Speaker
Joshua Isaacson
Description
Event generation for the LHC takes a large amount of resources to reach the desired number of events. Additionally, with the next generation of supercomputers focusing on increasing the number of GPUs per CPU, it is necessary to develop an efficient way of generating events on GPUs. To this end, I will introduce a novel implementation of the Brends-Giele algorithm on GPUs and demonstrate the improved performance compared to traditional CPUs.
Primary author
Joshua Isaacson