.png){kind=icon}
返回
CiTST-AdderNets: Computing in Toggle Spin Torques MRAM for Energy-Efficient AdderNets
.png){kind=icon}
PRE
AI
DOI：10.1109/TCSI.2023.3343081.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recently, Adder Neural Networks (AdderNets) have gained widespread attention as an alternative to traditional Convolutional Neural Networks (CNNs) for deep learning tasks. AdderNets use lightweight addition operations to replace multiplication and accumulation (MAC) operations, but can keep almost the same accuracy compared to other CNNs. Nevertheless, challenges still exist with regards to hardware resources, power consumption, and communication bandwidth, primarily due to the 'Von-Neumann bottlenecks'. However, computing-in-memory (CIM) architecture based on magnetic random-access memory (MRAM) has great potential for edge DNN implementation. In this paper, we propose a novel CIM paradigm using a novel Toggle-Spin-Torques (TST) driven MRAM for energy-efficient AdderNets (called CiTST_AdderNets). In CiTST_AdderNets, MRAM is driven by the interplay of the field-free spin orbit torque (SOT) effect and the spin transfer torque (STT) effect, which offers a fascinating prospect for energy efficiency and speed. Furthermore, a novel CIM paradigm is proposed to implement the dominating subtraction and sum operations in AdderNets, reducing data transfer and the related energy. Meanwhile, a highly parallel array structure integrating computation and storage is designed to support CiTST_AdderNets. In addition, a mapping strategy is proposed to efficiently map the convolution layer on the array. Fully connected layers can also be efficiently computed. The CiTST-AdderNets macro is designed by using a 65-nm CMOS process. Results show that our CiTST-AdderNets consumes about 1.65 mJ, 9.29 mJ, and 42.46 mJ for running VGG8, ResNet-50, and ResNet-18 respectively at 8-bit fixed-point precision. Compared to state-of-the-art platforms, our macro achieves an energy efficiency improvement of 1.45 x to 66.78 x.
Keyword:
Computing-in-memory
toggle-spin-torques
magnetic random-access memory
adder neural networks
期刊
IF:
5.2
论文数:
9.9K
被引数:
2.2W
机构
引用论文
分享收藏Field-free spin-orbit torque-induced switching of perpendicular magnetization in a ferrimagnetic layer with a vertical composition gradient具有垂直组成梯度的亚铁磁层中无场自旋轨道转矩引起的垂直磁化切换.png)
NATURE COMMUNICATIONS
OAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏Current-induced magnetization switching in atom-thick tungsten engineered perpendicular magnetic tunnel junctions with large tunnel magnetoresistanceNATURE COMMUNICATIONSOAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏Effect of annealing temperature on the fabrication of self-assembled gold droplets on various type-B GaAs surfacesCrystEngComm
CrystEngCommIF0
PREAI
分享收藏Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏
查看更多内容