Please, bring your own laptop. All the PATC courses at BSC are free of charge.
Course Convener: Xavier Martorell, CS/Programming Models
Course Lecturers: Rosa M. Badia, CS/Workflows and Distributed Computing, Bryan Jiménez (University of Utrecht), Joan Verdaguer-Codina (COEIC)
LOCATION: UPC Campus Nord premises.Vertex Building, Room VS208
Level: BASIC: for students with little previous experience with Python
Prerequisites: Basic Python programming, all examples of the course will be presented in Python.
Objectives: The objectives of this course are to understand the basic concepts on programming with Python and its support for parallelism.
Learning Outcomes: The students who finish this course will be able to develop simple parallel benchmarks with Python, and analyze their execution and tune their behaviour in parallel architectures.
Agenda:
Day 1 (Monday, July 6th, 2020)
Session 1 / 9:30 am – 1:00 pm (2 h lectures, 1 h practical)
1. Introduction to parallel programming and Python
11:00 Coffee break
2. Practical: How to compile and run python applications
Session 2 / 2:00pm – 5:30 pm (2h lectures, 1h practical)
1. Scientific Python: NumPy, SciPy, MatplotLib, Bokeh
16:00 Coffee break
2. Practical: Simple python programs and optimizations
Day 2 (Tuesday, July 7th, 2020)
Session 1 / 9:30 am - 1:00 pm (1.5 h lectures, 1.5 h practical)
1. Parallelism in Python. Shared memory
2. Introduction to performance analysis. Paraver: tool to analyze and understand performance
3. Python pools
11:00 Coffee break
3. Practical: Examples of python parallelism
Session 2 / 2:00 pm - 5:30 pm (1.5 h lectures, 1.5 h practical)
1. Distributed memory
Visualizing distributed environments with Paraver
2. Python queues
16:00 Coffee break
3. Practical: Trace generation and trace analysis
4. Practical: environment on RPi
Day 3 (Wednesday, July 8th, 2020)
Session 1 / 9:30 am - 1:00 pm (1 h lecture, 2h practical)
1. Introduction to PyCOMPSs
2. PyCOMPSs syntax
11:00 Coffee break
3.PyCOMPSs hands-on
Session 2 / 2:00 pm - 5:30 pm (2 h lectures, 1 h practical)
1. PyCUDA and support for accelerators
2. Debugging
16:00 Coffee break
3. Hands-on with PyCUDA
END of COURSE
