Welcome Here  Shenzhen Mingjiada Electronics Co., Ltd.

On 26 September, Intel officially announced the Xeon 6 performance core processor (codenamed Granite Rapids). It is reported that compared to the previous generation of processors, the performance of the Xeon 6 performance core processor is doubled, and with more cores, double memory bandwidth, and built-in AI acceleration, it meets the challenges of AI from the edge to the datacentre to the cloud environment. Designed with a modular SoC architecture, the Xeon 6 performance core processors offer a high degree of flexibility and scalability with a rich product portfolio for cloud service providers, OEMs, ODMs, ISVs and more.

In the field of cloud computing, Intel® Xeon 6 processors offer significant improvements in the number of cores per circuit, single-core performance, and performance per watt compared to the previous generation of processors, which can help cloud service providers effectively reduce computing costs. Compared to the fifth-generation Intel® Xeon® Scalable processors, the Xeon 6 processor has up to two times the number of cores per circuit, up to 1.2 times the average single-core performance, up to 1.6 times the average performance per watt, and an average of 30 per cent TCO2 savings at the same level of performance. Meanwhile, in workloads such as general-purpose compute, data and web services, scientific computing, and AI that are commonly found in the datacenter, the Xeon 6 performance core processors also deliver significant improvements in performance and performance per watt compared to previous-generation processors3.

The Xeon 6900P family of processors (codenamed Granite Rapids-AP), which is being announced, comes with up to 128 cores and supports up to 6400 MT per second of DDR5 memory, 8800 MT per second of MRDIMM memory, six UPI 2.0 links (at rates up to 24 GT per second), 96 PCIe 5.0 or 64 CXL 2.0 lanes, 504MB of L3 cache, Advanced Matrix Extension (Intel AMX) with FP16 data format support, MRDIMM options for memory bandwidth-sensitive workloads such as AI and scientific computing, and new support for CXL 2.0.