About
Awright!? I’m Perry Gibson, working at the intersection of machine learning📉 and systems🔩.
I currently work at Fractile as a Member of Technical Staff, with a focus on ML Compilers.
In 2024 I completed a PhD at the gicLAB (University of Glasgow), supervised by Dr José Cano Reyes.
I believe that compilers are a key technology for bridging the gap between high-level application code and efficient hardware execution. Domain-specific compilers like Apache TVM, or frameworks for building them, like MLIR are increasingly important in today’s commercial and research landscape.
Compilers also have an important place in the era of accelerated, application focused hardware, both in their design, and for code generation. That’s why I’m at Fractile!
In my PhD, I explored across-stack optimisation of deep neural networks, with a compiler-centric perspective.
You can find some of my research work under /Publications. And other publications and posts under /Posts, and open source contributions under /oss.
Past research visits include the Barcelona Supercomputing Centre (2019, PRACE Summer of HPC) and Northeastern University (2022, Boston).
You can read more about my work on my LinkedIn, GitHub, Google Scholar, or blog.
