Wednesday, 21 October 2020 at 09:00
It will shown a course targeted to improve the overall performance of a code in Solid Earth, currently in use at the
CHEESE Center of Excellence H2020 project.
First, parallel performance profiling tools will be provided on the initial version of the code to find the so-called
Starting from the profiling analysis, it will show how and where to intervene with respect to the hardware characterization
of the HPC machine used for the investigation.
We will show also how debug tools will be useful in the development / optimization phase to eliminate any
possible bugs introduced in the writing (or redesign) of new parts of the code.
Finally, it will be shown how to improve the overall performance of the code with respect to other popular parameters
such as I / O, vectorization, etc.
At the end of the course the student will be able to:
- use a concrete methodology to improve the performance of a code in Solid Earth already in use in the context of
- find and solve all the main bottlenecks of an application with respect to appropriate computational metrics
and the machine used
- use appropriate debugging tools to eliminate any bugs that may arise during the development / optimization phase
Researchers in Solid Earth interested to learn and use all those techniques and related tools that may allow them
to improve the performance of their code on current HPC architectures in the shortest possible time.
-Basic knowledge of LINUX/UNIX.
-Knowledge of C, FORTRAN, MPI or OpenMP is recommended. Notions of Parallel computing techniques and algorithms
for Solid Earth applications