Dynamic Power Management for Neuromorphic Many-Core Systems

by   Sebastian Hoeppner, et al.

This work presents a dynamic power management architecture for neuromorphic many core systems such as SpiNNaker. A fast dynamic voltage and frequency scaling (DVFS) technique is presented which allows the processing elements (PE) to change their supply voltage and clock frequency individually and autonomously within less than 100 ns. This is employed by the neuromorphic simulation software flow, which defines the performance level (PL) of the PE based on the actual workload within each simulation cycle. A test chip in 28 nm SLP CMOS technology has been implemented. It includes 4 PEs which can be scaled from 0.7 V to 1.0 V with frequencies from 125 MHz to 500 MHz at three distinct PLs. By measurement of three neuromorphic benchmarks it is shown that the total PE power consumption can be reduced by 75 and a 50 maintaining temporary peak system performance to achieve biological real-time operation of the system. A numerical model of this power management model is derived which allows DVFS architecture exploration for neuromorphics. The proposed technique is to be used for the second generation SpiNNaker neuromorphic many core system.


page 6

page 7

page 8

page 14

page 15


A 1.2-V 162.9-pJ/cycle Bitmap Index Creation Core with 0.31-pW/bit Standby Power on 65-nm SOTB

The ability to maximize the performance during peak workload hours and m...

Run-Time Accuracy Reconfigurable Stochastic Computing for Dynamic Reliability and Power Management

In this paper, we propose a novel accuracy-reconfigurable stochastic com...

The SpiNNaker 2 Processing Element Architecture for Hybrid Digital Neuromorphic Computing

This paper introduces the processing element architecture of the second ...

Synaptic Scaling and Optimal Bias Adjustments for Power Reduction in Neuromorphic Systems

Recent animal studies have shown that biological brains can enter a low ...

Limitations in odour recognition and generalisation in a neuromorphic olfactory circuit

Neuromorphic computing is one of the few current approaches that have th...

Functional Specification of the RAVENS Neuroprocessor

RAVENS is a neuroprocessor that has been developed by the TENNLab resear...

Integer Factorization with a Neuromorphic Sieve

The bound to factor large integers is dominated by the computational eff...

Please sign up or login with your details

Forgot password? Click here to reset