flat MPI.","PeriodicalId":198768,"journal":{"name":"2008 IEEE International Conference on Cluster Computing","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117267084","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}
Pub Date : 2008-10-31DOI: 10.1109/CLUSTR.2008.4663800
Sylvain Guinepain, L. Gruenwald
Query response time is the number one metrics when it comes to database performance. Because of data proliferation, efficient access methods and data storage techniques have become increasingly critical to maintain an acceptable query response time. Retrieving data from disk is several orders of magnitude slower than retrieving it from memory, it is easy to see the direct correlation between query response time and the number of disk I/Os. One of the common ways to reduce disk I/Os and therefore improve query response time is database clustering, which is a process that partitions the database vertically (attribute clustering) and/or horizontally (record clustering). A clustering is optimized for a given set of queries. However in dynamic systems the queries change with time, the clustering in place becomes obsolete, and the database needs to be re-clustered dynamically. This paper presents an efficient algorithm for attribute clustering that dynamically and automatically generates attribute clusters based on closed item sets mined from the attributes sets found in the queries running against the database. The paper then discusses how this algorithm can be implemented using the cluster computing paradigm to reduce query response time even further through parallelism and data redundancy.
{"title":"Using cluster computing to support automatic and dynamic database clustering","authors":"Sylvain Guinepain, L. Gruenwald","doi":"10.1109/CLUSTR.2008.4663800","DOIUrl":"https://doi.org/10.1109/CLUSTR.2008.4663800","url":null,"abstract":"Query response time is the number one metrics when it comes to database performance. Because of data proliferation, efficient access methods and data storage techniques have become increasingly critical to maintain an acceptable query response time. Retrieving data from disk is several orders of magnitude slower than retrieving it from memory, it is easy to see the direct correlation between query response time and the number of disk I/Os. One of the common ways to reduce disk I/Os and therefore improve query response time is database clustering, which is a process that partitions the database vertically (attribute clustering) and/or horizontally (record clustering). A clustering is optimized for a given set of queries. However in dynamic systems the queries change with time, the clustering in place becomes obsolete, and the database needs to be re-clustered dynamically. This paper presents an efficient algorithm for attribute clustering that dynamically and automatically generates attribute clusters based on closed item sets mined from the attributes sets found in the queries running against the database. The paper then discusses how this algorithm can be implemented using the cluster computing paradigm to reduce query response time even further through parallelism and data redundancy.","PeriodicalId":198768,"journal":{"name":"2008 IEEE International Conference on Cluster Computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130659775","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：