Long Live TIME: Improving Lifetime and Security for NVM-Based Training-in-Memory Systems
Nonvolatile memory (NVM)-based training-in-memory (TIME) systems have emerged that can process the neural network (NN) training in an energy-efficient manner. However, the endurance of NVM cells is disappointing, rendering concerns about the lifetime of TIME systems, because the weights of NN models...
Main Authors: | Lin, Yujun, Han, Song |
---|---|
Other Authors: | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
Format: | Article |
Published: |
IEEE
2021
|
Online Access: | https://hdl.handle.net/1721.1/129440 |
Similar Items
-
Long Live TIME: Improving Lifetime for Training-In-Memory Engines by Structured Gradient Sparsification
by: Han, Song
Published: (2021) -
Improving NVM Lifetime Using Task Stack Migration on Low-End MCU-Based Devices
by: Jeongmin Lee, et al.
Published: (2022-01-01) -
NVM-Shelf: Secure Hybrid Encryption with Less Flip for Non-Volatile Memory
by: Thomas Haywood Dadzie, et al.
Published: (2020-08-01) -
An Empirical Evaluation of NVM-Aware File Systems on Intel Optane DC Persistent Memory Modules
by: Guangyu Zhu, et al.
Published: (2021-08-01) -
Q-Selector-Based Prefetching Method for DRAM/NVM Hybrid Main Memory System
by: Jeong-Geun Kim, et al.
Published: (2020-12-01)