Paolo Bientinesi

Professor in High-Performance Computing. Interests: automatic generation of algorithms and code, numerical linear algebra, tensor operations, performance prediction, computer music.

Contact

paolo.bientinesi@umu.se

Works at

Professor at Department of Computing Science

Plan 2, MIT-huset, UMIT-lab Umeå universitet, 901 87 Umeå

Affiliated as professor at High Performance Computing Centre North (HPC2N) Role: Director

MIT huset, Campustorget 5, 2 tr Umeå universitet, 901 87 Umeå

My research is in High-Performance and Automatic Computing.

I especially welcome interdisciplinary research, for example in materials science, molecular dynamics, as well as computational chemistry, biology, and physics.

The common thread in my research is the exploitation of domain-specific, problem-specific, and architecture-specific knowledge for the development of high-performance algorithms.

More information about my research, CV and publications

Accelerating Deep Learning Inference in Constrained Embedded Devices Using Hardware Loops and a Dot Product Unit

IEEE Access, IEEE 2020, Vol. 8 : 165913-165926

Vreča, Jure; Sturm, Karl J. X.; Gungl, Ernest; et al.

View publications in DiVA

Published: 27 Oct, 2020

New Director to lead HPC2N

Published: 25 Feb, 2020

Algorithms that generate algorithms