Results 1 - 10
of
410
Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers
, 2010
"... ..."
(Show Context)
The Network Weather Service: A Distributed Resource Performance Forecasting Service for Metacomputing
- Journal of Future Generation Computing Systems
, 1999
"... ..."
(Show Context)
Cloud Computing and Grid Computing 360-Degree Compared
, 2008
"... Cloud Computing has become another buzzword after Web 2.0. However, there are dozens of different definitions for Cloud Computing and there seems to be no consensus on what a Cloud is. On the other hand, Cloud Computing is not a completely new concept; it has intricate connection to the relatively ..."
Abstract
-
Cited by 248 (9 self)
- Add to MetaCart
(Show Context)
Cloud Computing has become another buzzword after Web 2.0. However, there are dozens of different definitions for Cloud Computing and there seems to be no consensus on what a Cloud is. On the other hand, Cloud Computing is not a completely new concept; it has intricate connection to the relatively new but thirteen-year established Grid Computing paradigm, and other relevant technologies such as utility computing, cluster computing, and distributed systems in general. This paper strives to compare and contrast Cloud Computing with Grid Computing from various angles and give insights into the essential characteristics of both.
High-Performance Parallel Programming in Java: Exploiting Native Libraries
, 1998
"... With most of today's fast scientific software written in Fortran and C, Java has a lot of catching up to do. In this paper we discuss how new Java programs can capitalize on high-performance libraries for other languages. With the help of a tool we have automatically created Java bindings for s ..."
Abstract
-
Cited by 73 (3 self)
- Add to MetaCart
With most of today's fast scientific software written in Fortran and C, Java has a lot of catching up to do. In this paper we discuss how new Java programs can capitalize on high-performance libraries for other languages. With the help of a tool we have automatically created Java bindings for several standard libraries: MPI, BLAS, BLACS, PBLAS, ScaLAPACK. Performance results are presented for Java versions of two benchmarks from the NPB and PARKBENCH suites on an IBM SP2 distributed memory machine using JDK and IBM's high-performance Java compiler. The results confirm that fast parallel computing in Java is indeed possible.
Optimizing bandwidth limited problems using one-sided communication and overlap
- In 20th International Parallel and Distributed Processing Symposium (IPDPS
, 2006
"... Abstract ..."
(Show Context)
GridDB: A Data-Centric Overlay for Scientific Grids
, 2004
"... We present GridDB, a data-centric overlay for scientific grid data analysis. In contrast to currently deployed process-centric middleware, GridDB manages data entities rather than processes. GridDB provides a suite of services important to data analysis: a declarative interface, type-checking, ..."
Abstract
-
Cited by 52 (1 self)
- Add to MetaCart
We present GridDB, a data-centric overlay for scientific grid data analysis. In contrast to currently deployed process-centric middleware, GridDB manages data entities rather than processes. GridDB provides a suite of services important to data analysis: a declarative interface, type-checking, interactive query processing, and memoization. We discuss several elements of GridDB: workflow/data model, query language, software architecture and query processing; and a prototype implementation. We validate GridDB by showing its modeling of real-world physics and astronomy analyses, and measurements on our prototype.
Scalable Work Stealing ∗
"... Irregular and dynamic parallel applications pose significant challenges to achieving scalable performance on large-scale multicore clusters. These applications often require ongoing, dynamic load balancing in order to maintain efficiency. Scalable dynamic load balancing on large clusters is a challe ..."
Abstract
-
Cited by 48 (3 self)
- Add to MetaCart
(Show Context)
Irregular and dynamic parallel applications pose significant challenges to achieving scalable performance on large-scale multicore clusters. These applications often require ongoing, dynamic load balancing in order to maintain efficiency. Scalable dynamic load balancing on large clusters is a challenging problem which can be addressed with distributed dynamic load balancing systems. Work stealing is a popular approach to distributed dynamic load balancing; however its performance on large-scale clusters is not well understood. Prior work on work stealing has largely focused on shared memory machines. In this work we investigate the design and scalability of work stealing on modern distributed memory systems. We demonstrate high efficiency and low overhead when scaling to 8,192 processors for three benchmark codes: a producer-consumer benchmark, the unbalanced tree search benchmark, and a multiresolution analysis kernel.
PARDIS: A Parallel Approach to CORBA
- In 6th IEEE International Symposium on High Performance Distributed Computation
, 1997
"... This paper describes PARDIS, a system carrying explicit support for interoperability of PARallel DIStributed applications. PARDIS is closely based on the Common Object Request Broker Architecture (CORBA) [OMG95]. Like CORBA, it provides interoperability between heterogeneous components by specifying ..."
Abstract
-
Cited by 47 (10 self)
- Add to MetaCart
(Show Context)
This paper describes PARDIS, a system carrying explicit support for interoperability of PARallel DIStributed applications. PARDIS is closely based on the Common Object Request Broker Architecture (CORBA) [OMG95]. Like CORBA, it provides interoperability between heterogeneous components by specifying their interfaces in a meta-language, the CORBA IDL, which can be translated into the language of interacting components, also providing interaction in a distributed domain. In order to provide support for interacting parallel applications, PARDIS extends the CORBA object model by a notion of an SPMD object. SPMD objects allow the request broker to interact directly with the distributed resources of a parallel application. To support distributed argument transfer, PARDIS introduces the notion of a distributed sequence --- a generalization of a CORBA sequence representing distributed data structures of parallel applications. In this report we will give a brief description of basic component i...
Globalized Newton–Krylov–Schwarz algorithms and software for parallel implicit CFD
- Int. J. High Perform. Comput. Appl
"... Implicit solution methods are important in applications modeled by PDEs with disparate temporal and spatial scales. Because such applications require high resolution with reasonable turnaround, parallelization is essential. The pseudo-transient matrix-free Newton-Krylov-Schwarz ( Y NKS) algorithmic ..."
Abstract
-
Cited by 46 (18 self)
- Add to MetaCart
(Show Context)
Implicit solution methods are important in applications modeled by PDEs with disparate temporal and spatial scales. Because such applications require high resolution with reasonable turnaround, parallelization is essential. The pseudo-transient matrix-free Newton-Krylov-Schwarz ( Y NKS) algorithmic framework is presented as a widely applicable answer. This article shows that for the classical problem of three-dimensional transonic Euler flow about an M6 wing, Y NKS can simultaneously deliver globalized, asymptotically rapid convergence through adaptive pseudo-transient continuation and Newton’s method; reasonable parallelizability for an implicit method through deferred synchronization and favorable communi-cation-to-computation scaling in the Krylov linear solver; and high per processor performance through attention to distributed memory and cache locality, especially through the Schwarz preconditioner. Two discouraging features of Y NKS methods are their sensitivity to the coding of the un-derlying PDE discretization and the large number of pa-rameters that must be selected to govern convergence. The authors therefore distill several recommendations from their experience and reading of the literature on vari-ous algorithmic components of Y NKS, and they describe a freely available MPI-based portable parallel software im-plementation of the solver employed here. 1
