Computer Systems
Computer Systems research at the School of Computing Science, University of Glasgow spans the hardware–software stack, developing scalable and efficient computing infrastructures from computer architecture and compilers to distributed systems, high-performance computing (HPC) and AI systems.
A central focus is hardware–software co-design, ensuring that compilers, runtime systems and programming models exploit multicore and manycore processors, GPUs, FPGAs, ASICs, AI accelerators and open architectures such as RISC-V. This improves performance, portability and efficiency across heterogeneous platforms while informing future hardware design.
The Glasgow Parallelism Group (GPG) investigates parallel and distributed computing, including application scaling from shared-memory systems to large-scale HPC and cloud infrastructures. Research addresses performance portability, parallel execution and accelerator-rich systems, emphasising open-source development and reproducibility. Distributed systems research examines how computation and data are managed across cloud, edge and cyber-physical environments, tackling orchestration, heterogeneity and latency across geographically distributed resources. The Glasgow Intelligent Computing Laboratory (gicLAB) advances AI systems through hardware–software co-design for machine learning and data-intensive workloads, including specialised accelerators and their efficient programming and deployment. Across these areas, the integration of platform design, systems software and reproducible research is a defining strength.
Project Highlights
dAIEDGE :A network of excellence for distributed, trustworthy, efficient and scalable AI at the Edge
dAIEDGE (A network of excellence for distributed, trustworthy, efficient and scalable AI at the Edge), funded by Horizon Europe. The dAIEDGE Network of Excellence (NoE) seeks to strengthen and support the development of a dynamic European cutting-edge AI ecosystem under the umbrella of the European Lighthouse for AI, and to sustain the development of advanced AI.
SECDA-DSE: Automated Design Space Exploration of FPGA-based Accelerators using LLMs
SECDA-DSE (Automated Design Space Exploration of FPGA-based Accelerators using LLMs), funded by UKRI APRIL AI Hub. An automated design space exploration framework that leverages LLMs to efficiently navigate hardware design spaces and generate optimised accelerator architectures. SECDA-DSE reduces design effort, accelerates development time, and improves the performance and scalability of FPGA-based AI accelerator designs.
M4Secure: Making memory management more secure
M4Secure (making memory management more secure), funded by EPSRC and Led by Jeremy Singer. M4Secure improves software security by developing an open-source framework for customizable, secure memory management libraries.