Scalability, Length: 1 hour
This set of three modules describes how to analyze and optimize the performance of an application on Stampede. It covers multiple scales, from collective MPI communication on thousands of nodes, down to individual threads on the AMD Barcelona processors.
XSEDE Training Information: https://www.xsede.org/for-users/training
|Keywords||Intermediate, Optimization for CPUs|
|Topics||Debuggers Profilers and Optimization Tools|