Back to Search
Start Over
A Ferroelectric-based Volatile/Non-volatile Dual-mode Buffer Memory for Deep Neural Network Accelerators
- Source :
- IEEE Transactions on Computers. :1-1
- Publication Year :
- 2021
- Publisher :
- Institute of Electrical and Electronics Engineers (IEEE), 2021.
-
Abstract
- In this paper, a dual-mode buffer memory based on the CMOS compatible HfZrO2 ferroelectric material is proposed for DNN accelerators. It can operate in both volatile eDRAM mode and non-volatile ferroelectric RAM (FeRAM) mode. The functionality of the proposed dual-mode memory bit-cell design is verified using SPICE simulation with the multi-domain Preisach physical model. A data-lifetime-aware memory mode configuration protocol is proposed to optimize the buffer access energy for both DNN inference and training. Detailed circuitry and architectural support for the dual-mode memory are discussed. For DNN training with ferroelectric-field-effect-transistor (FeFET) and SRAM-based compute-in-memory (CIM) accelerator, the proposed dual-mode buffer design improves the overall energy efficiency by 92.2%~98.7%, 44.1%~47.6%, 12.6%~13.0% compared to baseline designs using SRAM buffer with the same buffer area, eDRAM and FeRAM with the same buffer capacity, respectively. For DNN inference with tensor-processing-unit (TPU)-like systolic array, the energy efficiency during computing is improved by 40.7%~45.6%, 18.4%~29.6% compared to the designs with eDRAM and FeRAM buffer, respectively. By storing the persistent data using the non-volatile mode, the energy efficiency of systolic array is improved by 2.3~5.5 over SRAM-based design when standby is frequent.
- Subjects :
- Hardware_MEMORYSTRUCTURES
business.industry
Computer science
Spice
Systolic array
eDRAM
Theoretical Computer Science
Non-volatile memory
Computational Theory and Mathematics
Hardware and Architecture
Logic gate
Ferroelectric RAM
System on a chip
Static random-access memory
business
Software
Computer hardware
Subjects
Details
- ISSN :
- 23263814 and 00189340
- Database :
- OpenAIRE
- Journal :
- IEEE Transactions on Computers
- Accession number :
- edsair.doi...........98eb02f7bfa2c19f3cece35dfd170cff