SAN JOSE, Calif., July 26, 2018 — Silicon Valley startup Tachyum Inc. announced today that Professor Steve Furber, the highly regarded original designer of the world’s leading embedded processor, the ARM microprocessor, has joined its Board of Advisors. In this capacity, Prof. Furber will help position the company’s Prodigy processor to achieve disruptive performance in Spiking Model neural simulations, as well as standard data center workloads.
Steve Furber is a long-time ICL Professor of Computer Engineering at the University of Manchester in the UK researching asynchronous processors, low-power design, on-chip interconnect and neural systems engineering. His most recent research project, SpiNNaker, is building a new kind of computer that directly mimics the workings of the human brain.
Prior to his academic career, Furber worked as a hardware designer and design manager at Acorn Computers Ltd. where he developed the BBC Micro computer and the ARM microprocessor. More than 120 billion ARM processors have been manufactured as of 2018. Prof. Furber has been named a Commander of the Order of the British Empire, a Distinguished Fellow of the British Computing Society, Fellow of the Royal Society and Fellow of the Royal Academy of Engineering.
“I look forward to collaborating with Tachyum to help its management make informed strategic decisions that will help accelerate the realization of their disruptive products,” said Furber.
“Steve Furber is a true giant in processor architecture development, as well as one of the world’s leading experts on human brain simulation research,” said Dr. Radoslav Danilak, Tachyum Co-founder and CEO. “We are extremely gratified to be able to collaborate with Professor Furber on our Prodigy processor.”
Tachyum’s Prodigy will provide unprecedented compute performance and power efficiency for Data Center and AI applications, and it will enable a new generation of Supercomputers. Prodigy is the smallest and fastest general purpose, 64-bit processor, requiring 10x less power and reducing server cost by 3x. New proprietary software has made many parts of the hardware found in a typical processor redundant. Shorter wires, due to a smaller core, translates into much greater speed for the processor. The ultra-low power Prodigy processor, will allow system integrators to build a 32 Tensor Exaflops AI supercomputer. This will enable users to simulate, in real-time, human brain-sized Neural Networks beginning in 2020, instead of 2028.