Dissertation Defense

Improving Programming Support for Hardware Accelerators Through Automata Processing Abstractions

Kevin Angstadt
2411 EECS BuildingMap
The adoption of hardware accelerators, such as Field-Programmable Gate Arrays, into general-purpose computation pipelines continues to rise, driven by recent trends in data collection and analysis as well as pressure from challenging physical design constraints in hardware. The architectural designs of many of these accelerators stand in stark contrast to the traditional von Neumann model of CPUs. Consequently, existing programming languages, maintenance tools, and techniques are not directly applicable to these devices, meaning that additional architectural knowledge is required for effective programming and configuration. Current programming models and techniques are akin to assembly-level programming on a CPU, thus placing significant burden on developers tasked with using these architectures. Because programming is currently performed at such low levels of abstraction, the software development process is tedious and challenging and hinders the adoption of hardware accelerators.
This dissertation explores the thesis that theoretical finite automata provide a suitable abstraction for bridging the gap between high-level programming models and maintenance tools familiar to developers and the low-level hardware representations that enable high-performance execution on hardware accelerators. We adopt a principled hardware/software co-design methodology to develop a programming model providing the key properties that we observe are necessary for success, namely performance and scalability, ease of use, expressive power, and legacy support.  Our programming model includes two new, front-end programming interfaces, an interactive high-performance debugger, and two novel automata-derived architectures.  Using empirical studies, logical reasoning, and statistical analyses, we demonstrate that our prototype artifacts scale to real-world applications, maintain manageable overheads, and support developers’ use of hardware accelerators. Collectively, the research efforts detailed in this dissertation help ease the adoption and use of hardware accelerators for data analysis applications, while supporting high-performance computation.


Sonya Siddique

Faculty Host

Prof. Westley Weimer