SPMD parallelization of octrees for CUDA architectures with applications to SPH and N-body

• Grant number: 13/01311-0
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: May 01, 2013
• End date: April 30, 2014
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Eraldo Pereira Marinho
• Grantee: Ana Carolina Camargo Borba
• Host Institution: Instituto de Geociências e Ciências Exatas (IGCE). Universidade Estadual Paulista (UNESP). Campus de Rio Claro. Rio Claro , SP, Brazil

Abstract

It is proposed an undergraduate research activity with IC FAPESP scholarship to the student Ana Carolina Camargo Borba, in the area of parallel programming, with case studies on algorithms for computational astrophysics simulations. The paradigm of parallelism is proposed SIMD (single instruction stream, multiple data stream) adapted to NVIDIA CUDA architecture. The main objective of this work is to introduce the student to the context of programming aimed at high-performance computing based on GPU, for scientific computing, as well as perform tests and measures of the efficiency of the new technique and produce simulation results that can be presented in specialized journals and conferences. (AU)