Intel Debuts 5G Server and Base Station Chips, Plus a PC Network Card (venturebeat.com) 8
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. From a report: 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.
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.
Re: (Score:2)
Re: (Score:1)
These are server CPUs to be deployed in cloud "AI" services.
Despite all the hoopla (Score:2)
Despite all the hoopla they still cannot do I/O and have extremely limited I/O bandwidth via the shared x4 bus.
and the mac pro has 2 pci-e card on it storage (Score:2)
and the mac pro has 2 pci-e card on it for storage as they T2 chip needs to be on the DMI bus.
So... how does it compare to the 2nd gen EPYC's? (Score:2)
Something that adding AI functionality isn't going to make up for AMD's smaller process and higher core count at the various price points.
100GB cap is an joke on an server when most home c (Score:2)
100GB cap is an joke on an server when most home caps are higher then that.