Data and computation are fundamental to the success of AI, which is why hyperscale data center operators are racing to build ever larger accelerator-based compute clusters. The market jolt caused by LLMs and ChatGPT has further accelerated the race. Scaling clusters requires innovation across many domains: the accelerator chips, their linkages within a node, the fabrics linking the nodes, whether InfiniBand or Ethernet-based, and their topology. The input-output (I/0) growth of each new generation of accelerator and the growth of bandwidth that needs to escape a compute node means using optical I/O is a matter of time. Each hyperscale operator has its preference; some back co-packaged optics (CPO), while others favor pluggable optics. But the use of optics continues to grow in such clusters. For example, Google uses its optical circuit switches as part of its TPU v4 accelerator-based AI compute clusters to reduce cost and improve system reliability and flexibility. And Broadcom has already developed CPO-based Tomahawk Ethernet switches; its latest Jericho3-AI chip developed to scale AI compute clusters can now also be CPO-based. This webinar will bring together industry experts and leading suppliers to discuss the challenges of scaling AI clusters. It will discuss why and likely when CPO will be needed. Issues such as bandwidth, I/O density, power requirements, and solutions will be detailed.

During the webinar, you’ll learn:

• AI workloads characteristics
• Interconnect requirements of AI workloads
• The various options of Optical Interconnect designs and topologies to support AI workloads
• Optica Interconnect in large scale AI clusters – How big is the market opportunity?

Who should attend? 

Switch System Vendors, Silicon Vendors, Optical Transceiver vendors, Cloud and Telecom Service Providers, IT buyers and Decision Makers, and Enterprise CIO and CTO

Agenda, Ticketpreise und Anmeldung findest du auf der Website zur Veranstaltung: