iTPlace: Machine Learning-Based Delay-Aware Transistor Placement for Standard Cell Synthesis

Tai Cheng Lee, Cheng Yen Yang, Yih Lang Li

Research output: Contribution to journalConference articlepeer-review

Abstract

Cell layout synthesis is a critical stage in modern digital IC design. In previous automatic synthesis solutions, algorithms always consider only cell area and routability. This is the first work to propose a method of delay-aware transistor placement for cell library synthesis at the sign-off level. We consider the delay and area of a cell in the transistor placement stage. Our methodology consists of three major steps. First, a search tree finds the candidate placement list that has the smallest area in a large search space. Then, a neural network filters out the unroutable candidates. Finally, a comparative convolutional neural network model, trained by sign-off level data, sorts the delays during the early placement stage. The experimental results show that the proposed CNN-based routable classifier can achieve up to 98% accuracy, and the proposed CNN-based delay ranker also can achieve up to 94.6% accuracy. The work obtains a 1.77% average sequential component delay improvement over the traditional cell synthesis method. Our method also has a 0.97% better delay performance than the human-level design.

Original languageEnglish
Article number9256764
JournalIEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD
Volume2020-November
DOIs
StatePublished - 2 Nov 2020
Event39th IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2020 - Virtual, San Diego, United States
Duration: 2 Nov 20205 Nov 2020

Fingerprint Dive into the research topics of 'iTPlace: Machine Learning-Based Delay-Aware Transistor Placement for Standard Cell Synthesis'. Together they form a unique fingerprint.

Cite this