基於多學習機器之製程熱點檢測

Abstract

由於在先進製程中，光罩波長遠大於製程尺寸，不可避免產生不預期之布局圖形變異。所以製程熱點偵測在可製造性設計領域中已成為極重要的課題之一。目前最先進的技術是直接結合圖樣比對與機器學習，但是不同於此，我們使用嶄新的技術全力展現機器學習的能力。 我們提出一個使用多學習機器的製程熱點偵測平台。經由結合拓樸分類和關鍵特徵的抽取，我們的熱點偵測平台能夠達到極高之準確率。並且為了加快速度，我們只針對可能出現熱點的地方做偵測，取代了對完整布局掃描的方式。並且在偵測結束時，進一步過濾偵測出來的熱點以減少偵測錯誤。 實驗結果顯示，我們的方法是具有極高的準確性和極快的訓練速度。並且，在正確性和偵測錯誤兩方面都超越2012 CAD Contest at ICCAD得獎隊伍。

Because of the widening sub-wavelength lithography gap in advanced fabrication technology, lithography hotspot detection has become an essential task in design for manufacturability. Current state-of-the-art works unite pattern matching and machine learning engines. Unlike them, we fully exploit the strengths of machine learning using delicate techniques. We propose a novel lithographic hotspot detection framework using multiple machine learning kernels. By combing topological classification and critical feature extraction, our hotspot detection framework achieves very high accuracy. Furthermore, to speed up the evaluation, we verify only possible layout clips instead of full layout scanning. After detection, we filter hotspots to reduce the false alarm. Experimental results show that the proposed framework is very accurate and demonstrates a rapid training convergence. Moreover, our framework outperforms the 2012 CAD Contest at ICCAD winner on accuracy and false alarm.