Guray Ozen   Senior Compiler Engineer at NVIDIA Contact

Research

Guray Ozen is a compiler software engineer at NVIDIA. His current research focus is on how the C, C++, Fortran languages, and OpenMP/OpenACC programming models should evolve to take advantage of the GPUs in the HPC area. He has made significant contributions to many production compilers such as clang, flang, and NVIDIA HPC compilers (formerly PGI compilers). Before joining NVIDIA, he worked in programming models team at Barcelona Supercomputing Center (BSC) from 2013 to 2018 while doing his Ph.D. in Universitat Politecnica de Catalunya – BarcelonaTech.

Language Committee Activities: OpenMP and OpenACC to represent NVIDIA.

Work

• NVIDIA, Compiler Software Engineer, NVIDIA HPC Compilers, GPU Group, 2018 - present
• NVIDIA, Compiler Research Intern, NVIDIA HPC Compilers, GPU Group, 2017
• IBM T.J. Watson Research Center, Short-term Researcher, Advanced Compilers Group, Yorktown Heights, New York, USA, 2016
• Barcelona Supercomputing Center, Researcher Assistant, Barcelona, Spain, 2013 - 2017
• Veripark, Akbank Software Engineer, Istanbul, Turkey, 2010 - 2012

Education

• PhD in Computer Architecture, 2018 (Excellent Cum Laude)  - BarcelonaTech, Universitat Politècnica de Catalunya (UPC), Spain.
• Compiler and runtime based parallelization and optimization for GPUs, Advisors: Jesus Labarta, Eduard Ayguade
• [PDF]
• MSc High-Performance Computing, 2014  - BarcelonaTech, Universitat Politècnica de Catalunya (UPC), Spain
• BSc in Computer Science Engineering, 2010  - Dokuz Eylul University, Turkey

Publications

• Performant Portable OpenMP [accepted]
  • CC22, Guray Ozen, Michael Wolfe
  • [PDF] [VIDEO]  [DOI]
• Non-Recurring Engineering (NRE) Best Practices: A Case Study with the NERSC/NVIDIA OpenMP Contract
  • SC21, Christopher Daley, Annemarie Southwell, Rahulkumar Gayatri, Scott Biersdorff, Craig Toepfer, Guray Ozen, Nicholas Wright
  • [PDF]
• OpenMP GPU Offload in Flang and LLVM
  • LLVM-HPC@SC18, Guray Ozen, Simone Atzeni, Michael Wolfe, Annemarie Southwell, Gary Klimowicz
  • [PDF]
• Collective Dynamic Parallelism for Directive Based GPU Programming Languages and Compilers
  • PACT 2016. Guray Ozen, Eduard Ayguade, Jesus Labarta
  • [PDF] [DOI]
• Offloading Support for OpenMP in Clang and LLVM
  • LLVM-HPC@SC16. Samuel Antao, Alexey Bataev, Arpith Jacob, Alexandre Eichenberger, Georgios Rokos, Matt Martineau, Tian Jin, Guray Ozen, Zehra Sura, Tong Chen, Hyojin Sung, Carlo Bertolli and Kevin O'Brien 
  • [PDF] [SLIDES] [DOI]
• Multiple Target Task Sharing Support for the OpenMP Accelerator Model
  • IWOMP 2016. Guray Ozen, Sergi Mateo, Eduard Ayguade, Jesus Labarta and James Beyer
  • [PDF] [SLIDES] [DOI]
• Exploring Dynamic Parallelism in OpenMP 
  • WACCPD@SC15. Guray Ozen, Eduard Ayguade, Jesus Labarta
  • [PDF] [SLIDES] [DOI]
• On the Roles of the Programmer, the Compiler and the Runtime System When Programming Accelerators in OpenMP
  • IWOMP 2014. Guray Ozen, Eduard Ayguade, Jesus Labarta
  • [PDF] [SLIDES] [DOI]

Talks

• Thinking OpenMP with NVIDIA HPC Compilers
  • NASA Advanced Supercomputing (NAS) Division, 2021
  • [Summary] [PDF]
• Accelerating Applications for NERSC's Perlmutter Supercomputer Using OpenMP and NVIDIA's HPC SDK
  • GPU Technology Conference (GTC) 2021, Silicon Valley Christopher Daley, Guray Ozen
• Compiler and Runtime Based Parallelization and Optimization for GPUs
  • SC18 Doctoral Showcase, Guray Ozen, Eduard Ayguade, Jesus Labarta
  • [Summary] [Poster] [PDF]
• Multi-target Task-Based Programming Model Exploiting OpenACC GPU Kernel
  • GPU Technology Conference (GTC) 2017, Silicon Valley
  • [SLIDES]