Intel announced a collaboration with Inspur, Ruijie Networks, and Silicom Connectivity Solutions to design and develop new infrastructure processing units (IPUs) using both a CPU and an FPGA.
The IPU – what Intel calls a Data Processing Unit (DPU) – is a programmable network device designed to offload network processing tasks such as storage virtualization, network virtualization, and security from the CPU. This reduces overhead and frees up the CPU to focus on its core data processing functions. They are becoming a real growing industry, with multiple products on the market from Nvidia, Marvell, Fungible and Xilinx.
Intel has already introduced an IPU, named Mount Evans, and is moving to a next-generation product called Oak Springs Canyon or officially the C6000X. It features both a Xeon D processor and an Intel Agilex FPGA to handle networking with custom programmable logic. Both processors have 16 GB of DDR4 memory.
More importantly, there are two 100Gbps ports as well as PCIe Gen4 x16 connectivity. It can support cloud infrastructure workloads such as Open vSwitch, NVMe over Fabrics (NVMEOF), and Remote Direct Memory Access (RDMA) over Converged Ethernet v2 (RoCEv2). Like previous IPU boards, the C6000X is made by Silicom, not Intel.
Intel has previously said its vision for programmable networks is based on open standards where the IPU is integral to delivering new network capabilities, such as telemetry, congestion control and traffic direction.
China is quite a large market for FPGAs, which is why the two Chinese companies Inspur (cloud infrastructure) and Ruijie Networks (digitalization of all industries) are involved. Both will deploy Oak Springs Canyon to provide custom solutions optimized for IPU.
Copyright © 2021 IDG Communications, Inc.