NCSA Training and Seminars
9 matches found
-
Learn how to use the Message Passing Interface (MPI) to parallelize your scientific applications. The basic concepts of message passing, including domain decomposition, collective communications, and several MPI library functions, will be covered. Access to an XSEDE supercomputing cluster will be provided for hands-on exercises.
-
This presentation will focus on the design of a purpose-built computer system for running deep learning frameworks at scale. The system consists of 16 IBM P9 AC922 servers with NVIDIA V100 GPUs and DDN storage and is available to the UIUC research community.
-
This workshop introduces Python GPU tools for porting and writing code that runs on GPUs. The primary tools used for this, Numba and CuPy, are presented with examples. Participants should have experience using Python.