Intel’s sale of its consumer 5G modem unit signaled its exit from the smartphone business last year, but the company remains heavily committed to participating in the growing 5G marketplace — primarily on the carrier and enterprise sides. Today, the company announced three chips built for various types of 5G computers, plus a 5G-optimized network adapter for PCs.
Up first is an updated second-generation Xeon Scalable processor, now at a top speed of 3.9GHz and bolstered by additional AI capabilities to aid with inference applications. The new chip promises up to 36% more performance than the first-generation version, with up to 42% more performance per dollar, though early second-generation chips were introduced in April 2019.
Intel says the Xeon Scalable is the “only CPU with AI built in” — a pitch that’s not exactly accurate, given the range of existing laptop and mobile CPUs with AI features, but one Intel further explains means “the only CPU on the market that features integrated deep learning acceleration.” Xeon Scalable’s Deep Learning Boost feature set promises up to 6 times more AI performance than AMD’s Rome processors, though Intel won’t quantify the number of TOPS available for AI processing, calling the metric “theoretical.” Regardless, Intel says Xeon Scalable will support the cloud AI needs of Alibaba, AWS, Baidu, Microsoft, and Tencent, as well as other major companies.
Network-optimized “N-SKUs” of the new Xeon Scalable will also be available, offering up to 58% more performance for network function virtualization workloads compared with the first chip. Customers such as China Mobile, SK Telecom, Sprint, and T-Mobile Poland are all using Xeon Scalable in their 5G networks. The boosted Xeon Scalable chips are officially available starting today.
Intel is also introducing the Atom P5900, billed as the first Intel architecture SoC for base stations and designed from the ground up for radio access network (RAN) needs. It’s a 10-nanometer chip with hardware-based network acceleration features, including integrated packet processing, ultra low latency, and a switch for inline cryptographic acceleration. It promises up to 1.8 times the integer throughput versus an Atom C3000, plus 5.6 times the packet security throughput and 3.7 times the packet balancing throughput compared with software-based alternatives.
The Atom P5900 is designed for use in 5G base stations, and Intel already has customers for the chip, including commitments from network hardware makers Ericsson, Nokia, and ZTE to use it in their RANs. Based on demand, Intel expects it will be the market leader in 5G base station silicon by 2021, ahead of its 2022 goal, with a 40% share of the growing business. With anticipated demand for 6 million 5G base stations by 2024, that could be good news for the company.
Intel also announced the eASIC, codenamed Diamond Mesa, which it’s calling its first 5G structured ASIC — an option for customers seeking custom chip solutions containing low-power, high-performance Intel processors plus customer-specific IP in silicon. Using a footprint compatible with prior Intel FPGA solutions, Diamond Mesa promises twice the performance or 50% lower power consumption versus prior-generation Intel ASICs. The company expects eASIC solutions to be used in 5G wireless datacenters, as well as in embedded, video, industrial, and military applications.
Last up, Intel announced the Ethernet 700 series, 5G-optimized network adapter cards with hardware-enhanced precision time protocol (PTP) for ultra low latency and similarly precise timing requirements — it’s targeting 100-nanosecond phase accuracy for 5G network service synchronization. The cards will be used in computers demanding split-second responsiveness for controlling industrial equipment, financial trading, emergency response, RAN connectivity, or video streaming. The Ethernet 700 series is sampling to customers now and will go into production in the second quarter of 2020.