Period and glitch reduction via clock skew scheduling, delay padding and glitchless

This thesis describes PGR, an architectural technique to reduce dynamic power via a glitch reduction strategy named GlitchLess, or to improve performance via clock skew scheduling (CSS) and delay padding (DP). It is integrated into VPR 5.0, and is invoked after the routing stage. Programmable delay...

Full description

Bibliographic Details
Main Author: Dong, Xiao
Format: Others
Language:English
Published: University of British Columbia 2009
Online Access:http://hdl.handle.net/2429/12869
id ndltd-LACETR-oai-collectionscanada.gc.ca-BVAU.-12869
record_format oai_dc
spelling ndltd-LACETR-oai-collectionscanada.gc.ca-BVAU.-128692013-06-05T04:17:46ZPeriod and glitch reduction via clock skew scheduling, delay padding and glitchlessDong, XiaoThis thesis describes PGR, an architectural technique to reduce dynamic power via a glitch reduction strategy named GlitchLess, or to improve performance via clock skew scheduling (CSS) and delay padding (DP). It is integrated into VPR 5.0, and is invoked after the routing stage. Programmable delay elements (PDEs) are used as a novel architecture modification to insert delay on fiip- flop (FF) clock inputs, enabling all optimization steps to share it, avoiding multiple architecture modifications. This thesis investigates the trade- off between power and performance, and finding an appropriate compromise considering process variation and timing uncertainties. To facilitate realistic power estimates, a popular activity estimator, ACE, is modified with a new model to estimate glitching power, taking into account the analog behavior of glitch pulse width reduction as it travels along FPGA routing tracks. We show that the original glitch estimation method can underestimate glitching power by up to 48%, and overestimate by up to 15%. In terms of performance, an average of 15% speedup can be achieved via CSS alone, or up to 37% for individual circuits. Although delay padding only benefits a few circuits, the average improvement of those circuits is an additional 10% of the original period, or up to 23% for individual circuits. In addition, GlitchLess is performed on both the original VPR and post-CSS solutions. On average, 16% of glitching power can be eliminated, or up to 63% for individual circuits.University of British Columbia2009-09-17T20:11:38Z2009-09-17T20:11:38Z20092009-09-17T20:11:38Z2009-11Electronic Thesis or Dissertation978807 bytesapplication/pdfhttp://hdl.handle.net/2429/12869eng
collection NDLTD
language English
format Others
sources NDLTD
description This thesis describes PGR, an architectural technique to reduce dynamic power via a glitch reduction strategy named GlitchLess, or to improve performance via clock skew scheduling (CSS) and delay padding (DP). It is integrated into VPR 5.0, and is invoked after the routing stage. Programmable delay elements (PDEs) are used as a novel architecture modification to insert delay on fiip- flop (FF) clock inputs, enabling all optimization steps to share it, avoiding multiple architecture modifications. This thesis investigates the trade- off between power and performance, and finding an appropriate compromise considering process variation and timing uncertainties. To facilitate realistic power estimates, a popular activity estimator, ACE, is modified with a new model to estimate glitching power, taking into account the analog behavior of glitch pulse width reduction as it travels along FPGA routing tracks. We show that the original glitch estimation method can underestimate glitching power by up to 48%, and overestimate by up to 15%. In terms of performance, an average of 15% speedup can be achieved via CSS alone, or up to 37% for individual circuits. Although delay padding only benefits a few circuits, the average improvement of those circuits is an additional 10% of the original period, or up to 23% for individual circuits. In addition, GlitchLess is performed on both the original VPR and post-CSS solutions. On average, 16% of glitching power can be eliminated, or up to 63% for individual circuits.
author Dong, Xiao
spellingShingle Dong, Xiao
Period and glitch reduction via clock skew scheduling, delay padding and glitchless
author_facet Dong, Xiao
author_sort Dong, Xiao
title Period and glitch reduction via clock skew scheduling, delay padding and glitchless
title_short Period and glitch reduction via clock skew scheduling, delay padding and glitchless
title_full Period and glitch reduction via clock skew scheduling, delay padding and glitchless
title_fullStr Period and glitch reduction via clock skew scheduling, delay padding and glitchless
title_full_unstemmed Period and glitch reduction via clock skew scheduling, delay padding and glitchless
title_sort period and glitch reduction via clock skew scheduling, delay padding and glitchless
publisher University of British Columbia
publishDate 2009
url http://hdl.handle.net/2429/12869
work_keys_str_mv AT dongxiao periodandglitchreductionviaclockskewschedulingdelaypaddingandglitchless
_version_ 1716587113090121728