Prof. P. K. Yeung, left, and doctoral student Kiran Ravikumar

A technical paper co-authored by AE doctoral student Kiran Ravikumar has been selected as one of the "Best Student Paper Finalists" by SC19 - the International Conference for High-Performance Computing, Networking, Storage, and Analysis.

Ravikumar is the lead author of "GPU Acceleration of Extreme Scale Pseudo-Spectral Simulations of Turbulence Using Asynchronism" one of only 75 papers that was accepted by SC19, one of the largest annual meetings of computing innovators in the world. Ravikumar's selection as a finalist puts him among the very top echelon of these elite researchers, said Prof. P. K. Yeung, Ravikumar's doctoral advisor.

Along with Yeung, and IBM researcher David Applehans, Ravikumar presented a new computer code capable utilizing the unique architecture of a new generation of Graphical Processing Unit (GPU) computers to solve highly complex turbulent fluid flow problems. The team has been given the opportunity to run the code on Oakridge National Lab's Summit computer.

"We know that the GPU computers are capable of processing huge calculations very quickly, but we also know they have their own unique language features that create a very steep learning curve for anyone who wants to use them. That's what makes this work so significant," said Yeung.

"We want to know the conditions of the flow, and that will require us to simulate it over time in a 3D environment. This will be the largest simulation of turbulent flow that's ever been done -- more than six trillion data points. That's more than the number of people living on Earth."