Flux d'outils automatisé à partir de langages spécifiques à un domaine pour générer des accélérateurs massivement parallèles sur des FPGA équipés de HBM

A new technical paper titled “Automatic Creation of High-bandwidth Memory Architectures from Domain-specific Languages: The Case of Computational Fluid Dynamics” was published by researchers at Politecnico di Milano and TU Dresden.

The paper states “In this article, we propose an automated tool flow from a domain-specific language for tensor expressions to generate massively parallel accelerators on high-bandwidth-memory-equipped FPGAs. Designers can use this flow to integrate and evaluate various compiler or hardware optimizations. We use computational fluid dynamics (CFD) as a paradigmatic example.”

Trouvez le article technique ici. Publié en mars 2023.

Stephanie Soldavini, Karl Friebel, Mattia Tibaldi, Gerald Hempel, Jeronimo Castrillon, and Christian Pilato. 2023. Automatic Creation of High-bandwidth Memory Architectures from Domain-specific Languages: The Case of Computational Fluid Dynamics. ACM Trans. Reconfigurable Technol. Syst. 16, 2, Article 21 (June 2023), 34 pages. https://doi.org/10.1145/3563553.

• Contenu propulsé par le référencement et distribution de relations publiques. Soyez amplifié aujourd'hui.
• Platoblockchain. Intelligence métaverse Web3. Connaissance Amplifiée. Accéder ici.
• La source: https://semiengineering.com/automated-tool-flow-from-domain-specific-languages-to-generate-massively-parallel-accelerators-on-hbm-equipped-fpgas/