New AI framework predicts chip design IR-drop with high accuracy

Researchers have developed LMM-IR, a novel multimodal framework for predicting static IR-drop in chip design. This approach utilizes a large-scale netlist transformer to process netlist topology as 3D point cloud representations, enabling efficient handling of complex netlists. By integrating netlist and image data, the model achieves state-of-the-art performance, outperforming previous winning teams in the ICCAD 2023 contest. AI

影响 This framework could significantly reduce chip design time by enabling faster and more accurate IR-drop prediction.

排序理由 The cluster contains a research paper detailing a new AI framework for a specific technical problem. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

• ICCAD 2023
• Kai Ma
• LMM-IR

• 论文
• 产品
• 基础设施

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →