We compute, idealy fast with simple obects (we call them 'primitive types') : floating point numbers. Float or double, some languages call them Real. This webinar will highligth some surprising aspects of their behaviour. These numbers which can be represented as floating point and induced errors or the other. Moreover, defferent use cases will be presented to spot traps of floating point computing, and find the perfect balance between performance, precision and correction. An important point is the difference of performance which appears on several hardwares when exotic numbers appears in the computation such as denormals, NaN, inf.
What are Gray Scott Thursdays?
Gray Scott Thursdays are a unique series of 18 live webinars, held every Thursday leading up to the Gray Scott School 2026. Each session is presented by our expert professors and provides an early dive into the key topics of High-Performance Computing, including:
CPU/GPU architectures, memory management, profiling, testing, and modern programming languages such as C++, Fortran, Julia and Python… and much more!
These webinars are a perfect opportunity to get a head start, learn directly from the instructors, and familiarize yourself with the tools, libraries, and methods that will be used during the intensive on-site training.
