Hardware Podcasts

ARM Inventor Steve Furber on SpiNNaker 1, 2, and Beyond

EE Times Current · 17 Nov 2023 · 45m

What this episode covers

Professor Steve Furber, co-designer of the ARM architecture and BBC Micro, discusses the SpiNNaker neuromorphic computing platform, explaining its massively parallel, multicast routing design intended to model biological neural networks in real time. He details the transition from SpiNNaker 1, which used software-defined neuron models on ARM cores, to SpiNNaker 2, which adds hardware accelerators for exponentials, random numbers, and matrix operations to support hybrid spiking and artificial neural networks. Furber notes that while SpiNNaker 1 served as a critical simulator for the Human Brain Project, SpiNNaker 2 aims to bridge the gap toward practical, low-power embedded robotics applications.

Most relevant to

established companies

Topics

Mentioned

Companies
University of Manchester, Italian Institute of Technology, Johns Hopkins University, Spin Cloud Systems, TU Dresden, Solistics
Products
SpiNNaker, BBC Micro, BrainScales, Loihi, TrueNorth
Chips
ARM

Related episodes from other shows

Other shows on the same ground, closest first.

  • The Amp Hour · 1h 08m

    Armstrong, Camenzind & Museums - Outstanding Oneirophoros Obituaries

    Hosts Chris Gammell and Dave Jones mourn the recent deaths of Neil Armstrong and Hans Camenzind, reflecting on their engineering legacies and the state of space exploration funding. They discuss the Spinnaker high-performance computing chip designed to model the human brain, noting its 57,600 ARM cores and the economic barriers to further miniaturization. The conversation shifts to practical hardware development, contrasting breadboarding with direct PCB prototyping for modern surface-mount components, and highlighting Osram's initiative to standardize LED footprints for easier second-sourcing.

    Microcontrollers & dev platformsPrototyping & iteration
    9 chapters

  • Over the Air · 24m

    AI at the Edge: Justin Schneck on the Future of Embedded Devices

    Justin Schneck, co-founder and CPO of Peridio, discusses the evolution of AI from cloud to edge, introducing Peridio's upcoming 'Avocado' OS designed to simplify embedded product development. He and host Ryan Prosser of Very explore the spectrum from cloud AI to embedded AI, noting how specialized silicon and miniaturized models are enabling practical applications like Garmin's radar-enabled bike lights. Schneck argues that while cloud AI handles massive compute, the real value lies in robust, self-initializing embedded systems that reduce hardware complexity for developers.

    Embedded firmwareAI & machine learning
    7 chapters

  • The Amp Hour · 1h 14m

    An Interview with Matt Richardson - Raspberry Risorgimento Regent

    Matt Richardson, the first US employee of the Raspberry Pi Foundation, discusses the platform's evolution, including the release of the Raspberry Pi 2 with its quad-core ARMv7 processor and 1GB RAM. He details the 'Hats' specification for expansion boards, which uses an EEPROM to automate driver configuration, and explains how the foundation balances its $35 educational mission with commercial products like the Compute Module. Richardson also shares insights from his personal projects, such as the 'Awesome Button' and 'Descriptive Camera,' highlighting his approach to integrating existing technology blocks for creative applications.

    Microcontrollers & dev platformsPCB design & layout
    10 chapters

  • Embedded.fm · 1h 01m

    87: Make My Own Steel Foundry

    Chip Gracey, co-founder of Parallax, discusses the design and philosophy behind the Propeller microcontroller, a chip featuring eight independent cores (cogs) for deterministic real-time control. He explains the decision to open-source the Propeller One Verilog code to foster community learning and innovation, while detailing the complex, years-long process of designing the Propeller Two using SPICE simulation and custom layout. Gracey contrasts this first-principles approach with modern ARM-based systems, advocating for simplicity, transparency, and the ability to understand hardware at the transistor level.

    Microcontrollers & dev platformsChips, FPGAs & semiconductors
    8 chapters

  • Embedded.fm · 48m

    237: Break All the Laws of Physics

    Jan Jongboom, a developer evangelist at Arm, discusses the Mbed ecosystem, including its online compiler, Mbed OS, and a new browser-based simulator for Cortex-M devices. He explains how the simulator allows developers to test code and peripherals without physical hardware, addressing the slow feedback loop of traditional embedded development. Jongboom also introduces uTensor, an inference framework that enables TensorFlow models to run on microcontrollers, and highlights the benefits of LoRa for long-range, low-power IoT connectivity.

    Embedded firmwareAI & machine learning
    6 chapters

The summary, chapters and topics are generated from the episode’s audio by this directory, not written by EE Times Current. The episode itself belongs to its publisher.