I’m Hashem – thanks for visiting my website! I’m currently pursuing a B.S. in Electrical Engineering with Honors (2022), a M.S. in Computer Science (2023), and a minor in Mathematics at Stanford University.
I’m mainly interested in machine learning algorithms, efficient software/hardware systems, and the intersection between those two. I’m also interested in applications of AI to vision and language, as well as applications of AI to the improvement of human productivity (including the way we build software!).
I’m currently doing research on methods for automatically generating efficient CUDA kernels for effective GPU acceleration of deep learning workloads, under the guidance of Professor Kunle Olukotun and PhD student Tian Zhao. Previously, I worked on FAST, an unsupervised end-to-end earthquake detection system that uses a novel method based on locality-sensitive hashing, under the guidance of Professor Peter Bailis and PhD student Kexin Rong.
Unsupervised Large-Scale Search for Similar Earthquake Signals paper
Clara Yoon, Karianne Bergen, Kexin Rong, Hashem Elezabi, William Ellsworth, Gregory Beroza, Peter Bailis, Philip Levis.
BSSA 2019 (Bulletin of the Seismological Society of America)
Locality-Sensitive Hashing for Earthquake Detection: A Case Study of Scaling Data-Driven Science
paper blog post video code
Kexin Rong, Clara Yoon, Karianne Bergen, Hashem Elezabi, Peter Bailis, Philip Levis, Gregory Beroza.
VLDB 2018 (Very Large Data Bases)
PGAS Access Overhead Characterization in Chapel paper
Engin Kayraklioglu, Olivier Serres, Ahmad Anbar, Hashem Elezabi, Tarek El-Ghazawi.
IPDPSW 2016 (IEEE International Parallel and Distributed Processing Symposium Workshops)