A5026370680- Advanced Memory and Neural Computing
- Advanced Neural Network Applications
- Parallel Computing and Optimization Techniques
- CCD and CMOS Imaging Sensors
- Blockchain Technology Applications and Security
- Cloud Data Security Solutions
- Viral Infections and Immunology Research
- Advanced MRI Techniques and Applications
- Privacy-Preserving Technologies in Data
- Parvovirus B19 Infection Studies
- Cryptography and Data Security
- Cytomegalovirus and herpesvirus research
- Radiation Effects in Electronics
- Ferroelectric and Negative Capacitance Devices
Nanjing University
2024-2025
Network-on-Chip (NoC) is a scalable on-chip communication architecture widely used in neural network accelerators. However, data-intensive applications like machine learning place significant demands on the NoC's and computation, often have degree of resilience to data noise, which allows use approximation techniques reduce execution time energy consumption for both computation communication, under constraints acceptable quality loss. Traditional approximate NoCs do not consider distribution...
Choices of dataflows, which are known as intra-core neural network (NN) computation loop nest scheduling and inter-core hardware mapping strategies, play a critical role in the performance energy efficiency NoC-based accelerators. Confronted with an enormous dataflow exploration space, this paper proposes automatic framework for generating optimizing full-layer-mappings based on two reinforcement learning algorithms including A2C PPO. Combining soft hard constraints, work transforms...
Network-on-Chip (NoC) is a scalable on-chip communication architecture for the NN accelerator, but with increase in number of nodes, delay becomes higher. Applications such as machine learning have certain resilience to noisy/erroneous transmitted data. Therefore, approximate promising solution improving performance by reducing traffic loads under constraint acceptable maximum accuracy loss neural networks. It key issue balance result quality and NoC systems. The traditional only considers...
In NoC-based neural network accelerators, many-to-one and many-to-many are prevalent traffic patterns. these patterns, there exists a need for communication synchronization between Processing Elements (PEs) of adjacent layers to optimize latency. The last received packet will determine the end time layer's computation. Communication Synchronization-aware Arbitration Policy (CSAP) is proposed in this paper handle problem, which uses negative feedback mechanism regulate sending rate each...