Data-dependent cycle-accurate power modeling of RTL-level IPs using machine learning
dc.contributor.advisor | Gerstlauer, Andreas, 1970- | |
dc.creator | Srour, Malek | |
dc.date.accessioned | 2018-08-07T15:56:34Z | |
dc.date.available | 2018-08-07T15:56:34Z | |
dc.date.created | 2018-05 | |
dc.date.issued | 2018-05-03 | |
dc.date.submitted | May 2018 | |
dc.date.updated | 2018-08-07T15:56:35Z | |
dc.description.abstract | In 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.description.department | Electrical and Computer Engineering | |
dc.format.mimetype | application/pdf | |
dc.identifier | doi:10.15781/T22F7K85V | |
dc.identifier.uri | http://hdl.handle.net/2152/65980 | |
dc.language.iso | en | |
dc.subject | Cycle-accurate power modeling | |
dc.subject | Power modeling | |
dc.subject | Machine learning | |
dc.subject | Chip design | |
dc.subject | Power estimation | |
dc.subject | Register transfer level | |
dc.subject | Abstraction level | |
dc.subject | Power predictions | |
dc.subject | Cycle-specific models | |
dc.title | Data-dependent cycle-accurate power modeling of RTL-level IPs using machine learning | |
dc.type | Thesis | |
dc.type.material | text | |
thesis.degree.department | Electrical and Computer Engineering | |
thesis.degree.discipline | Electrical and Computer Engineering | |
thesis.degree.grantor | The University of Texas at Austin | |
thesis.degree.level | Masters | |
thesis.degree.name | Master of Science in Engineering |
Access full-text files
Original bundle
1 - 1 of 1
Loading...
- Name:
- SROUR-MASTERSREPORT-2018.pdf
- Size:
- 1.29 MB
- Format:
- Adobe Portable Document Format