English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In the logic synthesis stage, structure transformations in the synthesis toolneed to be combined into optimization sequences and act on the circuit to meetthe specified circuit area and delay. However, logic synthesis optimizationsequences are time-consuming to run, and predicting the quality of the results(QoR) against the synthesis optimization sequence for a circuit can helpengineers find a better optimization sequence faster. In this work, we proposea deep learning method to predict the QoR of unseen circuit-optimizationsequences pairs. Specifically, the structure transformations are translatedinto vectors by embedding methods and advanced natural language processing(NLP) technology (Transformer) is used to extract the features of theoptimization sequences. In addition, to enable the prediction process of themodel to be generalized from circuit to circuit, the graph representation ofthe circuit is represented as an adjacency matrix and a feature matrix. Graphneural networks(GNN) are used to extract the structural features of thecircuits. For this problem, the Transformer and three typical GNNs are used.Furthermore, the Transformer and GNNs are adopted as a joint learning policyfor the QoR prediction of the unseen circuit-optimization sequences. Themethods resulting from the combination of Transformer and GNNs are benchmarked.The experimental results show that the joint learning of Transformer andGraphSage gives the best results. The Mean Absolute Error (MAE) of thepredicted result is 0.412.

The prediction of the quality of results in Logic Synthesis using Transformer and Graph Neural Networks