Breakthrough in AI Cloud systems

2 min read

TU Dresden, the University of Manchester, Racyics and GlobalFoundries (GF) have announced the tapeout of the SpiNNaker2 chip, an artificial intelligence chip inspired by the human brain.

The SpiNNaker infrastructure was developed by the University Manchester, while the hybrid AI architecture was created at TU Dresden and the adaptive body bias IP platform ABX by Racyics. GF’s 22FDX solution was utlised to create the SpiNNaker2 - a realtime neuromorphic AI processor with unparalleled levels of efficiency and below millisecond latency for event-based systems.

The SpiNNaker2 has been designed to scale up to a 70.000 chip cloud system while maintaining strict real time operation. It is a key enabler for real time AI at massive data rates. and is expected to have a disruptive impact on AI applications such as smart cities, 5G, tactile internet and autonomous driving, which are beyond current hardware because of their triple demands on low latency, high throughput, and high energy efficiency.

The full 10 Mio core SpiNNaker2 machine, called ‘SpiNNcloud’, will be deployed at TU Dresden for research purposes. In parallel, the startup ‘SpiNNcloud Systems’ will make SpiNNaker2 commercially available.

SpiNNaker2 is a multi-processor system for event based real-time processing of both classic AI and upcoming sparse, event-based compute paradigms inspired by the parsimonious, on-demand processing nature of the brain. It has been developed within the European Union flagship project “Human Brain Project”.It features a patented event-based compute architecture with power management and custom AI hardware acceleration. Its backbone is a tailored, light weight communication infrastructure that can be scaled from edge devices up to large scale server/cloud applications, while not suffering from the inherent slow-down that usually results from scaling computing up to cloud dimensions.

Professor Steve Furber (University of Manchester) said, “There is still a great deal to learn from biology if we are to realise the full potential of AI in the future. SpiNNaker2 has been designed to bridge the gulf between realistic brain models and AI so that each may increasingly be informed by the other”.

“Our holistic sparsity-optimised system design, combined with a unique hybrid AI framework enables real-time AI at an unprecedented large-scale. We will do world-class research on novel machine learning via the SpiNNaker2 machine at TU Dresden, but we are proud to also offer this unique AI commercially through our startup SpiNNcloud Systems”, added Professor Christian Mayr (TU Dresden).

SpiNNaker2 was realised in the 22FDX Ecosystem using the adaptive body biasing IP platform (ABX) from Racyics to leverage the full potential of 22FDX. It enables SpiNNaker2 to robustly operate at the minimum energy point of the processing elements at 0.50V with additional support of dynamic voltage and frequency scaling for instantaneous high performance on demand. As a result, SpiNNaker2 is able to leverage the advanced power saving features of 22FDX, the flagship technology offered by GF Dresden.

The complete chip design was done using makeChip, a turnkey hosted design environment for 22FDX offered by Racyics. This approach was key for the academic group to close the so-called lab-to-fab gap and deliver a very complex System-on-Chip for volume production successfully.