View Profile

Ahmad Tarraf

Computer Science · TU Darmstadt

https://researchid.co/ahmad.tarraf
@parallel.informatik.tu-darmstadt.de
158Google Scholar Citations
7Google Scholar h-index
5Google Scholar i10-index

Biography

Dr. Ahmad Tarraf is a senior researcher in computational science at the Technical University of Darmstadt (TUDa), where he has worked since 2021 on performance prediction, behavioral modeling, and optimization of High-Performance Computing (HPC) applications and systems within the Laboratory for Parallel Programming. His research focuses on efficient file and storage systems, malleability, performance analysis, and machine learning in HPC.He has contributed to several national and EuroHPC projects, including ADMIRE and DEEP-SEA, and is currently pursuing his habilitation.

Education

Dr. Tarraf earned his B.Sc. in Mechatronics Engineering from RHU Lebanon in 2013 and his M.Sc. in Mechatronics Engineering from TUDa in 2016. In 2017, he joined the Institute of Computer Science at the University of Frankfurt as a research assistant, exploring the formal abstraction and verification of analog mixed-signal circuits. He received his doctoral degree (Dr. rer. nat.) in Computer Science from the University of Frankfurt in early 2021, graduating Magna Cum Laude.

Recent Google Scholar Publications

  1. ENSIMA-Energieoptimiertes High-Performance Computing für Finite-Elemente-Simulationen in der Produktentwicklung
    Hannover: Technische Informationsbibliothek , 2026, 2026
  2. When AI Bends Metal: AI-Assisted Optimization of Design Parameters in Sheet Metal Forming
    arXiv preprint arXiv:2511.22302 , 2025, 2025 | Citations: 1.0
  3. Fantastic Hardware Counters and How to Find Them: Automating the Detection of Noise-Resilient Performance Counters in HPC
    Proceedings of the SC'25 Workshops of the International Conference for High … , 2025, 2025 | Citations: 1.0
  4. EquilibrIO: Taming the I/O Tides in High-Performance Computing
    2025 IEEE International Conference on Cluster Computing (CLUSTER), 1-12 , 2025, 2025
  5. A deep look into the temporal i/o behavior of hpc applications
    2025 IEEE International Parallel and Distributed Processing Symposium (IPDPS … , 2025, 2025 | Citations: 4.0

Links