{"title":"Performance evaluation of the SGI Altix 3700","authors":"T. Dunigan, J. Vetter, P. Worley","doi":"10.1109/ICPP.2005.61","DOIUrl":"https://doi.org/10.1109/ICPP.2005.61","url":null,"abstract":"SGI recently introduced the Altix 3700. In contrast to previous SGI systems, the Altix uses a modified version of the open source Linux operating system and the latest Intel IA-64 processors, the Intel Itanium2. The Altix also uses the next generation SGI interconnect, Numalink3 and NUMAflex, which provides a NUMA, cache-coherent, shared memory, multi-processor system. In this paper, we present a performance evaluation of the SGI Altix using microbenchmarks, kernels, and mission applications. We find that the Altix provides many advantages over other non-vector machines and it is competitive with the Cray XI on a number of kernels and applications. The Altix also shows good scaling, and its globally shared memory allows users convenient parallelization with OpenMP or pthreads.","PeriodicalId":440948,"journal":{"name":"2005 International Conference on Parallel Processing (ICPP'05)","volume":"212 Pt B 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117081922","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":"Fault-tolerant routing in meshes/tori using planarly constructed fault blocks","authors":"D. Xiang, Jiaguang Sun, Jie Wu, K. Thulasiraman","doi":"10.1109/ICPP.2005.40","DOIUrl":"https://doi.org/10.1109/ICPP.2005.40","url":null,"abstract":"A few faulty nodes can make an n-dimensional mesh or torus network unsafe for fault-tolerant routing methods based on the block fault model, where the whole system (n-dimensional space) forms a fault block. A new concept, called extended local safety information in meshes or tori, is proposed to guide fault-tolerant routing, and classifies fault-free nodes inside 2-dimensional planes. Many nodes globally marked as unsafe become locally enabled inside 2-dimensional planes. A fault-tolerant routing algorithm based on extended local safety information is proposed for k-ary n-dimensional meshes/tori. Our method does not need to disable any fault-free nodes, unlike many previous methods, and this enhances the computational power of the system and improves performance of the routing algorithm greatly. All fault blocks are constructed inside 2-dimensional planes rather than in the whole system. Extensive simulation results are presented and compared with the previous methods.","PeriodicalId":440948,"journal":{"name":"2005 International Conference on Parallel Processing (ICPP'05)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129489748","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":"Ferry: an architecture for content-based publish/subscribe services on P2P networks","authors":"Yingwu Zhu, Yimin Hu","doi":"10.1109/ICPP.2005.41","DOIUrl":"https://doi.org/10.1109/ICPP.2005.41","url":null,"abstract":"Leveraging DHTs (distributed hash table), we propose Ferry, an architecture for content-based publish/subscribe services. With its novel design in subscription installation, subscription management and event delivery algorithm, Ferry can serve as a scalable platform to host any and many content-based publish/subscribe services: any publish/subscribe service with a unique scheme can run on top of Ferry, and many publish/subscribe services can run together on top of Ferry. For each of the publish/subscribe services running on top of Ferry, Ferry does not need to maintain or dynamically generate any dissemination tree. Instead, it exploits the embedded trees in DHTs such as Chord to deliver events, thereby imposing little overhead. By delivering events along DHT links, Ferry has two main advantages: (1) it eliminates the cost in construction and maintenance of the dissemination trees; (2) it allows further optimization, i.e., the DHT link maintenance messages could be piggybacked onto the event delivery messages to reduce the maintenance cost which is inherent and nontrivial in DHTs. Moreover, Ferry can support a publish/subscribe scheme with a very large number of event attributes.","PeriodicalId":440948,"journal":{"name":"2005 International Conference on Parallel Processing (ICPP'05)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126251629","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 new fault information model for fault-tolerant adaptive and minimal routing in 3-D meshes","authors":"Zhen Jiang, Jie Wu, Dajin Wang","doi":"10.1109/ICPP.2005.9","DOIUrl":"https://doi.org/10.1109/ICPP.2005.9","url":null,"abstract":"In this paper we rewrite Wang's Minimal-Connected-Component (MCC) model in 2D meshes without using global information so that not only the existence of a minimal path can be ensured at the source, but also such a path can be formed by routing decisions at intermediate nodes along the path. We extend this MCC model and the corresponding routing in 2D meshes to 3D meshes. It is based on our early work on fault tolerant adaptive and minimal routing and the boundary information model in 3D meshes. We study fault tolerant adaptive and minimal routing from the source and the destination and consider the positions of the source and destination when the new faulty components are constructed. Specifically, all faulty nodes will be contained in some disjoint faulty components and a healthy node will be included in a faulty component only if using it in the routing will definitely cause a non-minimal routing path. A sufficient and necessary condition is proposed for the existence of the minimal routing path in the presence of our faulty components. Based on such a condition, the corresponding routing will guarantee a minimal path whenever it exists.","PeriodicalId":440948,"journal":{"name":"2005 International Conference on Parallel Processing (ICPP'05)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121381711","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":"Filter decomposition for supporting coarse-grained pipelined parallelism","authors":"Wei Du, G. Agrawal","doi":"10.1109/ICPP.2005.42","DOIUrl":"https://doi.org/10.1109/ICPP.2005.42","url":null,"abstract":"We consider the filter decomposition problem in supporting coarse-grained pipelined parallelism. This form of parallelism is suitable for data-driven applications in scenarios where the data is available on a repository or a data collection site on the Internet, and the final results are required on a user's desktop. A filter decomposition algorithm takes an application divided into a sequence of atomic filters, and maps them into a given number of filters. We propose three polynomial time algorithms for this problem. Dynamic programming algorithm MIN/spl I.bar/ONETRIP optimizes the one trip cost for a packet passing through the pipeline. MIN/spl I.bar/BOTTLENECK is also a dynamic programming algorithm, which minimizes the time spent on the bottleneck stage. Finally, MIN/spl I.bar/TOTAL is an approximate greedy algorithm which tries to minimize the total execution time. The results show that our heuristic algorithms work quite well in practice, with the possible exception of MIN/spl I.bar/ONETRIP when the number of packets is large. However, the relative performance of the algorithms is not always what we would expect, because of the certain limitations in how we model the problem.","PeriodicalId":440948,"journal":{"name":"2005 International Conference on Parallel Processing (ICPP'05)","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116365861","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":"SAREC: a security-aware scheduling strategy for real-time applications on clusters","authors":"T. Xie, X. Qin, A. Sung","doi":"10.1109/ICPP.2005.68","DOIUrl":"https://doi.org/10.1109/ICPP.2005.68","url":null,"abstract":"Security requirements of security-critical real-time applications must be met in addition to satisfying timing constraints. However, conventional real-time scheduling algorithms ignore the applications' security requirements. In recognition that an increasing number of applications running on clusters demand both real-time performance and security, we investigate the problem of scheduling a set of independent real-time tasks with various security requirements. We propose a security overhead model that is capable of measuring security overheads incurred by security-critical tasks. Further, we propose a security-aware scheduling strategy, or SAREC, which integrates security requirements into scheduling for real-time applications by employing our security overhead model. To evaluate the effectiveness of SAREC, we implement a security-aware real-time scheduling algorithm (SAREC-EDF), which incorporates the earliest deadline first (EDF) scheduling algorithm into SAREC Extensive simulation experiments show that SAREC-EDF significantly improves overall system performance over three baseline scheduling algorithms (variations of EDF) by up to 72.55%.","PeriodicalId":440948,"journal":{"name":"2005 International Conference on Parallel Processing (ICPP'05)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125807852","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}
Doruk Bozdag, F. Özgüner, E. Ekici, Ümit V. Çatalyürek
{"title":"A task duplication based scheduling algorithm using partial schedules","authors":"Doruk Bozdag, F. Özgüner, E. Ekici, Ümit V. Çatalyürek","doi":"10.1109/ICPP.2005.15","DOIUrl":"https://doi.org/10.1109/ICPP.2005.15","url":null,"abstract":"We propose a novel replication-based two-phase scheduling algorithm designed to achieve DAG scheduling with small makespans and high efficiency. In the first phase, the schedule length of the application is minimized using a novel approach that utilizes partial schedules. In the second phase, the number of processors required is minimized by eliminating and merging these partial schedules. Experimental results on random DAGs show that the makespans generated by the proposed algorithm are slightly better than those generated by the well known CPFD algorithm whereas the number of processors used is less than half of what is needed by CPFD solutions.","PeriodicalId":440948,"journal":{"name":"2005 International Conference on Parallel Processing (ICPP'05)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121833259","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":"Locality-aware randomized load balancing algorithms for DHT networks","authors":"Haiying Shen, Chengzhong Xu","doi":"10.1109/ICPP.2005.49","DOIUrl":"https://doi.org/10.1109/ICPP.2005.49","url":null,"abstract":"Structured P2P overlay networks based on a consistent hashing function have an aftermath load balance problem that needs to be dealt with. A load balancing method should take into account both proximity and dynamic features of DHTs, Randomized matching between heavily loaded nodes with lightly loaded nodes can deal with the dynamic feature. But current randomized methods are unable to consider physical proximity of the node simultaneously. There are locality-aware methods that rely on an additional logical network to capture the physical locality in load balancing. Due to the cost for network construction and maintenance, these locality-aware algorithms can hardly deal with DHTs with churn. This paper presents a locality-aware randomized load balancing algorithm to deal with both of the proximity and dynamic features of DHTs. We introduce a factor of randomness in the probing process in a range of proximity to deal with the DHT churn. We further improve the randomized load balancing efficiency by d-way probing. Simulation results show the superiority of a locality-aware 2-way randomized load balancing in DHTs, in comparison with other pure random policies and locality-aware sequential algorithms. In DHTs with churn, it performs no worse than the best churn resilient algorithm.","PeriodicalId":440948,"journal":{"name":"2005 International Conference on Parallel Processing (ICPP'05)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133558758","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":"Differentiated search in hierarchical peer-to-peer networks","authors":"Chen Wang, Li Xiao, Pei Zheng","doi":"10.1109/ICPP.2005.32","DOIUrl":"https://doi.org/10.1109/ICPP.2005.32","url":null,"abstract":"Although the original intent of the peer-to-peer (P2P) concept is to treat each participant equally, heterogeneity widely exists in deployed P2P networks. In this paper, we suggest to improve the search efficiency of P2P network by utilizing the query answering heterogeneity. Our proposed differentiated search (DiffSearch) algorithm can evolve an unstructured P2P network to a two-tier hierarchical structure, where peers with high query answering capabilities are grouped in the first tier, which has higher priority to be queried than the second tier. Because the query answering capability is extremely unbalanced among peers, a high query success ratio can be achieved by querying only a small portion of the network. The search traffic is dramatically reduced due to the shrunken search space. Our trace analysis and simulation show that the DiffSearch algorithm can save up to 60% of search traffic.","PeriodicalId":440948,"journal":{"name":"2005 International Conference on Parallel Processing (ICPP'05)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128544007","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":"Timing high performance kernels through empirical compilation","authors":"R. C. Whaley, D. Whalley","doi":"10.1109/ICPP.2005.77","DOIUrl":"https://doi.org/10.1109/ICPP.2005.77","url":null,"abstract":"There are a few application areas, which remain almost untouched by the historical and continuing advancement of compilation research. For the extremes of optimization required for high performance computing on one end, and embedded systems at the opposite end of the spectrum, many critical routines are still hand-tuned, often directly in assembly. At the same time, architecture implementations are performing an increasing number of compiler-like transformations in hardware, making it harder to predict the performance impact of a given series of optimizations applied at the ISA level. These issues, together with the rate of hardware evolution dictated by Moore's Law, make it almost impossible to keep key kernels running at peak efficiency. Automated empirical systems, where direct timings are used to guide optimization, have provided the most successful response to these challenges. This paper describes our approach to performing empirical optimization, which utilizes a low-level iterative compilation framework specialized for optimizing high performance computing kernels. We present results showing that this approach can not only provide speedups over traditional optimizing compilers, but can improve overall performance when compared to the best hand-tuned kernels selected by the empirical search of our well-known ATLAS package.","PeriodicalId":440948,"journal":{"name":"2005 International Conference on Parallel Processing (ICPP'05)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133813850","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}