Show simple item record

dc.contributor.advisorGerstlauer, Andreas, 1970-
dc.creatorSrour, Malek
dc.date.accessioned2018-08-07T15:56:34Z
dc.date.available2018-08-07T15:56:34Z
dc.date.created2018-05
dc.date.issued2018-05-03
dc.date.submittedMay 2018
dc.identifierdoi:10.15781/T22F7K85V
dc.identifier.urihttp://hdl.handle.net/2152/65980
dc.description.abstractIn a chip design project, early design planning has a strong impact on the schedule and the cost of design. Power estimation is part of early design planning, and it greatly affects design decisions. Power modeling performed at a high level of abstraction is fast but inaccurate due to lack of circuit switching activity information. By contrast, power modeling performed at a low level of abstraction is more accurate as the synthesized circuit synthesis is known, but this simulation is typically slow. This report explores a power modeling approach performed at register transfer level (RTL). It exploits machine learning models in order to have a fast yet relatively accurate cycle-by-cycle power estimation. The approach is data-dependent, where cycle-specific models are trained based on the switching activity of signals obtained from RTL simulation and cycle-by-cycle power values obtained from a reference gate-level simulation of an existing RTL design. Therefore, if any changes are applied to the RTL design, re-training of models is required. The approach aims at obtaining fast yet accurate power predictions for new invocations of a given trained model using signal activity information collected during simulation of the unmodified RTL. At a low level, the complete visibility of signals in a design unintuitively might cause overtraining the model leading to inaccurate estimation. The suggested model employs automatic feature selection in each cycle. Based on the invocations used to train the cycle-by-cycle models, only signals that may switch during a given cycle will be selected as the features for their respective cycle-specific model. The method was tested on an 8-by-8 DCT design and the power estimates were within 6.5% of those from a commercial power analysis tool. This report also simulates and compares the approach of cycle-specific models to the approach of a single global model for all cycles and show that the cycle-specific approach is twice as accurate.
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.subjectCycle-accurate power modeling
dc.subjectPower modeling
dc.subjectMachine learning
dc.subjectChip design
dc.subjectPower estimation
dc.subjectRegister transfer level
dc.subjectAbstraction level
dc.subjectPower predictions
dc.subjectCycle-specific models
dc.titleData-dependent cycle-accurate power modeling of RTL-level IPs using machine learning
dc.typeThesis
dc.date.updated2018-08-07T15:56:35Z
dc.description.departmentElectrical and Computer Engineering
thesis.degree.departmentElectrical and Computer Engineering
thesis.degree.disciplineElectrical and Computer Engineering
thesis.degree.grantorThe University of Texas at Austin
thesis.degree.levelMasters
thesis.degree.nameMaster of Science in Engineering
dc.type.materialtext


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record