Qualification Type: | PhD |
---|---|
Location: | Cambridge |
Funding for: | UK Students, EU Students, International Students |
Funding amount: | Not Specified |
Hours: | Full Time |
Placed On: | 6th September 2024 |
---|---|
Closes: | 2nd October 2024 |
Reference: | NR43165 |
Applications are invited for a PhD student to work on the UK's Advanced Research Invention Agency (ARIA) is supporting an ambitious programme of work that aims to reduce the hardware costs associated with training AI models by more than 1000x.
The objective of our project, funded within this programme, is to develop a scalable and modular simulation framework. This will require multiple levels of simulation focused at different system layers and levels of fidelity. A key goal is to allow novel hardware ideas to be easily incorporated and evaluated, i.e. to aid the development of next-generation hardware for GenAI.
The work at Cambridge (and Imperial) will focus on the simulation of the accelerator hardware. To guarantee simulation fidelity, we will perform cross-validation of our simulation with real FPGA implementations. This will require modelling of both compute hardware and memory subsystems.
There is significant scope for research into the design of such simulation environments, for example (but not limited to): hardware for training Transformers, techniques to allow novel ideas to be specified, modelled and prototyped quickly, methods for rapid and intelligent design-space exploration and optimisation, machine-learning based tools for the rapid and interactive interpretation and analysis of results, new methods to automatically generate and validate simulation models at different levels of fidelity and techniques for high-performance simulation.
Candidates
Applications are encouraged from students with an interest in computer architecture, simulation, optimisation and design-space exploration, machine learning and systems research.
We are looking for a highly motivated and intellectually curious individual capable of thinking and working independently. Applicants are expected to have a first-class honours degree from a UK university, or an equivalent standard from an overseas university, in computer science or a related subject. Having a Master's degree in a relevant subject is highly desirable.
Research Group
PhD projects will be supervised by Prof. Robert Mullins (PI), Prof. Timothy Jones or Dr Rika Antonova at the University of Cambridge. The overall project is led by Dr. Yiren Zhao at Imperial College, who will be supported by Prof. George Constantinides and Prof. Wayne Luk. The team also includes Dr. Mai Luo and Prof. Michael O'Boyle from the University of Edinburgh. Overall, there will be excellent opportunities for collaboration between more than a dozen PhD students and post-doctoral researchers working on this project at Imperial, University of Cambridge and the University of Edinburgh.
Application Process
Please make your application through the University Application Portal: https://www.postgraduate.study.cam.ac.uk/courses/directory/cscspdpcs
Students wishing to pursue a PhD at the University of Cambridge are required to submit:
These positions are open to UK citizens or overseas students. Full details of the University's entrance requirements and scholarships are specified on the following link: https://www.postgraduate.study.cam.ac.uk/
The University actively supports equality, diversity and inclusion and encourages applications from all sections of society.
Type / Role:
Subject Area(s):
Location(s):