Back

Ahmad

Nawab

I work as a computational scientist at ECMWF. The main focus of my work is the GPU adaptation of the physical parameterizations in the integrated forecasting system (IFS). Source-to-source translation is a key component of ECMWF's GPU adaptation strategy, and I am one of the core developers of Loki, ECMWF's in-house source-to-source translation tool. Previously, I have also worked on improving the vectorizability of HYDRA, the production computational fluid dynamics code of Rolls-Royce plc.

Session Chair

This person is not chairing any sessions.

Presenter

This person is not presenting any session, minisymposium or paper presentation.

Author

This person is not authoring any minisymposium or paper presentation.

Poster

P33 - Optimizing Data Offload in the IFS Using GPU-Aware Data Structures and Source-To-Source Translation

Tuesday, June 27, 2023 19:30
Climate, Weather and Earth Sciences
Chemistry and Materials
Computer Science, Machine Learning, and Applied Mathematics
Applied Social Sciences and Humanities
Engineering
Life Sciences
Physics
With
Johan Ericsson, Ahmad Nawab, and Balthasar Reuter (ECMWF); Philippe Marguinaud and Judicaël Grasset (Meteo-France); and Michael Lange (ECMWF)

P01 - Achieving Performance Portability on ECMWF’s Open-Source Operational Wave Model ecWAM Using Source-To-Source Translation and GPU-Aware Data-Structures

Tuesday, June 27, 2023 19:30
Climate, Weather and Earth Sciences
Chemistry and Materials
Computer Science, Machine Learning, and Applied Mathematics
Applied Social Sciences and Humanities
Engineering
Life Sciences
Physics
With
Michael Staneker and Ahmad Nawab (ECMWF)