DG-RePlAce: A Dataflow-Driven GPU-Accelerated Analytical Global Placement Framework for Machine Learning Accelerators

arXiv:2404.13049v1 Announce Type: cross
Abstract: Global placement is a fundamental step in VLSI physical design. The wide use of 2D processing element (PE) arrays in machine learning accelerators poses new challenges of scalability and Quality of Results (QoR) for state-of-the-art academic global placers. In this work, we develop DG-RePlAce, a new and fast GPU-accelerated global placement framework built on top of the OpenROAD infrastructure, which exploits the inherent dataflow and datapath structures of machine learning accelerators. Experimental results with a …

abstract academic accelerators arrays art arxiv challenges cs.ar cs.lg dataflow design element framework fundamental global gpu machine machine learning placement processing quality results scalability state type work