Details
Poster
Presenter(s)
![Supriya Chakraborty Headshot](https://confcats-catavault.s3.amazonaws.com/CATAVault/ieeecass/master/files/styles/cc_user_photo/s3/user-pictures/23491.jpg?h=ba31c323&itok=bpTdFX9q)
Display Name
Supriya Chakraborty
- Affiliation
-
AffiliationIndian Institute of Technology Delhi
- Country
Abstract
In this paper, we present a unified FPGA based electrical test-bench for characterizing different emerging Non-Volatile Memory (NVM) chips. In particular, we present detailed electrical characterization and benchmarking of multiple commercially available, off-the-shelf, NVM chips viz.: MRAM, FeRAM, CBRAM, and ReRAM. We investigate important NVM parameters such as: (i) current consumption patterns, (ii) endurance, and (iii) error characterization. The proposed FPGA based testbench is then utilized for a Proof-of-Concept (PoC) Neural Network (NN) image classification application. Four emerging NVM chips are benchmarked against standard SRAM and Flash technology for the AI application as active weight memory during inference mode.