Please use this identifier to cite or link to this item:
https://doi.org/10.1109/TMAG.2020.3024172
Title: | SIMBA: A Skyrmionic In-Memory Binary Neural Network Accelerator | Authors: | Miriyala, Venkata Pavan Kumar Vishwanath, Kale Rahul Fong, Xuanyao |
Keywords: | Science & Technology Technology Physical Sciences Engineering, Electrical & Electronic Physics, Applied Engineering Physics Binary neural networks (BNNs) in-memory computing magnetic skyrmions spin Hall effect and spin-transfer torque (STT) nano-oscillators spintronics CIRCUIT |
Issue Date: | Nov-2020 | Publisher: | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | Citation: | Miriyala, Venkata Pavan Kumar, Vishwanath, Kale Rahul, Fong, Xuanyao (2020-11). SIMBA: A Skyrmionic In-Memory Binary Neural Network Accelerator. IEEE TRANSACTIONS ON MAGNETICS 56 (11). ScholarBank@NUS Repository. https://doi.org/10.1109/TMAG.2020.3024172 | Abstract: | Magnetic skyrmions are emerging as potential candidates for next-generation non-volatile memories. In this article, we propose an in-memory binary neural network (BNN) accelerator based on the non-volatile skyrmionic memory, which we call as Skyrmionic In-Memory BNN Accelerator (SIMBA). SIMBA consumes 26.7 mJ of energy and 2.7 ms of latency when running inference on a VGG-like BNN. In addition, SIMBA saves up to 97.07% in energy consumption with $3.73\times $ speedup compared with the other accelerators in the literature at similar inference accuracy. Furthermore, we demonstrate improvements in the performance of SIMBA by optimizing material parameters, such as saturation magnetization, anisotropic energy, and damping ratio. Finally, we show that the inference accuracy of BNNs is robust against the possible stochastic behavior of SIMBA (88.5%±1%). | Source Title: | IEEE TRANSACTIONS ON MAGNETICS | URI: | https://scholarbank.nus.edu.sg/handle/10635/245795 | ISSN: | 0018-9464 1941-0069 |
DOI: | 10.1109/TMAG.2020.3024172 |
Appears in Collections: | Staff Publications Elements |
Show full item record
Files in This Item:
File | Description | Size | Format | Access Settings | Version | |
---|---|---|---|---|---|---|
Miriyala, Vishwanath, Fong - 2020 - SIMBA A Skyrmionic In-Memory Binary Neural Network Accelerator.pdf | Published version | 2.9 MB | Adobe PDF | CLOSED | None |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.