Please use this identifier to cite or link to this item:
http://hdl.handle.net/10609/149763
Title: | Implementación distribuida maleable del método Laplace |
Author: | Reina León, José |
Tutor: | Jorba, Josep |
Others: | Iserte, Sergio |
Abstract: | High-performance computing (HPC) is a key tool in many areas where computing power and high storage capacity are needed. This is usually carried out by clusters of computers working together to increase individual computing power. Once a task is assigned to certain computing nodes, the only thing left to do is wait until it is finished to release the resources that have been assigned to it. Malleability is presented as the ability to adapt to a variable number of computing nodes during the execution of a specific task. This allows for an improvement in the overall performance of the cluster, allowing for an increase in the number of jobs completed per unit of time. It is also able to allow priority jobs to be executed even if there are no resources available at the time they are included in the job manager. In this project, we will implement the malleability of a real application using the DMR API. It will also be executed on a real HPC cluster and the corresponding tests and analysis will be carried out in order to demonstrate the performance improvement that we can achieve thanks to the malleability of applications. |
Keywords: | MPI recursos dinámicos DMR maleabilidad |
Document type: | info:eu-repo/semantics/masterThesis |
Issue Date: | 26-Jan-2024 |
Publication license: | http://creativecommons.org/licenses/by-nc-nd/3.0/es/ |
Appears in Collections: | Trabajos finales de carrera, trabajos de investigación, etc. |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
jreinalTFM0124memoria.pdf | Memoria del TFM | 668,87 kB | Adobe PDF | View/Open |
Share:
This item is licensed under aCreative Commons License