GLASS
GLASS: Scaling AI Systems
An ARIA-funded Scaling Compute Project
GLASS is a revolutionary new project, rethinking the way we build AI inference systems.
The project aims to solve the existing communication bottleneck in AI systems. The project rethinks system design at multiple levels, from the low level physical design to the highest level application. It combines innovation in photonics, networking, computer architecture, memory systems, hardware/software co-design, distributed systems and more. GLASS will address real-world challenges such as resilience and recovery, manufacturability, and operational constraints.
The Vision
Or how we plan to change computing as you know it
The goal of the project is to develop an AI inference system at 1/1000 of the cost. It aims to fit an AI system with 100's to 1000's of AI accelerators within a single server. A single server that provides so much acceleration power will enable more researchers to do frontier AI research, and for industry and universities to afford developing and using cutting edge AI algorithms.
The project aims to achieve more than just cutting costs and increasing access to resources, but also increasing AI sustainability. The project will provide significant power reduction, coupled with reduced use of physical resources and reduced embodied carbon.
The project will use optical interconnect through glass to connect all the accelerators, removing the existing communications bottleneck. By putting all the accelerators within a single server, we can rethink what a system is: what should be the memory hierarchy? How should it be managed? How to prevent, detect and recover from failures?
This is going to completely change the way we do AI research: from the availability of affordable compute resources, through the rethinking of AI models for systems, to the use of acceleration across many scientific computing domains.
The Team
Prof Noa Zilberman
Prof Noa Zilberman is the Principal Investigator of the GLASS project. She leads the Computing Infrastructure Group at Oxford, exploring scalable, sustainable and resilient networking and computing infrastructure.
Prof Amro Awad
Prof Amro Awad investigates new usecases enabled by emerging memory technologies and architectures, and also explores novel memory architecture optimizations for important workloads such as AI training.
Prof Dominic O'Brien
Prof Dominic O’Brien has a wide range of optoelectronic systems integration projects, successfully delivering high-data rate connectivity
Prof Martin Booth
Prof Martin Booth's research covers a wide range of optical systems engineering, ranging from biomedical imaging through to laser-based precision manufacturing.
Prof Patric Salter
Prof Patrick Salter is passionate about UK manufacturing and translating ideas from academia through to impact in industry.
Prof Dan Rogers
Prof Dan Rogers is focused on power electronics and experimental cooling systems.
Prof Konstantina Vogiatzaki
Prof Konstantina Vogiatzaki explores multiscale computational modelling that help answer fundamental question in the broad field of fluid dynamics, and applying it to cooling systems.
Dr Smita Vijaya Kumar
Senior Researcher in Software Systems
Dr Peng Qian
Senior Researcher in Software Systems
Dr Giovanni Tretola
Postdoctoral Researcher in computational fluid dynamics for Cooling Systems.
Dr Mohan Wang
Postdoctoral Researcher in photonic systems
Dr Kaswar Ali
Senior Researcher in Power Electronics
Mary Nzilani
Programme Manager
Jason Miller
DPhil Student in systems and networks
Haoxiang Huang
DPhil Student in networks
Ziji Chen
DPhil Student in AI systems
Alex Lozano
DPhil Student in AI systems
Boan Fang
DPhil Student in optoelectronic systems
William Taylor
DPhil Student in memory systems
Hakam Atassi
DPhil Student in memory systems
Zhukun Wang
DPhil Student in networks and memory systems
Dr Aleks Ristic-Smith
Postoctoral researcher in power and cooling
Publications
Most of our work is still under wraps, but here are some of our latest outputs:
William Taylor, Sunho Lee, Haoyu Wang, Noa Zilberman, and Amro Awad. VERVE: VErifiable Value Retrieval Leveraging Value rEuse in Accelerator Memory, IEEE ICCD 2026.
Ziji Chen, Steven Chien, Peng Qian, Noa Zilberman. Seeing is believing: The case for hardware-centric inefficiency detection and remediation. ACM SoCC 2026.
Hakam Atassi, Noa Zilberman, Amro Awad. Hardware-Managed Heterogeneous High-Bandwidth Memory and Flash in LLM Inference Systems. IEEE Computer Architecture Letters 2026.
Boan Fang, Martin J. Booth, Patrick S. Salter, and Dominic O'Brien. Comparing Electronic-Photonic Interconnects for Large Scale Advanced Packaging Systems. IEEE Photonics Society Summer Topicals Meeting Series (SUM) 2026.
Mohan Wang, Martin J. Booth, and Patrick S. Salter. Straight directional couplers via scan-engineered index control for dense photonic integration. Optics Letters 51.17, 2026.