Pioneering a New Path in Parallel Programming Beyond Moore’s Law

Informations projet

BeyondMoore

N° de convention de subvention: 949587

DOI

10.3030/949587

Date de signature de la CE 13 Octobre 2020

Date de début 1 Août 2021

Date de fin 31 Juillet 2027

Financé au titre de

• EXCELLENT SCIENCE - European Research Council (ERC)

Coût total

€ 1 500 000,00

Contribution de l’UE

€ 1 500 000,00

Coordonné par

KOC UNIVERSITY
Türkiye

CORDIS fournit des liens vers les livrables publics et les publications des projets HORIZON.

Les liens vers les livrables et les publications des projets du 7e PC, ainsi que les liens vers certains types de résultats spécifiques tels que les jeux de données et les logiciels, sont récupérés dynamiquement sur OpenAIRE .

Livrables

Open Research Data Pilot (1)

Data Management Plan

The project is part of the Open Research Data Pilot and is thus fully committed to ensure the open access of all its relevant results and data The primary results of the project are expected to take the form of an opensource software available through the project website and public repositories Even though it was linked to the first WP it is related to all the WPs

Publications

Thesis and dissertations (2)

Autonomous Execution for Multi-GPU Systems: CPU-Free Blueprint and Compiler Support

Auteurs: Javid Baydamirli
Publié dans: 2023
Éditeur: Koç University

GPU-Centric Communication Schemes: When CPUs Take a Back Seat

Auteurs: Ismayil Ismayilov
Publié dans: 2023
Éditeur: Koç University

Conference proceedings (9)

P-MoVE: Performance Monitoring and Visualization with Encoded Knowledge

Auteurs: Fatih Taşyaran, Osman Yasal, José A. Morgado, Aleksandar Ilic, Didem Unat, Kamer Kaya
Publié dans: SC24-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2025, Page(s) 1531-1542
Éditeur: IEEE
DOI: 10.1109/scw63240.2024.00193

Snoopie: A Multi-GPU Communication Profiler and Visualizer

Auteurs: Mohammad Kefah Taha Issa, Muhammad Aditya Sasongko, Ilyas Turimbetov, Javid Baydamirli, Doğan Sağbili, and Didem Unat
Publié dans: In Proceedings of the 38th ACM International Conference on Supercomputing (ICS '24), Numéro 38th, 2024, Page(s) 525–536
Éditeur: Association for Computing Machinery
DOI: 10.1145/3650200.3656597

CPU- and GPU-initiated Communication Strategies for Conjugate Gradient Methods on Large GPU Clusters

Auteurs: James D. Trotter, Sinan Ekmekçibaşı, Doğan Sağbili, Johannes Langguth, Xing Cai, Didem Unat
Publié dans: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2026, Page(s) 298-315
Éditeur: ACM
DOI: 10.1145/3712285.3759774

Multi-GPU Communication Schemes for Iterative Solvers: When CPUs are Not in Charge

Auteurs: Ismayil Ismayilov, Javid Baydamirli, Doğan Sağbili, Mohamed Wahib, and Didem Unat.
Publié dans: ICS '23: Proceedings of the 37th International Conference on Supercomputing, Numéro In Proceedings of the 37th, 2023, Page(s) 192–202
Éditeur: ACM
DOI: 10.1145/3577193.3593713

A Device-Side Execution Model for Multi-GPU Task Graphs

Auteurs: Ilyas Turimbetov, Mohamed Wahib, Didem Unat
Publié dans: Proceedings of the 39th ACM International Conference on Supercomputing, 2025, Page(s) 384-396
Éditeur: ACM
DOI: 10.1145/3721145.3730426

Autonomous Execution for Multi-GPU Systems: Compiler Support

Auteurs: Javid Baydamirli, Tal Ben Nun, Didem Unat
Publié dans: SC24-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2025, Page(s) 1129-1140
Éditeur: IEEE
DOI: 10.1109/scw63240.2024.00155

Balanced and Elastic End-to-end Training of Dynamic LLMs

Auteurs: Mohamed Wahib, Muhammed Abdullah Soyturk, Didem Unat
Publié dans: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2026, Page(s) 1351-1367
Éditeur: ACM
DOI: 10.1145/3712285.3759775

Uniconn: A Uniform High-Level Communication Library for Portable Multi-GPU Programming

Auteurs: Doğan Sağbili, Sinan Ekmekçibaşı, Khaled Z. Ibrahim, Tan Nguyen, Didem Unat
Publié dans: 2025 IEEE International Conference on Cluster Computing (CLUSTER), 2025, Page(s) 1-12
Éditeur: IEEE
DOI: 10.1109/cluster59342.2025.11186498

GPU-Initiated Resource Allocation for Irregular Workloads

Auteurs: Ilyas Turimbetov, MA Sasongko, and Didem Unat
Publié dans: ExHET '24: Proceedings of the 3rd International Workshop on Extreme Heterogeneity Solutions, 2024, Page(s) 1-8, ISBN 9798400705373
Éditeur: ACM
DOI: 10.1145/3642961.3643799

Peer reviewed articles (3)

The Persistent Challenge of Data locality in Post-Exascale Era

Auteurs: Didem Unat, Anshu Dubey, Emmanuel Jeannot, John Shalf
Publié dans: Computing in Science & Engineering, 2025, Page(s) 1-9, ISSN 1521-9615
Éditeur: American Institute of Physics
DOI: 10.1109/mcse.2025.3567586

Precise Event Sampling on AMD Versus Intel: Quantitative and Qualitative Comparison

Auteurs: Muhammad Aditya Sasongko, Milind Chabbi, Paul HJ Kelly, Didem Unat
Publié dans: IEEE Transactions on Parallel and Distributed Systems, Numéro vol 34 no 5, 2023, Page(s) 1594-1608, ISSN 1045-9219
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tpds.2023.3257105

A sparse tensor generator with efficient feature extraction

Auteurs: Tugba Torun, Ameer Taweel, Didem Unat
Publié dans: Frontiers in Applied Mathematics and Statistics, Numéro 11, 2025, ISSN 2297-4687
Éditeur: Frontiers Media SA
DOI: 10.3389/fams.2025.1589033