Professional Documents
Culture Documents
3
ENSEMBLE MODELS
How Deep Learning Can Drive Physical Synthesis Towards More Predictable Legalization, ISPD’19
7
ML DESIGN SPACE EXPLORATION
Intelligently explore a large design space to find the optimal target
Source : aiindex.org
10
CLASSICAL MACHINE LEARNING VS DEEP LEARNING
No need for feature engineering
Deep Learning
Performance
Machine Learning
Amount of Data
https://arxiv.org/ftp/arxiv/papers/1803/1803.01164.pdf
11
LEARNING PARADIGMS
12
OUTLINE
feature
learned map
weights
15
CNN VARIATIONS
ShuffleNet V2
https://arxiv.org/pdf/1810.00736.pdf
16
POWER PREDICTION WITH MACHINE LEARNING
ShuffleNet V2
PRIMAL: Power Inference using Machine Learning (DAC’19) 18
POWER PREDICTION WITH CNN
DL has better accuracy than ML for large design
Upsampling/Transposed Convolution
(Blue input, green output)
Fully Convolutional Networks for Semantic Segmentation, CVPR’15
20
DRC HOTSPOT PREDICTION WITH FCN
ROUTENET: Routability Prediction for Mixed-Size Designs Using Convolutional Neural Network, ICCAD’18
21
ROUTENET MODEL
ROUTENET: Routability Prediction for Mixed-Size Designs Using Convolutional Neural Network, ICCAD’18
22
DRC HOTSPOT DETECTION EVALUATION
ROUTENET: Routability Prediction for Mixed-Size Designs Using Convolutional Neural Network, ICCAD’18
23
GRAPH CONVOLUTIONAL NETWORK (GCN)
GCN aggregates information from neighboring nodes
1 3
2
5 7
9 1 7
1 [1 x 64]
4 3
Encoding
1 [1 x 32] 8
Aggregation
1 [1 x 4] 2 [1 x 4] 3 [1 x 4] 4 [1 x 4]
1 2 3 4 [4 x 4] 1 2 5 6 [4 x 4] 1 3 7 8 [4 x 4] 1 4 8 9 [4 x 4]
25
25
GCN BASED TESTABILITY PREDICTION
Logic Level
SCOAP_C0
SCOAP_C1
SCOAP_OB
Layer 1 Layer 2 Layer 3 Fully Connected Layers
1
1
0 0
0 0
High Performance Graph Convolutional Networks with Applications in Testability Analysis, DAC’19
26
TESTABILITY PREDICTION ACCURACY
Testing Accuracy(%) 1
0.9
100 0.8
K: # GCN 0.7
Layers
95 0.6
0.5
90 0.4
0.3
85 0.2
0.1
80 0
75
70
65
60
1 31 61 91 121 151 181 211 241 271
Precision Recall F1 score Accuracy
Epochs
• Generative models
GAN
ILT
Wafer
33
LithoGAN: End-to-End Lithography Modeling with Generative Adversarial Networks , DAC’19
REINFORCEMENT LEARNING BACKGROUND
34
REINFORCEMENT LEARNING CATEGORIES
(𝑺, 𝒂)
𝑸 𝝅(𝒔)
Value-based Policy-based
Gradient free
Evolutionary
Algorithm
41
POTENTIAL OF UNSUPERVISED LEARNING
42
OUTLINE
44
FEATURE SELECTION
• Filter method
• Evaluate relationship between features and target to compute importance of each feature
• Wrapper method
• Add features one at a time
• Embedded method
• Lasso regression: zero weight for unimportant features
46
1D FEATURE ENCODING
Robust Power Estimation and Simultaneous Switching Noise Prediction Methods Using Machine Learning, GTC’19 47
2D FEATURE ENCODING
Map array of registers to an 2D image
49
MODELING
Always try classical machine learning to establish a strong baseline
Use Linear Regression, SVM and XGBoost
Hyperparameter tuning:
Start with small dataset and make sure you can overfit it with the model
Gradually increase model complexity if you can not overfit the training dataset
Cross validation
50
DATA IMBALANCE ISSUE
It is very common to have much more non-DTs (negative class) than DTs
(positive class), imbalance ratio more than 100X
High Performance Graph Convolutional Networks with Applications in Testability Analysis, DAC’19
51
WEIGHTED LABEL
Apply weights to compensate the bias {2, 3, 4, 5,.... 10, 20, 30, 40, 50}
+ + - +
- -
High Performance Graph Convolutional Networks with Applications in Testability Analysis, DAC’19
53
CONCLUSIONS
• Deep learning and machine learning can improve quality and productivity
of design automation in many ways.
54