vlsi mask optimization: from shallow to deep learning

VLSI Mask Optimization:From Shallow To Deep Learning

Haoyu Yang1, Wei Zhong2, Yuzhe Ma1, Hao Geng1,Ran Chen1, Wanli Chen1, Bei Yu1

1The Chinese University of Hong Kong2Dalian University of Technology

1 / 22

Moore’s Law to Extreme Scaling

1940 1950 1960 1970 1980 1990 2000 2010 2020

10,000,000,000

110

1001,000

10,000100,000

1,000,00010,000,000

100,000,0001,000,000,000

Invention of the Transistor

10 1 0.1 0.01

Year

Num

ber o

f Tra

nsis

tors

per I

nteg

rate

d C

ircui

t

Moore’s LawProcess Technology (µm

<latexit sha1_base64="1XOQUpYJ4Navgj2rMp+JfrNOobQ=">AAAB7nicbVA9TwJBEJ3DL8Qv1NJmI5hYkTsaLElsLDERMIEL2VsW2LC7d9mdMyEXfoSNhcbY+nvs/DcucIWCL5nk5b2ZzMyLEiks+v63V9ja3tndK+6XDg6Pjk/Kp2cdG6eG8TaLZWweI2q5FJq3UaDkj4nhVEWSd6Pp7cLvPnFjRawfcJbwUNGxFiPBKDqpW+2rlKjqoFzxa/4SZJMEOalAjtag/NUfxixVXCOT1Npe4CcYZtSgYJLPS/3U8oSyKR3znqOaKm7DbHnunFw5ZUhGsXGlkSzV3xMZVdbOVOQ6FcWJXfcW4n9eL8XRTZgJnaTINVstGqWSYEwWv5OhMJyhnDlCmRHuVsIm1FCGLqGSCyFYf3mTdOq1wK8F9/VKs5HHUYQLuIRrCKABTbiDFrSBwRSe4RXevMR78d69j1VrwctnzuEPvM8fNUyOxg==</latexit><latexit sha1_base64="1XOQUpYJ4Navgj2rMp+JfrNOobQ=">AAAB7nicbVA9TwJBEJ3DL8Qv1NJmI5hYkTsaLElsLDERMIEL2VsW2LC7d9mdMyEXfoSNhcbY+nvs/DcucIWCL5nk5b2ZzMyLEiks+v63V9ja3tndK+6XDg6Pjk/Kp2cdG6eG8TaLZWweI2q5FJq3UaDkj4nhVEWSd6Pp7cLvPnFjRawfcJbwUNGxFiPBKDqpW+2rlKjqoFzxa/4SZJMEOalAjtag/NUfxixVXCOT1Npe4CcYZtSgYJLPS/3U8oSyKR3znqOaKm7DbHnunFw5ZUhGsXGlkSzV3xMZVdbOVOQ6FcWJXfcW4n9eL8XRTZgJnaTINVstGqWSYEwWv5OhMJyhnDlCmRHuVsIm1FCGLqGSCyFYf3mTdOq1wK8F9/VKs5HHUYQLuIRrCKABTbiDFrSBwRSe4RXevMR78d69j1VrwctnzuEPvM8fNUyOxg==</latexit><latexit sha1_base64="1XOQUpYJ4Navgj2rMp+JfrNOobQ=">AAAB7nicbVA9TwJBEJ3DL8Qv1NJmI5hYkTsaLElsLDERMIEL2VsW2LC7d9mdMyEXfoSNhcbY+nvs/DcucIWCL5nk5b2ZzMyLEiks+v63V9ja3tndK+6XDg6Pjk/Kp2cdG6eG8TaLZWweI2q5FJq3UaDkj4nhVEWSd6Pp7cLvPnFjRawfcJbwUNGxFiPBKDqpW+2rlKjqoFzxa/4SZJMEOalAjtag/NUfxixVXCOT1Npe4CcYZtSgYJLPS/3U8oSyKR3znqOaKm7DbHnunFw5ZUhGsXGlkSzV3xMZVdbOVOQ6FcWJXfcW4n9eL8XRTZgJnaTINVstGqWSYEwWv5OhMJyhnDlCmRHuVsIm1FCGLqGSCyFYf3mTdOq1wK8F9/VKs5HHUYQLuIRrCKABTbiDFrSBwRSe4RXevMR78d69j1VrwctnzuEPvM8fNUyOxg==</latexit><latexit sha1_base64="1XOQUpYJ4Navgj2rMp+JfrNOobQ=">AAAB7nicbVA9TwJBEJ3DL8Qv1NJmI5hYkTsaLElsLDERMIEL2VsW2LC7d9mdMyEXfoSNhcbY+nvs/DcucIWCL5nk5b2ZzMyLEiks+v63V9ja3tndK+6XDg6Pjk/Kp2cdG6eG8TaLZWweI2q5FJq3UaDkj4nhVEWSd6Pp7cLvPnFjRawfcJbwUNGxFiPBKDqpW+2rlKjqoFzxa/4SZJMEOalAjtag/NUfxixVXCOT1Npe4CcYZtSgYJLPS/3U8oSyKR3znqOaKm7DbHnunFw5ZUhGsXGlkSzV3xMZVdbOVOQ6FcWJXfcW4n9eL8XRTZgJnaTINVstGqWSYEwWv5OhMJyhnDlCmRHuVsIm1FCGLqGSCyFYf3mTdOq1wK8F9/VKs5HHUYQLuIRrCKABTbiDFrSBwRSe4RXevMR78d69j1VrwctnzuEPvM8fNUyOxg==</latexit>

µm<latexit sha1_base64="1XOQUpYJ4Navgj2rMp+JfrNOobQ=">AAAB7nicbVA9TwJBEJ3DL8Qv1NJmI5hYkTsaLElsLDERMIEL2VsW2LC7d9mdMyEXfoSNhcbY+nvs/DcucIWCL5nk5b2ZzMyLEiks+v63V9ja3tndK+6XDg6Pjk/Kp2cdG6eG8TaLZWweI2q5FJq3UaDkj4nhVEWSd6Pp7cLvPnFjRawfcJbwUNGxFiPBKDqpW+2rlKjqoFzxa/4SZJMEOalAjtag/NUfxixVXCOT1Npe4CcYZtSgYJLPS/3U8oSyKR3znqOaKm7DbHnunFw5ZUhGsXGlkSzV3xMZVdbOVOQ6FcWJXfcW4n9eL8XRTZgJnaTINVstGqWSYEwWv5OhMJyhnDlCmRHuVsIm1FCGLqGSCyFYf3mTdOq1wK8F9/VKs5HHUYQLuIRrCKABTbiDFrSBwRSe4RXevMR78d69j1VrwctnzuEPvM8fNUyOxg==</latexit><latexit sha1_base64="1XOQUpYJ4Navgj2rMp+JfrNOobQ=">AAAB7nicbVA9TwJBEJ3DL8Qv1NJmI5hYkTsaLElsLDERMIEL2VsW2LC7d9mdMyEXfoSNhcbY+nvs/DcucIWCL5nk5b2ZzMyLEiks+v63V9ja3tndK+6XDg6Pjk/Kp2cdG6eG8TaLZWweI2q5FJq3UaDkj4nhVEWSd6Pp7cLvPnFjRawfcJbwUNGxFiPBKDqpW+2rlKjqoFzxa/4SZJMEOalAjtag/NUfxixVXCOT1Npe4CcYZtSgYJLPS/3U8oSyKR3znqOaKm7DbHnunFw5ZUhGsXGlkSzV3xMZVdbOVOQ6FcWJXfcW4n9eL8XRTZgJnaTINVstGqWSYEwWv5OhMJyhnDlCmRHuVsIm1FCGLqGSCyFYf3mTdOq1wK8F9/VKs5HHUYQLuIRrCKABTbiDFrSBwRSe4RXevMR78d69j1VrwctnzuEPvM8fNUyOxg==</latexit><latexit sha1_base64="1XOQUpYJ4Navgj2rMp+JfrNOobQ=">AAAB7nicbVA9TwJBEJ3DL8Qv1NJmI5hYkTsaLElsLDERMIEL2VsW2LC7d9mdMyEXfoSNhcbY+nvs/DcucIWCL5nk5b2ZzMyLEiks+v63V9ja3tndK+6XDg6Pjk/Kp2cdG6eG8TaLZWweI2q5FJq3UaDkj4nhVEWSd6Pp7cLvPnFjRawfcJbwUNGxFiPBKDqpW+2rlKjqoFzxa/4SZJMEOalAjtag/NUfxixVXCOT1Npe4CcYZtSgYJLPS/3U8oSyKR3znqOaKm7DbHnunFw5ZUhGsXGlkSzV3xMZVdbOVOQ6FcWJXfcW4n9eL8XRTZgJnaTINVstGqWSYEwWv5OhMJyhnDlCmRHuVsIm1FCGLqGSCyFYf3mTdOq1wK8F9/VKs5HHUYQLuIRrCKABTbiDFrSBwRSe4RXevMR78d69j1VrwctnzuEPvM8fNUyOxg==</latexit><latexit sha1_base64="1XOQUpYJ4Navgj2rMp+JfrNOobQ=">AAAB7nicbVA9TwJBEJ3DL8Qv1NJmI5hYkTsaLElsLDERMIEL2VsW2LC7d9mdMyEXfoSNhcbY+nvs/DcucIWCL5nk5b2ZzMyLEiks+v63V9ja3tndK+6XDg6Pjk/Kp2cdG6eG8TaLZWweI2q5FJq3UaDkj4nhVEWSd6Pp7cLvPnFjRawfcJbwUNGxFiPBKDqpW+2rlKjqoFzxa/4SZJMEOalAjtag/NUfxixVXCOT1Npe4CcYZtSgYJLPS/3U8oSyKR3znqOaKm7DbHnunFw5ZUhGsXGlkSzV3xMZVdbOVOQ6FcWJXfcW4n9eL8XRTZgJnaTINVstGqWSYEwWv5OhMJyhnDlCmRHuVsIm1FCGLqGSCyFYf3mTdOq1wK8F9/VKs5HHUYQLuIRrCKABTbiDFrSBwRSe4RXevMR78d69j1VrwctnzuEPvM8fNUyOxg==</latexit> )

40048086

286386

486 Pentium

Pentium IIPentium 4

Core 2 DuoCore i7

Doubles every 2.1 yrs

A7

A10 A11

A12

Intel MicroprocessorsApple Microprocessors

2 / 22

Challenge 1: Failure (Hotspot) Detection

Pre-OPC Layout Post-OPC Mask Hotspot on Wafer

I RET: OPC, SRAF, MPLI Still hotspot: low fidelity patternsI Simulations: extremely CPU intensive

Ra#o

%of%lith

ograph

y%sim

ula#

on%#me%

(normalize

d%by%40n

m%nod

e)%

Technology%node�

Required(computa/onal(/me(reduc/on!�

3 / 22

Challenge 2: Optical Proximity Correction (OPC)

Design target Mask Wafer

without OPC

with OPC

4 / 22

Why Deep Learning?I Feature Crafting v.s. Feature Learning

Although prior knowledge is considered during manually feature design, informationloss is inevitable.Feature learned from mass dataset is more reliable.

I ScalabilityWith shrinking down circuit feature size, mask layout becomes more complicated.Deep learning has the potential to handle ultra-large-scale instances while traditionalmachine learning may suffer from performance degradation.

I Mature Libraries

5 / 22

Outline

Hotspot Detection via Machine Learning

OPC via Machine Learning

Heterogeneous OPC

6 / 22

Outline

Hotspot Detection via Machine Learning

OPC via Machine Learning

Heterogeneous OPC

7 / 22

Hotspot Detection Hierarchy

Increasing verificationaccuracy

Sampling

Hotspot Detection

Lithography Simulation

(Relative) CPU runtime at each level

I Sampling (DRC Checking):scan and rule check each region

I Hotspot Detection:verify the sampled regions and report potential hotspots

I Lithography Simulation:final verification on the reported hotspots

7 / 22

Early Study of DNN-based Hotspot Detector∗

I Total 21 layers with 13 convolution layers and 5 pooling layers.I A ReLU is applied after each convolution layer.

…

…Hotspot

Non-Hotspot

512x512x4256x256x4

256x256x8

128x128x16128x128x8

64x64x16 64x64x3232x32x32 32x32x32

16x16x32

2048

512

C1

P1 C2-1C2-2 C2-3

P2 C3-1 C3-2 C4-1P3C3-3 C4-2 C4-3

C5-1 C5-2 C5-3P4 P5

∗Haoyu Yang, Luyang Luo, et al. (2017). “Imbalance aware lithography hotspot detection: a deep learningapproach”. In: JM3 16.3, p. 033504.

8 / 22

What Does Deep Learning Learn?

Origin Pool1 Pool2

Pool3 Pool4 Pool5

9 / 22

The Biased Learning Algorithm [DAC’17]†

Training Set

Update ε

yh=[0,1]

yn=[1-ε, ε]

MGD:

end-to-end

training

Stop Criteria

Trained Model

Yes

No

80 82 84 86 88 902,000

3,000

4,000

Accuracy (%)Fa

lseAlarm

Shift-Boundary Bias

†Haoyu Yang, Jing Su, et al. (2017). “Layout Hotspot Detection with Feature Tensor Generation and DeepBiased Learning”. In: Proc. DAC, 62:1–62:6.10 / 22

Optimizing AUC [ASPDAC’19]‡

The AUC objective:LΦ(f ) = 1

N+N−

∑N+

i=1∑N−

j=1 Φ(

f(x+

i)− f

(x−j))

.

Approximation candidates:

PSL ΦPSL(z) = (1− z)2

PHL ΦPHL(z) = max(1− z, 0)

PLL ΦPLL(z) = log(1 + exp(−βz))

R ΦR∗(z) =

{−(z− γ)p, if z > γ0, otherwise

‡Wei Ye et al. (2019). “LithoROC: lithography hotspot detection with explicit ROC optimization”. In:Proc. ASPDAC, pp. 292–298.

11 / 22

Conventional Clip based Solution

Region

…

Conventional Hotspot Detector

Hotspot

Non-Hotspot

Clips

I A binary classification problem.I Scan over whole region.I Single stage detector.

I Scanning is time consuming and single stage is not robust to false alarm.

12 / 22

Region based approach [DAC’19]

Region

Hotspot Core

Region-based Hotspot Detector

Feature Extraction

Clip Proposal Network

Refinement

I Learning what and where is hotspot at same time.I Classification Problem -> Classification & Regression Problem.

Ran Chen et al. (2019). “Faster Region-based Hotspot Detection”. In: Proc. DAC, 146:1–146:6.13 / 22

Outline

Hotspot Detection via Machine Learning

OPC via Machine Learning

Heterogeneous OPC

14 / 22

OPC Previous Work

Classic OPCI Model/Rule-based OPC

[Cobb+,SPIE’02][Kuang+,DATE’15][Awad+,DAC’16][Su+,ICCAD’16]1. Fragmentation of shape edges;2. Move fragments for better printability.

I Inverse Lithography[Pang+,SPIE’05][Gao+,DAC’14][Poonawala+,TIP’07][Ma+,ICCAD’17]1. Efficient model that maps mask to

aerial image;2. Continuously update mask through

descending the gradient of contourerror.

Machine Learning OPC[Matsunawa+,JM3’16][Choi+,SPIE’16][Xu+,ISPD’16][Shim+,APCCAS’16]

1. Edge fragmentation;2. Feature extraction;3. Model training.

14 / 22

Machine Learning-based SRAF InsertionSRAF Insertion with Machine Learning [ISPD’16]¶

Label: 1

Label: 0

0 1 2N%1sub%sampling0point

Tackling Robustness with Dictionary Learning [ASPDAC’19]‖

n+

s+

1<latexit sha1_base64="9uRmigbRU2gk7L38QsMLLMB+/9s=">AAAB7HicbVBNS8NAEJ34WetX1aOXxSIIhZKIoMeiF48VTFtoQ9lsJ+3SzSbsboQS+hu8eFDEqz/Im//GbZuDtj4YeLw3w8y8MBVcG9f9dtbWNza3tks75d29/YPDytFxSyeZYuizRCSqE1KNgkv0DTcCO6lCGocC2+H4bua3n1BpnshHM0kxiOlQ8ogzaqzky5quef1K1a27c5BV4hWkCgWa/cpXb5CwLEZpmKBadz03NUFOleFM4LTcyzSmlI3pELuWShqjDvL5sVNybpUBiRJlSxoyV39P5DTWehKHtjOmZqSXvZn4n9fNTHQT5FymmUHJFouiTBCTkNnnZMAVMiMmllCmuL2VsBFVlBmbT9mG4C2/vEpal3XPrXsPV9XGbRFHCU7hDC7Ag2towD00wQcGHJ7hFd4c6bw4787HonXNKWZO4A+czx/o/Y4U</latexit><latexit sha1_base64="9uRmigbRU2gk7L38QsMLLMB+/9s=">AAAB7HicbVBNS8NAEJ34WetX1aOXxSIIhZKIoMeiF48VTFtoQ9lsJ+3SzSbsboQS+hu8eFDEqz/Im//GbZuDtj4YeLw3w8y8MBVcG9f9dtbWNza3tks75d29/YPDytFxSyeZYuizRCSqE1KNgkv0DTcCO6lCGocC2+H4bua3n1BpnshHM0kxiOlQ8ogzaqzky5quef1K1a27c5BV4hWkCgWa/cpXb5CwLEZpmKBadz03NUFOleFM4LTcyzSmlI3pELuWShqjDvL5sVNybpUBiRJlSxoyV39P5DTWehKHtjOmZqSXvZn4n9fNTHQT5FymmUHJFouiTBCTkNnnZMAVMiMmllCmuL2VsBFVlBmbT9mG4C2/vEpal3XPrXsPV9XGbRFHCU7hDC7Ag2towD00wQcGHJ7hFd4c6bw4787HonXNKWZO4A+czx/o/Y4U</latexit><latexit sha1_base64="9uRmigbRU2gk7L38QsMLLMB+/9s=">AAAB7HicbVBNS8NAEJ34WetX1aOXxSIIhZKIoMeiF48VTFtoQ9lsJ+3SzSbsboQS+hu8eFDEqz/Im//GbZuDtj4YeLw3w8y8MBVcG9f9dtbWNza3tks75d29/YPDytFxSyeZYuizRCSqE1KNgkv0DTcCO6lCGocC2+H4bua3n1BpnshHM0kxiOlQ8ogzaqzky5quef1K1a27c5BV4hWkCgWa/cpXb5CwLEZpmKBadz03NUFOleFM4LTcyzSmlI3pELuWShqjDvL5sVNybpUBiRJlSxoyV39P5DTWehKHtjOmZqSXvZn4n9fNTHQT5FymmUHJFouiTBCTkNnnZMAVMiMmllCmuL2VsBFVlBmbT9mG4C2/vEpal3XPrXsPV9XGbRFHCU7hDC7Ag2towD00wQcGHJ7hFd4c6bw4787HonXNKWZO4A+czx/o/Y4U</latexit><latexit sha1_base64="9uRmigbRU2gk7L38QsMLLMB+/9s=">AAAB7HicbVBNS8NAEJ34WetX1aOXxSIIhZKIoMeiF48VTFtoQ9lsJ+3SzSbsboQS+hu8eFDEqz/Im//GbZuDtj4YeLw3w8y8MBVcG9f9dtbWNza3tks75d29/YPDytFxSyeZYuizRCSqE1KNgkv0DTcCO6lCGocC2+H4bua3n1BpnshHM0kxiOlQ8ogzaqzky5quef1K1a27c5BV4hWkCgWa/cpXb5CwLEZpmKBadz03NUFOleFM4LTcyzSmlI3pELuWShqjDvL5sVNybpUBiRJlSxoyV39P5DTWehKHtjOmZqSXvZn4n9fNTHQT5FymmUHJFouiTBCTkNnnZMAVMiMmllCmuL2VsBFVlBmbT9mG4C2/vEpal3XPrXsPV9XGbRFHCU7hDC7Ag2towD00wQcGHJ7hFd4c6bw4787HonXNKWZO4A+czx/o/Y4U</latexit>

{ N { {{⇡

s<latexit sha1_base64="N1eK0lTaQQAFA6yHzcECkl4oWJk=">AAAB6HicbVBNS8NAEJ3Ur1q/qh69LBbBU0lEqMeiF48t2A9oQ9lsJ+3azSbsboQS+gu8eFDEqz/Jm//GbZuDtj4YeLw3w8y8IBFcG9f9dgobm1vbO8Xd0t7+weFR+fikreNUMWyxWMSqG1CNgktsGW4EdhOFNAoEdoLJ3dzvPKHSPJYPZpqgH9GR5CFn1FipqQflilt1FyDrxMtJBXI0BuWv/jBmaYTSMEG17nluYvyMKsOZwFmpn2pMKJvQEfYslTRC7WeLQ2fkwipDEsbKljRkof6eyGik9TQKbGdEzVivenPxP6+XmvDGz7hMUoOSLReFqSAmJvOvyZArZEZMLaFMcXsrYWOqKDM2m5INwVt9eZ20r6qeW/Wa15X6bR5HEc7gHC7BgxrU4R4a0AIGCM/wCm/Oo/PivDsfy9aCk8+cwh84nz/epYz3</latexit><latexit sha1_base64="N1eK0lTaQQAFA6yHzcECkl4oWJk=">AAAB6HicbVBNS8NAEJ3Ur1q/qh69LBbBU0lEqMeiF48t2A9oQ9lsJ+3azSbsboQS+gu8eFDEqz/Jm//GbZuDtj4YeLw3w8y8IBFcG9f9dgobm1vbO8Xd0t7+weFR+fikreNUMWyxWMSqG1CNgktsGW4EdhOFNAoEdoLJ3dzvPKHSPJYPZpqgH9GR5CFn1FipqQflilt1FyDrxMtJBXI0BuWv/jBmaYTSMEG17nluYvyMKsOZwFmpn2pMKJvQEfYslTRC7WeLQ2fkwipDEsbKljRkof6eyGik9TQKbGdEzVivenPxP6+XmvDGz7hMUoOSLReFqSAmJvOvyZArZEZMLaFMcXsrYWOqKDM2m5INwVt9eZ20r6qeW/Wa15X6bR5HEc7gHC7BgxrU4R4a0AIGCM/wCm/Oo/PivDsfy9aCk8+cwh84nz/epYz3</latexit><latexit sha1_base64="N1eK0lTaQQAFA6yHzcECkl4oWJk=">AAAB6HicbVBNS8NAEJ3Ur1q/qh69LBbBU0lEqMeiF48t2A9oQ9lsJ+3azSbsboQS+gu8eFDEqz/Jm//GbZuDtj4YeLw3w8y8IBFcG9f9dgobm1vbO8Xd0t7+weFR+fikreNUMWyxWMSqG1CNgktsGW4EdhOFNAoEdoLJ3dzvPKHSPJYPZpqgH9GR5CFn1FipqQflilt1FyDrxMtJBXI0BuWv/jBmaYTSMEG17nluYvyMKsOZwFmpn2pMKJvQEfYslTRC7WeLQ2fkwipDEsbKljRkof6eyGik9TQKbGdEzVivenPxP6+XmvDGz7hMUoOSLReFqSAmJvOvyZArZEZMLaFMcXsrYWOqKDM2m5INwVt9eZ20r6qeW/Wa15X6bR5HEc7gHC7BgxrU4R4a0AIGCM/wCm/Oo/PivDsfy9aCk8+cwh84nz/epYz3</latexit><latexit sha1_base64="N1eK0lTaQQAFA6yHzcECkl4oWJk=">AAAB6HicbVBNS8NAEJ3Ur1q/qh69LBbBU0lEqMeiF48t2A9oQ9lsJ+3azSbsboQS+gu8eFDEqz/Jm//GbZuDtj4YeLw3w8y8IBFcG9f9dgobm1vbO8Xd0t7+weFR+fikreNUMWyxWMSqG1CNgktsGW4EdhOFNAoEdoLJ3dzvPKHSPJYPZpqgH9GR5CFn1FipqQflilt1FyDrxMtJBXI0BuWv/jBmaYTSMEG17nluYvyMKsOZwFmpn2pMKJvQEfYslTRC7WeLQ2fkwipDEsbKljRkof6eyGik9TQKbGdEzVivenPxP6+XmvDGz7hMUoOSLReFqSAmJvOvyZArZEZMLaFMcXsrYWOqKDM2m5INwVt9eZ20r6qeW/Wa15X6bR5HEc7gHC7BgxrU4R4a0AIGCM/wCm/Oo/PivDsfy9aCk8+cwh84nz/epYz3</latexit>

{{

0@

Dp↵Ap�W

1A

<latexit sha1_base64="pllvYHRduEvsHhXfv04wTS8CO7g=">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</latexit><latexit sha1_base64="pllvYHRduEvsHhXfv04wTS8CO7g=">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</latexit><latexit sha1_base64="pllvYHRduEvsHhXfv04wTS8CO7g=">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</latexit><latexit sha1_base64="pllvYHRduEvsHhXfv04wTS8CO7g=">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</latexit>

xt<latexit sha1_base64="Ep9PhwZ48W8s50rMVlok5byKlns=">AAAB+XicbVDLSgMxFL3js9bXqEs3wSK4KjMi6LLoxmUF+4B2GDKZtA3NJEOSKZahf+LGhSJu/RN3/o2ZdhbaeiDkcM695OREKWfaeN63s7a+sbm1Xdmp7u7tHxy6R8dtLTNFaItILlU3wppyJmjLMMNpN1UUJxGnnWh8V/idCVWaSfFopikNEjwUbMAINlYKXbcfSR7raWIv9BSaaujWvLo3B1olfklqUKIZul/9WJIsocIQjrXu+V5qghwrwwins2o/0zTFZIyHtGepwAnVQT5PPkPnVonRQCp7hEFz9fdGjhNdhLOTCTYjvewV4n9eLzODmyBnIs0MFWTx0CDjyEhU1IBipigxfGoJJorZrIiMsMLE2LKKEvzlL6+S9mXd9+r+w1WtcVvWUYFTOIML8OEaGnAPTWgBgQk8wyu8Obnz4rw7H4vRNafcOYE/cD5/ACeTk1M=</latexit><latexit sha1_base64="Ep9PhwZ48W8s50rMVlok5byKlns=">AAAB+XicbVDLSgMxFL3js9bXqEs3wSK4KjMi6LLoxmUF+4B2GDKZtA3NJEOSKZahf+LGhSJu/RN3/o2ZdhbaeiDkcM695OREKWfaeN63s7a+sbm1Xdmp7u7tHxy6R8dtLTNFaItILlU3wppyJmjLMMNpN1UUJxGnnWh8V/idCVWaSfFopikNEjwUbMAINlYKXbcfSR7raWIv9BSaaujWvLo3B1olfklqUKIZul/9WJIsocIQjrXu+V5qghwrwwins2o/0zTFZIyHtGepwAnVQT5PPkPnVonRQCp7hEFz9fdGjhNdhLOTCTYjvewV4n9eLzODmyBnIs0MFWTx0CDjyEhU1IBipigxfGoJJorZrIiMsMLE2LKKEvzlL6+S9mXd9+r+w1WtcVvWUYFTOIML8OEaGnAPTWgBgQk8wyu8Obnz4rw7H4vRNafcOYE/cD5/ACeTk1M=</latexit><latexit sha1_base64="Ep9PhwZ48W8s50rMVlok5byKlns=">AAAB+XicbVDLSgMxFL3js9bXqEs3wSK4KjMi6LLoxmUF+4B2GDKZtA3NJEOSKZahf+LGhSJu/RN3/o2ZdhbaeiDkcM695OREKWfaeN63s7a+sbm1Xdmp7u7tHxy6R8dtLTNFaItILlU3wppyJmjLMMNpN1UUJxGnnWh8V/idCVWaSfFopikNEjwUbMAINlYKXbcfSR7raWIv9BSaaujWvLo3B1olfklqUKIZul/9WJIsocIQjrXu+V5qghwrwwins2o/0zTFZIyHtGepwAnVQT5PPkPnVonRQCp7hEFz9fdGjhNdhLOTCTYjvewV4n9eLzODmyBnIs0MFWTx0CDjyEhU1IBipigxfGoJJorZrIiMsMLE2LKKEvzlL6+S9mXd9+r+w1WtcVvWUYFTOIML8OEaGnAPTWgBgQk8wyu8Obnz4rw7H4vRNafcOYE/cD5/ACeTk1M=</latexit><latexit sha1_base64="Ep9PhwZ48W8s50rMVlok5byKlns=">AAAB+XicbVDLSgMxFL3js9bXqEs3wSK4KjMi6LLoxmUF+4B2GDKZtA3NJEOSKZahf+LGhSJu/RN3/o2ZdhbaeiDkcM695OREKWfaeN63s7a+sbm1Xdmp7u7tHxy6R8dtLTNFaItILlU3wppyJmjLMMNpN1UUJxGnnWh8V/idCVWaSfFopikNEjwUbMAINlYKXbcfSR7raWIv9BSaaujWvLo3B1olfklqUKIZul/9WJIsocIQjrXu+V5qghwrwwins2o/0zTFZIyHtGepwAnVQT5PPkPnVonRQCp7hEFz9fdGjhNdhLOTCTYjvewV4n9eLzODmyBnIs0MFWTx0CDjyEhU1IBipigxfGoJJorZrIiMsMLE2LKKEvzlL6+S9mXd9+r+w1WtcVvWUYFTOIML8OEaGnAPTWgBgQk8wyu8Obnz4rw7H4vRNafcOYE/cD5/ACeTk1M=</latexit>

s<latexit sha1_base64="N1eK0lTaQQAFA6yHzcECkl4oWJk=">AAAB6HicbVBNS8NAEJ3Ur1q/qh69LBbBU0lEqMeiF48t2A9oQ9lsJ+3azSbsboQS+gu8eFDEqz/Jm//GbZuDtj4YeLw3w8y8IBFcG9f9dgobm1vbO8Xd0t7+weFR+fikreNUMWyxWMSqG1CNgktsGW4EdhOFNAoEdoLJ3dzvPKHSPJYPZpqgH9GR5CFn1FipqQflilt1FyDrxMtJBXI0BuWv/jBmaYTSMEG17nluYvyMKsOZwFmpn2pMKJvQEfYslTRC7WeLQ2fkwipDEsbKljRkof6eyGik9TQKbGdEzVivenPxP6+XmvDGz7hMUoOSLReFqSAmJvOvyZArZEZMLaFMcXsrYWOqKDM2m5INwVt9eZ20r6qeW/Wa15X6bR5HEc7gHC7BgxrU4R4a0AIGCM/wCm/Oo/PivDsfy9aCk8+cwh84nz/epYz3</latexit><latexit sha1_base64="N1eK0lTaQQAFA6yHzcECkl4oWJk=">AAAB6HicbVBNS8NAEJ3Ur1q/qh69LBbBU0lEqMeiF48t2A9oQ9lsJ+3azSbsboQS+gu8eFDEqz/Jm//GbZuDtj4YeLw3w8y8IBFcG9f9dgobm1vbO8Xd0t7+weFR+fikreNUMWyxWMSqG1CNgktsGW4EdhOFNAoEdoLJ3dzvPKHSPJYPZpqgH9GR5CFn1FipqQflilt1FyDrxMtJBXI0BuWv/jBmaYTSMEG17nluYvyMKsOZwFmpn2pMKJvQEfYslTRC7WeLQ2fkwipDEsbKljRkof6eyGik9TQKbGdEzVivenPxP6+XmvDGz7hMUoOSLReFqSAmJvOvyZArZEZMLaFMcXsrYWOqKDM2m5INwVt9eZ20r6qeW/Wa15X6bR5HEc7gHC7BgxrU4R4a0AIGCM/wCm/Oo/PivDsfy9aCk8+cwh84nz/epYz3</latexit><latexit sha1_base64="N1eK0lTaQQAFA6yHzcECkl4oWJk=">AAAB6HicbVBNS8NAEJ3Ur1q/qh69LBbBU0lEqMeiF48t2A9oQ9lsJ+3azSbsboQS+gu8eFDEqz/Jm//GbZuDtj4YeLw3w8y8IBFcG9f9dgobm1vbO8Xd0t7+weFR+fikreNUMWyxWMSqG1CNgktsGW4EdhOFNAoEdoLJ3dzvPKHSPJYPZpqgH9GR5CFn1FipqQflilt1FyDrxMtJBXI0BuWv/jBmaYTSMEG17nluYvyMKsOZwFmpn2pMKJvQEfYslTRC7WeLQ2fkwipDEsbKljRkof6eyGik9TQKbGdEzVivenPxP6+XmvDGz7hMUoOSLReFqSAmJvOvyZArZEZMLaFMcXsrYWOqKDM2m5INwVt9eZ20r6qeW/Wa15X6bR5HEc7gHC7BgxrU4R4a0AIGCM/wCm/Oo/PivDsfy9aCk8+cwh84nz/epYz3</latexit><latexit sha1_base64="N1eK0lTaQQAFA6yHzcECkl4oWJk=">AAAB6HicbVBNS8NAEJ3Ur1q/qh69LBbBU0lEqMeiF48t2A9oQ9lsJ+3azSbsboQS+gu8eFDEqz/Jm//GbZuDtj4YeLw3w8y8IBFcG9f9dgobm1vbO8Xd0t7+weFR+fikreNUMWyxWMSqG1CNgktsGW4EdhOFNAoEdoLJ3dzvPKHSPJYPZpqgH9GR5CFn1FipqQflilt1FyDrxMtJBXI0BuWv/jBmaYTSMEG17nluYvyMKsOZwFmpn2pMKJvQEfYslTRC7WeLQ2fkwipDEsbKljRkof6eyGik9TQKbGdEzVivenPxP6+XmvDGz7hMUoOSLReFqSAmJvOvyZArZEZMLaFMcXsrYWOqKDM2m5INwVt9eZ20r6qeW/Wa15X6bR5HEc7gHC7BgxrU4R4a0AIGCM/wCm/Oo/PivDsfy9aCk8+cwh84nz/epYz3</latexit>

N

n+

s+

1<latexit sha1_base64="9uRmigbRU2gk7L38QsMLLMB+/9s=">AAAB7HicbVBNS8NAEJ34WetX1aOXxSIIhZKIoMeiF48VTFtoQ9lsJ+3SzSbsboQS+hu8eFDEqz/Im//GbZuDtj4YeLw3w8y8MBVcG9f9dtbWNza3tks75d29/YPDytFxSyeZYuizRCSqE1KNgkv0DTcCO6lCGocC2+H4bua3n1BpnshHM0kxiOlQ8ogzaqzky5quef1K1a27c5BV4hWkCgWa/cpXb5CwLEZpmKBadz03NUFOleFM4LTcyzSmlI3pELuWShqjDvL5sVNybpUBiRJlSxoyV39P5DTWehKHtjOmZqSXvZn4n9fNTHQT5FymmUHJFouiTBCTkNnnZMAVMiMmllCmuL2VsBFVlBmbT9mG4C2/vEpal3XPrXsPV9XGbRFHCU7hDC7Ag2towD00wQcGHJ7hFd4c6bw4787HonXNKWZO4A+czx/o/Y4U</latexit><latexit sha1_base64="9uRmigbRU2gk7L38QsMLLMB+/9s=">AAAB7HicbVBNS8NAEJ34WetX1aOXxSIIhZKIoMeiF48VTFtoQ9lsJ+3SzSbsboQS+hu8eFDEqz/Im//GbZuDtj4YeLw3w8y8MBVcG9f9dtbWNza3tks75d29/YPDytFxSyeZYuizRCSqE1KNgkv0DTcCO6lCGocC2+H4bua3n1BpnshHM0kxiOlQ8ogzaqzky5quef1K1a27c5BV4hWkCgWa/cpXb5CwLEZpmKBadz03NUFOleFM4LTcyzSmlI3pELuWShqjDvL5sVNybpUBiRJlSxoyV39P5DTWehKHtjOmZqSXvZn4n9fNTHQT5FymmUHJFouiTBCTkNnnZMAVMiMmllCmuL2VsBFVlBmbT9mG4C2/vEpal3XPrXsPV9XGbRFHCU7hDC7Ag2towD00wQcGHJ7hFd4c6bw4787HonXNKWZO4A+czx/o/Y4U</latexit><latexit sha1_base64="9uRmigbRU2gk7L38QsMLLMB+/9s=">AAAB7HicbVBNS8NAEJ34WetX1aOXxSIIhZKIoMeiF48VTFtoQ9lsJ+3SzSbsboQS+hu8eFDEqz/Im//GbZuDtj4YeLw3w8y8MBVcG9f9dtbWNza3tks75d29/YPDytFxSyeZYuizRCSqE1KNgkv0DTcCO6lCGocC2+H4bua3n1BpnshHM0kxiOlQ8ogzaqzky5quef1K1a27c5BV4hWkCgWa/cpXb5CwLEZpmKBadz03NUFOleFM4LTcyzSmlI3pELuWShqjDvL5sVNybpUBiRJlSxoyV39P5DTWehKHtjOmZqSXvZn4n9fNTHQT5FymmUHJFouiTBCTkNnnZMAVMiMmllCmuL2VsBFVlBmbT9mG4C2/vEpal3XPrXsPV9XGbRFHCU7hDC7Ag2towD00wQcGHJ7hFd4c6bw4787HonXNKWZO4A+czx/o/Y4U</latexit><latexit sha1_base64="9uRmigbRU2gk7L38QsMLLMB+/9s=">AAAB7HicbVBNS8NAEJ34WetX1aOXxSIIhZKIoMeiF48VTFtoQ9lsJ+3SzSbsboQS+hu8eFDEqz/Im//GbZuDtj4YeLw3w8y8MBVcG9f9dtbWNza3tks75d29/YPDytFxSyeZYuizRCSqE1KNgkv0DTcCO6lCGocC2+H4bua3n1BpnshHM0kxiOlQ8ogzaqzky5quef1K1a27c5BV4hWkCgWa/cpXb5CwLEZpmKBadz03NUFOleFM4LTcyzSmlI3pELuWShqjDvL5sVNybpUBiRJlSxoyV39P5DTWehKHtjOmZqSXvZn4n9fNTHQT5FymmUHJFouiTBCTkNnnZMAVMiMmllCmuL2VsBFVlBmbT9mG4C2/vEpal3XPrXsPV9XGbRFHCU7hDC7Ag2towD00wQcGHJ7hFd4c6bw4787HonXNKWZO4A+czx/o/Y4U</latexit>

(yt>,

p↵qt

>,p

�ht)>

<latexit sha1_base64="3vr0io9AZpu7HAdYTCJI5kH6cbY=">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</latexit><latexit sha1_base64="3vr0io9AZpu7HAdYTCJI5kH6cbY=">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</latexit><latexit sha1_base64="3vr0io9AZpu7HAdYTCJI5kH6cbY=">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</latexit><latexit sha1_base64="3vr0io9AZpu7HAdYTCJI5kH6cbY=">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</latexit>

¶Xiaoqing Xu et al. (2016). “A machine learning based framework for sub-resolution assist featuregeneration”. In: Proc. ISPD, pp. 161–168.

‖Hao Geng et al. (2019). “SRAF Insertion via Supervised Dictionary Learning”. In: Proc. ASPDAC,pp. 406–411.

15 / 22

Machine Learning Assists Model-based OPC [ASPDAC’19]∗∗

I Replace lithography simulation (slow) with machine learning-based EPE predictor(fast) in OPC iterations.

∗∗Bentian Jiang et al. (2019). “A fast machine learning-based mask printability predictor for OPCacceleration”. In: Proc. ASPDAC, pp. 412–419.

16 / 22

GAN-OPC [DAC’18]††

…

0.2 0.8

BadMask

GoodMask

Discrim

inator

Generator

…

EncoderD

ecoder

Target

Mask

Target & Mask

I Better starting points for legacy OPC engine and reduce iteration count.††Haoyu Yang, Shuhe Li, et al. (2018). “GAN-OPC: Mask Optimization with Lithography-guided Generative

Adversarial Nets”. In: Proc. DAC, 131:1–131:6.17 / 22

Outline

Hotspot Detection via Machine Learning

OPC via Machine Learning

Heterogeneous OPC

18 / 22

An Observation of Previous OPC SolutionsMachine learning solutions rely on legacy OPC engines

Generator RealFake

Generator

(a)

(b)

Feed-forward Back-propagetion

Discriminator

Litho-Simulator

Legacy OPC engines exhibit different performance on different designs

1 2 3 4 5 6 7 8 9 1002468·104

Design ID

MSE

MB-OPCILT

18 / 22

A Design of Heterogeneous OPC Framework

Classification Model

ILT

MB-OPC

Mask

MaskDesignDesigns

OPC-1

OPC-N

Masks

Masks

… …

We design a classification model that can determine the best OPC engine for a givendesign at trivial cost.

19 / 22

Training on Artificial DesignsI Training data comes from GAN-OPC and is labeled according to results of MB-OPC

and ILT.I Test on 10 designs from ICCAD 2013 CAD Contest.

0 20 40 60 80 1000.00

20.00

40.00

60.00

80.00

100.00

Epoch

Accuracy

(%)

Training Testing

20 / 22

Experimental Results

1 2 3 4 5 6 7 8 9 100

2

4

6

8·104

Design ID

MSE

MB-OPCILT

HOPC

Several BenefitsI Does not require extremely high prediction accuracy of the classification model.I Take advantages of different OPC solutions on different designs.

21 / 22

Conclusion and Discussion

So Far:I Recent progress of deterministic machine learning model for hotspot detectionI State-of-the-art machine learning solutions for OPC and SRAF insertionI A heterogeneous OPC framework guided by a classification engine

Future:I Manufacturability issues.I Classification challenge when more than two OPC engines are available.

22 / 22