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

Informazioni relative al progetto

BeyondMoore

ID dell’accordo di sovvenzione: 949587

DOI

10.3030/949587

Data della firma CE 13 Ottobre 2020

Data di avvio 1 Agosto 2021

Data di completamento 31 Luglio 2027

Finanziato da

• EXCELLENT SCIENCE - European Research Council (ERC)

Costo totale

€ 1 500 000,00

Contributo UE

€ 1 500 000,00

Coordinato da

KOC UNIVERSITY
Türkiye

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Risultati finali

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

Pubblicazioni

Thesis and dissertations (2)

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

Autori: Javid Baydamirli
Pubblicato in: 2023
Editore: Koç University

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

Autori: Ismayil Ismayilov
Pubblicato in: 2023
Editore: Koç University

Conference proceedings (9)

P-MoVE: Performance Monitoring and Visualization with Encoded Knowledge

Autori: Fatih Taşyaran, Osman Yasal, José A. Morgado, Aleksandar Ilic, Didem Unat, Kamer Kaya
Pubblicato in: SC24-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2025, Pagina/e 1531-1542
Editore: IEEE
DOI: 10.1109/scw63240.2024.00193

Snoopie: A Multi-GPU Communication Profiler and Visualizer

Autori: Mohammad Kefah Taha Issa, Muhammad Aditya Sasongko, Ilyas Turimbetov, Javid Baydamirli, Doğan Sağbili, and Didem Unat
Pubblicato in: In Proceedings of the 38th ACM International Conference on Supercomputing (ICS '24), Numero 38th, 2024, Pagina/e 525–536
Editore: Association for Computing Machinery
DOI: 10.1145/3650200.3656597

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

Autori: James D. Trotter, Sinan Ekmekçibaşı, Doğan Sağbili, Johannes Langguth, Xing Cai, Didem Unat
Pubblicato in: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2026, Pagina/e 298-315
Editore: ACM
DOI: 10.1145/3712285.3759774

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

Autori: Ismayil Ismayilov, Javid Baydamirli, Doğan Sağbili, Mohamed Wahib, and Didem Unat.
Pubblicato in: ICS '23: Proceedings of the 37th International Conference on Supercomputing, Numero In Proceedings of the 37th, 2023, Pagina/e 192–202
Editore: ACM
DOI: 10.1145/3577193.3593713

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

Autori: Ilyas Turimbetov, Mohamed Wahib, Didem Unat
Pubblicato in: Proceedings of the 39th ACM International Conference on Supercomputing, 2025, Pagina/e 384-396
Editore: ACM
DOI: 10.1145/3721145.3730426

Autonomous Execution for Multi-GPU Systems: Compiler Support

Autori: Javid Baydamirli, Tal Ben Nun, Didem Unat
Pubblicato in: SC24-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2025, Pagina/e 1129-1140
Editore: IEEE
DOI: 10.1109/scw63240.2024.00155

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

Autori: Mohamed Wahib, Muhammed Abdullah Soyturk, Didem Unat
Pubblicato in: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2026, Pagina/e 1351-1367
Editore: ACM
DOI: 10.1145/3712285.3759775

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

Autori: Doğan Sağbili, Sinan Ekmekçibaşı, Khaled Z. Ibrahim, Tan Nguyen, Didem Unat
Pubblicato in: 2025 IEEE International Conference on Cluster Computing (CLUSTER), 2025, Pagina/e 1-12
Editore: IEEE
DOI: 10.1109/cluster59342.2025.11186498

GPU-Initiated Resource Allocation for Irregular Workloads

Autori: Ilyas Turimbetov, MA Sasongko, and Didem Unat
Pubblicato in: ExHET '24: Proceedings of the 3rd International Workshop on Extreme Heterogeneity Solutions, 2024, Pagina/e 1-8, ISBN 9798400705373
Editore: ACM
DOI: 10.1145/3642961.3643799

Peer reviewed articles (3)

The Persistent Challenge of Data locality in Post-Exascale Era

Autori: Didem Unat, Anshu Dubey, Emmanuel Jeannot, John Shalf
Pubblicato in: Computing in Science & Engineering, 2025, Pagina/e 1-9, ISSN 1521-9615
Editore: American Institute of Physics
DOI: 10.1109/mcse.2025.3567586

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

Autori: Muhammad Aditya Sasongko, Milind Chabbi, Paul HJ Kelly, Didem Unat
Pubblicato in: IEEE Transactions on Parallel and Distributed Systems, Numero vol 34 no 5, 2023, Pagina/e 1594-1608, ISSN 1045-9219
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tpds.2023.3257105

A sparse tensor generator with efficient feature extraction

Autori: Tugba Torun, Ameer Taweel, Didem Unat
Pubblicato in: Frontiers in Applied Mathematics and Statistics, Numero 11, 2025, ISSN 2297-4687
Editore: Frontiers Media SA
DOI: 10.3389/fams.2025.1589033