Florent Lopez

Postdoctoral Researcher

I am a postdoctoral researcher in the numerical analysis group at the STFC Rutherford Appleton Laboratory. I finished my PhD in 2015 at the Université Paul Sabatier Toulouse III on Task based multifrontal solvers for heterogeneous architectures and it was conducted in the context of the qr_mumps solver under the supervision of Alfredo Buttari.

My research interests lie in the domain of numerical linear algebra and high performance computing. I am particularly interested in the development of direct solvers for solving large sparse linear systems of equations. I am currently involved in the NLAFET project, a EU-funded Horizon 2020 project, aiming at improving the performance and scalability of linear algebra software for the emerging extreme-scale systems.

  • Sparse linear algebra
  • High performance computation
  • GPU computing

ORCID id: 0000-0002-8479-5749

Refereed articles:

  1. Implementing multifrontal sparse solvers for multicore architectures with sequential task flow runtime systems
    E Agullo, A Buttari, A Guermouche and F Lopez
    ACM Trans Math Software. 43, no. 2 (2016): 1-22, doi:10.1145/2898348.

Preprints & Technical reports:

  1. Experiments with sparse Cholesky using a sequential task-flow implementation
    I Duff, J Hogg and F Lopez
    RAL Technical Reports RAL-TR-2016-016 (2016), Rutherford Appleton Laboratory, Chilton, England. (PDF)

  • qr_mumps qr_mumps is a software package for the solution of sparse, linear systems on multicore computers.