NTT, Red Hat, NVIDIA, Fujitsu unveil new edge AI solution for real-time data analysis

The newly introduced solution comprises the IOWN All-Photonics Network (APN) and data pipeline acceleration technologies within the IOWN Data-Centric Infrastructure (DCI). NTT’s accelerated data pipeline for AI leverages Remote Direct Memory Access (RDMA) over APN to gather and process sensor data at the edge.

Red Hat OpenShift’s container orchestration technology aims to enhance operational flexibility by enabling workload deployment across geographically dispersed and remote data centers, according to the companies. Demonstrations by NTT and Red Hat have showcased the solution’s capacity to minimize power consumption while maintaining low latency for real-time AI analysis at the edge.

“As AI, sensing technology and networking innovation continues to accelerate, using AI analysis to assess and triage input at the network’s edge will be critical, especially as data sources expand almost daily,” the company notes in a written release.

“Using AI analysis on a large scale, however, can be slow and complex, and can be associated with higher maintenance costs and software upkeep to onboard new AI models and additional hardware. With edge computing capabilities emerging in more remote locations, AI analysis can be placed closer to the sensors, reducing latency and increasing bandwidth.”

Highlights of the proof of concept include NTT’s accelerated data pipeline for AI inference, real-time AI data analysis facilitated by Red Hat OpenShift, and NVIDIA A100 Tensor Core GPUs and NVIDIA ConnectX-6 NICs for AI inference.

Read more:

Red Hat on navigating the frontiers of information with observability at the edge

Red Hat takes on low-resource challenges with Device Edge platform

Article Topics

data  |  edge AI  |  Fujitsu  |  IOWN  |  NTT  |  Nvidia  |  Red Hat