9th Workshop on Python for High-Performance and Scientific Computing
Posted: 6 Nov 2020 | 15:27
The 9th Workshop on Python for High-Performance and Scientific Computing (PyHPC) at SC20 will once again bring researchers and developers together to share their experiences of using Python across a wide range of disciplines and applications.
EPCC is a member of the PyHPC Organizing Committee and this year we are co-chairing PyHPC's 9th Workshop on Python for High-Performance and Scientific Computing at SC20 on Friday 13 Nov, 10:00–18:30 EST.
This workshop’s programme features special guests Mike Bauer (Legate, NVIDIA) and Lisandro Dalcin (MPI4PY, KAUST). Topics include:
- Enabling shared memory access to Python processes in task-based programming models
- Workarounds for Python workflows in HPC environments
- Experiences in developing a distributed Agent-Based modelling (ABM) distributed toolkit in Python
- New contributions to a distributed, asynchronous many-task (AMT) computing framework that encompasses the entire computing process, from a Jupyter front-end for managing code and results to the collection and visualization of performance data
- A new high-performance Python API with a C++ core to represent data as a table and provide distributed data operations
- And a computation environment for HPC that aims to accelerate microstructural analytics scaling Numpy workflows to enable multidimensional image analysis of diverse specimens.
Neelofer Banglawala, EPCC