I am a PhD candidate in programming languages and deep learning at the University of Edinburgh.

Naums Mogers

My PhD is supervised by Christophe Dubach and co-supervised by Michel Steuwer, Michael O’Boyle and Kenneth Heafield.

I am a member of the Compiler and Architecture Design Group (CArD), the Institute for Computing Systems Architecture (ICSA) and a visiting student at Mila - Quebec AI Institute and McGill School of Computer Science.

My project focuses on optimizing compilation techniques that benefit from functional intermediate representation (IR) with deep neural nets and GPUs as a case study. I also worked on this topic with Ryota Tomioka while on an internship at Microsoft Research Cambridge. My other interests include software/hardware codesign for DL: while interning at ARM Research Cambridge, I worked with Giacomo Gabrielli and Ali Zaidi on a compiler that generates FPGA designs in the Spatial HLS language with LSTM networks as a case study. I also participate in the teaching of algorithms, machine learning, Java and cognitive science.

Here is my video introduction of my PhD project; you can download my CV here.

Education

MSc by Research in Compilers and Programming Languages
MSc in Artificial Intelligence
BEng in Computer Science (with a year in industry)

Visits & Internships

Visiting Student at Mila - Quebec AI Institute, Montreal, Canada
Graduate Research Trainee at McGill University, Montreal, Canada
Research Intern at Microsoft Research, Cambridge, UK
Collaboration with Huawei at University of Edinburgh
Engineering Intern at Sophos, Abingdon, UK

Publications

Mapping Parallelism in a Functional IR through Constraint Satisfaction: A Case Study on Convolution for Mobile GPUs
Automatic Generation of Specialized Direct Convolutions for Mobile GPUs
Towards Mapping Lift to Deep Neural Network Accelerators
Sensor Organism

Awards

PhD scholarship
1st Prize for the IBM and Swiss Re Hackathon Challenge
Best Poster Award
Best Poster Award
York Award
Accepted to Google Compiler and Programming Language Summit
Accepted to Facebook PhD London Tech Talk
Accepted to Google Inside Look Program
Public Engagement: Raspberry Pi Project Funding

Work Experience

News Annotator (for NLP research) at Thomson Reuters, UK
IT and Digital Summer Intern at EDF Energy, Brighton, UK
Web Designer Intern at Stockholm Environment Institute York
System Administrator / Software Developer at M2 Ltd, Riga, Latvia

Teaching

Object-Oriented Programming
Algorithms, Data Structures And Learning
Introductory Applied Machine Learning
Machine Learning; Algorithms; Microcontrollers
Software Testing
Compiling Techniques
Processing Formal And Natural Languages
Raspberry Pi / Raspbian / Windows 10 IoT

Presentations

Talk, Systems, PL and Compilers Group at McGill University
Poster, Google Compiler and Programming Language Summit'19, Munich, Germany
Talk, ARM Research Summit: "Renegotiating Accelerator Abstractions (Post-Moore's Law)" workshop. Austin, Texas, USA
Talk, Workshop on Emerging Deep Learning Accelerators, HiPEAC, Valencia, Spain
Tutorial, International Symposium on Performance Analysis of Systems and Software (ISPASS), Belfast, UK
Poster, Google Compiler and Programming Language Summit'17, Munich, Germany
Invited talk, Glasgow Systems Seminar, University of Glasgow, UK
Poster, The Scottish Informatics and Computer Science Alliance (SISCA), University of Dundee, UK

Contacts

naums.mogers(at)gmail.com

naums.mogers(at)ed.ac.uk