Zaman Lantra

Introduction

I am an assistant professor (Research focussed) in the Department of Computer Science. I completed my PhD in High performance Computing at the University of Warwick (2021-2025), under the supervision of Dr. Gihan Mudalige.

Before my PhD, I worked at the London Stock Exchange Group (LSEG) Technology as a Specialist Software Engineer, where I was responsible for designing and developing performance-critical software components for equity, derivatives and CFD markets. I hold a BSc (Hons) in Electronic and Telecommunication Engineering from the University of Moratuwa, Sri Lanka, and I also completed a research internship at LiveLabs, Department of Information Technology, Singapore Management University, Singapore.

Research Interest

My research focuses on advancing numerical simulation software for high-performance computing, with particular emphasis on massively parallel architectures, reconfigurable computing systems, and compiler and code-generation technologies.

I aim to address the challenges of performance portability and scalability on modern heterogeneous systems, including platform-specific optimizations, as demonstrated during my PhD research developing OP-PICLink opens in a new window, a domain-specific language (DSL) for unstructured mesh-based particle-in-cell (PIC) simulations.

Currently, I am part of the Virtual Exascale Calculations Transform Aviation (VECTALink opens in a new window) project, funded by UKRI and Rolls-Royce, where I work on accelerating production-grade unstructured mesh CFD applications using the OP2Link opens in a new window DSL.

PhD Thesis

Particle-in-cell (PIC) methods are widely used to model plasma dynamics, a key area of research in next-generation energy production through nuclear fusion. Ensuring the performance portability of such simulations across emerging heterogeneous high-performance computing systems has become a critical challenge in scientific computing. One promising approach is the use of high-level abstractions, such as domain-specific languages (DSLs).

In my PhD thesis, we introduced OP-PICLink opens in a new window, a new DSL for unstructured PIC computations, building on the techniques pioneered in OP2Link opens in a new window, a DSL for unstructured mesh algorithms. This work was carried out as part of the ExCALIBUR NEPTUNELink opens in a new window project, in collaboration with the UK Atomic Energy Authority and the University of York.

OP-PIC enables scientists to describe problems at a high level, while relying on automatic source-to-source translation and code generation to produce efficient backend implementations in MPI, OpenMP, CUDA, HIP, and SYCL. This approach achieves performance portability across major HPC architectures using a single unified codebase.

We benchmarked OP-PIC on leading HPC systems including LUMI-G, ARCHER2, Tursa, and Bede, reaching simulation scales exceeding 140 billion elements on up to 1,024 GPU devices. The results were presented at top-tier conferences such as ICPP'24 and SC'24.

Tech Stack : C/C++, Python, MPI, OpenMP, CUDA, HIP, SYCL, Kokkos, Legion, CMake, Make, Spack, Arm Forge DDT, GDB, Valgrind, Intel Advisor/VTune, Nsight compute/nvProf, ROCProfiler, SLURM, Bash, Clang.

Teaching

I was a Senior Graduate Teaching Assistant in the Department of Computer Science during my PhD, where I supported the following undergraduate modules:

• CS118 – Programming for Computer Scientists (Java)
• CS139 – Web Development Technologies (HTML, CSS, Python, Flask, SQLAlchemy)
• CS258 – Database Systems (Java, PostgreSQL)
• MA117 – Programming for Scientists (Java)

I also contributed to exam paper marking for Web Development Technologies and served as a Support Examination Invigilator during the Summer 2023 examination period in the Department of Computer Science.

Publications

• Zaman Lantra, Steven A. Wright, and Gihan R. Mudalige. 2024. OP-PIC - an Unstructured-Mesh Particle-in-Cell DSL for Developing Nuclear Fusion Simulations. In Proceedings of the 53rd International Conference on Parallel Processing (ICPP '24). Association for Computing Machinery, New York, NY, USA, 294–304. https://doi.org/10.1145/3673038.3673130Link opens in a new window

  [slidesLink opens in a new window][videoLink opens in a new window]

• S.A. Wright, C. Ridgers, G.R. Mudalige, Z. Lantra, J. Williams, A.Sunderland, H.S. Thorne, W. Arter. 2024. Developing performance portable plasma edge simulations : a survey, Computer Physics Communications. 109123. ISSN 0010-4655. doi:10.1016/j.cpc.2024.109123

• M. A. Smith, S. A. Wright, Z. Lantra and G. Mudalige, "The P3 Explorer: An Open Database of Performance, Portability, and Productivity," 2025 33rd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP), Turin, Italy, 2025, pp. 512-517, doi: 10.1109/PDP66500.2025.00079Link opens in a new window

• R. Kumarasiri, A. Niroshan, Z. Lantra, T. Madusanka, C. U. S. Edussooriya and R. Rodrigo, "Gait Analysis Using RGBD Sensors," 2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV), Singapore, 2018, pp. 460-465, doi: 10.1109/ICARCV.2018.8581295.
• Kasthuri Jayarajah, Zaman Lantra, and Archan Misra. 2016. Fusing WiFi and Video Sensing for Accurate Group Detection in Indoor Spaces. In Proceedings of the 3rd International on Workshop on Physical Analytics (WPA '16). Association for Computing Machinery, New York, NY, USA, 49–54. https://doi.org/10.1145/2935651.2935659Link opens in a new window
• Archan Misra, Zaman Lantra, and Kasthuri Jayarajah "Ontology-aided feature correlation for multi-modal urban sensing", Proc. SPIE 9831, Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR VII, 98310A (12 May 2016); https://doi.org/10.1117/12.2225143Link opens in a new window