An MPSoC for energy-efficient database query processing

Haas, Sebastian; Arnold, Oliver; Nothen, Benedikt; Scholze, Stefan; Ellguth, Georg; Dixius, Andreas; Höppner, Sebastian; Schiefer, Stefan; Hartmann, Stephan; Henker, Stephan; Hocker, Thomas; Schreiter, Jörg; Eisenreich, Holger; Schlusler, Jens-Uwe; Walter, Dennis; Seifert, Tobias; Pauls, Friedrich; Hasler, Mattis; Chen, Yong; Hensel, Hermann; Moriam, Sadia; Matúš, Emil; Mayr, Christian; Schüffny, René; Fettweis, Gerhard

doi:10.1145/2897937.2897986

Cited by 10 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SpiNNaker (Furber et al, 2014 ) is a digital neuromorphic hardware system based on low-power ARM processors built for the real-time simulation of spiking neural networks (SNNs). On the basis of the first-generation SpiNNaker architecture and our previous work in power efficient multi-processor systems on chip (Haas et al, 2016 , 2017 ), the second generation SpiNNaker system (SpiNNaker2) is currently being developed in the Human Brain Project (Amunts et al, 2016 ). By employing a state-of-the-art CMOS technology and advanced features such as per-core power management, more processors can be integrated per chip at significantly increased energy-efficiency.…”

Section: Methodsmentioning

confidence: 99%

Memory-Efficient Deep Learning on a SpiNNaker 2 Prototype

et al. 2018

Self Cite

View full text Add to dashboard Cite

The memory requirement of deep learning algorithms is considered incompatible with the memory restriction of energy-efficient hardware. A low memory footprint can be achieved by pruning obsolete connections or reducing the precision of connection strengths after the network has been trained. Yet, these techniques are not applicable to the case when neural networks have to be trained directly on hardware due to the hard memory constraints. Deep Rewiring (DEEP R) is a training algorithm which continuously rewires the network while preserving very sparse connectivity all along the training procedure. We apply DEEP R to a deep neural network implementation on a prototype chip of the 2nd generation SpiNNaker system. The local memory of a single core on this chip is limited to 64 KB and a deep network architecture is trained entirely within this constraint without the use of external memory. Throughout training, the proportion of active connections is limited to 1.3%. On the handwritten digits dataset MNIST, this extremely sparse network achieves 96.6% classification accuracy at convergence. Utilizing the multi-processor feature of the SpiNNaker system, we found very good scaling in terms of computation time, per-core memory consumption, and energy constraints. When compared to a X86 CPU implementation, neural network training on the SpiNNaker 2 prototype improves power and energy consumption by two orders of magnitude.

show abstract

Section: Methodsmentioning

confidence: 99%

Memory-Efficient Deep Learning on a SpiNNaker 2 Prototype

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…The second aspect for improvements is the application of circuit design techniques to enhance both the compute performance and the energy efficiency of SpiNNaker2. This includes specific hardware extensions to the neuromorphic Processing Element (PE) as shown in Section 8.5 and power management techniques, such as dynamic voltage and frequency scaling [105], that have been proven on previous MPSoCs in the fields of mobile communication [88,181] and database processing [87].…”

Section: Scaling Performance and Efficiencymentioning

confidence: 99%

SpiNNaker: A Spiking Neural Network Architecture

Furber¹,

Bogdan²

2020

View full text Add to dashboard Cite

show abstract

“…SpiNNaker [27] is a digital neuromorphic hardware system based on low-power ARM processors built for the real-time simulation of spiking neural networks (SNNs). On the basis of the first-generation SpiNNaker architecture and our previous work in power efficient multi-processor systems on chip [28], [29], the second generation SpiNNaker system (SpiNNaker 2) is currently being developed in the Human Brain Project [30]. By employing a state-of-the art CMOS technology and advanced features such as per-core power management, more processors can be integrated per chip at significantly increased energy-efficiency.…”

Section: A System Overviewmentioning

confidence: 99%

Efficient Reward-Based Structural Plasticity on a SpiNNaker 2 Prototype

Yan

Kappel

Neumärker

et al. 2019

IEEE Trans. Biomed. Circuits Syst.

Self Cite

View full text Add to dashboard Cite

Advances in neuroscience uncover the mechanisms employed by the brain to efficiently solve complex learning tasks with very limited resources. However, the efficiency is often lost when one tries to port these findings to a silicon substrate, since brain-inspired algorithms often make extensive use of complex functions such as random number generators, that are expensive to compute on standard general purpose hardware. The prototype chip of the 2nd generation SpiNNaker system is designed to overcome this problem. Low-power ARM processors equipped with a random number generator and an exponential function accelerator enable the efficient execution of brain-inspired algorithms. We implement the recently introduced reward-based synaptic sampling model that employs structural plasticity to learn a function or task. The numerical simulation of the model requires to update the synapse variables in each time step including an explorative random term. To the best of our knowledge, this is the most complex synapse model implemented so far on the SpiNNaker system. By making efficient use of the hardware accelerators and numerical optimizations the computation time of one plasticity update is reduced by a factor of 2. This, combined with fitting the model into to the local SRAM, leads to 62% energy reduction compared to the case without accelerators and the use of external DRAM. The model implementation is integrated into the SpiNNaker software framework allowing for scalability onto larger systems. The hardware-software system presented in this work paves the way for power-efficient mobile and biomedical applications with biologically plausible brain-inspired algorithms.

show abstract

An MPSoC for energy-efficient database query processing

Cited by 10 publications

References 17 publications

Memory-Efficient Deep Learning on a SpiNNaker 2 Prototype

Memory-Efficient Deep Learning on a SpiNNaker 2 Prototype

SpiNNaker: A Spiking Neural Network Architecture

Efficient Reward-Based Structural Plasticity on a SpiNNaker 2 Prototype

Contact Info

Product

Resources

About