ARM introduces new architecture for artificial intelligence and machine learning
ARM, the Cambridge-based microprocessor company has just announced a new processor architecture that it promises will give a significant boost to artificial intelligence and machine learning technology.
The new technology, announced this Tuesday, is called DynamIQ and ARM describes it as "probably the biggest micro-architectural shift since ARM announced 64-bit ARMv8-A in 2011." This "monumental shift in multicore microarchitecture" is not the processor itself -- new Cortex-A processors will be built by ARM’s partners, both of which will be announced later this year.
It is a foundation of all future processors to come.
Why is this so important? Because these new processors won’t be built just for the smartphones of the future. They’re expected to make appearances in home appliances, cars, AI and ML machines, both big and small.
ARM describes the architecture as "evolutionary step forward for ARM big.LITTLE technology."
Big.Little allowed devices to use two types of processors -- low-powered ones for menial tasks, and high-powered ones for more demanding tasks. They also came in pairs of cores -- 2+2, 2+4 or 4+4. The new technology will allow for different combinations (1+3, or 1+7 for example).
"The flexibility and versatility of DynamIQ will redefine the multi-core experience across a greater range of devices from edge to cloud across a secure, common platform," ARM says in a blog post here. "DynamIQ technology will be pervasive in our cars, our homes, and of course our smartphones as well as countless other connected devices where machine learning is applied to the zettabytes of data they generate -- both within the cloud and at the device level -- advancing AI for a more natural and intuitive user experience."
Published under license from ITProPortal.com, a Future plc Publication. All rights reserved.