[PDF][PDF] El Criterio de Informació n de Akaike en la Obtenció n de Modelos Estadısticos de Rendimiento

DR Martınez, J Albın, J Cabaleiro, T Pena… - … : XX Jornadas de …, 2009 - researchgate.net
Este artıculo presenta un método de obtención de modelos estadısticos de rendimiento de
aplicaciones paralelas basado en la selección de modelos mediante el criterio de …

Implementing multidestination worms in switch-based parallel systems: Architectural alternatives and their impact

CB Stunkel, R Sivaram, DK Panda - Proceedings of the 24th Annual …, 1997 - dl.acm.org
Multidestination message passing has been proposed as an attractive mechanism for
efficiently implementing multicast and other collective operations on direct networks …

Parallel application experience with replicated method invocation

J Maassen, T Kielmann, HE Bal - … and Computation: Practice …, 2001 - Wiley Online Library
We describe and evaluate a new approach to object replication in Java, aimed at improving
the performance of parallel programs. Our programming model allows the programmer to …

[PDF][PDF] LFC: a communication substrate for Myrinet

RAF Bhoedjang, T Rühl, HE Bal - … Conference of the Advanced School for …, 1998 - Citeseer
LFC is a new, low-level communication substrate for Myrinet, designed to support the
development of high-performance communication software for parallel systems. LFC is …

Performance modeling of mpi applications using model selection techniques

DR Martinez, JC Cabaleiro, TF Pena… - 2010 18th Euromicro …, 2010 - ieeexplore.ieee.org
A new method for obtaining models of the performance of parallel applications based on
statistical analysis is presented in this paper. This method is based on the Akaike's …

Implementing multidestination worms in switch-based parallel systems: Architectural alternatives and their impact

R Sivaram, CB Stunkel… - IEEE Transactions on …, 2000 - ieeexplore.ieee.org
Multidestination message passing has been proposed as an attractive mechanism for
efficiently implementing multicast and other collective operations on direct networks …

高速互连网络中基于网卡的归约计算硬件卸载机制.

常俊胜, 熊泽宇, 徐金波 - Journal of National University of …, 2022 - search.ebscohost.com
聚合通信广泛应用于高性能计算的研究和工程领域. 在大规模的科学和工程计算中,
聚合通信开销占据很大比例, 有时甚至可达到全部消息传递开销的80%, 是高性能计算系统的 …

[PDF][PDF] Method invocation based communication models for parallel programming in Java

J Maassen - 2003 - research.vu.nl
There is a growing interest in using Java for high-performance parallel applications. Java
offers a clean and type-safe object-oriented programming model and its support for …

Density profiles in a classical coulomb fluid near a dielectric wall. ii. weak-coupling systematic expansions

JN Aqua, F Cornu - Journal of Statistical Physics, 2001 - Springer
In the framework of the grand-canonical ensemble of statistical mechanics, we give an exact
diagrammatic representation of the density profiles in a classical multicomponent plasma …

Characterization of message-passing overhead on the AP3000 multicomputer

J Tourino, R Doallo - International Conference on Parallel …, 2001 - ieeexplore.ieee.org
The performance of the communication primitives of parallel computers is critical for the
overall system performance. The characterization of the communication overhead is very …