A Deep-Learning-Aided Pipeline for Efficient Post-Silicon Tuning

2022/07/01 by Liao, Yiwen, Yang, Bin, Latty, Raphaël +1
#FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2207.00336

Abstract

In post-silicon validation, tuning is to find the values for the tuning knobs, potentially as a function of process parameters and/or known operating conditions. In this sense, an more efficient tuning requires identifying the most critical tuning knobs and process parameters in terms of a given figure-of-merit for a Device Under Test (DUT). This is often manually conducted by experienced experts. However, with increasingly complex chips, manual inspection on a large amount of raw variables has become more challenging. In this work, we leverage neural networks to efficiently select the most relevant variables and present a corresponding deep-learning-aided pipeline for efficient tuning.

Related

• Self-Learning Tuning for Post-Silicon Validation
• Experts in the Loop: Conditional Variable Selection for Accelerating Post-Silicon Analysis Based on Deep Learning
• ML²Tuner: Efficient Code Tuning via Multi-Level Machine Learning Models
• HW-Aware Initialization of DNN Auto-Tuning to Improve Exploration Time and Robustness
• Deep Learning Regression of VLSI Plasma Etch Metrology