Titlebook: High Performance Computing on Vector Systems 2009; Michael Resch,Sabine Roller,Hiroaki Kobayashi Conference proceedings 2010 Springer-Verl

迷住

BSC-CNS Research and Supercomputing Resources of Catalonia (UPC) took the initiative of creating a National Supercomputing Center in Barcelona. BSC-CNS (Barcelona Supercomputing Center—Centro Nacional de Supercomputación) is the National Supercomputing Facility in Spain and was officially constituted in April 2005. BSC-CNS manages MareNostrum,

nocturnal

大洪水

Going Forward with GPU Computingy which relies on training users and taking advantage of Grand Challenges, involving early access users and system administrators. We also describe some preliminary results and raise questions which need to be addressed in the near future.

CLEFT

pantomime

HPC Architecture from Application Perspectivesoftware infrastructure for peta-scale simulations and data handling. This paper addresses the key technological elements for realizing such a system from the architectural point of view. The author recognizes that the SIMD-based approach is getting pervasive as a core processor technology capable of

DUST

A Language for Fortran Source to Source Transformationons. The language provides mechanisms and constructs which facilitate the parsing of codes, the collection of the necessary information, the transformation of the code segments and the definition of the transformed code including all features to get a well defined transformed program. We shortly des

生存环境

增减字母法

Development of APIs for Desktop Supercomputingly generates a Grid-enabled workflow script needed to execute jobs on a Grid system. The Script Generator API enables users to develop their application with the complex job flow which cannot be generated using existing workflow tools. We implemented the Script Generator API in our Grid infrastructu

柳树；枯黄

esoteric

From Static Domains to Graph Decomposition for Heterogeneous Cluster Programming application based on the MPI extension. This ongoing project is also presented in this document. This middleware allow us to dynamically generate a set of domains that fits to the problem to be solved on an heterogeneous cluster. The main goal is to adapt the partitioning to dynamic and unpredictab