Optimization of IBIS-AMI Model Parameters with ML Algorithms

Serial link speeds have increased 25X in under 20 years, thus increasing the complexity of the IBIS algorithmic modeling interface (AMI) models used in simulating these links. With the increased speed and complexity of designs, it is crucial to analyze channels to ensure sufficient margin for error-free data transmission.

An exhaustive manual search method is typically used to find the best set of parameters for a given channel, but given the increased number of model parameters and ranges, this approach can quickly become computationally expensive, even with parallel execution. Machine learning (ML) techniques have proven effective in modeling complex systems with numerous interacting components and nonlinear relationships.

The featured cover story in the October 2025 edition of Signal Integrity Journal by Cadence’s Jared James and Dr. Ambrish Varma describes the use of Cadence Sigrity signal and power integrity (SI/PI) solution ML optimization algorithm to quickly and efficiently converge on the best set of parameters in a set of IBIS-AMI models. The application of Sigrity was investigated for refining IBIS-AMI parameters to find the optimal set of values to maximize a specific metric.

Machine Learning Optimization

The ML algorithm was applied to the optimization of AMI parameters in a serial link simulation. The results show that the algorithm was able to successfully find good results for three different channels. This method found a good set of parameters in fewer simulations than if a traditional manual method had been deployed, saving the use of limited human and compute resources. In most test cases tried, it was found that only 100 simulations were needed to find the best set of parameters.

IBIS-AMI Model Generation

For this study, heavily parametrized IBIS-AMI models were needed to leverage the Sigrity ML optimization technology. A model based on the OIF-CEI-112G- LR standard was selected due to its large number of parameter combinations. Had the traditional manual method been used, there were a total of six different parameters that could be optimized between the RX and TX models, translating to 636,804 simulations for complete coverage of the solution space.

Simulation Setup

A testbench was built in an IBIS-AMI simulator, shown below. The simulation was run long enough to allow the decision feedback equalizer (DFE) to adapt to the incoming data (~70kbits), and to accumulate ~100kbits for making measurements. The simulation was run with 64 steps per user interface and a vertical resolution of 2048, allowing sufficient detail for taking accurate measurements.

Simulation Results

The figure below shows the optimization convergence for three different channels: short channel (left), medium channel (center), and long channel (right).

It is clearly shown that the ML optimization found parameters that resulted in good open eye results at the RX.

Conclusion

In this paper, the application of Cadence’s Sigrity SI/PI ML technology was investigated for refining IBIS-AMI parameters to quickly and efficiently converge on the best set of parameters in a set of IBIS-AMI models. The ML algorithm was applied to the optimization of AMI parameters in a serial link simulation. The results confirmed that the algorithm successfully found good results for three different channels in significantly fewer simulations (average of about 100) than if a traditional manual method had been deployed, saving the use of limited human and compute resources.

To learn about the details of this study, you can view the Signal Integrity Journal cover story here. To learn more about the features and benefits of Sigrity SI/PI analysis, visit our Sigrity product page.