Biography

Muhammad Abdelghaffar Awad (he/him) is a Member of Technical Staff at AMD Research. At AMD Research, he focuses on designing and building system-level software, libraries, and runtimes to solve problems that include heterogeneous computing, parallel and distributed GPU computing, and AI-based performance analysis. He earned his M.S. and Ph.D. degrees from the Electrical and Computer Engineering Department at the University of California, Davis. At UC Davis, he was working under the supervision of Professor John D. Owens and his dissertation focused on fully concurrent GPU data structures. He received his B.Sc. degree in Naval Architecture and Marine Engineering from the Faculty of Engineering, Alexandria University, Egypt in 2013. His research interests include parallel and distributed computing, heterogeneous computing, performance analysis, dynamic GPU data structures, and computer graphics.

Most of my papers and grad school projects' source code are available on GitHub. Here are links to the source code of the data structures that I designed and built:

• Dynamic GPU B-Tree optimized for updates
• Multiversion GPU B-Tree
• GPU (on-device) epoch-based memory reclamation scheme to safely reclaim memory for concurrent GPU data structures
• Dynamic hash-based GPU graph data structure (integrated into Gunrock)
• High-performance static GPU hash tables
• Bucketed Cuckoo hash set written in PTX and JIT-compiled.

Dissertation

Refereed Publications

Non-refereed Publications