Renesas tapes out spiking neural network chip

Renesas tapes out spiking neural network chip

Interviews |
By Nick Flaherty

Renesas is taping out a chip using the spiking neural network (SNN) technology developed by Brainchip.

This is part of a move to boost the leading edge performance of its chips for the Internet of Things, Sailesh Chittipeddi became Executive Vice President and General Manager of IoT and Infrastructure Business Unit at Renesas Electronics and the former CEO of IDT tells eeNews Europe.

This strategy has seen the company develop the first silicon for ARM’s M85 and RISC-V cores, along with new capacity and foundry deals.

“We are very happy to be at the leading edge and now we have made a rapid transition to address our ARM shortfall but we realise the challenges in the marketplace and introduced the RISC-V products to make sure we don’t fall behind in the new architectures,” he said.

“Our next move is to more advanced technology nodes to push the microcontrollers into the gigahertz regime and that’s where the is overlap with microprocessors. The way I look at it is all about the system performance.”

“Now you have accelerators for driving AI with neural processing units rather than a dual core CPU. We are working with a third party taping out a device in December on 22nm CMOS,” said Chittipeddi.

Brainchip and Renesas signed a deal in December 2020 to implement the spiking neural network technology. Tools are vital for this new area. “The partner gives us the training tools that are needed,” he said.

The take up of the technology depends on the market adoption, he says.

“We want to see where the market reception is the highest, that is what determines whether we bring things in house or through a third party.”

He points to working with Andes on RISC-V cores and then moving to developing its own cores.  “You will find something similar on the AI side where accelerators will get pulled in internally and some will not, it will be based entirely on the market activity. Our general philosophy is to internalise things – that’s very challenging but that is what dictates where we put our money and investment

User experience

“Now that we are starting to piece together bits of the puzzle, how do we dominate the ecosystem? It’s how we stich it together – it’s the user experience. How do you make it seamless so that customer A and customer Z can get to their desired outcome seamlessly, all the way from the availability and ease of use of machine learning models to the implementation of the microcontroller with the least amount of clicks to access the cloud,” he said.

“To me the next big step in the journey is the user experience. The ease of use of the analytics starts to matter – cloud providers have their own tools but the question is how easy is it for our customer to use their tools, so its about the API and probably a set of things to help them scripts.

“Ship and forget is the ideal model you want to get to,” he said. “Arduino reaches 30m users without being bothered on a day to day basis. That’s something we can learn from,” he said.

Chip shortage

Renesas has had a good year, he says. “It was a tale of good stuff and some stuff that was really challenging,” he said. “2022 will be a decent year for us. I’m not saying we’re immune from macroeconomic forces but given the forces on the supply chain most customers have been relatively positive about the ability to supply them. So our teams across manufacturing, supply chain and sales did a very good job keeping customers satisfied.”

“Our internal capacity requirements is still at 40, 55 60nm tight and some of our products are still there, it’s easing up a little bit. What we’ve done which might be different is we have signed long term agreements with customers, so we have invested capex with our partners to commit to capacity in the three to five year horizon. Its not just an internal discussion. Whether that’s new lines or new fabs, there’s a little bit of both.”

There are fabs coming on in 2024 and 2025 with a foundry partner and a new 300mm fab for the MF3 and MF4 process for microcontrollers with embedded flash, as well as new 200mm capacity. It is also reopening its Kofu fab for power devices

“In our plans we see a continuing need for sustained investment,” he said. “The capacity constraint is still there in the IoT world. That’s where the biggest consumption of silicon ends up occurring.”

It’s 40nm RV40F runs internally and at TSMC and it is looking to expand that to other foundries as well, he says. “We are working with another partner to move the 40nm process,” he said.

Other related articles

If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :    eeNews on Google News


Linked Articles