Andriy Glustsov
Software Engineer at Intel Corporation
San Diego, California, United States
Summary
🤩
Rockstar🎓
Top SchoolAndriy Glustsov is a seasoned software engineer with 13+ years specializing in bare-metal and Linux kernel development for ARM-based SoCs, drivers, and system bring-up for telecom baseband processors. He combines low-level firmware and device driver expertise (CPRI, PCIe, SRIO, IPSec, SPAcc) with higher-level system and application design in C++ and Java across Windows, Windows CE and embedded Linux. At Intel and Mindspeed he focused on performance-sensitive validation and firmware that bridges silicon and system software, and his open-source work includes performance and multithreading improvements to high-profile projects like oneDNN and ISPC. Comfortable across kernel, firmware and user-space layers, he also brings database and protocol experience (PostgreSQL, ISO-8583, EMV) that informs robust validation and integration. Based in San Diego, he blends deep hardware-adjacent engineering with practical software architecture, often surfacing subtle performance fixes that improve real-world throughput.
13 years of coding experience
12 years of employment as a software developer
Master's degree, Computer Science, Master's degree, Computer Science at Donec'kij Nacional'nij Tehnicnij Universitettechnician, computer engineering, technician, computer engineering at Donetsk Technical School of Industrial Automatics
Stackoverflow
5,874reputation
338kreached
127answers
13questions
assembly
top-5%
Github Skills (37)
opencl10
programming-language10
c-language10
multithreading10
llvm10
windows10
gpu-programming10
compiler-compiler10
deep-learning10
thread10
hyper-threading10
performance-optimization10
convolution10
simd10
compiler10
Programming languages (7)
Github contributions (5)
uxlfoundation/oneDNN
Dec 2021 - Oct 2022
oneAPI Deep Neural Network Library (oneDNN)
Role in this project:
Back-end Developer & Performance Engineer
Back-end Developer & Performance EngineerContributions:149 reviews, 30 commits, 62 PRs in 9 months
Contributions summary:Andriy primarily focused on optimizing and enhancing the oneDNN library, particularly for GPU-accelerated deep neural network computations. Their contributions involved refining the OpenCL kernels, specifically removing obsolete code and extending zero padding to the batch dimension in reorder operations. They also implemented on-the-fly zero points within the JIT convolution kernels and introduced enhancements like better mask handling, showing a focus on improving performance and expanding the library's capabilities. The user was involved in adding zero points to the sum post-op and enabling zero points for deconvolutions.
neural-networkoneapionednndeep-learningdeep-neural-networks
ispc/ispc
Aug 2014 - Jun 2015
Intel® Implicit SPMD Program Compiler
Role in this project:Back-end Developer
Back-end DeveloperContributions:42 commits in 10 months
Contributions summary:Andriy primarily focused on improving the multi-threading capabilities of the Intel SPMD Program Compiler (ISPC), specifically addressing issues on the Windows platform. Their contributions involved modifying the test framework (`run_tests.py`) to correctly handle multithreading by implementing a queue-based waiting mechanism instead of a thread join loop. Furthermore, the user added comments to explain the implemented fixes. They also added a patch for LLVM 3.5 to enable proper debugging under Windows.
compilerspmdispcprogramming-languageintel
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.