Results 191 to 200 of about 5,289 (241)

RRAM-DNN: An RRAM and Model-Compression Empowered All-Weights-On-Chip DNN Accelerator

IEEE Journal of Solid-State Circuits, 2021
This article presents an energy-efficient deep neural network (DNN) accelerator with non-volatile embedded resistive random access memory (RRAM) for mobile machine learning (ML) applications. This DNN accelerator implements weight pruning, non-linear quantization, and Huffman encoding to store all weights on RRAM, enabling single-chip processing for ...
Ziyun Li 0001, Zhehong Wang, Li Xu 0006, Qing Dong 0001, Bowen Liu 0001, Chin-I Su, Wen-Ting Chu, George Tsou, Yu-Der Chih, Tsung-Yung Jonathan Chang, Dennis Sylvester, Hun-Seok Kim, David T. Blaauw   +12 more
openaire   +1 more source

Resistance switching for RRAM applications

Science China Information Sciences, 2011
Resistive random access memory (RRAM or ReRAM) is a non-volatile memory (NVM) technology that consumes minimal energy while offering sub-nanosecond switching. In addition, the data stability against high temperature and cycling wear is very robust, allowing new NVM applications in a variety of markets (automotive, embedded, storage, RAM).
Frederick T. Chen, Heng-Yuan Lee, Yu-Sheng Chen, Yenya Hsu, Lijie Zhang, Pang-Shiu Chen, Weisu Chen, Peiyi Gu, Wenhsing Liu, Sumin Wang, Chen-Han Tsai, Shyh-Shyuan Sheu, Ming-Jinn Tsai, Ru Huang 0001   +13 more
openaire   +1 more source

Parasitic engineering for RRAM control

Solid-State Electronics, 2018
The inevitable current overshoot which follows forming in filamentary RRAM devices is often perceived as a source of variability that should be minimized. This sentiment has led to efforts to curtail the overshoot by decreasing the parasitic capacitance using highly integrated 1T-1R or 1R-1R device structures. While this is readily achievable in single
P R, Shrestha, D M, Nminibapiel, D, Veksler, J P, Campbell, J T, Ryan, H, Baumgart, K P, Cheung   +6 more
openaire   +2 more sources

RRAM based learning acceleration

Proceedings of the International Conference on Compilers, Architectures and Synthesis for Embedded Systems, 2016
Deep Learning (DL) is becoming popular in a wide range of domains. Many emerging applications, ranging from image and speech recognition to natural language processing and information retrieval, rely heavily on deep learning techniques, especially the Neural Networks (NNs).
Yu Wang 0002, Lixue Xia, Ming Cheng, Tianqi Tang 0001, Boxun Li, Huazhong Yang   +5 more
openaire   +1 more source

Analysis of RRAM Reliability Soft-Errors on the Performance of RRAM-Based Neuromorphic Systems

2017 IEEE Computer Society Annual Symposium on VLSI (ISVLSI), 2017
Due to the limitation in speed and throughput of the traditional Von Neumann architecture, the interest in braininspired neuromorphic systems has been the focus of recent research activities. RRAM device has been extensively used as synapses in neuromorphic systems due to its many advantages including small size and compatibility with CMOS fabrication ...
Amr M. S. Tosson, Shimeng Yu, Mohab H. Anis, Lan Wei   +3 more
openaire   +1 more source

Intelligent Computing with RRAM

2019 IEEE 11th International Memory Workshop (IMW), 2019
RRAM-based in-memory-computing is a promising approach to go beyond von Neumann architecture and attributes to remarkable improvement in power efficiency and performance density. In this work, we examine our developments in device optimization for high-linearity SET/RESET updating and analyze the device reliability issues.
Peng Yao, Wenqiang Zhang, Meiran Zhao, Yudeng Lin, Wei Wu, Bin Gao, He Qian, Huaqiang Wu   +7 more
openaire   +1 more source

On the Reliability of RRAM-Based Neural Networks

2023 IFIP/IEEE 31st International Conference on Very Large Scale Integration (VLSI-SoC), 2023
Emerging device technologies such as Resistive RAMs (RRAMs) are under investigation by many researchers and semiconductor companies; not only to realize e.g., embedded non-volatile memories, but also to enable energy-efficient computing making use of new data processing paradigms such as computation-in-memory.
Aziza H., Zambelli C., Hamdioui S., Diware S., Bishnoi R., Gebregiorgis A.   +5 more
openaire   +2 more sources

Compute-in-RRAM with Limited On-chip Resources

2021 IEEE 3rd International Conference on Artificial Intelligence Circuits and Systems (AICAS), 2021
Compute-in-memory (CIM) is a new computing paradigm that addresses the memory-wall problem in the deep learning accelerator. Resistive Random Access Memory (RRAM) is an emerging non-volatile memory that is suitable as on-chip embedded memory to store the weights of the deep neural network (DNN) models. In this paper, first we will review general design
Anni Lu, Xiaochen Peng, Shimeng Yu
openaire   +1 more source

A RRAM-Based Associative Memory Cell

2021 IEEE International Symposium on Circuits and Systems (ISCAS), 2021
In general, intelligent systems require knowledge databases storing memory associations for mimicking the capabilities of the human brain. Conventional associative memory cells are constructed based on SRAM, a type of volatile memory consisting of large numbers of transistors per stored bit.
Yihan Pan 0003, Patrick Foster, Alexander Serb, Themis Prodromakis   +3 more
openaire   +1 more source

Advanced Simulation of RRAM Memory Cells

2019 IEEE 13th International Conference on ASIC (ASICON), 2019
Resistive random-access memories (RRAMs) are overwhelmingly viewed as potential candidates for the next generation of non-volatile memory devices. Here, we discuss the advantages of the kinetic Monte Carlo (KMC) simulation framework for RRAMs. We use a robust KMC simulator to analyze transport in promising oxide structures.
Badami, Oves, Georgiev, Vihar, Ding, Jie, Asenov, Asen, Sadi, Toufik   +5 more
openaire   +2 more sources