Naums Mogers
PhD student in AI and optimising compilation
I am a third year PhD student in the CDT Pervasive Parallelism at the University of Edinburgh. My PhD is supervised by Dr Christophe Dubach and co-supervised by Dr Michel Steuwer; I am a member of the Lift research group.
My research interests are deep neural networks (DNN), optimising compilation and optimisation of DNN for portable performance. I have worked on these topics within my PhD project, as a research intern at Microsoft Research and ARM Research and in a yearlong collaboration with Huawei. My PhD work includes extension of a functional data-parallel language Lift, its IR and a compiler implemented in Scala to generate optimised ML kernels in OpenCL, in a proprietary BrainWave language and hardware accelerator designs in Spatial.
My past projects include OpenCL and Python-based neural network-accelerated ant swarm simulation (Bachelor’s project) and programming microcontroller-driven robots in C and Python. I worked with FPGAs, Raspberry Pi, Arduino and Mbed microcontrollers; in my research, I have worked with NVIDIA and ARM GPUs. My research includes extending Caffe functionality for optimised execution on Android, using Tensorflow and PyTorch; in the six internships I did, I worked on an antivirus core in C, C++, Python and Bash, wrote websites using PHP, JavaScript and MySQL and developed accounting software in Visual Basic. I participate in teaching of algorithms, machine learning, Java and cognitive science.
For more information, see my talk slides, research poster and project page.

Education
Doctor of Philosophy (PhD) in
Optimising Compilation of Machine Learning Models for Heterogeneous Hardware
Supervised by Christophe Dubach @ University of Edinburgh
The focus of my research is rewrite rules-based compilation of the functional domain-specific language Lift for DNNs into OpenCL. The goal is to abstract DNNs from hardware without losing neither device-specific optimisations, nor performance-preserving portability. My approach involves expressing DNNs functionally, encoding parametrised optimisations as rewrite rules and exploring a huge search space of optimisations and their parameters. In addition to NVIDIA GPUs, I targeted ARM Mali GPUs for the yearlong collaboration with Huawei, where I cross-compiled DNN-code for HiKey.
Master of Science (MSc) by Research in
Optimisation of CNNs Using A Functional Data-Parallel Language
Supervised by Christophe Dubach @ University of Edinburgh
Within this project, I expressed a CNN in the functional language Lift and explored the optimisational space of data tiling and grouping and weighting sequentialization, exploiting coalesced memory accesses and data locality. I presented a poster on this work at the Google PhD Summit in Munich.
Master of Science (MSc) in
Artificial Intelligence
Supervised by Christophe Dubach @ University of Edinburgh
Dissertation title: ‘Expressing Artificial Neural Networks In A Functional Data-Parallel Language For GPU Acceleration’. The curriculum included courses in Machine Learning, Robotics and Cognitive Science.
Bachelor of Engineering (BEng) in
Computer Science (with a year in industry)
Supervised by Simon O'Keefe @ University of York
Dissertation title: ‘Memory In Simulated Swarms’. The curriculum was focused on system programming (schedulability analysis, embedded software, real-time systems, compilers) and artificial intelligence (neural computing, search algorithms, multi-agent systems, swarm intelligence).
Research Internships & Collaborations

Research Intern
ARM Research, CambridgeSep 2019 - Dec 2019
My project while at the ARM Architecture Research group focused on using rewriting compilation to generate optimal hardware accelerator designs for compute-intensive applications such as LSTM networks. To this end, I extended the intermediate representation and the compiler of the Lift compiler to generate HDL descriptions in the Spatial language.

Research Intern
Microsoft Research, CambridgeAug 2018 - Oct 2018
I worked on the project BrainWave, extending the functional data-parallel Lift compiler to a specialized machine learning accelerator. This work included extensive changes to all parts of the compilation chain including type checking, memory management, rewriting and code generation.

Collaboration with Huawei
University of EdinburghSep 2017 - Aug 2018
Within this yearlong collaboration with Huawei, I focused on optimising CNNs for embedded devices, which included porting Caffe to the Android OS on the Huawei Kirin 960-based HiKey 960 board with ARM Mali G71 GPU.

Research Intern
York Centre for Complex Systems Analysis (YCCSA)Jul 2015 - Sep 2015
I designed a biologically inspired cellular model for a Wireless Sensor Network of Arduinos, capturing such biological properties as adaptivity, self-organization and fault-tolerance. Research topics covered include Artificial Epigenetic Regulatory Networks, Genetic Programming and Cell Signalling.
Awards
IBM and Swiss Re first prize
September 2016, HackZurichMy team won in the IBM & Swiss Re challenge against 20 teams in the largest European hackathon HackZurich. We also became one of 25 finalists out of 152 teams in the main hackathon challenge. We developed a Machine Learning app for risk prediction using home IoT sensors and IBM analytic technologies.
YouTube demo
Best Poster Award
March 2016, National Student Research ConferencePoster on my summer research project "The Sensor Organism" at YCCSA.
Poster (PDF)
Project blog
York Award
July 2015, The University of YorkThe York Award is a programme of personal and skills development offered by the University of York in partnership with leading public, private and voluntary sector organisations.
Best Poster Award
October 2015, York Doctoral SymposiumPoster on my summer research project "The Sensor Organism" at YCCSA.
Poster (PDF)
Project blog
Teaching
Teaching Assistant / Marker, University of Edinburgh
Object-Oriented Programming (2017 - 2019)
Teaching Assistant, University of Edinburgh
Introductory Applied Machine Learning (2017 - 2018)
Marker, University of Edinburgh
Machine Learning; Algorithms; Microcontrollers (2008 - 2019)
Tutor, Facultative School For Talented Children
Software Testing (2017)
Tutor, University of Edinburgh
Compiling Techniques (2016)
Demonstrator, University of Edinburgh
Processing Formal And Natural Languages (2016)
Marker, University of Edinburgh
Raspberry Pi / Raspbian / Windows 10 IoT (2016)
Workshop tutor, Microsoft Student Partners
Scholarships
CDT Pervasive Parallelism2016 – 2020, University of EdinburghFour-year scholarship sponsored by the Engineering and Physical Sciences Research Council. |
|
Public Engagement: Raspberry Pi project2014, University of YorkThrough a call for proposals, I acquired funding to design and develop a Raspberry Pi-related project that helps promote technology in schools. The project included microcontroller programming in Python and Scratch, electric circuit design and use of actuators. I conducted a Raspberry Pi workshop for schoolteachers and participated in technology exhibition. |
Presentations
Google Compiler and Programming Language Summit 2019, Munich, Germany
Talk (Sep 2019): Functional Interface for Performance Portability on Parallel Accelerators (PDF)
ARM Research Summit: "Renegotiating Accelerator Abstractions (Post-Moore's Law)" workshop. Austin, Texas, USA
Talk (Jan 2019): Towards Mapping Lift to Deep Neural Network Accelerators (PDF)
Workshop on Emerging Deep Learning Accelerators (HiPEAC), Valencia, Spain
Tutorial (Apr 2018): Lift: Performance Stencil Code Generation with Lift (Tutorial page)
International Symposium on Performance Analysis of Systems and Software (ISPASS), Belfast, UK
Poster (Dec 2017): Optimisation of Neural Computations Using a Functional Data-Parallel Language (PDF)
Google Compiler and Programming Language Summit 2017, Munich, Germany
Invited talk (Oct 2017): Computational Optimisation of CNNs Using a Functional Data-Parallel Language
Glasgow Systems Seminar, University of Glasgow, UK
Poster (Jun 2017): Optimisation of Neural Computations Using a Functional Data-Parallel Language (PDF)
The Scottish Informatics and Computer Science Alliance, University of Dundee, UK
Attended Academic Events

ARM Research Summit
September 2019, ARM, Austin
Gave a talk on functional interfaces as a good match for the abstraction between a wide range of applications and hardware accelerators. Attended a great set of keynotes, talks and panel discussions.

Google PhD Summit
December 2017, Google Munich
I presented a poster on my research project and participated in the round tables where Google engineers shared highlights of Google’s latest research in the area of programming language implementation and how this research is applied to compilers and language tooling at Google.

Google Inside Look
August 2017, Google London
Selected by Google for their exclusive Inside Look Program, offering top Technical students a fully sponsored two day program of tech talks, workshops, and other technical development content. Awarded to only 31 students out of thousands of applicants from Europe, Middle East and Africa.

Facebook PhD London Tech Talk
October 2018, Facebook London
Selected by Facebook for a PhD Open House event for a talk and panel about research at Facebook.
Work Experience
Jul 2014
Engineering Intern
SophosMy responsibilities included antivirus engine development in C/C++/Python, manual and automated testing, code reviews, debugging, documentation maintenance and software release preparation. My team employed Agile Development practices including pair programming and daily planning meetings.
Sep 2012
IT and Digital Summer Intern
EDF EnergyFull-time internship at R&D department in C++ OCR software development and IT support.
Aug 2012
Web Designer Intern
Stockholm Environment Institute YorkPart-time internship in web development.
Dec 2014
System Administrator / Software Developer
M2 LtdPart-time during the academic year and full-time during summers, my responsibilities included PHP and Visual Basic development, and IT support.
Publications
- Naums Mogers, Valentin Radu, Lu Li, Jack Turner, Michael O'Boyle, and Christophe Dubach. "Automatic Generation of Specialized Direct Convolutions for Mobile GPUs", at General Purpose Processing Using GPU (GPGPU ’20). San Diego, 2020. PDF
- Naums Mogers, Aaron Smith, Dimitrios Vytiniotis, Michel Steuwer, Christophe Dubach, Ryota Tomioka. "Towards Mapping Lift to Deep Neural Network Accelerators", at the Workshop on Emerging Deep Learning Accelerators (EDLA) @ HiPEAC. Valencia, 2019. PDF
- Naums Mogers, Dimitris Lagos, and Martin Albrecht Trefzer. "The Sensor Organism", York Doctoral Symposium. York, 2015.