My 2025 Predictions for AI Infrastructure

Yes, it’s that season of the year, again – predictions time. We’ve learned a lot about AI infrastructure during the last...

Read more
Latency in AI Networking – Inevitable Limitation to Solvable Challenge

While latency is often discussed as an unavoidable bottleneck in networking and system performance, advancements in technology are changing this...

Read more
My SC24 Recap – Why Not Go with NVIDIA?

Just got back from Atlanta, this year’s site of the SC24 conference. Here are some highlights from the international conference...

Read more
OCP Global Summit – AI, Cooling, and Cool Networking Innovations

The OCP Global Summit took place a couple of weeks ago in San Jose, California. As usual, it was a...

Read more
Optimize Your Enterprise AI with the Right Cluster Fabric

ChatGPT was introduced on November 30, 2022. Since then, AI (artificial intelligence) has become the most used buzzword across virtually...

Read more
Subscribe
to our newsletter

Sign up to get the latest news and insights.

First Ethernet DDC Scheduled AI Fabric Now in Production

Artificial intelligence (AI) and machine learning (ML) have witnessed dramatic growth since the end of 2022, with hyperscalers building huge...

Read more
Ethernet Moves into Dominant Position in AI Networking

Massive June-July 2024 Announcements to Push Ethernet into Dominant Position in AI Networking. Arista, Broadcom, Cisco, and Nvidia all message growing...

Read more
Fabric for AI Training Clusters – Should InfiniBand Be Your Default?

Are you one of the lucky ones that gets to build large-scale AI training clusters? If so, you’ve probably realized...

Read more
A High-Performance Back-End Ethernet Fabric for AI GPU Clusters

There’s an exciting race going on right now – and I’m not referring to a sporting event at the Olympics....

Read more
GPU and AI ASIC Diversity to Drive Ethernet

As we enter the second half of 2024, the AI/ML market is rapidly moving towards next-generation GPUs and AI ASICs....

Read more
Building an 8K GPU Cluster with High-Performance Ethernet Connectivity

Let’s go under the hood of DriveNets Network Cloud-AI…When building a large GPU cluster for artificial intelligence (AI) training purposes,...

Read more
AI & Networking – a Match Made in Heaven

In a lot of cases, when talking about artificial intelligence (AI), we end up talking about networking. In many other...

Read more
2024 OCP Regional Summit – My Takeaways

From Microsoft’s vision of future innovation to ByteDance’s test results of Ethernet scheduled fabric. Lisbon is a lovely city (though I’m...

Read more
AI Networking Options – Smart NICs vs. Scheduled Fabric

Breaking a world record is easy. Just start as fast as you can and gradually increase your speed until you...

Read more
What’s happening with AI Networking & the UEC?

The Ultra Ethernet Consortium (UEC), part of the Linux Foundation’s Joint Development Foundation, was formed in July 2023 by a...

Read more
NVIDIA GTC 2024 – Networking is Cool Again!

Just wrapped up an incredible experience at the Nvidia GTC conference! This year’s event brought together some of the brightest...

Read more
Clearing Confusion about Distributed Disaggregated Chassis for AI

DDC was defined by AT&T within the OCP, implemented using DNOS to be deployed into CSP networks, and has evolved...

Read more
Why DriveNets Can Lead in Ethernet-based AI Networking

AI is dominating the discussions in the cloud infrastructure markets, and it’s for a good reason. AI may be the...

Read more
Network Cloud-AI – From Theory to Practice

Recently we completed independent lab testing of different architectures used as a back-end networking fabric for AI clusters. Conducted by...

Read more
AI Networking Moves Ahead with DriveNets and Broadcom Jericho3AI

We have all witnessed the significant growth of the AI market since the end of 2022. Hyperscale companies like Microsoft,...

Read more
DriveNets Contribution to the Latest Version of the OCP DDC Standard is Accepted 

DriveNets has an ongoing commitment to maintaining Distributed Disaggregated Chassis (DDC) as the most innovative and promising networking technology. ...

Read more
3 Takeaways from the AI Hardware & Edge AI Summit Event

More than a week ago I returned from the “AI Hardware & Edge AI Summit” event in Santa Clara. You...

Read more
Panel Recap: Next Generation System Design for Maximizing ML Performance

Last week, I attended the “AI Hardware & Edge AI Summit” in Santa Clara. I was honored to participate in...

Read more
Can You Really Compare Clos to Chassis when running AI applications?

The well-known and commonly mentioned Clos topology dates back 70 years to an article by an American engineer called Charles...

Read more
A Robust Fabric: Failure Recovery in DDC

In previous blog posts about Distributed Disaggregated Chassis (DDC) for AI workloads, we mentioned two possible networking issues that can...

Read more
Achieving Lossless Connectivity Fabric with DDC

In our earlier post, we discussed the importance of Distributed Disaggregated Chassis (DDC) architecture for reducing AI workload job completion...

Read more
Reduce AI Job Completion Time with DDC

As the volume and complexity of artificial intelligence (AI) models continue to grow, reducing job completion time (JCT) and improving...

Read more
InfiniBand vs Ethernet – Why Ethernet fits AI Networking needs

Artificial intelligence (AI) has revolutionized various industries, driving the need for efficient networking solutions to support the massive data demands...

Read more
DriveNets Enters the AI Networking, A Market Expected to Exceed $10B by 2027

AI took the world by storm early this year, with ChatGPT showing a transformational leap in how humans interact with...

Read more
Addressing the Next Network Bottleneck

The network as a bottleneck that slows down applications and prevents new use cases (and business) from becoming feasible seems...

Read more