Filters








127 Hits in 3.1 sec

Real-Time Performance Monitoring, Adaptive Control, and Interactive Steering of Computational Grids

Jeffrey S. Vetter, Daniel A. Reed
2000 The international journal of high performance computing applications  
Acknowledgments Virtue and Autopilot are the work of a dedicated team of researchers in the Pablo group: Ruth Aydt, Mario Medina, James Oly, Mario Pantano, Ben Schaeffer, Donald Schmidt, Eric Shaffer,  ...  management problem, we have developed PPFS II, an adaptive, intelligent portable parallel file system.  ...  Introduction The scope of high-performance computing is rapidly expanding from single parallel systems to clusters of heterogeneous sequential and parallel systems.  ... 
doi:10.1177/109434200001400407 fatcat:5dkamlg74ffq5jd37vm4dqpgly

Providing structure for medium-grained distributed object-based computation

R. Durrant, J. Sweeney, M. Fleury, A.C. Downton, A.E. Clark
1999 Proceedings of the International Symposium on Distributed Objects and Applications  
PPF and RMI have been wedded together in a software toolkit, providing a development environment which includes performance prediction, analysis, and guided code generation.  ...  The PPF processing model with asynchronous message-passing in a multi-threaded environment is in effect a version of the actor paradigm which is a dynamic form of encapsulated system.  ...  ORB-style processing is a continuation of a direction PPF had already taken towards encapsulated parallel systems.  ... 
doi:10.1109/doa.1999.794045 dblp:conf/doa/DurrantSFDC99 fatcat:mckx7y5ilfepznbklaelwdnh2a

Flexibility and performance of parallel file systems [chapter]

David Kotz, Nils Nieuwejaar
1996 Lecture Notes in Computer Science  
As we gain experience with parallel file systems, it becomes Ames under agreement numbers NCC 2-849 and NAG 2-936.  ...  The Portable Parallel File System (PPFS) [19] is a testbed for experimenting with parallel file-system issues.  ...  Yet few parallel file systems have been designed specifically to support a variety of high-level libraries.  ... 
doi:10.1007/3-540-61695-0_1 fatcat:vidtowrmird2lcki65kl56jf6y

pC++/streams

Jacob Gotwals, Suresh Srinivas, Dennis Gannon
1995 Proceedings of the fifth ACM SIGPLAN symposium on Principles and practice of parallel programming - PPOPP '95  
The design and implementation of portable, efficient, and expressive mechanisms for I/O on complex distributed data structures -such as found in adaptive parallel applications -is a challenging problem  ...  PC++, an object-parallel language. pC++lstreams is intended for developers of parallel programs requiring efficient high-level I/O abstractions for checkpointing, scientific visualization, and debugging  ...  Extensible File Systems (ELFS) Parallel tile PPFS, systems: CM-5 UIUC'S Panda Library, CMMD I/0, MPI-10, Jovian, Argonne's (and many others) PetSc/Chameleon pC++/streams SP-112 Vesta,  ... 
doi:10.1145/209936.209939 dblp:conf/ppopp/GotwalsSG95 fatcat:cf4ss775nvd6ziuccvay2ztkji

A Requirements Analysis for Parallel KDD Systems [chapter]

William A. Maniatty, Mohammed J. Zaki
2000 Lecture Notes in Computer Science  
Our analysis shows that parallel data mining solutions require the following components: parallel data mining algorithms, parallel and distributed data bases, parallel file systems, parallel I/O, tertiary  ...  This paper explores a migration path out of this bottleneck by considering an integrated hardware and software approach to parallelize data mining.  ...  PABLO, another SIO member group, has created the portable parallel file systems (PPFS II), designed to support efficient access of large data sets in scientific applications with irregular access patterns  ... 
doi:10.1007/3-540-45591-4_47 fatcat:ekp6fbwpufh3bd4y6o5e6syz2i

A Study of I/o in a pArallel Finite Element Groundwater Transport Code

David Mackay, G. Mahinthakumar, Ed D'Azevedo
1998 The international journal of high performance computing applications  
For example, the PABLO [14] performance analysis environment and PPFS (Portable Parallel File System) [16] are developed at University of Illinois.  ...  Several groups are performing active research in high performance portable parallel I/O solutions under the multi-agency Scalable I/O Initiative [9] .  ... 
doi:10.1177/109434209801200301 fatcat:wvvqpcurpzc3bkxijthdfv3bfu

A Flexible Multiagent Parallel File System for Clusters [chapter]

María S. Perez, Jesús Carretero, Félix García, José M. Peña, Víctor Robles
2003 Lecture Notes in Computer Science  
In this sense, parallel I/O is becoming one of the major topics in the area of high-performance systems.  ...  Many of these applications require access to huge data repositories and other I/O sources, being the I/O phase a bottleneck in the computing systems, due to its poor performance.  ...  Currently, there are different parallel file systems, such as Galley [11] , Parallel File System (PFS) [4] and Portable Parallel File System (PPFS) [8] , which offer highperformance services to access  ... 
doi:10.1007/3-540-44864-0_26 fatcat:fg3lyqybffd73cyzaveoekuxxi

High-Performance Techniques for Parallel I/O [chapter]

Avery Ching, Kenin Coloma, Wei-keng Liao, Alok Choudhary, Jianwei Li
2007 Handbook of Parallel Computing  
GPFS The General Parallel File System (GPFS) from IBM is a shared disk file system. It runs on both AIX and Linux and has been installed on numerous high-performance clusters such as ASCI Purple.  ...  In high-performance computing, it is typical for a file system to relax consistency semantics or for a file system that supports strict consistency to also support less strict consistency semantics.  ... 
doi:10.1201/9781420011296.ch35 fatcat:52nfmmdeunflpehwcbulkwhsly

Survey of Storage Systems for High-Performance Computing

2018 Supercomputing Frontiers and Innovations  
However, the overall application performance is often held back by I/O bottlenecks due to insufficient performance of file systems or I/O libraries for highly parallel workloads.  ...  In current supercomputers, storage is typically provided by parallel distributed file systems for hot data and tape archives for cold data.  ...  Even though it was designed primarily for local file systems, POSIX is widely used, even in parallel distributed file systems, and thus provides excellent portability.  ... 
doi:10.14529/jsfi180103 fatcat:hi3qctpl7rfvjgl53pxmqwqviy

An Iteration Aware Multidimensional Data Distribution Prototype for Computing Clusters

Baoqiang Yan, Philip Rhodes
2006 2006 IEEE International Conference on Cluster Computing  
Within the context of the Granite Scientific Database system, we created a new iteration aware data distribution system that accelerates data transfer between a data server and the client cluster.  ...  Disk and network latency must be taken into account when applying parallel computing to large multidimensional datasets because they can hinder performance by reducing the rate at which data can be fed  ...  Portability, if realized, is done through an abstract level atop multiple parallel file systems, such as ADIO in ROMIO [15] , a portable implementation of MPI-IO.  ... 
doi:10.1109/clustr.2006.311863 dblp:conf/cluster/YanR06 fatcat:q6kcyfusrzczhdcff2fff2oxt4

Input/output characteristics of scalable parallel applications

Phyllis E. Crandall, Ruth A. Aydt, Andrew A. Chien, Daniel A. Reed
1995 Proceedings of the 1995 ACM/IEEE conference on Supercomputing (CDROM) - Supercomputing '95  
Indeed, for many otherwise scalable parallel applications, input/output is emerging as a major performance bottleneck.  ...  The design of scalable input/output systems depends critically on the input/output requirements and access patterns for this emerging class of large-scale parallel applications.  ...  To quantify these eects, we ported the ESCAT code to PPFS, our portable parallel le system [8] , and congured the le system with write behind and global request aggregation policies.  ... 
doi:10.1145/224170.224396 dblp:conf/sc/CrandallACR95 fatcat:m7oxxjlcdbhjrpz5leyg2nm6gy

Bridging the Gap Between Parallel File Systems and Local File Systems: A Case Study with PVFS

Peng Gu, Jun Wang, Robert Ross
2008 2008 37th International Conference on Parallel Processing  
performance for parallel file systems, especially for those applications with partially overlapped access patterns.  ...  Parallel Virtual File System (PVFS) is chosen as an example.  ...  A number of research projects exist in the areas of parallel I/O and parallel file systems, such as PPFS [10] and PIOUS [16] .  ... 
doi:10.1109/icpp.2008.43 dblp:conf/icpp/GuWR08 fatcat:iojluemyynhk5ercfuozbezeeq

MAPFS: A flexible multiagent parallel file system for clusters

María S. Pérez, Jesús Carretero, Félix García, José M. Peña, Víctor Robles
2006 Future generations computer systems  
In this sense, parallel I/O is becoming one of the major topics in the area of high-performance systems.  ...  Many of these applications require access to huge data repositories and other I/O sources, making the I/O phase a bottleneck in the computing systems, due to its poor performance.  ...  Currently, there are different parallel file systems, such as Galley [25] , Parallel File System (PFS) [9] and Portable Parallel File System (PPFS) [16] , which offer high-performance services to access  ... 
doi:10.1016/j.future.2005.09.006 fatcat:5f5emwf23fgk7iqxdyifqeszsi

An experimental evaluation of I/O optimizations on different applications

M.A. Kandaswamy, M. Kandemir, A. Choudhary, D. Bernholdt
2002 IEEE Transactions on Parallel and Distributed Systems  
A combination of architectural and software solutions is normally needed to obtain good I/O performance.  ...  Index Terms-I/O optimizations, parallel architectures, I/O intensive applications, disk layout, collective I/O.  ...  PPFS [15] is a portable user-level parallel I/O library that uses a client/ server model.  ... 
doi:10.1109/tpds.2002.1019861 fatcat:2npd5thoy5detocy4g4dyrv7hq

An experimental evaluation of I/O optimizations on different applications

M.A. Kandaswamy, M. Kandemir, A. Choudhary, D. Bernholdt
2002 IEEE Transactions on Parallel and Distributed Systems  
A combination of architectural and software solutions is normally needed to obtain good I/O performance.  ...  Index Terms-I/O optimizations, parallel architectures, I/O intensive applications, disk layout, collective I/O.  ...  PPFS [15] is a portable user-level parallel I/O library that uses a client/ server model.  ... 
doi:10.1109/tpds.2002.1158267 fatcat:l6hxfd4mnrdmtpiedzx4osrwgy
« Previous Showing results 1 — 15 out of 127 results