Reliable In-Memory Neuromorphic Computing Using Spintronics

Recently Spin Transfer Torque Random Access Memory (STT-MRAM) technology has drawn a lot of attention for the direct implementation of neural networks, because it offers several advantages such as near-zero leakage, high endurance, good scalability, small foot print and CMOS compatibility. The stori...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2019 24th Asia and South Pacific Design Automation Conference (ASP-DAC) s. 1 - 7
Hlavní autoři: Munch, Christopher, Bishnoi, Rajendra, Tahoori, Mehdi B.
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: ACM 21.01.2019
Témata:
Biological neural networks
defect modeling
Fabrication
MTJ
neuromorphic computing
Neuromorphic engineering
Neurons
Redundancy
Scalability
Torque
ISSN:2153-697X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Recently Spin Transfer Torque Random Access Memory (STT-MRAM) technology has drawn a lot of attention for the direct implementation of neural networks, because it offers several advantages such as near-zero leakage, high endurance, good scalability, small foot print and CMOS compatibility. The storing device in this technology, the Magnetic Tunnel Junction (MTJ), is developed using magnetic layers that requires new fabrication materials and processes. Due to complexities of fabrication steps and materials, MTJ cells are subject to various failure mechanisms. As a consequence, the functionality of the neuromorphic computing architecture based on this technology is severely affected. In this paper, we have developed a framework to analyze the functional capability of the neural network inference in the presence of the several MTJ defects. Using this framework, we have demonstrated the required memory array size that is necessary to tolerate the given amount of defects and how to actively decrease this overhead by disabling parts of the network.
ISSN:2153-697X
DOI:10.1145/3287624.3288745