Since 2010, I am pursuing my research Scientist position at the Innovative Computing Laboratory (ICL) at the University of Tennessee.
Before that, I was conducting my research at the INPT
University (National Polytechnic Institut of Toulouse).
During this time, I was working at the
in the Parallel Algorithms Team.
One of my research interests focus on the development and implementation of
Parallel Linear Algebra routines for Scalable Distributed Heterogeneous Architectures
such as the classical CPUs and accelerators (Intel Xeon-Phi, Nvidia GPUs, AMD GPUs).
The goal is to create software frameworks that enable programmers to simplify
the process of developing applications that can achieve both high performance
and portability across a range of new architectures.
The development of such programming models that enforce asynchronous, out of order
scheduling of operations is the concept used as the basis for the definition
of a scalable yet highly efficient software framework for Computational Linear Algebra applications.
another research interests is the development and implementation of numerical
algorithms and software for large scale parallel sparse problems.
One of my objectives is to develop hybrid approaches that combine direct
and iterative algorithms to solve systems of linear algebraic equations with
large sparse coefficient matrices.
Such systems arise in numerical applications involving the solution of partial differential equations.
A typical grand challenge application and industrial numerical simulation
requires the use of powerful parallel computing platform along with parallel
algorithm to run on these platforms.
In this context, i am interested in how to develop robust and scalable parallel
preconditioners to accelerate convergence of the parallel iterative solver.
I study preconditionning techniques for solving
general sparse linear systems on massively distributed parallel computing platforms.
These techniques are referred to as domain decomposition methods utilizing the Schur complement system.