With the growth of cloud computing and the increasing adoption of supercomputers, server processors must evolve to meet today’s needs. Which are not limited only to having a large number of cores, but to being able to offer a series of technologies that make them competitive and functional with the needs of current software.
Sapphire Rapids, Intel Xeon processor designed for AI
In a press release written by Lisa Spelman, vice president and general manager of Xeon and Memory Group, Intel gave new details about its fourth generation Intel Xeon Scalable processors, confirming rumors about this processor.
Intel’s strategy for its Intel Xeon vs AMD EPYC futures is clear, opting for a market that AMD has not bet on, such as artificial intelligence. And yes, Intel has confirmed the rumors about Sapphire Rapids, starting with the implementation of the AMX or Advanced Matrix Extensions units. What is the addition of Tensor units for AI in processor cores which represent a qualitative leap in this regard compared to the AVX-512 instructions that Intel has been using until now. On the other hand, since AI requires bandwidth, the HBM memory usage, which will be used in conjunction with the DDR5 memory which will also be supported by this CPU server.
But this is not the only novelty of the Intel Sapphire Rapids, since Intel has announced the implementation of the DSA o Data flow accelerator. A unit responsible for moving data between the different components of the processor. Which, in plain language, means it’s a smart network adapter or a SmartNIC built into the processor. A piece of hardware that is going to be mainstream in hardware designs for years to come and not just by Intel and not in the CPU world exclusively.
In addition to the new technologies described, the Sapphire Rapids will have PCI Express 5.0 support with CXL technology, which also represents a paradigm shift in the intercommunication of the CPU with the components that use this bus. Allow the processor and graphics card to have fully consistent memory access automatically.
We will have to wait until 2022
The launch of Sapphire Rapids will not take place until 2022, as production of this server processor will begin in the first quarter of 2022, peaking in the second quarter. So the first servers and data centers with Sapphire Rapids will not be ready until 2022. Although most of them are already affected, as it is common to contract in this market 12 months in advance.
We know since 2019 that Sapphire Rapids will be the CPU of the Intel Aurora supercomputer, coupled with the Intel Xe-HPC Ponte Vecchio model. Being the first supercomputer in years with pure Intel hardware in terms of CPU and GPU. The delay in manufacturing the Sapphire Rapids may be due to Intel’s current desire to ditch its 10nm SuperFin node wafers for its Alder Lake desktop and laptop processors.
