My research interests span the areas of parallel and distributed computing, dynamic load balancing, performance modeling, performance evaluation, robustness analysis, process algebra, and stochastic computing environment. The core of my research lies in identifying robust resource allocations via a numerical analysis of performance modeling of the parallel execution of applications on parallel computing resources. During my research, I worked on a number of novel techniques for analyzing the robustness of resource allocations in parallel and distributed computing environments. The key highlights of my research are: performance modeling of resource allocations in parallel and distributed computing using stochastic process algebra, robustness evaluation using a passage time analysis (numerical analysis of Markovian models) of the developed performance models of resource allocations, first implementation of the dynamic loop scheduling (DLS) methods in a simulation framework for a comparative analysis of the execution performance of these methods, study of the use of a model free machine learning (reinforcement learning) approach towards an automatic selection of the best DLS method for scheduling time-stepping scientific applications, formulation of robustness metrics for dynamic scheduling methods used in parallel computing systems and a study towards an online selection, of the most robust dynamic scheduling method, using machine learning techniques, first implementation of a learning based methodology for an online prediction of the robustness of DLS methods using an artificial neural network, a power-aware execution of scientific applications parallel and distributed computing systems using an existing model-based framework that combines the functionalities of DLS methods with a feedback limited look ahead controller, and a combined dual-stage framework for robust scheduling of scientific applications in heterogeneous environments with uncertain processor availability.
As a part of my contribution to the computer society, I have authored and co-authored a number of articles published in renowned IEEE and ACM conferences, journals, and book chapters. This also led me to present my work at some of the top computer science tier 1 conferences (such as the ACM Super Computing Conference, the IEEE International Parallel and Distributed Processing Symposium, and others) and network with the best academic professionals in the field.
I had also been selected to be a part of a delegation of 200 young scientists from around the world to attend the Heidelberg Laureate Forum (to meet laureates in Math and Computer Science) at Heidelberg, Germany, October 2014. More details on the HLF forum can be found at their website at: http://www.heidelberg-laureate-forum.org/
Presenting at The ACM Super Computing Conference 2014
Heidelberg Laureate Forum 2014 - Laureate Manjul Bhargava displaying card trick using parity bits
Heidelberg Laureate Forum 2014 - Turing Award Winner Leslie Lamport