Allison Piper
Software Engineer at NVIDIA
City of Albany, New York, United States
Summary
🤩
RockstarAllison Piper is a software engineer with 11 years of experience specializing in high-performance C++ and CUDA core compute libraries at NVIDIA. She maintains and optimizes foundational GPU libraries such as Thrust, CUB, and NVBench, focusing on performance tuning, compiler-warning fixes, and robust cross-platform build configurations. Her contributions include implementing managed memory abstractions for STL containers, refactoring device APIs, and improving code generation and maintainability—work that directly impacts widely used open-source CUDA tooling. Based in Albany, NY, she blends backend engineering rigor with performance engineering instincts, often surfacing subtle signedness and execution-space issues that improve long-term stability. Peers rely on her to modernize build systems and deprecate legacy configurations while preserving high-throughput compute behavior.
11 years of coding experience
Github Skills (11)
cuda10
algorithms10
c-language10
cpp10
gpgpu10
cprogramming-language10
gpu10
performance-optimization10
accelerated-computing10
cmake9
c179
Programming languages (12)
Github contributions (5)
NVIDIA/cub
Feb 2020 - Dec 2022
[ARCHIVED] Cooperative primitives for CUDA C++. See https://github.com/NVIDIA/cccl
Role in this project:
Back-end Developer & Performance Engineer
Back-end Developer & Performance EngineerContributions:11 releases, 303 reviews, 299 commits in 2 years 10 months
Contributions summary:Allison primarily contributed to bug fixes and performance optimizations within the CUDA C++ library. Their work involved addressing compiler warnings, correcting signedness issues, and improving code generation through tuning parameters. The user also added and updated CMake configurations, and documentation related to these changes. The user also refactored code to use correct device APIs and corrected several compilation warnings, improving the code's robustness and maintainability.
cxxprimitivesnvidia-hpc-sdknvidiacpp20
NVIDIA/thrust
Feb 2020 - Jan 2023
[ARCHIVED] The C++ parallel algorithms library. See https://github.com/NVIDIA/cccl
Role in this project:Back-end Developer
Back-end DeveloperContributions:12 releases, 247 reviews, 490 commits in 2 years 11 months
Contributions summary:Allison primarily contributed to the Thrust library by adding missing header includes, cleaning up warnings, and fixing code that generated execution space warnings. The user also implemented a new managed memory pointer class to support STL containers with universal memory allocators and integrated various Thrust algorithms and random number generators. Further contributions involved the deprecation of older C++ standards and compiler versions, and updating the build configuration, testing and CUDA library targets.
c-plus-pluscxxnvidia-hpc-sdknvidiacpp20
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.