Accelerating Low Bit-width Neural Networks at the Edge, PIM or FPGA: A Comparative Study

Nakul Kochar, Lucas Ekiert, Deniz Najafi, Deliang Fan, Shaahin Angizi

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

1 Scopus citations

Abstract

Deep Neural Network (DNN) acceleration with digital Processing-in-Memory (PIM) platforms at the edge is an actively-explored domain with great potential to not only address memory-wall bottlenecks but to offer orders of performance improvement in comparison to the von-Neumann architecture. On the other side, FPGA-based edge computing has been followed as a potential solution to accelerate compute-intensive workloads. In this work, adopting low-bit-width neural networks, we perform a solid and comparative inference performance analysis of a recent processing-in-SRAM tape-out with a low-resource FPGA board and a high-performance GPU to provide a guideline for the research community. We explore and highlight the key architectural constraints of these edge candidates that impact their overall performance. Our experimental data demonstrate that the processing-in-SRAM can obtain up to ∼160x speed-up and up to 228x higher efficiency (img/s/W) compared to the under-test FPGA on the CIFAR-10 dataset.

Original languageEnglish (US)
Title of host publicationGLSVLSI 2023 - Proceedings of the Great Lakes Symposium on VLSI 2023
PublisherAssociation for Computing Machinery
Pages625-630
Number of pages6
ISBN (Electronic)9798400701252
DOIs
StatePublished - Jun 5 2023
Event33rd Great Lakes Symposium on VLSI, GLSVLSI 2023 - Knoxville, United States
Duration: Jun 5 2023Jun 7 2023

Publication series

NameProceedings of the ACM Great Lakes Symposium on VLSI, GLSVLSI

Conference

Conference33rd Great Lakes Symposium on VLSI, GLSVLSI 2023
Country/TerritoryUnited States
CityKnoxville
Period6/5/236/7/23

All Science Journal Classification (ASJC) codes

  • General Engineering

Keywords

  • deep neural networks
  • fpga
  • processing-in-memory
  • sram

Fingerprint

Dive into the research topics of 'Accelerating Low Bit-width Neural Networks at the Edge, PIM or FPGA: A Comparative Study'. Together they form a unique fingerprint.

Cite this