MacroRank: Ranking Macro Placement Solutions Leveraging Translation Equivariancy
Published:
We present MacroRank to predict the relative order of the quality of macro placement solutions.
Published:
We present MacroRank to predict the relative order of the quality of macro placement solutions.
Published:
We present CircuitNet, an open-source dataset for machine learning applications in electronic design automation.
Published:
We present TimingPredict, a timing engine inspired graph neural network model for pre-routing slack prediction.
Published:
We present DREAMPlace, a deep learning toolkit-enabled VLSI placement framework. With the analogy between nonlinear VLSI placement and deep learning training problem, this tool is developed with deep learning toolkit for flexibility and efficiency. The tool runs on both CPU and GPU. Over 30X speedup over the CPU implementation (RePlAce) is achieved in global placement and legalization on ISPD 2005 contest benchmarks with a Nvidia Tesla V100 GPU.
Published:
We present OpenMPL, an open-source multiple patterning layout decomposition framework for advanced multiple patterning lithography.
Published:
We present Limbo, an open-source C/C++ library with various parsers, utilities and algorithms for VLSI CAD. See documentation.
Published:
We present MrDP, a detailed placer that can handle multiple-row height cells in designs.
Published:
We present DFI, a fill optimization framework with multiple objectives and constraints.
Published:
We present a triple patterning lithography aware detailed placement solver, TPLPlace.
Published:
We present a high performance MPL-Decomposer to resolve the layout decomposition problem for multiple patterning lithography.