Compute Express Link™ (CXL™): Memory Challenges and CXL Solutions

Logo
Presented by

Chris Petersen (Facebook) and Prakash Chauhan (Google)

About this talk

Compute Express Link™ (CXL™) is an industry supported cache-coherent interconnect for processors, memory expansion and accelerators. CXL supports dynamic multiplexing between a rich set of protocols that includes I/O (CXL.io, based on PCIe®), caching (CXL.cache) and memory (CXL.memory) semantics. CXL.mem allows a host processor to access memory attached to a CXL device. CXL.mem transactions are simple memory load and store transactions that run downstream from the host processor which takes care of all the associated coherency flows. This webinar will explore how the CXL.mem protocol can deliver power-efficient performance with emerging applications such as AI, HPC, DL and comms with a coherent interface and low latency. This webinar will also explore type-3 devices and use cases for memory bandwidth expansion, memory capacity expansion and storage class memory.
Related topics:

More from this channel

Upcoming talks (0)
On-demand talks (15)
Subscribers (5220)
Compute Express Link® (CXL®) is a new breakthrough high-speed CPU interconnect that enables a high-speed, efficient performance between the CPU and platform enhancements and workload accelerators. Industry leaders Alibaba, Cisco, Dell EMC, Facebook, Google, Hewlett Packard Enterprise, Huawei, Intel Corporation and Microsoft have teamed up to form an open industry standard group to develop technical specifications that facilitate breakthrough performance for emerging usage models while supporting an open ecosystem for data center accelerators and other high-speed enhancements.