Arm supports academic research and recognizes the importance of maintaining strong links between academia and industry for continued research innovation. As part of this mission, Arm Research Collaborations have established seven Centres of Excellence (CoE), broadening research opportunities and strengthening links through a range of activities, including sponsoring students completing their PhDs. Part of a blog series, we take a look at the inspirational work each of our Centres are undertaking, fueling research success and collaboration between academia and industry.
The School of Informatics at the University of Edinburgh is engaged in academic and industrially relevant research, encouraging undergraduates and PhD students to participate in their increasingly collaborative ecosystem. The Arm Edinburgh Centre of Excellence supports fundamental research questions across a wide range of computer science, including compute efficiency and security, heterogeneous parallel systems, and the IoT. Arm Research is sponsoring seven students at Edinburgh, all undertaking research in contrasting areas, ranging from data center architecture to graphics pipeline optimization and stimulation. Each student is assigned an industrial supervisor here at Arm, with some completing an internship on-site to augment their research. Get to know the students and at the Edinburgh Centre of Excellence their research projects.
Our collaboration goes beyond sponsoring students. Together with the University of Michigan, we are traveling beyond Moore's Law - learn more now.
In the final year of his PhD, Lewis’ research hopes to find new ways to automatically speed up real-time rendering applications, and create tools to help developers optimize them across a range of platforms. The project has explored a range of techniques, such as source-to-source compiler optimization, and shader specialization using insights about data-flow patterns from OpenGL execution traces. His internship at Arm has allowed him to gain some valuable experience working on a SPIR-V backend for LLVM.
Alec has previously worked in Paris as a Machine Learning Research Engineer, and his research at Edinburgh lies at the intersection of AI and cyber security. Alec is also due to spend three to six months at Arm working on his project, aiming to investigate using Artificial Intelligence to build automatic network threat detection and counteraction mechanisms. The Connected Home Watch project designs a suite of defensive methods for threat detection, counteraction, and privacy preservation, while also addressing the human and legal factors.
Vasilis’ research interests include the areas of distributed systems and computer architecture, with his PhD research focusing on the theory and practice of enforcing consistency in the datacenter and the multiprocessor. At the theory front, Vasilis’ work uncovers the various abstract specifications that enforce distinct consistency guarantees. In practice, he is conducting investigations into the trade-offs of implementing asynchronous replication protocols, with modern datacenter-grade hardware, for example, RDMA). Vasilis and his supervisors have consolidated their insights on replication protocols with the existing research on the language-level memory models, and have proposed and implemented Kite.
Haoyu is a first year PhD student at Edinburgh, and previously participated in the 2+2 joint program between the University of Edinburgh and the South China University of Technology. His project designs defensive methods for automatic threat detection and counteraction, advancing state-of-the-ad techniques for cyber resilience and applying them in the new home loT setting. Haoyu’s aim is to make homes of the future trustworthy, developing a comprehensive toolbox deployable on future home routers or specialized security modules.
Adarsh’s research targets several areas of memory systems design, aiming to apply the end-to-end philosophy to memory protection wherein he advocates for protection at the highest granularity. This is opposed to intermediary points in the hierarchy, allowing for the highest protection. Instead of using ECC, DRAMRep replicates data redundantly across memory controllers on different processor chips in a multi-socket (NUMA) system. His work also aims to use replication for improved performance by permitting the replicated data to be read and allowing writes to be initiated at either replica, while still maintaining strong consistency.
Dmitrii’s research focuses on two important problems of modern cloud computing: the high latency of address translation for big-memory applications, and the inefficient use of precious memory resources in highly consolidated serverless deployments. With the challenges cloud computing faces today, Dmitrii aims to address the two challenges while fully preserving existing virtual memory abstractions and mechanisms. With his degree in Applied Mathematics and Physics from the Moscow Institute of Physics and Technology (MIPT), we are excited to see the outcome of his research.
Jackson is another of our PhD students at Edinburgh, and has previously carried out an internship at Arm Cambridge in the Compilers team. His work plans to describe the computations performed by several accelerators in a compiler. This involves applying them to a large body of real-world code, and setting out to obtain an understanding about whether there is benefit to compiling existing code to large- to medium-scale accelerators. With the end of Denard scaling, the microprocessor industry is increasingly forced to turn to specialization of hardware, Jackson’s work is incredibly interesting.
“Based on the breadth and internationally recognized quality of its research, the School of Informatics attracts outstanding PhD students across a wide range of topics of direct relevance to us. We are delighted to be able to work with them to help support some of the most talented next generation of computer scientists and engineers. During their projects, our staff benefit from access to cutting edge academic research in areas such as IoT, memory and security, with numerous joint publications and conference presentations. On graduation, many of these students take up positions of employment with Arm or companies in our wider ecosystem, contributing to our success for years to come.” Andrea Kells – Research Ecosystem Director
“Based on the breadth and internationally recognized quality of its research, the School of Informatics attracts outstanding PhD students across a wide range of topics of direct relevance to us. We are delighted to be able to work with them to help support some of the most talented next generation of computer scientists and engineers. During their projects, our staff benefit from access to cutting edge academic research in areas such as IoT, memory and security, with numerous joint publications and conference presentations. On graduation, many of these students take up positions of employment with Arm or companies in our wider ecosystem, contributing to our success for years to come.”
Andrea Kells – Research Ecosystem Director
Our Centres of Excellence are just one way that we collaborate with academia and industry. Find out more about our Collaborations team and how we are helping shape the industry, and read our recent blogs highlighting the work we do. In terms of tools and support, we can also provide research access to IP and technical support. This allows our partners and future collaborators the chance to work with and understand our vision at Arm, helping us build the future of technology.
Learn more about Arm Research Collaborations
This post represents one of Arm Research’s Centres of Excellence. Click the following link to find out about our other established Centres of Excellence: