LIgand Generator and portable drug discovery platform AT Exascale

Livrables

Final version of D6.2.

Lessons learnt from the LIGATE Project.

Initial Dissemination and Communication Plan

To define the strategy to disseminate and communicate the project results. The activity, led by CHELONIA in tight collaboration with DOMPE, will analyze the strategies and will implement the actions to optimize the dissemination and communication of the project results, beyond the project partners and time-frame.

Validated Platform on Known Dataset

This task is devoted to functionally validate the outcome of the CADD platform enhancement. This task includes the preparation of a dataset composed by known compounds derived from literature and publicly available databases. This dataset will be used as a test-case for the platform for the continuous validation and performance assessment of the platform. The task defines the baseline for the CADD platform validation process and assesses the improvement reached in terms of the selected metrics. A specific action will be carried out to: ● Definition of benchmark datasets for validation of ligand poses and binding affinity calculations; quality control of structures datasets (DOMPE, UNIBAS); ● Evaluation of the baseline of the CADD platform; ● Evaluation and definition of the novel baseline of the intermediate and final tool version (Alpha, Beta, Candidate, Release).

Solution Validation Result

Final validation of the different solution components and of the solution as a whole.

Initial Validation Result

Initial validation of the different solution components and of the solution as a whole

Final runtime and autotuning framework

The final runtime and autotuning report describes the state of the programming model and runtime system after the completion of the autotuning, heterogeneity and energy optimization tasks. It will summarize the framework features, the advancements made in the optimization tasks, and evaluate its performance.

Setup and Maintenance of LIGATE Website & Social Media

Coordination of dissemination (LIGATE webpage, workshops, conferences, articles, and book) and communication (use of social networks such as LinkedIN, Facebook, Twitter and YouTube) activities.

Intermediate runtime and autotuning framework

This intermediate report describes the progress made on runtime system optimization, including autotuning, scheduling and data distribution improvements, as well as energy optimization.

Publications

SYnergy: Fine-grained Energy-Efficient Heterogeneous Computing for Scalable Energy Saving

Auteurs: Kaijie Fan, Marco D'Antonio, Lorenzo Carpentieri, Biagio Cosenza, Federico Ficarelli, and Daniele Cesarini
Publié dans: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC '23), Numéro 69, 2023, Page(s) 1–13
Éditeur: Association for Computing Machinery
DOI: 10.1145/3581784.3607055

Tunable and Portable Extreme-Scale Drug Discovery Platform at Exascale: the LIGATE Approach

Auteurs: Gianluca Palermo, Gianmarco Accordi, Davide Gadioli, Emanuele Vitali, Cristina Silvano, Bruno Guindani, Danilo Ardagna, Andrea R. Beccari, Domenico Bonanni, Carmine Talarico, Filippo Lunghini, Jan Martinovic, Paulo Silva, Ada Bohm, Jakub Beranek, Jan Krenek, Branislav Jansik, Luigi Crisci, Biagio, Cosenza, Peter Thoman, Philip Salzmann, Thomas Fahringer, Leila Alexander, Gerardo Tauriello, Torsten
Publié dans: Proceedings of the 20th ACM International Conference on Computing Frontiers (CF '23), 2023, Page(s) 272–278
Éditeur: Association for Computing Machinery
DOI: 10.1145/3587135.3592172

On the Compilation Performance of Current SYCL Implementations

Auteurs: Thoman, Peter and Molina Heredia, Facundo and Fahringer, Thomas
Publié dans: IWOCL 22: International Workshop on OpenCL, 2022
Éditeur: ACM
DOI: 10.1145/3529538.3529548

HEAppE Middleware: From Desktop to HPC

Auteurs: Jakub Konvička, Václav Svatoň, Jan Křenek
Publié dans: Proceedings of Euro-Par 2023: Parallel Processing Workshops. Lecture Notes in Computer Science, Numéro 14352, 2024, Page(s) 252–255, ISBN 978-3-031-48802-3
Éditeur: Springer
DOI: 10.1007/978-3-031-48803-0_27

SYCL-Bench 2020: Benchmarking SYCL 2020 on AMD, Intel, and NVIDIA GPUs

Auteurs: Luigi Crisci, Lorenzo Carpentieri, Peter Thoman, Aksel Alpay, Vincent Heuveline, Biagio Cosenza
Publié dans: Proceedings of the 12th International Workshop on OpenCL and SYCL (IWOCL '24), Numéro 1, 2024, Page(s) 1–12
Éditeur: Association for Computing Machinery
DOI: 10.1145/3648115.3648120

MALIBOO: When Machine Learning meets Bayesian Optimization

Auteurs: Bruno Guindani, Danilo Ardagna, Alessandra Guglielmi
Publié dans: Proceedings of IEEE 7th International Conference on Smart Cloud (SmartCloud), 2022, Page(s) 1-9, ISBN 978-1-6654-5180-2
Éditeur: IEEE
DOI: 10.1109/smartcloud55982.2022.00008

An Analysis of Long-Tailed Network Latency Distribution and Background Traffic on Dragonfly+

Auteurs: Majid Salimi Beni, Biagio Cosenza
Publié dans: Proceedings of Benchmarking, Measuring, and Optimizing: 14th BenchCouncil International Symposium, Bench 2022, 2023, Page(s) 123–142
Éditeur: Springer-Verlag
DOI: 10.1007/978-3-031-31180-2_8

FLEXDP: flexible frequency scaling for energy-delay product optimization of GPU applications

Auteurs: Kaijie Fan, Biagio Cosenza, Ben H. H. Juurlink
Publié dans: ACM International Conference on Computing Frontiers, 2022
Éditeur: ACM
DOI: 10.1145/3528416.3530241

Towards a Portable Drug Discovery Pipeline with SYCL 2020

Auteurs: Luigi Crisci, Majid Salimi Beni, Biagio Cosenza, Nicolò Scipione, Davide Gadioli, Emanuele Vitali,Gianluca Palermo, Andrea Rosario Beccari
Publié dans: IWOCL 22: International Workshop on OpenCL, 2021
Éditeur: ACM
DOI: 10.1145/3529538.3529688

SimSYCL: A SYCL Implementation Targeting Development, Debugging, Simulation and Conformance

Auteurs: Peter Thoman, Fabian Knorr, Luigi Crisci
Publié dans: Proceedings of the 12th International Workshop on OpenCL and SYCL (IWOCL '24), Numéro 3, 2024, Page(s) 1–12
Éditeur: Association for Computing Machinery
DOI: 10.1145/3648115.3648136

Domain-Specific Energy Modeling for Drug Discovery and Magnetohydrodynamics Applications

Auteurs: Lorenzo Carpentieri, Marco D'Antonio, Kaijie Fan, Luigi Crisci, Biagio Cosenza, Federico Ficarelli, Daniele Cesarini, Gianmarco Accordi, Davide Gadioli, Gianluca Palermo, Peter Thoman, Philip Salzmann, Philipp Gschwandtner, Markus Wippler, Filippo Marchetti, Daniele Gregori, Andrea Rosario Beccari
Publié dans: Proceedings of SC-W '23 - International Workshop on the Environmental Sustainability of High-Performance Software, 2023, Page(s) 1790–1800
Éditeur: ACM
DOI: 10.1145/3624062.3624261

An Asynchronous Dataflow-Driven Execution Model For Distributed Accelerator Computing

Auteurs: Philip Salzmann, Fabian Knorr, Peter Thoman, Philipp Gschwandtner, Biagio Cosenza, Thomas Fahringer
Publié dans: Proceedings of 2023 IEEE/ACM 23rd International Symposium on Cluster, Cloud and Internet Computing (CCGrid), 2023, Page(s) 82-93, ISBN 979-8-3503-0120-5
Éditeur: IEEE
DOI: 10.1109/ccgrid57682.2023.00018

ndzip-gpu: efficient lossless compression of scientific floating-point data on GPUs

Auteurs: Fabian Knorr, Peter Thoman, Thomas Fahringer
Publié dans: SC '21: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2021
Éditeur: ACM
DOI: 10.1145/3458817.3476224

An extreme-scale virtual screening platform for drug discovery

Auteurs: Gadioli, Davide and Vitali, Emanuele and Ficarelli, Federico and Latini, Chiara and Manelfi, Candida and Talarico, Carmine and Silvano, Cristina and Beccari, Andrea. R. and Palermo, Gianluca
Publié dans: ACM International Conference on Computing Frontiers, 2022
Éditeur: ACM
DOI: 10.1145/3528416.3530872

EMPI: Enhanced Message Passing Interface in Modern C++

Auteurs: Majid Salimi Beni, Luigi Crisci, Biagio Cosenza
Publié dans: Proceedings of 2023 IEEE/ACM 23rd International Symposium on Cluster, Cloud and Internet Computing (CCGrid), 2023, Page(s) 141-153
Éditeur: IEEE
DOI: 10.1109/ccgrid57682.2023.00023

Unlocking performance portability on LUMI-G supercomputer: A virtual screening case study

Auteurs: Gianmarco Accordi, Davide Gadioli, Gianluca Palermo, Luigi Crisci, Lorenzo Carpentieri, Biagio Cosenza, Andrea R. Beccari
Publié dans: Proceedings of the 12th International Workshop on OpenCL and SYCL (IWOCL '24), Numéro 9, 2024, Page(s) 1–4
Éditeur: Association for Computing Machinery
DOI: 10.1145/3648115.3648125

Understanding the I/O Impact on the Performance of High-Throughput Molecular Docking

Auteurs: Stefano Markidis, Davide Gadioli, Emanuele Vitali, Gianluca Palermo
Publié dans: PDSW 2021 (SC21 Workshop) 6TH INTERNATIONAL PARALLEL DATA SYSTEMS WORKSHOP (HELD IN CONJUNCTION WITH SC21: THE INTERNATIONAL CONFERENCE FOR HIGH PERFORMANCE COMPUTING, NETWORKING, STORAGE AND ANALYSIS), 2021
Éditeur: IEEE Xplore
DOI: 10.1109/pdsw54622.2021.00007

Command Horizons: Coalescing Data Dependencies while Maintaining Asynchronicity

Auteurs: Peter Thoman, Philipp Salzmann
Publié dans: Asynchronous Many-Task Systems and Applications. WAMTA 2023. Lecture Notes in Computer Science, Numéro 13861, 2023, Page(s) 13–26, ISBN 978-3-031-32315-7
Éditeur: Springer
DOI: 10.1007/978-3-031-32316-4_2

Celerity: How (Well) Does the SYCL API Translate to Distributed Clusters?

Auteurs: Philip Salzmann, Fabian Knorr, Peter Thoman, Biagio Cosenza
Publié dans: IWOCL 22: International Workshop on OpenCL, 2022
Éditeur: ACM
DOI: 10.1145/3529538.3530004

Automatic Discovery of Collective Communication Patterns in Parallelized Task Graphs

Auteurs: Fabian Knorr, Philip Salzmann, Peter Thoman, Thomas Fahringer
Publié dans: International Journal of Parallel Programming, 2024, ISSN 0885-7458
Éditeur: Kluwer Academic Publishers
DOI: 10.1007/s10766-024-00767-y

Declarative Data Flow in a Graph-Based Distributed Memory Runtime System

Auteurs: Knorr Fabian, Thoman Peter, Fahringer Thomas
Publié dans: International Journal of Parallel Programming, Numéro 51, 2023, Page(s) 150–171, ISSN 0885-7458
Éditeur: Kluwer Academic Publishers
DOI: 10.1007/s10766-022-00743-4

Balancing Tracking Granularity and Parallelism in Many-Task Systems: The Horizons Approach

Auteurs: Peter Thoman, Philip Salzmann
Publié dans: SN Computer Science, Numéro 5, 2024, Page(s) 409, ISSN 2661-8907
Éditeur: Springer Nature
DOI: 10.1007/s42979-024-02749-w

A Review on Parallel Virtual Screening Softwares for High-Performance Computers

Auteurs: Natarajan Arul Murugan, Artur Podobas, Davide Gadioli, Emanuele Vitali, Gianluca Palermo, Stefano Markidis
Publié dans: Pharmaceuticals, Numéro 15(1):63, 2022, ISSN 1424-8247
Éditeur: Multidisciplinary Digital Publishing Institute (MDPI)
DOI: 10.3390/ph15010063

Integrating Bayesian Optimization and Machine Learning for the Optimal Configuration of Cloud Systems

Auteurs: Bruno Guindani, Danilo Ardagna, Alessandra Guglielmi, Roberto Rocco, Gianluca Palermo
Publié dans: IEEE Transactions on Cloud Computing, Numéro 12(1), 2024, Page(s) 277-294, ISSN 2168-7161
Éditeur: Institute of Electrical and Electronics Engineers Inc.
DOI: 10.1109/tcc.2024.3361070

Addressing docking pose selection with structure-based deep learning: Recent advances, challenges and opportunities

Auteurs: Serena Vittorio, Filippo Lunghini, Pietro Morerio, Davide Gadioli, Sergio Orlandini, Paulo Silva, null Jan Martinovic, Alessandro Pedretti, Domenico Bonanni, Alessio Del Bue, Gianluca Palermo, Giulio Vistoli, Andrea R. Beccari
Publié dans: Computational and Structural Biotechnology Journal, Numéro 23, 2024, Page(s) 2141-2151, ISSN 2001-0370
Éditeur: Elsevier
DOI: 10.1016/j.csbj.2024.05.024

HyperQueue: Efficient and ergonomic task graphs on HPC clusters

Auteurs: Jakub Beránek, Ada Böhm, Gianluca Palermo, Jan Martinovič, Branislav Jansík
Publié dans: SoftwareX, Numéro 27, 2024, Page(s) 101814, ISSN 2352-7110
Éditeur: Elsevier BV
DOI: 10.1016/j.softx.2024.101814

Out of kernel tuning and optimizations for portable large-scale docking experiments on GPUs

Auteurs: Gianmarco Accordi, Davide Gadioli, Emanele Vitali, Luigi Crisci, Biagio Cosenza, Andrea Beccari, Gianluca Palermo
Publié dans: Journal of Supercomputing, Numéro 80, 2024, Page(s) 11798–11815, ISSN 0920-8542
Éditeur: Kluwer Academic Publishers
DOI: 10.1007/s11227-023-05884-y

A Portable Drug Discovery Platform for Urgent Computing

Auteurs: Davide Gadioli, Gianmarco Accordi, Jan Krenek, Martin Golasowski, Ladislav Foltyn, Jan Martinovic, Andrea R. Beccari, Gianluca Palermo
Publié dans: Procedia Computer Science, Numéro 240, 2024, Page(s) 42-51, ISSN 1877-0509
Éditeur: Elsevier
DOI: 10.1016/j.procs.2024.07.007

Automated benchmarking of combined protein structure and ligand conformation prediction

Auteurs: Michèle Leemann, Ander Sagasta, Jerome Eberhardt, Torsten Schwede, Xavier Robin, Janani Durairaj
Publié dans: Proteins, Numéro 91(12), 2023, Page(s) 1912-1924, ISSN 0887-3585
Éditeur: Wiley-Liss Inc
DOI: 10.1002/prot.26605

Enabling performance portability on the LiGen drug discovery pipeline

Auteurs: Luigi Crisci, Lorenzo Carpentieri, Biagio Cosenza, Gianmarco Accordi, Davide Gadioli, Emanuele Vitali, Gianluca Palermo, Andrea Rosario Beccari
Publié dans: Future Generation Computer Systems, Numéro 158, 2024, Page(s) 44-59, ISSN 0167-739X
Éditeur: Elsevier BV
DOI: 10.1016/j.future.2024.03.045

GPU-optimized Approaches to Molecular Docking-based Virtual Screening in Drug Discovery: A Comparative Analysis

Auteurs: Emanuele Vitali, Federico Ficarelli, Mauro Bisson, Davide Gadioli, Massimiliano Fatica, Andrea R. Beccari, Gianluca Palermo
Publié dans: Journal of Parallel and Distributed Computing, Numéro 186, 2024, ISSN 0743-7315
Éditeur: Academic Press
DOI: 10.1016/j.jpdc.2023.104819

Poster: HyperQueue: Overcoming Limitations of HPC Job Managers

Auteurs: Stanislav Böhm, Jakub Beránek, Vojtěch Cima, Roman Macháček, Vyomkesh Jha, Alfréd Kočí, Branislav Jansík, Jan Martinovič
Publié dans: SC 21, The International Conference for High Performance Computing, Networking, Storage, and Analysis, 2021
Éditeur: SC 21, The International Conference for High Performance Computing, Networking, Storage, and Analysis
DOI: 10.5281/zenodo.7298549

Poster: HEAppE Middleware: From Desktop to HPC

Auteurs: Jakub Konvička, Václav Svatoň, Jan Křenek
Publié dans: Euro-Par 2023: Parallel Processing Workshops, 2024
Éditeur: Springer
DOI: 10.5281/zenodo.11080405

Livrables

Publications

Partager cette page

Télécharger