BrainScaleS-1 — Heidelberg University

Learn about Heidelberg University's neuromorphic hardware: BrainScaleS-1

BrainScaleS-1 At A Glance

Release Year: 2016
Status: Released
Chip Type: Mixed-signal
Software: PyNN.brainscales, BrainScaleS-1 OS
Applications: Neuroscientific research into Learning and developmental processes, energy-efficient spiking neural networks
Neurons: 196608
Synapses: 43253760
Weight bits: 4 bits
On-Chip Learning: true
Power: ~600 W

The BrainScaleS-1 is an accelerated spiking neuromorphic system integrating 200k adaptive exponential integrate-and-fire neurons, 43M plastic synapses, and event routing on a silicon wafer substrate. It enables fast emulation of complex neural dynamics and exploration of STDP-type synaptic plasticity.

The BrainScaleS-1 accelerated neuromorphic system is an wafer-scale integrated circuit architecture for emulating biologically-inspired spiking neural networks.
It was developed by researchers at the Heidelberg University and collaborators.
Key features of the BrainScaleS-1 system include:

System Architecture

  • 20 wafers comprising 384 ASICs interconnected by a configurable circuit-switched event routing network on a silicon wafer
  • Every ASIC integrate a custom analog core with 512 neuron circuits, 112k plastic synapses, floating-gate-based analog parameter storage, STDP-type long-term and STP-type short-term plasticity and an event routing network

Neural and Synapse Circuits

  • Implements the Adaptive Exponential Integrate-and-Fire (AdEx) neuron model with individually configurable model parameters
  • On-chip synapse correlation and plasticity measurement enable programmable spike-timing dependent plasticity

Software and Experiment Control

  • BrainScaleS OS provides a full software stack including:
    • High-level PyNN-based experiment interfaces
    • C++ core libraries for configuration, calibration and control
    • Mapping and routing tools to translate neural models onto hardware
  • Allows both novice and expert usage with varying levels of abstraction
  • Supports batch-mode and hybrid-mode experiments (chip-in-the-loop)

Applications and Experiments

  • Accelerated (10,000-fold compared to biological real time) emulation of complex spiking neuron dynamics
  • Exploration of synaptic plasticity models and critical network dynamics at biological timescales

The accelerated operation and flexible architecture facilitate applications in computational neuroscience research.

DateTitleAuthorsVenue/Source
September 2023From clean room to machine room: commissioning of the first-generation BrainScaleS wafer-scale neuromorphic systemHartmut Schmidt, José Montes, Andreas Grübl, Maurice Güttler, Dan Husmann, Joscha Ilmberger, Jakob Kaiser, Christian Mauch, Eric Müller, Lars Sterzenbach, Johannes Schemmel and Sebastian SchmittNeuromorphic Computing and Engineering
May 2022The operating system of the neuromorphic BrainScaleS-1 systemEric Müller, Sebastian Schmitt, Christian Mauch, Sebastian Billaudelle, Andreas Grübl, Maurice Güttler, Dan Husmann, Joscha Ilmberger, Sebastian Jeltsch, Jakob Kaiser, Johann Klähn, Mitja Kleider, Christoph Koke, José Montes, Paul Müller, Johannes Partzsch, Felix Passenberg, Hartmut Schmidt, Bernhard Vogginger, Jonas Weidner, Christian Mayr, Johannes SchemmelNeurocomputing
March 2016Neuromorphic Computer Coming OnlineNo author listedPress Release by Heidelberg University
June 2010A wafer-scale neuromorphic hardware system for large-scale neural modelingJohannes Schemmel, Daniel Brüderle, Andreas Grübl, Matthias Hock, Karlheinz Meier, Sebastian Millner2010 IEEE International Symposium on Circuits and Systems (ISCAS)
June 2008Wafer-scale integration of analog neural networksJohannes Schemmel, Johannes Fieres, Karlheinz Meier2008 IEEE International Joint Conference on Neural Networks (IJCNN)

Help Us Improve this Guide

Our hardware guide is community-maintained. If you know of a chip we should add, see an error, or have updated information, please let us know by opening an issue on our GitHub repository.

Strategic Vision for Open Neuromorphic

Strategic Vision for Open Neuromorphic

Why 'open' matters and where we want to take the Open Neuromorphic community

Open Neuromorphic Evolves: Announcing Our Charter and First Executive Committee Election

Open Neuromorphic Evolves: Announcing Our Charter and First Executive Committee Election

Open Neuromorphic is introducing an organizational charter and holding its first Executive Committee elections to foster growth and collaboration. Learn more and get involved!

Spiking Neural Network (SNN) Library Benchmarks

Spiking Neural Network (SNN) Library Benchmarks

Discover the fastest Spiking Neural Network (SNN) frameworks for deep learning-based optimization. Performance, flexibility, and more analyzed in-depth