Data-dependent cycle-accurate power modeling of RTL-level IPs using machine learning
MetadataShow full item record
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.
Showing items related by title, author, creator and subject.
Pish, S.; Herbst, J; Wardell, D; Gattozzi, A; Flynn, M. (2015-06)From local utility grids to electric ships, providing power to an ever increasing variety and magnitude of loads requires power grids that are more flexible, resilient, and efficient than ever before. In many cases, these ...
Analysis of the Power Quality Impact of Multiple Directed Energy Loads on an Electric Ship Power System Hebner, R. E.; Gattozzi, A. L; Cohn, K. R; Colson, W. B. (2010-06)The electrical power system of an all-electric ship has been modeled in Simulink for the case of a ship supporting several high power directed energy loads, among which are a Free Electron Laser (FEL), an Active Denial ...
Uriarte, F. M.; Mashayekh, S. (undated)Frequent matrix factorizations due to power electronic switch commutations are computationally expensive. This paper addresses this burden by treating power electronic switches as dependant sources instead of time-varying ...