Graphcore raises $30m to launch intelligent processor

1 min read

Graphcore, a machine learning company which emerged from XMOS in the last few months, has completed a $30million funding round. According to CEO Nigel Toon – who is also chairman of XMOS – the funding means the company will now have the resources necessary to innovate more quickly and ‘at scale’.

“Our investors are not just bringing money,” he said, “they’re also providing connections and market insights that will help us to develop products that solve major industry challenges.

According to Toon, Graphcore’s technology will reduce the cost of accelerating AI applications in the cloud and enable recent deep learning applications to evolve more rapidly towards useful, general artificial intelligence.

“One of the fundamental questions we have addressed is how to build highly parallel processors, complete with software tools and libraries, that are faster, more flexible and easy to use, so developers can explore machine intelligence approaches across a much broader front,” he continued.

Graphcore says it has developed an intelligent processing unit (IPU), said to be a new type of processor that will help to accelerate the development of current and next generation machine intelligence products. It is said to hold ‘the complete machine learning model’ and to have more than 100 times the memory bandwidth of other solutions.