Filters








5 Hits in 5.4 sec

Graph partitioning for parallel applications in heterogeneous Grid environments

S. Kumar, S. K. Das, R. Biswas
2002 Proceedings 16th International Parallel and Distributed Processing Symposium  
The problem of partitioning irregular graphs and meshes for parallel computations on homogeneous systems has been extensively studied.  ...  Our partitioning algorithm, called MiniMax, generates and maps partitions onto a heterogeneous system with the objective of minimizing the maximum execution time of the parallel distributed application  ...  Vertex and edge weights for this graph range uniformly between 1 and 4; the degree of vertices also lie in the range 1-4. Here, edges are highly localized to a vertex.  ... 
doi:10.1109/ipdps.2002.1015564 dblp:conf/ipps/KumarDB02 fatcat:qw67iuy3hrb5tpces7oxtqjshy

Compiling C for the EARTH multithreaded architecture

L.J. Hendren, Xinan Tang, Yingchun Zhu, G.R. Gao, Xun Xue, Haiying Cai, P. Ouellet
Proceedings of the 1996 Conference on Parallel Architectures and Compilation Technique  
Multithreaded architectures provide an opportunity for e ciently executing programs with irregular parallelism and/or irregular locality.  ...  In this paper we introduce EARTH-C, our extended C language which contains simple constructs for specifying control parallelism and data locality.  ...  EM-C is a parallel extension of the C languages designed for e cient parallel programming in the EM-4 multiprocessor 20].  ... 
doi:10.1109/pact.1996.552551 dblp:conf/IEEEpact/HendrenTZGXCO96 fatcat:uhvsnylow5aqbfo3fkwj26wyte

The Pencil Code, a modular MPI code for partial differential equations and particles: multipurpose and multiuser-maintained [article]

on behalf of the Pencil Code Collaboration Axel Brandenburg
2021 Zenodo  
.: 2021, "The Pencil Code, a modular MPI code for partial differential equations and particles: multipurpose and multiuser-maintained," Journal of Open Source Software 5, 2684 (arXiv:2009.08231) .  ...  This is the current version; see the "Scientific Usage of the Pencil Code" under http://pencil-code.nordita.org/highlights/ (DOI:10.5281/zenodo.3466444) for the currently about 600 publications using the  ...  To achieve good parallelization, we use explicit (as opposed to compact) finite differences.  ... 
doi:10.5281/zenodo.4553325 fatcat:2icmms6n3zawfmoceifloeo6me

Pencil Code [article]

on behalf of the Pencil Code Collaboration Axel Brandenburg
2020 Zenodo  
This is the current version; see the "Scientific Usage of the Pencil Code" under http://pencil-code.nordita.org/highlights/ (DOI:10.5281/zenodo.3466444) for the currently over 560 publications using the  ...  To achieve good parallelization, we use explicit (as opposed to compact) finite differences.  ...  Used in batch scripts for multiprocessor runs.  ... 
doi:10.5281/zenodo.3961647 fatcat:wrpaz23op5a2doysqq3zk7xme4

Multi-Objective System-Level Management of Modern Green Data Centers

Ali Pahlevan
2019
Andreas Burg (internal examiner), for taking their valuable time out of their busy schedule to review this manuscript and providing me with their insightful comments.  ...  For all of these reasons, I am deeply grateful to him. The following paragraph, I will express my sincerest gratitude to those who helped me to produce this manuscript.  ...  In addition, during these years of living in Switzerland, there were many great Iranian friends who made life with all its ups-and-downs sweet and enjoyable for me.  ... 
doi:10.5075/epfl-thesis-9457 fatcat:3dmwdvgfovdere2kmcbsja57wi