As the design layout of integrated circuits (ICs) is continually scaling down, sub-resolution assist features (SRAF) have been extensively used in resolution enhancement technique (RET) applications to enhance lithography printing fidelity and widen the manufacturing process window (PW). With conventional SRAF insertion techniques, rule-based SRAF (RB-SRAF) and model-based SRAF (MB-SRAF) methods have been widely adopted. The typical RB-SRAF is an efficient method to generate SRAFs consistently for simple designs, but cannot be optimized for multiple critical patterns or complex layout schemes. Although MB-SRAF is able to achieve better process window as well as reducing conflicts between placement rules and clean-up rules, many iterations for convergence and extremely high computational costs are required. The explosion of machine learning techniques could facilitate the complex processes of mask optimization, such as SRAF insertion. In this paper, generative adversarial network was studied on a Via layer of advanced 3D NAND flash memory, by training target images and Inverse Lithography Technology (ILT) images of target patterns. GAN models, pix2pix and CycleGAN, were first trained and then utilized to synthesize realistic ILT images. These ILT images were eventually translated to polygons of SRAF with simplification process and mask manufacturing rules check (MRC) constraints. The simulation results demonstrate that CycleGAN approach can place SRAF with comparable performance to mask optimization (MO) result which was optimized by the Tachyon Source-Mask Optimizer (SMO). Most importantly, the efficiency of SRAF insertion can be enhanced significantly through the generative adversarial network.
This work compared the CD-based and image-assistant approaches for calibrating the OPC models. OPC models were
first developed for 65nm-node memory contact layer and calibrated by contact test patterns with various ellipticities. The
image-assistant model is a hybrid one calibrated by SEM contours and 1D measurement results, while the CD-based
model calibration uses 1D measurement results as the sole data source. The fitting errors, model prediction ability and
OPCed results were compared between these two models. Besides, the challenges on calibrating the edge-detection
algorithm of the CD SEM images to the extracted contours of OPC tool were also discussed. Finally, the layouts
corrected by CD-based and image-assistant models were written on a test mask for wafer-level comparison.
The results displayed that the CD-based model showed smaller error on fitting and interpolation, but image-assistant
model got improvement on extrapolation prediction of array-edge contact, unknown contact pattern and long contacts.
The wafer-level comparison also revealed the image-assistant model outperformed to the CD-based model by smaller
correction error on unexpected patterns.