Intel has confirmed the announcement of "a multi-chip platform for autonomous driving" that will compete with Nvidia's platforms at the the Consumer Electronics Show in January.
Speaking to EETimes.com, Jack Weast, Intel's principal engineer and chief architect of autonomous driving solutions, said that the new solution will combine the EyeQ 5 SoC, Intel's low-power Atom SoCs, and other hardware including I/O and Ethernet connectivity. The EyeQ 5 is an energy-efficient chip developed by Mobileye - now an Intel company.
Intel unveiled its GO development platform for autonomous driving earlier this year, describing its Atom processor C3000 as a chip that "delivers high performance per watt, packing substantial compute into low-power designs." But currently it is not clear how the Atom SoC shares processing tasks with EyeQ 5.
"We looked at the entire set of workload necessary for autonomous vehicles, Weast said. "We allocated and partitioned the compute loads among multiple chips." He added that FPGA is not part of the new multi-chip solution.
Speaking at the "AutoMobility LA" auto Show in Los Angeles, Intel's CEO Brian Krzanich said Intel "can deliver more than twice the deep-learning performance efficiency than the competition [meaning Nvidia].
Nvidia has released the Drive PX Xavier SoC designed for autonomous driving. While Mobileye's EyeQ5 delivers 24 trillion operations per second (TOPS) at 10 watts, the DRIVE PX Xavier offers 30 TOPS of performance, while consuming 30 watts of power.
Nvidia is now promoting its latest Pegasus SoC, scheduled for delivery in 2018, designed to perform 320 TOPS - more than 10x the performance of its predecessor - at 500 watts of power.