Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Cheol-Won Jo"'
Autor:
Kwang-Yeob Lee, Cheol-Won Jo
Publikováno v:
ISOCC
Deep learning algorithms are computationally intensive and require dedicated hardware accelerators. Deep learning algorithms repeat multiply-accumulate (MAC) operations. This process produces a large number of partial sums that account for about 60%
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::36b6e505f79428af603badd46f9faaf6
https://doi.org/10.1109/isocc50952.2020.9332993
https://doi.org/10.1109/isocc50952.2020.9332993
Autor:
Cheol-Won Jo, Kwang-Yeob Lee
Publikováno v:
ISOCC
In this paper, MAC computation, which is the most used operation in neural network computing, is accelerated by multicycle_path. When using a pipeline, we can not divide the operation into fixed delays. Thus, exiting pipelines determine the operating
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::94cb6e8fb99df813bcc7cb3d9870556e
https://doi.org/10.1109/isocc47750.2019.9078500
https://doi.org/10.1109/isocc47750.2019.9078500