Dell EMC, Facebook, Google, Intel and others create Advance CXL to boost data centre performance


Clare Hopping

13 Mar, 2019

Some of the world’s biggest tech companies have announced their commitment to developing open standards in the world of data centre and cloud computing, with the introduction of the Compute Express Link (CXL) standards group.

Alibaba, Cisco, Dell EMC, Facebook, Google, Hewlett Packard Enterprise, Huawei, Intel and Microsoft want to make sure high-speed CPU-to-Device and CPU-to-Memory processes and equipment are standardised to enhance data centre performance.

The group will focus on making the CXL Specification 1.0 mainstream among tech businesses, interconnecting CPUs with platforms and workloads. It will build upon the existing PCI Express (PCIe) infrastructure, using the PCIe 5.0 interface to improve the I/O protocol, memory protocol and coherency interface.

“CXL is an important milestone for data-centric computing, and will be a foundational standard for an open, dynamic accelerator ecosystem,” said Jim Pappas, director of technology initiatives at Intel.

“Like USB and PCI Express, which Intel also co-founded, we can look forward to a new wave of industry innovation and customer value delivered through the CXL standard.”

Intel was one of the founding fathers of the CXL protocol, developing the interconnect four years ago. However, the company now wants it to become a standardised technology and so recruited many of its partners to develop it into a set of standards that could be used by the industry to improve data centre infrastructure.

“Microsoft is joining the CXL consortium to drive the development of new industry bus standards to enable future generations of cloud servers,” said Dr Leendert van Doorn, distinguished engineer at Microsoft’s Azure division.

“Microsoft strongly believes in industry collaboration to drive breakthrough innovation. We look forward to combining efforts of the consortium with our own accelerated hardware achievements to advance emerging workloads from deep learning to high performance computing for the benefit of our customers.”