| Biography | |
|---|---|
 Prof. Farzad Mashayek University of Illinois at Chicago, USA |
|
| Title: Large-Scale Parallel-Computing of Turbulence | |
| Abstract:
Turbulent flows are commonly present in many natural and technological applications, yet their accurate prediction has eluded scientists and engineers for nearly two centuries. Simulations of various turbulent flows consistently occupy a major portion of resources provided by the fastest supercomputers worldwide. In this talk, we will discuss our recent effort to extend and optimize our in-house Discontinuous Spectral Element Method (DSEM) code for simulation of turbulent flows on some of the largest available supercomputers. A separate code has been written to perform the pre-processing procedures on a local machine. It stores the minimum amount of information that is required for the DSEM code to start in parallel, extracted from the mesh file, into text files (pre-files). The files are generated to ensure fast read performance on different file-systems, such as Lustre and General Parallel File System (GPFS). The results from various tests to demonstrate the performance improvement of DSEM on various supercomputers will be presented and discussed.
| |
| Biography:
Farzad Mashayek received a Ph.D. degree in Mechanical Engineering from the State University of New York at Buffalo in 1994. He is currently Professor and Head of the Department of Mechanical and Industrial Engineering at the University of Illinois at Chicago. Mashayek’s research interests are in the areas of turbulent combustion, plasma, electrostatic atomization and solid-ion batteries. He is a Fellow of the American Society of Mechanical Engineers and an Associate Fellow of the American Institute of Aeronautics and Astronautics. Mashayek has received the CAREER award form the National Science Foundation and the Young Investigator award from the U.S. Office of Naval Research. He has organized and hosted multiple conferences and technical sessions in the areas related to turbulent reacting flows.
| |
