Tianjic: A Unified and Scalable Chip Bridging Spike-Based and Continuous Neural Computation

Deng, Lei; Wang, Guanrui; Li, Guoqi; Li, Shuangchen; Liang, Ling; Zhu, Meng-Yang; Wu, Yujie; Yang, Zheyu; Zou, Zhe; Pei, Jing; Wu, Zhenzhi; Hu, Xing; Ding, Yufei; He, Wei; Xie, Yuan; Shi, Luping

doi:10.1109/jssc.2020.2970709

Cited by 125 publications

(69 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Third, for large-scale networks, we adopted some optimization mechanisms to ensure that multiple networks could run efficiently on the chip. These mechanisms included a point-to-point routing scheme and an adjacent multicast routing strategy 17 . The cores communicated with each other via a 2D-mesh method.…”

Section: Flexible Module Cooperationmentioning

confidence: 99%

“…Second, to adapt to dynamic environments, we developed a high-level decision-making module based on a hybrid neural state machine (HNSM) to integrate different modules flexibly, providing the capability to oversee and schedule different information flows, as well the capacity to be extended for dealing with increasing tasks during the implementation process. Third, inspired by neocortical regions organized with cortical columns 29 , we developed a scalable computing system based on our cross-paradigm neuromorphic chip, Tianjic, and a customized tool chain for hardware and software co-design 16,17 . The system has the potential to underpin brain-inspired system evolution and growth, similar to that exhibited in the human brain 30 .…”

mentioning

confidence: 99%

See 1 more Smart Citation

A hybrid and scalable brain-inspired robotic platform

Zou

Zhao

et al. 2020

Sci Rep

Self Cite

View full text Add to dashboard Cite

Recent years have witnessed tremendous progress of intelligent robots brought about by mimicking human intelligence. However, current robots are still far from being able to handle multiple tasks in a dynamic environment as efficiently as humans. To cope with complexity and variability, further progress toward scalability and adaptability are essential for intelligent robots. Here, we report a brain-inspired robotic platform implemented by an unmanned bicycle that exhibits scalability of network scale, quantity and diversity to handle the changing needs of different scenarios. The platform adopts rich coding schemes and a trainable and scalable neural state machine, enabling flexible cooperation of hybrid networks. In addition, an embedded system is developed using a cross-paradigm neuromorphic chip to facilitate the implementation of diverse neural networks in spike or non-spike form. The platform achieved various real-time tasks concurrently in different real-world scenarios, providing a new pathway to enhance robots’ intelligence.

show abstract

Section: Flexible Module Cooperationmentioning

confidence: 99%

mentioning

confidence: 99%

A hybrid and scalable brain-inspired robotic platform

Zou

Zhao

et al. 2020

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…In terms of the integration of both neuromorphic primitives (e.g., spiking neural networks) and DNNs, there is the Tianjic chip [17,62], a multi-chip many-core architecture providing a hybrid platform toward artificial general intelligence. The Tianjic chip, consisting of 156 functional cores, shows significant improvement in both throughput (1.6× to 10 2 ×) and power efficiency (12× to 10 4 ×) compared with the GPU.…”

Section: Multi-chip Many-core Architecturesmentioning

confidence: 99%

“…Although all chips are functional in the multi-chip many-core system, different workloads may occupy different number of chips/cores, since in these spatially weight-stationary mappings, the number of cores consumed is kind of proportional to the model size. Configuration parameters are summarized in Table 1, which are collected from existing multi-chip many-core architectures [17,62,67,89,96]. As for hyperparameters in our RL-based approach, the learning rates of the actor and the critic are set as α θ = 0.0002 and α w = 0.001, with the discount factor γ = 0.98.…”

Section: Experiments Setupmentioning

confidence: 99%

“…With these considerations, multi-chip many-core neural network systems, which assemble a number of cores into one chip and further interconnect these chips, are attracting increasing attention. These multi-chip many-core systems, from conventional technology such as SpiNNaker [60], TrueNorth [2], Loihi [14], Tianjic [17,62], and Simba [67], to emerging technology, such as PUMA [3] with memristors, provide high parallelism benefited from decentralized execution, and can be scaled to very large systems with reasonable fabrication costs.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Core Placement Optimization for Multi-chip Many-core Neural Network Systems with Reinforcement Learning

Deng

et al. 2020

ACM Trans. Des. Autom. Electron. Syst.

Self Cite

View full text Add to dashboard Cite

Multi-chip many-core neural network systems are capable of providing high parallelism benefited from decentralized execution, and they can be scaled to very large systems with reasonable fabrication costs. As multi-chip many-core systems scale up, communication latency related effects will take a more important portion in the system performance. While previous work mainly focuses on the core placement within a single chip, there are two principal issues still unresolved: the communication-related problems caused by the non-uniform, hierarchical on/off-chip communication capability in multi-chip systems, and the scalability of these heuristic-based approaches in a factorially growing search space. To this end, we propose a reinforcement-learning-based method to automatically optimize core placement through deep deterministic policy gradient, taking into account information of the environment by performing a series of trials (i.e., placements) and using convolutional neural networks to extract spatial features of different placements. Experimental results indicate that compared with a naive sequential placement, the proposed method achieves 1.99× increase in throughput and 50.5% reduction in latency; compared with the simulated annealing, an effective technique to approximate the global optima in an extremely large search space, our method improves the throughput by 1.22× and reduces the latency by 18.6%. We further demonstrate that our proposed method is capable to find optimal placements taking advantages of different communication properties caused by different system configurations, and work in a topology-agnostic manner. CCS Concepts: • Computer systems organization → Architectures; Parallel architectures; • Computing methodologies → Reinforcement learning;

show abstract

Integrated Memristor Network for Physiological Signal Processing

Cai

Yue

et al. 2023

Adv Elect Materials

View full text Add to dashboard Cite

Humans are complex organisms made by millions of physiological systems. Therefore, physiological activities can represent physical or mental states of the human body. Physiological signal processing is essential in monitoring human physiological features. For example, non‐invasive electroencephalography (EEG) signals can be used to reconstruct brain consciousness and detect eye movements for identity verification. However, physiological signal processing requires high resolution, high sensitivity, fast responses, and low power consumption, hindering practical hardware design for physiological signal processing. The bionic capability of memristor devices is very promising in the context of building physiological signal processing hardware and they have demonstrated a handful of advantages over the traditional Von Neumann architecture system in accelerating neural networks. Memristor networks can be integrated as a hardware system for physiological signal processing that can deliver higher energy efficiency and lower latency compared to traditional implementations. This review paper first introduces memristor characteristics, followed by a comprehensive literature study of memristor‐based networks. Physiology signal processing applications enabled by these integrated memristor networks are also presented in this review. In summary, this paper aims to provide a new perspective on physiological signal processing using integrated memristor networks.

show abstract

Tianjic: A Unified and Scalable Chip Bridging Spike-Based and Continuous Neural Computation

Cited by 125 publications

References 77 publications

A hybrid and scalable brain-inspired robotic platform

A hybrid and scalable brain-inspired robotic platform

Core Placement Optimization for Multi-chip Many-core Neural Network Systems with Reinforcement Learning

Integrated Memristor Network for Physiological Signal Processing

Contact Info

Product

Resources

About