Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

LRO-based Pluggable VCSEL and SiP Transceivers for AI Clusters

Open Compute Project via YouTube

Overview

Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
This presentation by Maxim Kuschnerov, Director of R&D at Huawei Technologies, explores optical network interconnectivity solutions for GPU clusters in AI applications. Learn about half-retimed pluggable transceivers that support 224Gbps and comply with optical interface standards, reducing manufacturing and maintenance costs. Discover how Linear Receiver Optics (LRO) can further decrease costs and power consumption using VCSELs for distances under 100m. The talk demonstrates 112G LRO pluggable solutions for both VCSELs and Silicon Photonics, covering various AI datacenter interconnectivity scenarios from multimode fiber up to 100m to single mode fiber up to 500m. Understand the advantages of these solutions, including superior performance, channel-adaptive functionality, interoperability with retimed pluggable solutions, low power consumption, low latency, and high reliability.

Syllabus

LRO-based Pluggable VCSEL and SiP Transceivers for AI clusters

Taught by

Open Compute Project

Reviews

Start your review of LRO-based Pluggable VCSEL and SiP Transceivers for AI Clusters

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.