HPC workshop: Advanced Parallel Application Profiling
Professor Jesus Labarta from the Barcelona Supercomputing Center (BSC) will lead this intensive workshop on the suite of application performance analysis tools developed at the BSC. There will also be ample opportunity for researchers to characterise their own codes with Prof. Labarta’s guidance.
Workshop overview
This intensive workshop is based around the suite of application performance analysis tools developed at the BSC. The workshop is the main purpose of Professor Labarta’s visit to UQ.
During the workshop, Prof. Labarta will develop participants’ expertise in the use of the following three BSC analysis tools for characterising and enhancing the performance of codes:
- Extrae
- Paraver
- Dimemas.
Extrae
Extrae is the tool that is used to gather data about the application as it is running. It generates an information-rich trace from the running program that can later be analysed and visualised using Paraver.
Extrae is a tool that uses different interposition mechanisms to inject probes into the target application so as to gather information regarding the application performance.
Extrae can collect data from programs written using the programming paradigms OpenMP, CUDA, OpenCL, pthreads, OmpSs (all with, or without, MPI) as well as Java and Python. Extrae can be used on X86_64, BlueGen/Q, Cray, nVidia GPU, Intel Xeon Phy, ARM, Android, K computer and FX10 hardware.
Paraver
The analytics data gathered by Extrae are analysed and visualised using Paraver. Paraver provides both a high-level qualitative view of what is going on as well as the ability to drill down to explore quantitative aspects of the applications performance.
Paraver was developed to respond to the need to have a qualitative global perception of the application's behaviour by visual inspection and then to be able to focus on the detailed quantitative analysis of the problems.
Dimemas
Dimemas is a performance analysis tool for message-passing programs. It enables the user to develop and tune parallel applications on a workstation, while providing an accurate prediction of their performance on the parallel target machine.
Dimemas is an application design tool that enables an application developer to work on a single CPU workstation but be able to predict the behaviour of their parallel code when ported to a target HPC system.
Workshop structure
The workshop will run for three full days. It will introduce and demonstrate the tools. A selection of parallel applications currently in active use on a UQ HPC have been selected for detailed analysis. There will also be ample opportunity for researchers to characterise their other codes with Professor Labarta’s guidance during the hands-on parts of the workshop.
Register
Tickets for this workshop are free, but please register: tinyurl.com/hpcworkshop-sept2019
Instructor bio
Professor Jesús Labarta received a B.S. in Telecommunications Engineering from the Technical University of Catalunya (UPC) in 1981 and his Ph.D. in Telecommunications Engineering also from UPC in 1983. He has been a full professor of Computer Architecture at UPC since 1990 and was Director of CEPBA-European Center of Parallelism at Barcelona from 1996 to 2005.
Since its creation in 2005, he has been the Director of the Computer Sciences Research Department within the Barcelona Supercomputing Center (BSC).
During his 35-year academic career, Prof. Labarta has made significant contributions in programming models and performance analysis tools for parallel, multicore and accelerated systems, with the sole objective of helping application programmers to improve their understanding of their application's performance and to improve programming productivity in the transition towards very large-scale systems. Under his supervision, his research team has been developing performance analysis and prediction tools (Paraver and Dimemas) and pioneering research on how to increase the intelligence embedded in these performance tools.
He has also been a driving force behind the task-based StarSs programming model, which gives runtime systems the required intelligence to dynamically exploit the potential parallelism and resources available. His team has influenced the evolution of the OpenMP standard with the OmpSs instantiation of StarSs, and, in particular, its tasking model.
He has constantly tried to incorporate his vision and ideas into industrial collaborations. These include projects partially funded by the European Commission, or with HPC companies.
Currently Prof. Labarta is the leader of the Performance Optimization and Productivity (POP) EU Center of Excellence where more than 100 users (both academic and SMEs) from a very wide range of application sectors receive performance assessments and suggestions for code refactoring efforts.
He has authored a large number of publications in peer-reviewed conferences and journals and has advised dozens of PhD students.