Spencer Spenst
Co-Founder at Thinky.gg
Abbotsford, British Columbia, Canada
Summary
👤
Senior🎓
Top SchoolSpencer Spenst is a full-stack software engineer and serial founder with 10 years of experience building product-focused architectures and polished front-end experiences from Abbotsford, British Columbia. As Co-Founder of LineLint and founder of Thinky.gg, he blends hands-on engineering with product leadership, shipping customer-facing systems and startup MVPs. His background includes enterprise-scale work at Microsoft on the Universal Store and pricing/availability systems, plus research and teaching roles at UBC that reflect a strong computer engineering foundation. An active contributor to GPGPU-Sim, he has enhanced CUDA/PTX parsing and simulation support—demonstrating rare low-level GPU and systems expertise alongside his web and product work. This mix of systems-level contributions and startup delivery makes him comfortable bridging deep technical challenges and fast product iterations.
10 years of coding experience
5 years of employment as a software developer
Bachelor of Applied Science, Computer Engineering, Bachelor of Applied Science, Computer Engineering at The University of British Columbia
French, English
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (7)
cuda10
c-language10
cprogramming-language10
ptx10
parsing9
parse9
parser9
Programming languages (4)
Github contributions (5)
gpgpu-sim/gpgpu-sim_distribution
May 2016 - Aug 2016
GPGPU-Sim provides a detailed simulation model of contemporary NVIDIA GPUs running CUDA and/or OpenCL workloads. It includes support for features such as TensorCores and CUDA Dynamic Parallelism as well as a performance visualization tool, AerialVisoin, and an integrated energy model, GPUWattch.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:38 commits, 5 PRs in 3 months
Contributions summary:Spencer primarily worked on enhancing the GPGPU-Sim simulator, focusing on CUDA and PTX code parsing and execution. Their contributions involved modifications to the cuobjdump utility for parsing PTX and ELF code, enabling the simulation of CUDA binaries. Furthermore, the user implemented functionalities for CUDA stream creation and the SST instruction, which is a domain specific function, and incorporated a basic implementation of the BSMAD instruction, improving the simulator's capabilities.
simsimulationgpgpuopenclnvidia
sspenst/thinky.gg
Jan 2022 - Feb 2023
A platform dedicated to high-quality puzzle games
Contributions:89 reviews, 718 commits, 878 PRs in 1 year
puzzlegamepathshortest-path
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.