Xplace: An Extremely Fast and Extensible Global Placement Framework
TimeWednesday, July 13th10:52am - 11:15am PDT
Location3007, Level 3
Event Type
Research Manuscript
Physical Design and Verification, Lithography and DFM
DescriptionPlacement serves as a fundamental step in VLSI physical design.
Recently, GPU-based global placer DREAMPlace had demonstrated its superiority over CPU-based global placers. In this work, we develop an ultra-fast GPU accelerated global placer Xplace which achieves around 2x speedup with better solution quality compared to DREAMPlace. We also extend Xplace with a Fourier neural operator-based gradient update strategy to further improve the solution quality.
We believe this work not only proposes a new, fast, extensible placement framework but also illustrates a possibility to incorporate a neural network into an analytical placer.