Banca de DEFESA: CARLA DOS SANTOS SANTANA

Uma banca de DEFESA de MESTRADO foi cadastrada pelo programa.
STUDENT : CARLA DOS SANTOS SANTANA
DATE: 13/01/2020
TIME: 09:00
LOCAL: Auditório nPITI
TITLE:

Workload scheduling analysis in geophysical numerical methods

KEY WORDS:

workload scheduling, FWI, LSM, work-stealing, centralized dynamic, decentralized static, decentralized dynamic, high-performance computing, MPI.

PAGES: 64
BIG AREA: Ciências Exatas e da Terra
AREA: Ciência da Computação
SUMMARY:

The tasks organization among computational nodes affects the performance of the program. In computationally expensive applications such as geophysical problems, the impact is more significant. The imbalance caused by inefficient task scheduling can generate an application non-scalable. Therefore this work investigates the workload scheduling in geophysical methods.

 Three types of workload scheduling will be compared: centralized dynamic (CD), decentralized static (DS), and decentralized dynamic (DD).  The CD was implemented with the technique master-slave, where the master node is responsible for the distribution of the tasks to other nodes called slaves. The DS with an equal division of tasks. The DD implements the work-stealing method proposed by Assis et al. 2019, where an idle node can steal the tasks of an overloaded node.

The principal geophysics method used was Full waveform inversion (FWI) 2D with the acoustic wave. To analyze the performance of workload scheduling methods, we employ a synthetic velocity model and present speedup, efficiency, and load distribution plots generated with different model sizes and different quantity of nodes. The FWI code and the workload scheduling methods were implemented in C to distributed memory parallelization and using the message passing interface (MPI) library.

With the results of the workload scheduling methods in FWI, it was applied the work-stealing (because this technique presented the more effective performance) in another geophysics problem: Least-squares migration (LSM).  We used the LSM with DS implemented by Chauris et al. 2017 to compare with the LSM with work-stealing. The LSM code and DS used in this problem were implemented in Fortran and the work-stealing in C. The communication between the nodes was implemented using MPI.  To analyze the performance of workload scheduling methods in LSM, we used the marmousi velocity model.

BANKING MEMBERS:
Presidente - 1673543 - SAMUEL XAVIER DE SOUZA
Interno - 009.071.370-24 - TIAGO TAVARES LEITE BARROS - UNICAMP
Externo à Instituição - Angelo Amâncio Duarte - UEFS
Externo à Instituição - CALEBE DE PAULA BIANCHINI - UPM
Externo à Instituição - HERVÉ CHAURIS