Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Mohammad Hasan Ahmadilivani"'
DeepAxe: A Framework for Exploration of Approximation and Reliability Trade-offs in DNN Accelerators
Autor:
Mahdi Taheri, Mohammad Riazati, Mohammad Hasan Ahmadilivani, Maksim Jenihhin, Masoud Daneshtalab, Jaan Raik, Mikael Sjödin, Björn Lisper
While the role of Deep Neural Networks (DNNs) in a wide range of safety-critical applications is expanding, emerging DNNs experience massive growth in terms of computation power. It raises the necessity of improving the reliability of DNN accelerator
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7a0344dac8b5f872b997b4aaa1159c22
http://arxiv.org/abs/2303.08226
http://arxiv.org/abs/2303.08226
Publikováno v:
2022 11th International Conference on Modern Circuits and Systems Technologies (MOCAST).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8d1926fb2298ace026e7f0720d0bb6aa
https://doi.org/10.1109/mocast54814.2022.9837551
https://doi.org/10.1109/mocast54814.2022.9837551
Reliability of embedded processors is one of the major concerns in safety-critical applications. Reliability is particularly expressed within the cache memories which are the largest part of new system on chips. Cache memories are the most vulnerable
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b01d0a6eba641a3f96a0415c7ac1a57d
https://doi.org/10.36227/techrxiv.14730219
https://doi.org/10.36227/techrxiv.14730219