- Library Home /
- Search Collections /
- Open Collections /
- Browse Collections /
- UBC Theses and Dissertations /
- Channel width reduction techniques for system-on-chip...
Open Collections
UBC Theses and Dissertations
UBC Theses and Dissertations
Channel width reduction techniques for system-on-chip circuits in field-programmable gate arrays Tom, Marvin
Abstract
Users of field-programmable gate arrays (FPGAs) typically measure the size of a FPGA by its logic capacity. If a design fits within the logic capacity limits of an FPGA, it is generally assumed that it must also be routable. To ensure this high routability, FPGA vendors typically over-design the routing network. Despite this over-design, there may still be circuits that remain un-routable in a given FPGA family. This thesis presents two new computer-aided design (CAD) tools, DHPack and Un/DoPack, that are able to route these un-routable circuits by trading off logic utilization for interconnect. DHPack uses the natural design hierarchy of the circuit to identify high congestion regions. For a set of benchmark circuits used in this thesis, DHPack is able to reduce channel width by 13% with a small area increase of 3%. DHPack can continue to decrease channel width by 29% with a larger area increase of 146%. Un/DoPack improves on DHPack by targeting hard channel width constraints without having to rely on the design hierarchy of the circuit to perform congestion estimation. For a set of benchmark circuits presented in this thesis, Un/DoPack can reduce channel width by 38% with an 18% penalty in critical path delay and 64% increase in area. The primary application of these tools is to make previously unroutable circuits routable by using an FPGA with more logic.
Item Metadata
Title |
Channel width reduction techniques for system-on-chip circuits in field-programmable gate arrays
|
Creator | |
Publisher |
University of British Columbia
|
Date Issued |
2006
|
Description |
Users of field-programmable gate arrays (FPGAs) typically measure the size of
a FPGA by its logic capacity. If a design fits within the logic capacity limits of an
FPGA, it is generally assumed that it must also be routable. To ensure this high
routability, FPGA vendors typically over-design the routing network. Despite this
over-design, there may still be circuits that remain un-routable in a given FPGA
family. This thesis presents two new computer-aided design (CAD) tools, DHPack and
Un/DoPack, that are able to route these un-routable circuits by trading off logic
utilization for interconnect. DHPack uses the natural design hierarchy of the circuit to
identify high congestion regions. For a set of benchmark circuits used in this thesis,
DHPack is able to reduce channel width by 13% with a small area increase of 3%.
DHPack can continue to decrease channel width by 29% with a larger area increase of
146%. Un/DoPack improves on DHPack by targeting hard channel width constraints
without having to rely on the design hierarchy of the circuit to perform congestion
estimation. For a set of benchmark circuits presented in this thesis, Un/DoPack can
reduce channel width by 38% with an 18% penalty in critical path delay and 64%
increase in area. The primary application of these tools is to make previously unroutable
circuits routable by using an FPGA with more logic.
|
Genre | |
Type | |
Language |
eng
|
Date Available |
2010-01-08
|
Provider |
Vancouver : University of British Columbia Library
|
Rights |
For non-commercial purposes only, such as research, private study and education. Additional conditions apply, see Terms of Use https://open.library.ubc.ca/terms_of_use.
|
DOI |
10.14288/1.0065607
|
URI | |
Degree | |
Program | |
Affiliation | |
Degree Grantor |
University of British Columbia
|
Graduation Date |
2006-05
|
Campus | |
Scholarly Level |
Graduate
|
Aggregated Source Repository |
DSpace
|
Item Media
Item Citations and Data
Rights
For non-commercial purposes only, such as research, private study and education. Additional conditions apply, see Terms of Use https://open.library.ubc.ca/terms_of_use.