Mohammad Ewais

Mohammad Ewais

PhD in Computer Engineering | ML/HPC Architect

I'm currently doing my PhD in Computer Engineering at the University of Toronto, I also work as a ML/HPC Architect at AMD. I have earned my MASc degree from the University of British Columbia, and before that I finished my BSc from Alexandria University. In my PhD, I am currently focused on exploring disaggregated memory architecture for datacenter. At AMD, I work on designing/architecting a line of datacenter GPUs to better support machine learning applications. I possess a strong passion for computer architecture, digital design, and CAD tools. With a comprehensive background spanning hardware and software, I have accumulated over 3 years of experience in ASIC/FPGA design, conducted research in computer architecture and memory hierarchy optimizations for 5+ years in both academia and industry, and contributed to LLVM-based compiler development for over 1 year.

Professional Experience

ML/HPC Architect

Advanced Micro Devices
Toronto, Canada
Nov 2023 - Present2 yearsCurrent

Design and architect datacenter GPUs for machine learning applications. Perform workload analysis, theoretical analysis, and ROI calculations for new architecture features.

GPU ArchitectureML WorkloadsPerformance AnalysisHPC

Compilers Engineer

Huawei Technologies
Toronto, Canada
May 2018 - Aug 20191 year 4 months

Worked on LLVM-based compiler for in-house GPU. Responsible for TableGen pattern matching, optimization passes, and C model debugging.

LLVMGPU CompilersTableGenOptimization

Teaching Assistant

German University in Cairo
Cairo, Egypt
Sep 2015 - Jan 20165 months

Taught digital systems design and microprocessors courses.

VHDLDigital DesignMicroprocessors

Research and Teaching Assistant

American University in Cairo
Cairo, Egypt
Jan 2015 - Aug 20161 year 8 months

Research on STT-RAM as main memory and taught various computer engineering courses.

Linux KernelMemory SystemsComputer Architecture

Education

Academic journey through computer engineering and research

PhD in Computer Engineering

University of Toronto
Toronto, Canada
Sep 2019 - Present6 years 3 monthsOngoing

Focus on disaggregated memory architecture for datacenter applications

MASc in Computer Engineering

University of British Columbia
Vancouver, Canada
Sep 2016 - May 20181 year 9 months

Specialized in cache compression and computer architecture

BSc in Communications and Electronics

Alexandria University
Alexandria, Egypt
Sep 2009 - May 20144 years 9 months

Foundation in electrical engineering and digital systems

15+
Years of Study
3
Degrees
9+
Publications

Skills & Expertise

A comprehensive overview of my technical skills and expertise across various domains

Programming

Concepts

Algorithms80%
Data Structures90%
OOP90%
Multithreading90%
Parallel Archs60%

Languages

C/C++90%
Python80%
Java70%
Go60%
CUDA40%

Skills Overview

Programming

75% avg

Digital Design

70% avg

Computer Architecture

76% avg

Machine Learning

60% avg

Cloud

67% avg

Miscellaneous

66% avg

Publications

Research contributions in computer architecture, memory systems, and FPGA acceleration

2
Journal Paper
4
Conference Paper
1
Poster
1
Workshop Paper
1
Thesis

2023

Journal Paper2023

Disaggregated Memory in the Datacenter: A Survey

Mohammad Ewais, Paul Chow

IEEE Access 11 (2023)

2022

Journal Paper2022

The Future of FPGA Acceleration in Datacenters and the Cloud

Bobda, Christophe, Joel Mandebi Mbongue, Paul Chow, Mohammad Ewais, Naif Tarafdar, Juan Camilo Vega, Ken Eguro

ACM Transactions on Reconfigurable Technology and Systems (TRETS) 15.3 (2022)

2021

Conference Paper2021

A Framework Integrating FPGAs in VNF Networks

Mohammad Ewais, Juan Camilo Vega, Alberto Leon-Garcia, Paul Chow

2021 12th International Conference on Network of the Future (NoF)

Poster2021

FFIVE: An FPGA Framework for Interactive VNF Environments

Juan Camilo Vega, Mohammad Ewais, Alberto Leon-Garcia, Paul Chow

2021 IEEE International Symposium On Field-Programmable Custom Computing Machines (FCCM 2021)

2020

Workshop Paper2020

Decoupling Approximation and Cache Compression

Amin Ghasemazar, Mohammad Ewais, Mieszko Lis

2020 Workshop on Approximate Computing Across the Stack (WAX 2020)

Conference Paper2020

2DCC: Cache Compression in Two Dimensions

Amin Ghasemazar, Mohammad Ewais, Prashant Nair, Mieszko Lis

2020 Design, Automation and Test in Europe Conference and Exhibition (DATE 2020)

2018

Thesis2018

Combining inter and intra-line cache compression

Mohammad Ewais

University of British Columbia

2016

Conference Paper2016

A virtual memory architecture to enhance STT-RAM performance as main memory

Mohammad A Ewais, Mohamed A Omran, Andrew Raafat, Yousra Alkabani

2016 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE 2016)

2014

Conference Paper2014

Smart employment of circuit redundancy to effectively counter trojans (SECRET) in third-party IP cores

Mohammed M Farag, Mohammad A Ewais

2014 International Conference on ReConFigurable Computing and FPGAs (ReConFig14)

Research Impact

My research spans computer architecture, memory systems, cache compression, FPGA acceleration, and datacenter disaggregation. I focus on practical solutions that bridge the gap between theoretical research and real-world applications in high-performance computing.

Let's Connect

Interested in collaboration, research opportunities, or just want to chat about computer architecture?

Contact Information

Location

Toronto, Canada

Send a Message