Developing Synthesis Flows Without Human Knowledge

Design flows are the explicit combinations of design transformations, primarily involved in synthesis, placement and routing processes, to accomplish the design of Integrated Circuits (ICs) and System-on-Chip (SoC). Mostly, the flows are developed based on the knowledge of the experts. However, due to the large search space of design flows and the increasing design complexity, developing Intellectual Property (IP)-specific synthesis flows providing high Quality of Result (QoR) is extremely challenging. This work presents a fully autonomous framework that artificially produces design-specific synthesis flows without human guidance and baseline flows, using Convolutional Neural Network (CNN). The demonstrations are made by successfully designing logic synthesis flows of three large scaled designs.

[1]  Haim Mendelson.  On Permutations with Limited Repetition , 1981, J. Comb. Theory, Ser. A.

[2]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[3]  Giovanni De Micheli,et al.  End-to-End Industrial Study of Retiming , 2018, 2018 IEEE Computer Society Annual Symposium on VLSI (ISVLSI).

[4]  Michael F. P. O'Boyle,et al.  Using machine learning to focus iterative optimization , 2006, International Symposium on Code Generation and Optimization (CGO'06).

[5]  R. Durrett.  Probability: Theory and Examples , 1993 .

[6]  Zhiru Zhang,et al.  A Parallelized Iterative Improvement Approach to Area Optimization for LUT-Based Technology Mapping , 2017, FPGA.

[7]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

[8]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[9]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[10]  Ning Qian,et al.  On the momentum term in gradient descent learning algorithms , 1999, Neural Networks.

[11]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[12]  Bernard Brezzo,et al.  TrueNorth: Design and Tool Flow of a 65 mW 1 Million Neuron Programmable Neurosynaptic Chip , 2015, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[13]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[14]  Honglak Lee,et al.  Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Units , 2016, ICML.

[15]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[16]  Sepp Hochreiter,et al.  Self-Normalizing Neural Networks , 2017, NIPS.

[17]  Camille Couprie,et al.  Learning Hierarchical Features for Scene Labeling , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Cunxi Yu,et al.  DAG-aware logic synthesis of datapaths , 2016, 2016 53nd ACM/EDAC/IEEE Design Automation Conference (DAC).

[19]  Martin Wattenberg,et al.  Ad click prediction: a view from the trenches , 2013, KDD.

[20]  Cunxi Yu,et al.  Advanced datapath synthesis using graph isomorphism , 2017, 2017 IEEE/ACM International Conference on Computer-Aided Design (ICCAD).