This is a series of lectures I gave at the Master's in HPC program in Trieste, Italy in January 2017. More info available on the Moodle e-learn platform for the Master in High Performance Computing. It is a collaborative of International Centre for Theoretical Physics and International School for Advanced Studies (Scuola Internazionale Superiore di Studi Avanzati).

- January 10, 2017 Introduction to Numerical Libraries for Linear Algebra
- January 10, 2017 Hardware for Numerical Libraries
- January 11, 2017 CUDA Programming
- January 11, 2017 CUDA's Asynchronous and Non-Blocking Techniques
- January 12, 2017 Numerical Libraries for Dense Linear Algebra
- January 12, 2017 The PLASMA Library for Tile Linear Algebra Algorithms
- January 13, 2017 Numerical Libraries for Sparse Linear Algebra
- January 13, 2017 Numerical Libraries for Batched Linear Algebra
- January 13, 2017 Optimization for Performance and Energy for Batched Matrix Computations on GPUs