GPU Computing: A Gentle Introduction

Date and Time: 
Thursday 2018 July 19th @ 2:30pm
ML main seminar
Alessandro Fanfarillo
General Purpose Graphics Processing Units (GPGPUs) are currently an established and attractive choice in the world of scientific computing, found in many of the fastest supercomputers in the world.
Although the challenges of programming such powerful devices are recurrent in many talks on GPGPUs, the most fundamentals questions about these new devices are often not discussed.
In this talk, questions like "why are the number of cores of the GPU rarely mentioned?", "what are the challenges of programming GPUs?", "what's the difference between a CPU and a GPU?", "do I need a software engineer to run my code on a GPU?" and many others will be answered in an accessible way.
Speaker Description: 

Dr. Alessandro Fanfarillo is a Senior Software Engineer at the National Center for Atmospheric Research. His work is mostly devoted to performance enhancement of parallel weather models, GPGPU computing and software design/refactoring of scientific codes. His research focuses on how to exploit heterogeneous architectures CPU+Accelerators and Partitioned Global Address Space (PGAS) languages (in particular coarray Fortran) for scientific purposes. He is also the lead developer of OpenCoarrays, the open-source library that implements the coarray support in the GNU Fortran compiler.

Event Category: