Simon Ewing
Software Engineer at Intel Corporation
Springfield, Oregon, United States
Summary
🤩
Rockstar🎓
Top SchoolSimon Ewing is a software engineer with seven years of research and industry experience, currently applying his expertise at Intel on high-performance GPU/OpenCL workloads. He holds a PhD in theoretical chemistry and transitioned from developing classical scattering code as an undergraduate to creating and optimizing quantum-mechanical algorithms for strongly correlated and periodic systems in graduate research. At Intel he contributes to performance-critical libraries such as oneDNN, improving OpenCL kernels, numeric stability, and combined-dimension reduction primitives for better GPU efficiency. Simon blends deep scientific modeling with practical systems engineering, making him adept at turning complex numerical methods into production-quality code. Based in Springfield, Oregon, he brings a rare mix of theoretical rigor and hands-on kernel-level optimization that accelerates both research and real-world applications.
7 years of coding experience
7 years of employment as a software developer
Bachelor of Science - BS, Physical Chemistry, 3.86, Bachelor of Science - BS, Physical Chemistry, 3.86 at University of OregonDoctor of Philosophy - PhD, Theoretical Chemistry, Doctor of Philosophy - PhD, Theoretical Chemistry at University of ChicagoSpringfield High School
Stackoverflow
125reputation
7kreached
0answers
3questions
Github Skills (22)
opencl10
performance-monitor10
c-language10
edn10
standard-library10
performance-analysis10
gpu10
c-library10
common-library10
cprogramming-language10
deep-neural-networks9
neural-network9
deep-learning9
cuda6
pointer6
Programming languages (2)
Github contributions (5)
uxlfoundation/oneDNN
Jun 2022 - Jan 2023
oneAPI Deep Neural Network Library (oneDNN)
Role in this project:
Back-end Developer
Back-end DeveloperContributions:44 reviews, 50 commits, 43 PRs in 6 months
Contributions summary:Simon's contributions primarily involve modifying OpenCL code related to the oneDNN library's GPU implementation, particularly focusing on OpenCL kernels. They fixed data type issues in floating-point operations, optimized vectorized resampling, and enabled post-operations within the reduction implementation. The user also introduced and refined a combined-dimension reduction implementation, indicating a focus on performance optimization and improving the library's functionality on GPUs. Their work encompasses changes to existing kernels and the introduction of new optimized primitives within the GPU/OpenCL framework.
bfloat16sse41avx512openmpopencl
aivscovid19/data_pipeline
Sep 2020 - Jun 2024
collect and process data
Contributions:5 reviews, 10 PRs, 63 pushes in 3 years 9 months
process-datacollectdata
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.