FIST: A Feature-Importance Sampling and Tree-Based Method for Automatic Design Flow Parameter Tuning

by   Zhiyao Xie, et al.

Design flow parameters are of utmost importance to chip design quality and require a painfully long time to evaluate their effects. In reality, flow parameter tuning is usually performed manually based on designers' experience in an ad hoc manner. In this work, we introduce a machine learning-based automatic parameter tuning methodology that aims to find the best design quality with a limited number of trials. Instead of merely plugging in machine learning engines, we develop clustering and approximate sampling techniques for improving tuning efficiency. The feature extraction in this method can reuse knowledge from prior designs. Furthermore, we leverage a state-of-the-art XGBoost model and propose a novel dynamic tree technique to overcome overfitting. Experimental results on benchmark circuits show that our approach achieves 25 compared to random forest method, which is the kernel of a highly cited previous work. Our approach is further validated on two industrial designs. By sampling less than 0.02 and 1.43


page 1

page 5


Bridging the Gap Between Layout Pattern Sampling and Hotspot Detection via Batch Active Learning

Layout hotpot detection is one of the main steps in modern VLSI design. ...

Feature Importance Measurement based on Decision Tree Sampling

Random forest is effective for prediction tasks but the randomness of tr...

Tree pyramidal adaptive importance sampling

This paper introduces Tree-Pyramidal Adaptive Importance Sampling (TP-AI...

Automatic Conversion from Flip-flop to 3-phase Latch-based Designs

Latch-based designs have many benefits over their flip-flop based counte...

Best Memory Architecture Exploration under Parameters Variations accelerated with Machine Learning

The design of effective memory architecture is of utmost importance in m...

Scaling Probe-Based Real-Time Dynamic Global Illumination for Production

We contribute several practical extensions to the probe based irradiance...

Please sign up or login with your details

Forgot password? Click here to reset