Listar Grupo de Arquitectura de Computadores (GAC) por data de publicación
Mostrando ítems 1-20 de 233
-
Parallel Sparse Modified Gram-Schmidt QR Decomposition
(Springer, 1996)[Abstract] We present a parallel computational method for the QR decomposition with column pivoting of a sparse matrix by means of Modified Gram-Schmidt orthogonalization. Nonzero elements of the matrix M to be decomposed ... -
Sparse Householder QR factorization on a mesh
(IEEE Computer Society, 1996-01)[Abstract] We analyze the parallelization of QR factorization by means of Householder transformations. This parallelization is carried out on a machine with a mesh topology (a 2-D torus to be more precise). We use a cyclic ... -
Sparse Givens QR Factorization on a Multiprocessor
(IEEE Computer Society, 1996-06-01)[Abstract] We present a parallel algorithm for the QR factorization with column pivoting of a sparse matrix by means of Givens rotations. Nonzero elements of the matrix M to be decomposed are stored in a one dimensional ... -
A PVM Based Library for Sparse Matrix Factorizations
(Springer, 1998)[Abstract] We present 3LM, a C Linked List Management Library for parallel sparse factorizations on a PVM environment which takes into account the fill-in, an important drawback of sparse computations. It is restricted to ... -
HPF-2 Support for Dynamic Sparse Computations
(Springer, 1998)[Abstract] There is a class of sparse matrix computations, such as direct solvers of systems of linear equations, that change the fill-in (nonzero entries) of the coefficient matrix, and involve row and column operations ... -
Characterization of message-passing overhead on the AP3000 multicomputer
(IEEE, 2001-09)[Abstract] The performance of the communication primitives of parallel computers is critical for the overall system performance. The characterization of the communication overhead is very important to estimate the global ... -
Efficient Parallel Numerical Solver for the Elastohydrodynamic Reynolds–Hertz Problem
(Elsevier BV * North-Holland, 2001-12-01)[Abstract] This work presents a parallel version of a complex numerical algorithm for solving an elastohydrodynamic piezoviscous lubrication problem studied in tribology. The numerical algorithm combines regula falsi, fixed ... -
Exploiting locality in the run-time parallelization of irregular loops
(C R C Press, LLC, 2002-12-10)[Abstract] The goal of this work is the efficient parallel execution of loops with indirect array accesses, in order to be embedded in a parallelizing compiler framework. In this kind of loop pattern, dependences can not ... -
A GIS-Embedded System to Support Land Consolidation Plans in Galicia.
(Taylor & Francis, 2003-06)[Abstract] Land consolidation is a strategic instrument for rural planning and thus economic development in the Spanish region of Galicia. This paper describes an experimental system embedded in a GIS environment to aid ... -
An Inspector-Executor Algorithm for Irregular Assignment Parallelization
(Springer, 2004)[Abstract] A loop with irregular assignment computations contains loop-carried output data dependences that can only be detected at run-time. In this paper, a load-balanced method based on the inspector-executor model is ... -
Performance analysis of Java message-passing libraries on fast Ethernet, Myrinet and SCI clusters
(IEEE Computer Society, 2004-01-08)[Abstract] The use of Java for parallel programming on clusters according to the message-passing paradigm is an attractive choice. In this case, the overall application performance will largely depend on the performance ... -
A middleware architecture for distributed systems management
(Academic Press, 2004-06)[Abstract] This paper presents a middleware solution for global management of any kind of distributed system, such as networks of PCs/workstations, clusters or server farms. Our approach lies in an object-oriented software ... -
Compiler support for parallel code generation through kernel recognition
(IEEE Computer Society, 2004-06-07)[Abstract] Summary form only given. The automatic parallelization of loops that contain complex computations is still a challenge for current parallelizing compilers. The main limitations are related to the analysis of ... -
A Grid Portal for an Undergraduate Parallel Programming Course
(Institute of Electrical and Electronics Engineers, 2005-08)[Abstract] This paper describes an experience of designing and implementing a portal to support transparent remote access to supercomputing facilities to students enrolled in an undergraduate parallel programming course. ... -
Non-blocking Java Communications Support on Clusters
(Springer, 2006)[Abstract] This paper presents communication strategies for supporting efficient non-blocking Java communication on clusters. The communication performance is critical for the overall cluster performance. It is possible ... -
Towards Low-Latency Model-Oriented Distributed Systems Management
(Springer, 2007)[Abstract] Windows and Unix systems have been traditionally very different with regard to configuration storage and management. In this paper we have adapted our CIM-based model-driven management framework, AdCIM, to ... -
Program Behavior Characterization Through Advanced Kernel Recognition
(Springer, 2007)[Abstract] Understanding program behavior is at the foundation of program optimization. Techniques for automatic recognition of program constructs (from now on, computational kernels) characterize the behavior of program ... -
Efficient Java Communication Protocols on High-speed Cluster Interconnects
(IEEE Computer Society, 2007-02-26)[Abstract] This paper presents communication strategies for achieving efficient parallel and distributed Java applications on clusters with high-speed interconnects. Communication performance is critical for the overall ... -
Automated and accurate cache behavior analysis for codes with irregular access patterns
(John Wiley & Sons Ltd., 2007-04-03)[Abstract] The memory hierarchy plays an essential role in the performance of current computers, so good analysis tools that help in predicting and understanding its behavior are required. Analytical modeling is the ideal ... -
High Performance Java Remote Method Invocation for Parallel Computing on Clusters
(IEEE Computer Society, 2007-11-12)[Abstract] This paper presents a more efficient Java remote method invocation (RMI) implementation for high-speed clusters. The use of Java for parallel programming on clusters is limited by the lack of efficient communication ...
