Allocating Independent Subtasks on Parallel Processors
IEEE Transactions on Software Engineering
Guided self-scheduling: A practical scheduling scheme for parallel supercomputers
IEEE Transactions on Computers
Factoring: a method for scheduling parallel loops
Communications of the ACM
Load-sharing in heterogeneous systems via weighted factoring
Proceedings of the eighth annual ACM symposium on Parallel algorithms and architectures
OpenMP: An Industry-Standard API for Shared-Memory Programming
IEEE Computational Science & Engineering
Load Balancing Highly Irregular Computations with the Adaptive Factoring
IPDPS '02 Proceedings of the 16th International Parallel and Distributed Processing Symposium
BOINC: A System for Public-Resource Computing and Storage
GRID '04 Proceedings of the 5th IEEE/ACM International Workshop on Grid Computing
GridR: An R-Based Grid-Enabled Tool for Data Analysis in ACGT Clinico-Genomics Trials
E-SCIENCE '07 Proceedings of the Third IEEE International Conference on e-Science and Grid Computing
Hi-index | 0.00 |
Parallel computing is becoming essential for nowadays data analysis in several disciplines. In order to profit from parallel processing of experimental data, specialized skills, software tools and suitable computing resources are required. Desktop grids and volunteer-based systems have proved themselves as powerful options where distributed idle resources from heterogeneous computers are aggregated to build powerful met computers. Software solutions are required to automate and assist the process of transformation and adaptation of current and new applications to run in these environments. Finally, it is desirable, for the same tool, to provide an efficient solution to orchestrate the execution of these programs using a diversity of dynamic environments. In this paper we describe an implementation of an integrated solution for the R language which allows the transformation and execution of parallel loops in heterogeneous and non-dedicated environments. The results obtained allow us to prove the feasibility of our proposal. Furthermore, several issues that tools like this must consider to improve their performance when integrating heterogeneous systems are described.