Big-little chiplets for in-memory acceleration of DNNs: A scalable heterogeneous architecture

Gokul Krishnan, A. Alper Goksoy, Sumit K. Mandal, Zhenyu Wang, Chaitali Chakrabarti, Jae-sun Seo, Umit Ogras, Yu Cao

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Monolithic in-memory computing (IMC) architectures face significant yield and fabrication cost challenges as the complexity of DNNs increases. Chiplet-based IMCs that integrate multiple dies with advanced 2.5D/3D packaging offers a low-cost and scalable solution. They enable heterogeneous architectures where the chiplets and their associated interconnection can be tailored to the non-uniform algorithmic structures to maximize IMC utilization and reduce energy consumption. This paper proposes a heterogeneous IMC architecture with big-little chiplets and a hybrid network-on-package (NoP) to optimize the utilization, interconnect bandwidth, and energy efficiency. For a given DNN, we develop a custom methodology to map the model onto the big-little architecture such that the early layers in the DNN are mapped to the little chiplets with higher NoP bandwidth and the subsequent layers are mapped to the big chiplets with lower NoP bandwidth. Furthermore, we achieve a scalable solution by incorporating a DRAM into each chiplet to support a wide range of DNNs beyond the area limit. Compared to a homogeneous chiplet-based IMC architecture, the proposed big-little architecture achieves up to 329× improvement in the energy-delay-area product (EDAP) and up to 2× higher IMC utilization. Experimental evaluation of the proposed big-little chiplet-based RRAM IMC architecture for ResNet-50 on ImageNet shows 259×, 139×, and 48× improvement in energy-efficiency at lower area compared to Nvidia V100 GPU, Nvidia T4 GPU, and SIMBA architecture, respectively.

Original languageEnglish (US)
Title of host publicationProceedings of the 41st IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781450392174
DOIs
StatePublished - Oct 30 2022
Event41st IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2022 - San Diego, United States
Duration: Oct 30 2022Nov 4 2022

Publication series

NameIEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD
ISSN (Print)1092-3152

Conference

Conference41st IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2022
Country/TerritoryUnited States
CitySan Diego
Period10/30/2211/4/22

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design

Fingerprint

Dive into the research topics of 'Big-little chiplets for in-memory acceleration of DNNs: A scalable heterogeneous architecture'. Together they form a unique fingerprint.

Cite this