Mawussi Zounon is Research Associate in the Numerical Linear Algebra
group at the University of Manchester. After his Engineering degree in
computation science, in 2011 from the Polytechnic Institute of Bordeaux
in France, he received in 2015 a PhD in computer science and applied mathematics
from the University of Bordeaux for his contribution to numerical
fault tolerant strategies for large sparse linear algebra solvers with
a special focus on Krylov subspace methods. His research interests
are in high-performance computing, parallel algorithms, numerical
analysis, and fault tolerance. Besides his current research activities
on task-based numerical linear algebra software, novel methods for
static and dynamic scheduling, offline auto-tuning and algorithm-based fault tolerant
techniques, he is actively contributing to efficient implementation
of Batched BLAS kernels on many-core architectures and to the
standardization of batched linear algebra computation in the HPC
Birds of a Feather
HPC Accelerators
Math Library Design
Parallel Algorithms
Parallel Applications
Scientific Software Development