System and method for predicting performance, power and area behavior of soft IP components in integrated circuit design
AssigneeArteris, Inc.
InventorBenny Winefeld
Life of this patent
Estimating the term…
Abstract
A system, and corresponding method, is described for using a model to predict the physical behavior of IP from an HDL representation of the IP. The system generated data for training and testing the model by treating the logical parameters and physical parameters subset as one for the IP block. The system digitizes the non-numerical parameters and compresses timing arcs. The system uses the trained model to characteristic behavior for an IP block directly from the combined vector of logical parameter values and physical parameter values.
Claims12
A method for accumulating data used as a training set for training a machine learning model capable of predicting one or more characteristics for any IP block, which has a set of input parameters, in order to optimize an IP block, the method comprising:
- generating a plurality of composite vectors based on a plurality of vectors of physical parameters and a plurality of vectors of logical parameters;
- analyzing the plurality of composite vectors to generate a gate level netlist for each combination of the plurality of vectors of physical parameters and the plurality of vectors of logical parameters;
- generating a characterization for each gate level netlist to produce a plurality of characterizations;
- and
- updating the training set using data selected from a set including at least one of:
- the plurality of vectors of logical parameters;
- the plurality of vectors of physical parameters;
- the plurality of composite vectors;
- and
- timing characterization.
Dependencies are inferred from the claim text.