Intel’s 2nd-generation Xeon Scalable processors are here

Aiming to empower businesses with deep learning capabilities, Intel last week launched the second generation of Xeon scalable processors, including the flagship Xeon Platinum 9200 processor with 56 cores, at its “Data-Centric Innovation Day” here. “This is a big day for us. It is the first truly data-centric launch in our history,” Navin Shenoy, Executive Vice President, Intel and General Manager, Data Center Group told reporters here adding “this thing is a beast.”
The new Intel Xeon Scalable processors with built-in Deep Learning Boost (DLB) technology add AI capabilities for the next era of data-driven Internet of Things (IoT) edge platforms. It also accelerates performance of up to 14 times for deep learning inference workloads such as object detection, speech recognition, and image classification.
“Half the world’s data was created in the last two years and only two per cent of it has been analysed. That leads us to great optimisation,” added Shenoy.
The flagship Xeon Scalable Platinum 9200 processor has been designed for high-performance computing (HPC), advanced analytics, artificial intelligence (AI) and high-density infrastructures.
It has 12 memory channels that aim to deliver breakthrough levels of performance with the highest Intel architecture FLOPS per rack along with the highest DDR4 native memory bandwidth support of any Intel Xeon processor platform.
“Intel Speed Select” technology provides enterprise and infrastructure-as-a-service (IaaS) providers more flexibility to address evolving workload needs. The new Xeon Scalable processors can be configured to performance settings of core counts and frequencies, thus, creating “three CPUs in one”.