PatrickĀ Stotko
PhD Candidate
Bonn, North Rhine-Westphalia, Germany
Summary
š¤©
RockstarPatrick Stotko is a PhD candidate and experienced software engineer with nine years of hands-on expertise in high-performance back-end systems and GPU-accelerated data structures. Based in Bonn and currently working as a postdoctoral researcher at the University of Bonn, he focuses on performance engineering for large-scale 3D data processing, contributing significant optimizations to the widely used Open3D library. His open-source work on stdgpu demonstrates deep proficiency in CUDA backend design, memory-leak fixes, and efficient STL-like GPU data structures that improve reliability and compile-time robustness. Patrick blends academic rigor with production-grade engineering, often tackling low-level dependency and architecture issues that yield measurable runtime improvements.
9 years of coding experience
Github Skills (10)
cuda10
data-structures10
c-language10
cpp10
gpgpu10
cprogramming-language10
performance-optimization10
data-structure10
3d10
gpu9
Programming languages (5)
Github contributions (5)
stotko/stdgpu
Aug 2019 - Nov 2022
stdgpu: Efficient STL-like Data Structures on the GPU
Role in this project:
Back-end Developer & Performance Engineer
Back-end Developer & Performance EngineerContributions:4 releases, 6 reviews, 468 commits in 3 years 3 months
Contributions summary:Patrick focused on improving the performance and functionality of the `stdgpu` library by addressing issues in core data structures and implementing optimizations. The user's contributions included fixing missing includes, refactoring code, and moving platform-specific code to a CUDA backend for enhanced performance. The commits also involved improvements to data structure functionalities, enhancing efficiency and reliability. Furthermore, the user addressed compilation errors and fixed warnings, indicating a focus on code quality and robust performance.
gpgpuhipopenmpopenclgpu-acceleration
isl-org/Open3D
Apr 2021 - Oct 2021
Open3D: A Modern Library for 3D Data Processing
Role in this project:Back-end Developer & Performance Engineer
Back-end Developer & Performance EngineerContributions:123 reviews, 67 commits, 68 PRs in 5 months
Contributions summary:Patrick primarily focused on improving the performance of the `isl-org/open3d` repository, specifically in the backend and core components. Their work included updating and optimizing dependencies, such as `stdgpu`, which is a core component for 3D data processing. They addressed memory leaks and implemented new fixed-size integer data types to enhance the library's functionality and efficiency. Furthermore, the user made changes related to CUDA architectures, which further suggests performance optimization efforts.
python3d-perceptionodometrytensorflowpointcloud
Find and Hire Top DevelopersWeāve 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.