Enabled on makeChip and powered by Racyics, the SpiNNaker2 chip forms the core of the newly launched SpiNNcould supercomputer!
May 5, 2025 − Enabled on makeChip and powered by Racyics ABX platform, the SpiNNaker2 chip forms the core of the newly launched SpiNNcloud supercomputer!
Developed at Technische Universität Dresden by Prof. Christian Mayer and his incredible team, the system marks a significant step forward in the advancement of neuromorphic computing. It comprises 35,000 SpiNNaker2 chips with over five million processor cores. Inspired by the architecture of the human brain, it enables new approaches to data center design, combining distributed memory and event-driven processing to deliver high flexibility with improved energy efficiency.
SpiNNaker2 was manufactured in 22Fdx technology. It employs Adaptive Body Biasing (ABB) in a Forward Body Bias (FBB) configuration, implemented using Racyics ABX® platform. In combination with Dynamic Voltage and Frequency Scaling (DVFS), this allows for adaptive near-threshold operation down to 0.5V.
The chip was developed using the cloud-based design platform makeChip, which reduces design complexity by offering a configurable design flow, preinstalled PDKs and IP, as well as access to commercial EDA tools within a fully scalable, high-performance IT infrastructure.
As a trusted partner in this project, Racyics congratulates SpiNNcloud GmbH, Prof. Christian Mayr, and the Chair of Highly-Parallel VLSI Systems and Neuro-Microelectronics at TU Dresden on this achievement. Well done!
If you are curious to learn more about the project, check out the press release
Related Semiconductor IP
- Automotive Adaptive Body Biasing Generator - GLOBALFOUNDRIES 22FDX
- Adaptive Body Biasing Generator - GLOBALFOUNDRIES 22FDX
- ULP Clock-Generator - GLOBALFOUNDRIES 22FDX
- ULP 10MHz Clock-Generator - GLOBALFOUNDRIES 22FDX
- 6-bit, 12 GSPS Flash ADC - GlobalFoundries 22nm
Related News
- TU Dresden, University of Manchester and GlobalFoundries Announce SpiNNaker2, a Breakthrough in AI Cloud Systems, Bringing Real-Time AI with below Millisecond Latency and high Energy Efficiency to Cloud Scale
- IBM leverages SoC tech in supercomputer design
- Mercury Computer Systems Provides Silicon IP to Raytheon for its MONARCH Programmable ''Supercomputer on a Chip''
- Xilinx Virtex-5 LXT Platform FPGAs Used in NEC's SX-9; World's Fastest Vector Supercomputer
Latest News
- Rambus Unveils HBM4E Controller: 16 GT/s, 2,048-Bit Interface, Enabling C-HBM4E
- AimFuture, a Leader in Home Appliance NPUs, to Integrate Mesacure Company’s AI Algorithms
- Security in the Quantum Era: From Cryptography to Trust — ICTK Introduces a Hardware Trust Foundation for the Quantum Era
- TES unveils a next-generation Elliptic Curve Digital Signature Algorithm (ECDSA) IP Core for Secure IoT, Blockchain, and Industrial Systems
- Seligman Ventures Leads Cognichip’s $60M Series A to Back Physics-Informed AI for Chip Design, Intel CEO Lip-Bu Tan and Seligman Ventures’ Umesh Padval Join the Board