Network Processors
Recently Published Documents


TOTAL DOCUMENTS

323
(FIVE YEARS 28)

H-INDEX

20
(FIVE YEARS 2)

2021 ◽  
Vol 3 (4) ◽  
pp. 208-218
Author(s):  
K. Muralidharan ◽  
S. Uma Maheswari

In the modern world, high performance embedded applications in the field of multimedia, networking, and imaging are increasing day by day. These applications require high performance and more complex out-of-order superscalar processor. These complex dynamic instructions scheduling superscalar processors need higher levels of on-chip integration designs which are often associated with power dissipation. These out-of-order superscalar processors achieve higher performance compared to other processors by simultaneous fetching, decoding and execution for multiple instructions in out-of-order that are used in the next generation network processors. The main data path resources of the processor use CAM+RAM structure which is the major power consuming unit in the overall out-of-order processor design. The proposed new design of CAM+RAM with power-gating technique reduces the overall average power consumption compared to the conventional design without any significant impact on their performance.


2021 ◽  
Author(s):  
Jian Hu Jian Hu ◽  
Xianlong Zhang ◽  
Xiaohua Shi

Abstract Deep learning has achieved competing results comparing with human beings in many fields. Traditionally, deep learning networks are executed on CPUs and GPUs. In recent years, more and more Neural Network accelerators have been introduced in both academia and industry to improve the performance and energy efficiency for deep learning networks. In this paper, we introduce a flexible and configurable functional NN accelerator simulator, which could be configured to simulate u-architectures for different NN accelerators. The extensible and configurable simulator is helpful for system-level exploration of u-architecture, as well as operator optimization algorithm developments. We also integrated the simulator into the TVM compilation stack as an optional back-end. Users can use TVM to write operators and execute them on the simulator. The simulator is going to be open sourced.


Author(s):  
Zhuolun He ◽  
Peiyu Liao ◽  
Siting Liu ◽  
Yuzhe Ma ◽  
Yibo Lin ◽  
...  

2020 ◽  
pp. 1-11
Author(s):  
Zhu Renjie ◽  
Ye Chunming ◽  
Fan Lumin ◽  
Chen Wei

Nowadays, science and technology are developing, more and more things need to be detected by science and technology, and the content that people need to understand is becoming more and more complex. Not only need to know its size, but also need to know some of the relevant comprehensive information or internal information. At present, people’s demands can no longer be met only by existing medical systems, so data fusion technology has emerged. This technology can simultaneously obtain a variety of information, express various information, seek the internal relationship between various information, and comprehensively process and improve this relationship. In view of the existing medical equipment, this paper puts forward the design method of multi-sensor data fusion technology. The original whole system is decomposed into several small particles and extracted from the original system. The extracted particles are arranged independently and the neural network system is formed. On the basis of neural network computing and implementing network feature service, this paper introduces how to establish a new medical equipment system based on network registration, discovery and various management and fault-tolerant conditions. This article is a community-oriented, long-distance service intelligent system based on family health care, designed on network processors and Android systems. By combining various technologies, collecting various body information parameters of patients, under the guidance of network protocol and existing remote technology, the gateway of intelligent home can talk to the community to a certain extent. In this way, the data collected in smart homes can be uploaded to other communities through the community network.


Sign in / Sign up

Export Citation Format

Share Document