Member of Technical Staff |
I am a Member of Technical Staff at AMD Research. My research interests include all aspects of computer architecture, with a focus on GPGPUs, hardware-software co-design, processing-in-memory, and deep learning acceleration.
I completed my Ph.D. studies in the Department of Computer Science at William & Mary, where I worked with Professor Adwait Jog in Insight Computer Architecture Lab. My dissertation focused on designing high-performance and energy-efficient GPU architectures with an emphasis on cache and interconnect design. Before joining William & Mary, I received my bachelor's and master's degrees in Computer Engineering at Cairo University, Egypt.
August 2021: Our submission Efficient Cache Utilization via Model-aware Data Placement for Recommendation Models is accepted @ MEMSYS 2021.
July 2021: Member of Technical Staff at AMD Research.
May 2021: I earned my Ph.D. in Computer Science from the William & Mary and received the Distinguished Dissertation Award in the Natural and Computational Sciences.
January 2021: Postdoc at AMD Research.
(MEMSYS 2021) Mohamed Assem Ibrahim, Onur Kayiran, Shaizeen Aga
Efficient Cache Utilization via Model-aware Data Placement for Recommendation Models,
In The International Symposium on Memory Systems, Virtual Event, September 2021
[Paper]
[Talk]
(HPCA 2021) Mohamed Assem Ibrahim, Onur Kayiran, Yasuko Eckert, Gabriel H. Loh, Adwait Jog
Analyzing and Leveraging Decoupled L1 Caches in GPUs,
In The 27th IEEE Symposium on High Performance Computer Architecture, Virtual Event, February 2021
(Acceptance rate: 63/258 = %24.4)
[Paper]
[Short Talk]
[Talk]
[Video]
(PACT 2020) Mohamed Assem Ibrahim, Onur Kayiran, Yasuko Eckert, Gabriel H. Loh, Adwait Jog
Analyzing and Leveraging Shared L1 Caches in GPUs,
In The 29th International Conference on Parallel Architectures and Compilation Techniques, Virtual Event, October 2020
(Acceptance rate: 35/137 = %25.5)
[Paper]
[Talk]
[Video]
(PACT 2019) Mohamed Assem Ibrahim, Hongyuan Liu, Onur Kayiran, Adwait Jog
Analyzing and Leveraging Remote-core Bandwidth for Enhanced Performance in GPUs,
In The 28th International Conference on Parallel Architectures and Compilation Techniques, Seattle, Washington, September 2019
(Acceptance rate: 34/126 = %26.9)
[Paper]
[Talk]
(ICS 2019) Haonan Wang, Mohamed Assem Ibrahim, Sparsh Mittal, Adwait Jog
Address-Stride Assisted Approximate Value Prediction in GPUs,
In The 33rd ACM International Conference on Supercomputing, Phoenix, Arizona, June 2019
(Acceptance rate: 45/193 = %23.3)
[Paper]
[Talk]
(MICRO 2018) Hongyuan Liu, Mohamed Assem Ibrahim, Onur Kayiran, Sreepathi Pai, Adwait Jog
Architectural Support for Efficient Large-Scale Automata Processing,
In The 51st International Symposium on Microarchitecture, Fukuoka, Japan, October 2018
(Acceptance rate: 74/348 = %21.3)
[Paper]
[Talk]
[Poster]
[Lightning Talk]
(SRC@MICRO 2018) Mohamed Assem Ibrahim, Hongyuan Liu, Onur Kayiran, Adwait Jog
Poster: Design and Analysis of Efficient Inter-core Communication in GPUs,
In The ACM Student Research Competition at The 51st International Symposium on Microarchitecture, Fukuoka, Japan, October 2018
[Abstract]
[Poster]
(HPCA 2018) Haonan Wang, Fan Luo, Mohamed Assem Ibrahim, Onur Kayiran, Adwait Jog
Efficient and Fair Multi-programming in GPUs via Effective Bandwidth Management,
In The 24th IEEE Symposium on High Performance Computer Architecture, Vienna, Austria, February 2018
(Acceptance rate: 54/260 = %20.7)
[Paper]
[Talk]
[Lightning Talk]
(HPCA 2017) Xulong Tang, Ashutosh Pattnaik, Huaipan Jiang, Onur Kayiran, Adwait Jog, Sreepathi Pai, Mohamed Assem Ibrahim, Mahmut T. Kandemir, Chita R. Das
Controlled Kernel Launch for Dynamic Parallelism in GPUs,
In The 23rd IEEE Symposium on High Performance Computer Architecture, Austin, Texas, February 2017
(Acceptance rate: 50/224 = %22.3)
[Paper]
(MES@ISCA 2015) Mohamed Assem Ibrahim, Hatem M El-Boghdadi
Investigating the Viability of Maximum Flexibility Selection Function in Bufferless 2D Meshes,
In The 3rd International Workshop on Many-core Embedded Systems, Portland, Oregon, June 2015
[Paper]
(ICC 2014) Omar Shoukry, Mohamed Assem Ibrahim, John Tadrous, Hesham El Gamal, Tamer ElBatt, Nayer Wanas, Yaser Elnakieb, Mohamed Khairy
Proactive Scheduling for Content Pre-fetching in Mobile Networks,
In IEEE International Conference on Communications, Sydney, Australia, June 2014
(Acceptance rate: 995/2,608 = 38%)
[Paper]
(MobiSys 2013) Mohamed Assem Ibrahim, Omar Shoukry, Hesham El Gamal, Tamer ElBatt, Nayer Wanas, Mohamed Abdel Raouf, Mohamed Zakaria, Ahmed Abdel Kader, Hakem Zayed
Demo: PAUL - Proactive Automated mobile User-centric content deLivery,
In The 11th International Conference on Mobile Systems, Applications, and Services, Taipei, Taiwan, June 2013
[Paper]
In reference to IEEE copyrighted material which is used with permission in this thesis, the IEEE does not endorse any of William and Mary’s products or services. Internal or personal use of this material is permitted. If interested in reprinting/republishing IEEE copyrighted material for advertising or promotional purposes or for creating new collective works for resale or redistribution, please go to http://www.ieee.org/publications_standards/publications/rights/rights_link.html to learn how to obtain a License from RightsLink. If applicable, University Microfilms and/or ProQuest Library, or the Archives of Canada may supply single copies of the dissertation.
(US11068458) Mohamed Assem Ibrahim, Onur Kayiran, Yasuko Eckert, Gabriel H. Loh
Adaptive Cache Reconfiguration via Clustering
[Link]
(US11068458) Mohamed Assem Ibrahim, Onur Kayiran, Yasuko Eckert
Mechanism for Distributed-system-aware Difference Encoding/Decoding in Graph Analytics
[Link]
(US10938709) Mohamed Assem Ibrahim, Onur Kayiran, Yasuko Eckert, Jieming Yin
Mechanism for Dynamic Latency-Bandwidth Trade-off for Efficient Broadcasts/Multicasts
[Link]
Distinguished Dissertation Award in the Natural and Computational Sciences, William & Mary [One recipient per year]
[Link]
March 2021: Analyzing and Leveraging Decoupled L1 Caches in GPUs @ HPCA 2021 [Slides].
October 2020: Analyzing and Leveraging Shared L1 Caches in GPUs @ PACT 2020 [Slides].
September 2019: Analyzing and Leveraging Remote-core Bandwidth for Enhanced Performance in GPUs @ PACT 2019 [Slides].
February 2018: Efficient and Fair Multi-programming in GPUs via Effective Bandwidth Management @ HPCA 2018 [Slides].
PhD Dissertation,
Rethinking Cache Hierarchy and Interconnect Design for Next-generation GPUs ,
Committee Members: Adwait Jog, Dmitry Evtyushkin, Bin Ren, Andreas Stathopoulos, Asit Mishra
Distinguished Dissertation Award from William & Mary
[Dissertation]
[Defense]
MSc Thesis,
On Enhancing the Performance of Bufferless Network-on-Chip,
Committee Members: Hatem El-Boghdadi, Amr Wassal, Mohammad Zaki Abdel-Majeed
[Thesis]
[Defense]
Member of Technical Staff at AMD Research
July 2021 - Present
Postdoctoral Researcher at AMD Research
January 2021 - June 2021
Co-Op Engineer at AMD Research
May 2020 - December 2020
Co-Op Engineer at AMD Research
May 2018 - August 2018
Research Software Development Engineer at Nile University
June 2012 - June 2013
Software Engineer at Inmobly
October 2011 - June 2013
PhD Student in Computer Science, William & Mary
Spring 2016 - Spring 2021
MSc in Computer Engineering, Cairo University
Fall 2010 - Fall 2015
BSc in Computer Engineering, Cairo University
Fall 2005 - Spring 2010
Disclaimer: This page contains personal archived (pre-print versions) articles published by IEEE, ACM, and other publishers. Copyright and all rights therein are retained by authors or by other copyright holders. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works, must be obtained from the copyright holder.