Profile

Prabindh Sundareson has over 20 years of experience in the technology industry. He completed his studies from Indian Institute of Science, Bangalore, and Thiagarajar College of Engineering. He started his career in Alstom/GE/GEC Alsthom, then worked with Texas Instruments in Bangalore and Dallas, in the areas of Graphics and Multimedia, Security, and System architectures for Automotive devices. He later worked with mobile major Samsung in their Research group in Bangalore where he participated in the co-development of Camera/Vision hardware IP along with labs in Dallas and Korea, and led the Graphics team. Currently he is an Architect at Nvidia, focusing on algorithms and systems for gaming, cloud, and HPC.

He has 11 patents granted at USPTO, and more than 14 patent applications under process. He has participated in the standardisation of OpenGL/ES and Vulkan specifications from Khronos.org. He is the founder chair of IEEE Consumer Electronics Chapter Bangalore, is an Executive committee member of Khronos.org Bangalore chapter, was the General Chair of the first ICCE-Asia 2017 conference, is a writer at GPUpowered.org. He has authored 4 books - "Will I Be Mine", "Quantum of Entanglement", "Sensibility through the eye of the needle", and a bilingual book "Tamil Poetry for Daily Life", (https://www.amazon.in/s?i=stripbooks&rh=p_27%3APrabindh+Sundareson). He lives in Bangalore, and likes giving back to Society.

Selected set of publications and patents ( https://scholar.google.co.in/citations?user=TFNCgcIAAAAJ)

PLINDER: The protein-ligand interactions dataset and evaluation resource
Determining high-interest durations of gameplay sessions from user inputs
A re-evaluation of fundamental transform structures for efficient implementation on semi-parallel DSP architectures
Parallel image pre-processing for in-game object classification
Face recognition accuracy enhancement in Consumer devices
E-Waste Detection and Collection assistance system using YOLOv5
Poster: Page table manipulation attack
Image synthesis method with DSP and GPU
UNSUPERVISED CLASSIFICATION OF GAMEPLAY VIDEO USING MACHINE LEARNING MODELS