Home

Giorgis Georgakoudis

Compiler Engineer, Intel

Compiler optimization, runtime systems, Python for HPC, and parallel programming systems.

I am a compiler and systems engineer specializing in middle-end optimization, runtime systems, and performance engineering. At Intel, I develop compiler optimizations to improve system performance. My work spans LLVM, MLIR, OpenMP, Numba, JIT compilation, and GPU computing, with the goal of improving performance portability and developer productivity for parallel applications.

Focus Areas

• Middle-end compiler infrastructure and optimization with LLVM, Clang, and MLIR
• JIT compilation and runtime specialization for heterogeneous systems
• Runtime systems, GPU offload, and performance engineering
• Python and parallel programming systems with OpenMP and Numba

Projects

Proteus

Proteus is a programmable JIT compiler for C and C++ applications that enables embedded JIT compilation and runtime specialization across CPU, CUDA, and HIP execution paths. Through annotations and programmatic APIs, it folds runtime values into generated code to unlock optimizations such as loop unrolling, constant propagation, and control-flow simplification beyond what static compilation can achieve.

• Led development of Proteus and served as Principal Investigator of the supporting $2.7M, three-year research project at LLNL (2024–July 2026).

PyOMP

PyOMP extends Numba with OpenMP parallel programming abstractions for Python, including directives, runtime functions, and GPU offloading through target constructs. It provides a familiar OpenMP programming model for Python users while enabling JIT-compiled execution across CPU and GPU systems.

• Co-lead and developer

Mneme

Mneme is a framework for recording and replaying GPU kernel executions as standalone, reproducible executables. Built around an LLVM instrumentation pass, it captures the execution context, LLVM IR, and required device memory state for each kernel, enabling isolated replay, compiler experimentation, and autotuning of launch parameters without modifying the original application workflow.

• Contributed to Mneme and its compiler-driven analysis and autotuning workflows at LLNL (2024–July 2026).

OpenMP

• Chair of the OpenMP Python Language Subcommittee, announced by the OpenMP ARB in February 2026
• Contributor to LLVM and OpenMP compiler/runtime technology

Publications & Service

• Publications: Google Scholar
• Open-source: GitHub
• Professional: LinkedIn
• Curriculum Vitae:
  • 1-page (PDF)
  • Short (PDF)
  • Full (PDF)

Contact

Work

giorgis.georgakoudis@intel.com

This page reflects my personal work and views, not official positions of Intel.