The résumé of Gus Henry Smith. Email me at gussmith@cs.washington.edu; see my website at justg.us.

Education

University of Washington

Paul G. Allen Center for Computer Science & Engineering

Pursuing Ph.D. since fall of 2018. Advised by Luis Ceze and Zach Tatlock. I work at the intersection of computer architecture and programming languages, exploring how we can use concepts from programming languages to make hardware design easier and the software/hardware boundary more seamless.

Penn State

The Schreyer Honor’s College

Graduated with combined M.S./B.S. in Computer Science and Engineering in spring of 2018. Advised by Vijaykrishnan Narayanan and John Sampson.

Research Projects

Glenside

UW SAMPL Lab/Real-time Machine Learning

Since the start of 2020, I have been working on software–hardware codesign for machine learning accelerators. My goal is to explore what happens when we treat hardware and compiler design as a program rewriting problem, allowing us to explore software and hardware transformations simultaneously. See the project’s GitHub page for more information.

Bring Your Own Datatypes

UW SAMPL Lab

From 2018–2020, I worked on a project enabling the exploration of new, nontraditional datatypes (i.e., alternatives to IEEE 754 floating point) in TVM, a deep learning compiler. I presented this work for my qualifying project presentation at UW in the winter of 2020.

Well Rounded

CSE 512 19sp (Data Viz with Jeff Heer) Final Project

In this final project, we visualized the posit datatype, aiming to convey how posits spread themselves through the space of real numbers. This was completed as a final project for Jeff Heer’s Data Visualization course in 19sp at the University of Washington. The project was inspired by my work in the datatypes space, and was completed with some of my architecture colleagues in my cohort.

Static Analysis for Processing in Memory Accelerator Design

PSU Microsystems Design Lab

Completed as my Master’s thesis at Penn State. Given a model of accelerating computation using Processing in Memory, I used LLVM to statically analyze workloads and detect potentially offloadable code sections.

ThirdEye: Shopping Assistant for the Visually Impaired

PSU Microsystems Design Lab

My undergraduate research at Penn State involved building a wearable system to assist the visually impaired in everyday tasks.

Industry Experience

Microsoft

Research Intern, AI and Advanced Architectures

In summer of 2019, I used my compilers experience to statically analyze deep learning workloads.

Google

Software Engineering Intern, Fuchsia

In summer of 2018, I implemented the RFCOMM protocol for one of Google’s OSes, Fuchsia.

Google

Software Engineering Intern, Chrome

In summer of 2017, I helped the Chrome Remote Desktop team identify and implement optimizations for embedded devices such as the Raspberry Pi.

Google

Software Engineering Intern, Android Internal Tools

In summer of 2016, I completed an internship writing Java-based Android profiling tools.

Conference Help