Productive Spatial Accelerator Programming

Informazioni relative al progetto

PSAP

ID dell’accordo di sovvenzione: 101002047

DOI

10.3030/101002047

Data della firma CE 5 Marzo 2021

Data di avvio 1 Gennaio 2022

Data di completamento 31 Dicembre 2026

Finanziato da

• EXCELLENT SCIENCE - European Research Council (ERC)

Costo totale

€ 1 980 917,00

Contributo UE

€ 1 980 917,00

Coordinato da

EIDGENOESSISCHE TECHNISCHE HOCHSCHULE ZUERICH
Switzerland

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 .

Pubblicazioni

Conference proceedings (28)

Low-Depth Spatial Tree Algorithms

Autori: Yves Baumann, Tal Ben-Nun, Maciej Besta, Lukas Gianinazzi, Torsten Hoefler, Piotr Luczynski
Pubblicato in: 2024 IEEE International Parallel and Distributed Processing Symposium (IPDPS), 2024
Editore: IEEE
DOI: 10.1109/ipdps57955.2024.00024

Network-Offloaded Bandwidth-Optimal Broadcast and Allgather for Distributed AI

Autori: Mikhail Khalilov, Salvatore Di Girolamo, Marcin Chrapek, Rami Nudelman, Gil Bloch, Torsten Hoefler
Pubblicato in: SC24: International Conference for High Performance Computing, Networking, Storage and Analysis, 2024, Pagina/e 1-17
Editore: IEEE
DOI: 10.1109/sc41406.2024.00109

High-Performance and Programmable Attentional Graph Neural Networks with Global Tensor Formulations

Autori: Maciej Besta, Pawel Renc, Robert Gerstenberger, Paolo Sylos Labini, Alexandros Ziogas, Tiancheng Chen, Lukas Gianinazzi, Florian Scheidl, Kalman Szenes, Armon Carigiet, Patrick Iff, Grzegorz Kwasniewski, Raghavendra Kanakagiri, Chio Ge, Sammy Jaeger, Jarosław Wąs, Flavio Vella, Torsten Hoefler
Pubblicato in: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2024, Pagina/e 1-16
Editore: ACM
DOI: 10.1145/3581784.3607067

Productive Performance Engineering for Weather and Climate Modeling with Python

Autori: Ben-Nun, Tal; Groner, Linus; Deconinck, Florian; Wicky, Tobias; Davis, Eddie; Dahm, Johann; Elbert, Oliver D.; George, Rhea; McGibbon, Jeremy; Trümper, Lukas; Wu, Elynn; Fuhrer, Oliver; Schulthess, Thomas; Hoefler, Torsten
Pubblicato in: SC'22: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, Numero 1, 2022
Editore: SC
DOI: 10.1109/sc41404.2022.00078

Bridging Control-Centric and Data-Centric Optimization

Autori: Tal Ben-Nun; Berke Ates; Alexandru Calotoiu; Torsten Hoefler
Pubblicato in: 2023
Editore: 21st ACM/IEEE International Symposium on Code Generation and Optimization
DOI: 10.1145/3579990.3580018

VENOM: A Vectorized N:M Format for Unleashing the Power of Sparse Tensor Cores

Autori: Roberto L. Castro, Andrei Ivanov, Diego Andrade, Tal Ben-Nun, Basilio B. Fraguela, Torsten Hoefler
Pubblicato in: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2024, Pagina/e 1-14
Editore: ACM
DOI: 10.1145/3581784.3607087

User-guided Page Merging for Memory Deduplication in Serverless Systems

Autori: Wei Qiu, Marcin Copik, Yun Wang, Alexandru Calotoiu, Torsten Hoefler
Pubblicato in: 2023 IEEE International Conference on Big Data (BigData), 2024, Pagina/e 159-169
Editore: IEEE
DOI: 10.1109/bigdata59044.2023.10386487

HexaMesh: Scaling to Hundreds of Chiplets with an Optimized Chiplet Arrangement

Autori: Iff, Patrick; Besta, Maciej; Cavalcante, Matheus; Fischer, Tim; Benini, Luca; Hoefler, Torsten
Pubblicato in: Numero 1, 2023
Editore: 60th Annual Design Automation Conference
DOI: 10.48550/arxiv.2211.13989

HammingMesh: A Network Topology for Large-Scale Deep Learning

Autori: T. Hoefler, T. Bonato, D. De Sensi, S. Di Girolamo, S. Li, M. Heddes, J. Belk, D. Goel, M. Castro, S. Scott
Pubblicato in: 2022
Editore: International Conference for High Performance Computing, Networking, Storage and Analysis
DOI: 10.48550/arxiv.2209.01346

Sparse Hamming Graph: A Customizable Network-on-Chip Topology

Autori: P. Iff, M. Besta, M. Cavalcante, T. Fischer, L. Benini, T. Hoefler
Pubblicato in: 2023
Editore: 60th Annual Design Automation Conference
DOI: 10.48550/arxiv.2211.13980

KafkaDirect: Zero-copy Data Access for Apache Kafka over RDMA Networks

Autori: K. Taranov, S. Byan, V. Marathe, T. Hoefler
Pubblicato in: 2022
Editore: ACM SIGMOD International Conference on Management of Data
DOI: 10.1145/3514221.3526056

Performance-detective

Autori: Larissa Schmid, Marcin Copik, Alexandru Calotoiu, Dominik Werle, Andreas Reiter, Michael Selzer, Anne Koziolek, Torsten Hoefler
Pubblicato in: Proceedings of the 36th ACM International Conference on Supercomputing, 2023, Pagina/e 1-13
Editore: ACM
DOI: 10.1145/3524059.3532391

ProbGraph: High-Performance and High-Accuracy Graph Mining with Probabilistic Set Representations

Autori: M. Besta, C. Miglioli, P. Sylos Labini, J. Tětek, P. Iff, R. Kanakagiri, S. Ashkboos, K. Janda, M. Podstawski, G. Kwasniewski, N. Gleinig, F. Vella, O. Mutlu, T. Hoefler
Pubblicato in: 2022
Editore: SC'22
DOI: 10.48550/arxiv.2208.11469

DiffDA: a Diffusion model for weather-scale Data Assimilation

Autori: Langwen Huang, Lukas Gianinazzi, Yuejiang Yu, Peter D. Dueben, Torsten Hoefler
Pubblicato in: DiffDA, 2024
Editore: ICML

Boosting Performance Optimization with Interactive Data Movement Visualization

Autori: P. Schaad, T. Ben-Nun, T. Hoefler
Pubblicato in: 2022
Editore: SC'22
DOI: 10.1109/sc41404.2022.00069

STen: An Interface for Efficient Sparsity in PyTorch

Autori: A. Ivanov, N. Dryden, T. Hoefler
Pubblicato in: 2022
Editore: In Sparsity in Neural Networks workshop
DOI: 10.48550/arxiv.2304.07613

Process-as-a-Service: Unifying Elastic and Stateful Clouds with Serverless Processes

Autori: Marcin Copik, Alexandru Calotoiu, Gyorgy Rethy, Roman Böhringer, Rodrigo Bruno, Torsten Hoefler
Pubblicato in: Proceedings of the ACM Symposium on Cloud Computing, 2024, Pagina/e 223-242
Editore: ACM
DOI: 10.1145/3698038.3698567

automatic deduction of cheap and accurate performance models

Autori: Larissa Schmid; Marcin Copik; Alexandru Calotoiu; Dominik Werle; Andreas Reiter; Michael Selzer; Anne Koziolek; Torsten Hoefler
Pubblicato in: ICS '22: Proceedings of the 36th ACM International Conference on Supercomputing, Numero 1, 2022
Editore: ICS'22
DOI: 10.5445/ir/1000146623

The Graph Database Interface: Scaling Online Transactional and Analytical Graph Workloads to Hundreds of Thousands of Cores

Autori: Maciej Besta, Robert Gerstenberger, Marc Fischer, Michal Podstawski, Nils Blach, Berke Egeli, Georgy Mitenkov, Wojciech Chlapek, Marek Michalewicz, Hubert Niewiadomski, Juergen Mueller, Torsten Hoefler
Pubblicato in: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2024, Pagina/e 1-18
Editore: ACM
DOI: 10.1145/3581784.3607068

Streaming Task Graph Scheduling for Dataflow Architectures

Autori: Tiziano De Matteis, Lukas Gianinazzi, Johannes de Fine Licht, Torsten Hoefler
Pubblicato in: Proceedings of the 32nd International Symposium on High-Performance Parallel and Distributed Computing, 2024, Pagina/e 225-237
Editore: ACM
DOI: 10.1145/3588195.3592999

Deinsum: Practically I/O Optimal Multilinear Algebra

Autori: A. Nikolaos Ziogas, G. Kwasniewski, T. Ben-Nun, T. Schneider, T. Hoefler
Pubblicato in: 2022
Editore: SC'22
DOI: 10.48550/arxiv.2206.08301

Asynchronous Distributed-Memory Triangle Counting and LCC with RMA Caching

Autori: Andras Strausz; Flavio Vella; Salvatore Di Girolamo; Maciej Besta; Torsten Hoefler
Pubblicato in: 2022 IEEE International Parallel and Distributed Processing Symposium (IPDPS), Numero 2, 2022
Editore: IEEE
DOI: 10.48550/arxiv.2202.13976

A data-centric optimization framework for machine learning

Autori: Rausch, Oliver; Ben-Nun, Tal; Dryden, Nikoli; Ivanov, Andrei; Li, Shigang; Hoefler, Torsten
Pubblicato in: Proceedings of the 36th ACM International Conference on Supercomputing, Numero 7, 2022
Editore: ACM International Conference on Supercomputing
DOI: 10.48550/arxiv.2110.10802

Maximum Flows in Parametric Graph Templates

Autori: T. Ben-Nun, L. Gianinazzi, T. Hoefler, Y. Oltchik
Pubblicato in: 2023
Editore: In Algorithms and Complexity - 13th International Conference
DOI: 10.48550/arxiv.2307.08420

Near-Optimal Wafer-Scale Reduce

Autori: Piotr Luczynski, Lukas Gianinazzi, Patrick Iff, Leighton Wilson, Daniele De Sensi, Torsten Hoefler
Pubblicato in: Proceedings of the 33rd International Symposium on High-Performance Parallel and Distributed Computing, 2024, Pagina/e 334-347
Editore: ACM
DOI: 10.1145/3625549.3658693

High Performance Unstructured SpMM Computation Using Tensor Cores

Autori: Patrik Okanovic, Grzegorz Kwasniewski, Paolo Sylos Labini, Maciej Besta, Flavio Vella, Torsten Hoefler
Pubblicato in: SC24: International Conference for High Performance Computing, Networking, Storage and Analysis, 2024, Pagina/e 1-14
Editore: IEEE
DOI: 10.1109/sc41406.2024.00060

FMI: Fast and Cheap Message Passing for Serverless Functions

Autori: Marcin Copik, Roman Böhringer, Alexandru Calotoiu, Torsten Hoefler
Pubblicato in: Proceedings of the 37th International Conference on Supercomputing, 2023, Pagina/e 373-385
Editore: ACM
DOI: 10.1145/3577193.3593718

Lifting C semantics for dataflow optimization

Autori: Alexandru Calotoiu; Tal Ben-Nun; Grzegorz Kwasniewski; Johannes de Fine Licht; Timo Schneider; Philipp Schaad; Torsten Hoefler
Pubblicato in: Proceedings of the 36th ACM International Conference on Supercomputing, Numero 1, 2022
Editore: 36th ACM International Conference on Supercomputing
DOI: 10.1145/3524059.3532389

Peer reviewed articles (3)

Deep learning and a changing economy in weather and climate prediction

Autori: Peter Bauer, Peter Dueben, Matthew Chantry, Francisco Doblas-Reyes, Torsten Hoefler, Amy McGovern, Bjorn Stevens
Pubblicato in: Nature Reviews Earth & Environment, Numero 4, 2023, Pagina/e 507-509, ISSN 2662-138X
Editore: Springer Nature
DOI: 10.1038/s43017-023-00468-z

Graph of Thoughts: Solving Elaborate Problems with Large Language Models

Autori: Maciej Besta, Nils Blach, Ales Kubicek, Robert Gerstenberger, Michal Podstawski, Lukas Gianinazzi, Joanna Gajda, Tomasz Lehmann, Hubert Niewiadomski, Piotr Nyczyk, Torsten Hoefler
Pubblicato in: Proceedings of the AAAI Conference on Artificial Intelligence, Numero 38, 2024, Pagina/e 17682-17690, ISSN 2374-3468
Editore: AAAI Press
DOI: 10.1609/aaai.v38i16.29720

Influence of Network Performance Variability on Application Scalability

Autori: Daniele De Sensi; Tiziano De Matteis; Konstantin Taranov; Salvatore Di Girolamo; Tobias Rahn; Torsten Hoefler
Pubblicato in: Proceedings of the ACM on Measurement and Analysis of Computing Systems, 6 (3), Numero 1, 2022, ISSN 0000-0000
Editore: Proc. ACM Meas. Anal. Comput. Syst.. Vol 6, Nr. 3, Association for Computing Machinery, Dec. 2022)
DOI: 10.1145/3570609

Other (1)

FMI: Fast and Cheap Message Passing for Serverless Functions

Autori: M. Copik, R. Böhringer, A. Calotoiu, T. Hoefler
Pubblicato in: 2023
Editore: ICS
DOI: 10.48550/arxiv.2305.08763