*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
Title: Architecture and Technology Co-optimization of Near-memory and In-memory 3D Accelerators
Committee:
Dr. Lim, Advisor
Dr. Krishna, Chair
Dr. Yu
Abstract: The objective of the proposed research is to perform both architectural and physical design scaling challenge exploration of near-memory and in-memory compute accelerators and address them through efficient multi-tier heterogeneous 3D integration. The preliminary research proposes 3D architectural and design scaling methodologies for compute-in-memory (CIM) accelerators and efficient EDA methodology to build high quality multi-tier 3D designs. The proposed research involves exploring in detail the architectural and physical design improvements that can be brought about in near-memory and in-memory compute accelerators through 3D integration using state-of-the-art accelerator benchmarks and evaluate them using state-of-the-art DNN workloads.