Generating power-optimal standard cell library specification using neural network technique

In VLSI semi-custom design approach, power-optimal standard cell library selection for a given block design requires time-consuming iterative processes. This paper presents a framework to select a standard cell library that can result in near-optimal power while satisfying targeted frequency. The fr...

Full description

Bibliographic Details
Main Authors: Lim, Sze Huang, Lim, Yang Wei, Mashohor, Syamsiah, Kamsani, Noor Ain, Mohd Sidek, Roslina, Hashim, Shaiful Jahari, Rokhani, Fakhrul Zaman
Format: Conference or Workshop Item
Language:English
Published: IEEE 2017
Online Access:http://psasir.upm.edu.my/id/eprint/68267/1/Generating%20power-optimal%20standard%20cell%20library%20specification%20using%20neural%20network%20technique.pdf
_version_ 1825933493083832320
author Lim, Sze Huang
Lim, Yang Wei
Mashohor, Syamsiah
Kamsani, Noor Ain
Mohd Sidek, Roslina
Hashim, Shaiful Jahari
Rokhani, Fakhrul Zaman
author_facet Lim, Sze Huang
Lim, Yang Wei
Mashohor, Syamsiah
Kamsani, Noor Ain
Mohd Sidek, Roslina
Hashim, Shaiful Jahari
Rokhani, Fakhrul Zaman
author_sort Lim, Sze Huang
collection UPM
description In VLSI semi-custom design approach, power-optimal standard cell library selection for a given block design requires time-consuming iterative processes. This paper presents a framework to select a standard cell library that can result in near-optimal power while satisfying targeted frequency. The framework relies on neural network model to quickly predict the total power of a block design associated with a given standard cell library in order to speed up the synthesis process. The experimental result based on various synthesized benchmark circuits demonstrated the effectiveness of proposed framework for near-optimal standard cell library specification.
first_indexed 2024-03-06T09:58:07Z
format Conference or Workshop Item
id upm.eprints-68267
institution Universiti Putra Malaysia
language English
last_indexed 2024-03-06T09:58:07Z
publishDate 2017
publisher IEEE
record_format dspace
spelling upm.eprints-682672019-05-10T08:28:36Z http://psasir.upm.edu.my/id/eprint/68267/ Generating power-optimal standard cell library specification using neural network technique Lim, Sze Huang Lim, Yang Wei Mashohor, Syamsiah Kamsani, Noor Ain Mohd Sidek, Roslina Hashim, Shaiful Jahari Rokhani, Fakhrul Zaman In VLSI semi-custom design approach, power-optimal standard cell library selection for a given block design requires time-consuming iterative processes. This paper presents a framework to select a standard cell library that can result in near-optimal power while satisfying targeted frequency. The framework relies on neural network model to quickly predict the total power of a block design associated with a given standard cell library in order to speed up the synthesis process. The experimental result based on various synthesized benchmark circuits demonstrated the effectiveness of proposed framework for near-optimal standard cell library specification. IEEE 2017 Conference or Workshop Item PeerReviewed text en http://psasir.upm.edu.my/id/eprint/68267/1/Generating%20power-optimal%20standard%20cell%20library%20specification%20using%20neural%20network%20technique.pdf Lim, Sze Huang and Lim, Yang Wei and Mashohor, Syamsiah and Kamsani, Noor Ain and Mohd Sidek, Roslina and Hashim, Shaiful Jahari and Rokhani, Fakhrul Zaman (2017) Generating power-optimal standard cell library specification using neural network technique. In: 2017 IEEE Asia Pacific Conference on Postgraduate Research in Microelectronics and Electronics (PrimeAsia), 31 Oct.-2 Nov. 2017, Kuala Lumpur, Malaysia. (pp. 101-104). 10.1109/PRIMEASIA.2017.8280374
spellingShingle Lim, Sze Huang
Lim, Yang Wei
Mashohor, Syamsiah
Kamsani, Noor Ain
Mohd Sidek, Roslina
Hashim, Shaiful Jahari
Rokhani, Fakhrul Zaman
Generating power-optimal standard cell library specification using neural network technique
title Generating power-optimal standard cell library specification using neural network technique
title_full Generating power-optimal standard cell library specification using neural network technique
title_fullStr Generating power-optimal standard cell library specification using neural network technique
title_full_unstemmed Generating power-optimal standard cell library specification using neural network technique
title_short Generating power-optimal standard cell library specification using neural network technique
title_sort generating power optimal standard cell library specification using neural network technique
url http://psasir.upm.edu.my/id/eprint/68267/1/Generating%20power-optimal%20standard%20cell%20library%20specification%20using%20neural%20network%20technique.pdf
work_keys_str_mv AT limszehuang generatingpoweroptimalstandardcelllibraryspecificationusingneuralnetworktechnique
AT limyangwei generatingpoweroptimalstandardcelllibraryspecificationusingneuralnetworktechnique
AT mashohorsyamsiah generatingpoweroptimalstandardcelllibraryspecificationusingneuralnetworktechnique
AT kamsaninoorain generatingpoweroptimalstandardcelllibraryspecificationusingneuralnetworktechnique
AT mohdsidekroslina generatingpoweroptimalstandardcelllibraryspecificationusingneuralnetworktechnique
AT hashimshaifuljahari generatingpoweroptimalstandardcelllibraryspecificationusingneuralnetworktechnique
AT rokhanifakhrulzaman generatingpoweroptimalstandardcelllibraryspecificationusingneuralnetworktechnique