This advanced manycore training is designed for experienced programmers who have some familiarity with OpenMP, and is a follow up to the topics covered in “Introduction to Manycore Progamming.” This training will focus on the use of reports and directives to improve vectorization and the implementation of proper memory access. We will also showcase new Intel VTune Amplifier XE capabilities that allow for in-depth memory access analysis and hybrid code profiling. Individuals who have already run on KNL nodes are not required to attend the introductory KNL course prior to attending this course. Hands-on exercises will be executed on the KNL-upgraded Stampede system at the Texas Advanced Computing Center (TACC).
Topics covered in this training:
- Vectorization, Multiprocessing & Multithreading
- Understanding Compiler Optimization Reports
- Using Intel Vtune and Advisor
Todd Evans, Ph.D.
Todd Evans joined TACC in 2013 as member of the High Performance Computing group. Todd received his Ph.D. in Physics from the University of Illinois at Urbana-Champaign in 2008. He spent the following two years as a postdoc in high-energy physics at the University of Regensburg and then three years as a postdoc in Nuclear Engineering at North Carolina State University. Since joining TACC his research focus has been HPC systems and application performance monitoring and analysis.
Recording Date: February 3, 2017