Thermal and IR Drop Analysis Using Convolutional Encoder-Decoder Networks

Computationally expensive temperature and power grid analyses are required during the design cycle to guide IC design. This paper employs encoder-decoder based generative (EDGe) networks to map these analyses to fast and accurate image-to-image and sequence-to-sequence translation tasks. The network takes a power map as input and outputs the corresponding temperature or IR drop map. We propose two networks: (i) ThermEDGe: a static and dynamic full-chip temperature estimator and (ii) IREDGe: a full-chip static IR drop predictor based on input power, power grid distribution, and power pad distribution patterns. The models are design-independent and must be trained just once for a particular technology and packaging solution. ThermEDGe and IREDGe are demonstrated to rapidly predict the on-chip temperature and IR drop contours in milliseconds (in contrast with commercial tools that require several hours or more) and provide an average error of 0.6% and 0.008% respectively.

[1]  Sani R. Nassif,et al.  Power grid analysis benchmarks , 2008, 2008 Asia and South Pacific Design Automation Conference.

[2]  Francesco Visin,et al.  A guide to convolution arithmetic for deep learning , 2016, ArXiv.

[3]  Jinwei Zhang,et al.  Full-Chip Thermal Map Estimation for Commercial Multi-Core CPUs with Generative Adversarial Learning**This work is supported in part by NSF grants under No. CCF-1816361, in part by NSF grant under No. CCF-2007135 and No. OISE-1854276. , 2020, 2020 IEEE/ACM International Conference On Computer Aided Design (ICCAD).

[4]  Sachin S. Sapatnekar,et al.  MAVIREC: ML-Aided Vectored IR-DropEstimation and Classification , 2020, ArXiv.

[5]  Andrew B. Kahng,et al.  IncPIRD: Fast Learning-Based Prediction of Incremental IR Drop , 2019, 2019 IEEE/ACM International Conference on Computer-Aided Design (ICCAD).

[6]  Raquel Urtasun,et al.  Understanding the Effective Receptive Field in Deep Convolutional Neural Networks , 2016, NIPS.

[7]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[8]  Farhang Yazdani,et al.  Foundations of Heterogeneous Integration: An Industry-Based, 2.5D/3D Pathfinding and Co-Design Approach , 2018 .

[9]  Sani R. Nassif,et al.  Multigrid-like technique for power grid analysis , 2001, IEEE/ACM International Conference on Computer Aided Design. ICCAD 2001. IEEE/ACM Digest of Technical Papers (Cat. No.01CH37281).

[10]  Yu-Bin Yang,et al.  Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections , 2016, NIPS.

[11]  Diana Marculescu,et al.  A learning-based autoregressive model for fast transient thermal analysis of chip-multiprocessors , 2012, 17th Asia and South Pacific Design Automation Conference.

[12]  Sachin S. Sapatnekar,et al.  Thermally-Aware Design , 2008 .

[13]  Eli Chiprout.  Fast flip-chip power grid analysis via locality and grid shells , 2004, ICCAD 2004.

[14]  Sheldon X.-D. Tan,et al.  Hot Spot Identification and System Parameterized Thermal Modeling for Multi-Core Processors Through Infrared Thermal Imaging , 2019, 2019 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[15]  Dit-Yan Yeung,et al.  Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting , 2015, NIPS.

[16]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Martin D. F. Wong,et al.  Fast algorithms for IR drop analysis in large power grid , 2005, ICCAD-2005. IEEE/ACM International Conference on Computer-Aided Design, 2005..

[18]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[19]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[20]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Dean Liu,et al.  Macro-modeling concepts for the chip electrical interface , 2002, DAC '02.

[22]  Gokhan Memik,et al.  Machine Learning-Based Temperature Prediction for Runtime Thermal Management Across System Components , 2018, IEEE Transactions on Parallel and Distributed Systems.

[23]  Wenbo Xia,et al.  DNN-based Fast Static On-chip Thermal Solver , 2020, 2020 36th Semiconductor Thermal Measurement, Modeling & Management Symposium (SEMI-THERM).

[24]  Sachin S. Sapatnekar,et al.  Partition-based algorithm for power grid design using locality , 2006, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[25]  Tsung-Shan Yang,et al.  IR drop prediction of ECO-revised circuits using machine learning , 2018, 2018 IEEE 36th VLSI Test Symposium (VTS).

[26]  Yiran Chen,et al.  PowerNet: Transferable Dynamic IR Drop Estimation via Maximum Convolutional Neural Network , 2020, 2020 25th Asia and South Pacific Design Automation Conference (ASP-DAC).

[27]  Sachin S. Sapatnekar,et al.  Template-based PDN Synthesis in Floorplan and Placement Using Classifier and CNN Techniques , 2020, 2020 25th Asia and South Pacific Design Automation Conference (ASP-DAC).