Extrae and Paraver: Profiling Weather and Climate Applications

The National Competence Centre for HPC in Austria is organizing this one-day training together with ESiWACE3, the Centre of Excellence in simulation of weather and climate in Europe. With expertise in earth system modelling, software design, and high-performance computing, ESiWACE3 is supporting scientists on the path to exascale computing.

This course is about the BSC performance analysis tools, which are a set of different tools to support developers on the evaluation, tuning, and optimization of their codes. There are two main applications: Extrae, devoted to generate trace-files for a post-mortem analysis without modifying the source code, and Paraver, which is a flexible performance analyzer of the Extrae traces. They support different programming models such as C/C++, Fortran, Python, MPI, and OpenMP, as well as tracing of hardware counters, user functions, etc. In this course we will demonstrate the use of the tools in profiling weather and climate models, as an example, but they can be applied to any field of HPC.

The course consists of a theoretical part and hands-on labs for participants to practice how to analyze an Extrae trace with Paraver. We will use a climate application as a demonstration, focusing on typical problems arising to numerical models and computational fluid dynamic applications.

Agenda & Content

See Agenda & Content in the left menu for a detailed timetable and course content.

Content level

Content level: Basic = 0:00h (0%) + Intermediate = 6:00h (100%) + Advanced = 0:00h (0%)

Entry level

Intermediate

Prerequisites

Experience with (weather and climate) simulations on HPC infrastructure

Fundamentals of MPI and OpenMP programming.

Target audience

Course for academia, industry, and public administration.

Registration

The registration form might close even before the deadline if the number of registrations has reached its maximum (and will open again if there are cancelations).

Please register with your official email address to prove your affiliation.

You will get an automatic confirmation via email (subject starting with "[Indico] Registration"), please check your Spam/Junk folders.

Following your successful registration, you will receive further information approximately 1 week before the course.