Rakesh Nagi wins MIT graph challenge for fifth consecutive year
Congratulations to Donald Biggar Willett Professor in Engineering Rakesh Nagi and his student team for winning the 2021 Student Innovation Awards at the MIT Graph Challenge. The student team was Mohammad Almasri and Neo Vasudeva from the ECE department. Their project is HyKernel: A Hybrid Selection of One/Two-Phase Kernels for Triangle Counting on GPUs.
Since the inception of the Graph Challenge in 2017, Nagi has received no less than an Honorable Mention every year.
In 2020, his team was named one of four Champions with At-Scale Sparse Deep Neural Network Inference With Efficient GPU Implementation.
In 2019, Nagi's three teams won the Student Innovation Award with Update on k-truss Decomposition on GPU, as well as two Honorable Mentions for Update on Triangle Counting on GPU and Accelerating Sparse Deep Neural Network on FPGA.
In 2018, Nagi's two teams claimed Finalist for Collaborative (CPU + GPU) Algorithms for Triangle Counting and Truss Decomposition, as well as the Student Innovation Award for Triangle Counting and Truss Decomposition using FPGA.
In 2017, Nagi began his winning streak with Honorable Mention for Collaborative (CPU + GPU) Algorithms for Triangle Counting and Truss Decomposition on the Minsky Architecture .
The MIT Graph Challenge "seeks input from diverse communities to develop graph challenges that take the best of what has been learned from groundbreaking efforts such as GraphAnalysis, Graph500, FireHose, MiniTri, and GraphBLAS to create a new set of challenges to move the community forward."