A Generative AI for Heterogeneous Network-on-Chip Design Space Pruning
| Autor: | Maxime Mirka, Maxime France-Pillois, Gilles Sassatelli, Abdoulaye Gamatié |
|---|---|
| Přispěvatelé: | ADAptive Computing (ADAC), Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier (LIRMM), Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM) |
| Rok vydání: | 2022 |
| Předmět: | |
| Zdroj: | HAL 25th Design, Automation, and Test in Europe Conference (DATE 2022) 25th Design, Automation, and Test in Europe Conference (DATE 2022), Mar 2022, Antwerp, Belgium |
| DOI: | 10.23919/date54114.2022.9774721 |
| Popis: | International audience; Often suffering from under-optimization, Networkson-Chip (NoCs) heavily impact the efficiency of domain-specific Systems-on-Chip. To cope with this issue, heterogeneous NoCs are promising alternatives. Nevertheless, the design of optimized NoCs satisfying multiple performance objectives is extremely challenging and requires significant expertise. Prior works failed to combine many objectives or required an extended design space exploration time. In this paper, we propose an approach based on generative artificial intelligence to help pruning complex design spaces for heterogeneous NoCs, according to configurable performance objectives. This is made possible by the ability of Generative Adversarial Networks to learn and generate relevant design candidates for the target NoCs. The speed and flexibility of our solution enable a fast generation of optimized NoCs that fit users' expectations. Through some experiments, we show how to obtain competitive NoC designs reducing the power consumption with no communication performance or area penalty compared to a given conventional NoC design. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|