Neither Ray nor Keith has met Pradeep before, but Ray was very interested in Fungible’s technology. Turns out Pradeep Sindhu, CEO and Co-founder, Fungible has had a long and varied career in the industry starting at Xerox Parc, then co-founding and becoming chief scientist at Juniper, and now reachitecting the data center with Fungible. Pradeep mentioned this at the end of the podcast, he has always been drawn to hard problems with the potential to open up immense possibilities. What he did at Juniper and what he is planning to accomplish with Fungible both fit that pattern.
Today, in a typical data center, we have servers, networking and storage equipment all connected through a fabric. But from Pradeep’s perspective none of it works well in support of data centric computing. What we have today is operating like changing a screw with a pliers. But if there existed some hardware that can execute data centric computing (or to follow the metaphor, a screw driver) well, the data center would operate much more efficiently, with more performance and better resource use.
Fungible was founded in 2015 with the idea that the industry is moving to a data centric computing paradigm and today’s data center is ill equipped to take IT there.
What is data centric computing
The IT industry has been moving to a new type of computing, that is focused on short bursts of CPU activity with relatively small packets of data coming off the network (from sensors/outside world, from storage, from other servers, etc.). Those workloads are often transient, short lived, are intended to be performed quickly and may not leave any persistent state.
We can see this in the emergence of micro-services architectures with Docker and k8s containers. But you don’t have to be using containers. It’s also present in machine learning where the update cycle of the neural network (with accelerators) takes lot’s of small bursts of computation while it consumes lots of small data items (pictures, text documents, ticker/status logs, etc. ).
Furthermore, the move to commodity hardware has taken the same x86/ARM core CPUs and used them to execute these small bursts of computation. And for some of these operations that may still make sense. But when the data center uses these same cores to perform data path packet processing. It bogs down the network. It consumes a lot of power, adds overhead (higher latencies), leads to packet loss, injects network jitter and a host of other problems.
So, in order to get the data packets to where they need to be with out those problems, networking endpoints need to be changed out to something designed to support data path critical workloads. Pradeep calls these data path critical work items “run to complete” code.
The critical question is what proportion of IT workloads are “data centric’ vs. not. While it might not be that high today, Pradeep and Fungible are betting that it’s going to be getting much higher over time. If we look at hyper-scalars today they are the forefront of this computing paradigm change and much of their workloads are moving to containerized execution.
The DPU enables data centric computing
Fungible plans to add a DPU that supports a power efficient, “run-to-complete” programming engine to the data center. By using DPUs, they can create a true fabric (using IPoE) that’s low latency, low jitter, lossless and provides full cross-sectional bandwidth.
The problem as Pradeep sees it is that the X86 and ARM cores are just not made to execute run-to-comple workloads well and this is required to provide a true fabric. Whereas Fungible has designed the DPU from the start to execute run-to-complete work.
Pradeep sees the data center of tomorrow utilizing JBoF(lash) & JBoD(isk) boxes with DPU(s) in front of them providing storage server services (block, file and object), JBoGP(Us) or JBoFP(GAs) boxes with DPU(s) in front of them providing accelerator/graphics server services, and compute boxes with DPU(s) and x86/ARM cores with DRAM-Optane PMEM in them providing CPU server and client services. All the DPUs together in a cluster would in total provide true fabric services.
Essentially, the DPUs would take over all data path operations and the storage, GPUS, CPUs would handle everything else. In effect, segregating data path and control path services in the data center.
Greenfield, brownfield or both
Keith and I both assumed this would be great for a green field deployments. But,. Pradeep said it’s designed to be incrementally added to servers, JBoFs, JBoDs, JBoGs/JBoFPs and start providing data path services within current data center fabric environments. Even as the rest of the data center remain unchanged.
At some point we talked about the programming model of the DPU. The DPU offers a bring your own Linux OS that can be programmed in any language you choose. But the critical, data-path functionalityi is coded in “C” to run as fast and as efficiently as possible.
Fungible has designed this hardware themselves. We didn’t get to talk about how they plan to market their product to the data center.
Pradeep also said to stay-tuned, and they were just about to announce their first product offering based on the DPU.
The podcast ran ~38 minutes. Pradeep, given his education and experience, is a very knowledgeable individual about the data center environment today. He’s certainly one of the most interesting IT tecnologist we have talked with in a while on the GreyBeards podcast. To say what Fungible is trying to do is aggressive and bold is an understatement. But Pradeep feels this is the only way forward to liberate the data center from its data path chains today. Both Keith and I thought we needed at least another hour or so to truly understand what they are doing and where they are going with it. Listen to the podcast to learn more.
Pradeep Sindhu, CEO and Co-Founder, Fungible
Pradeep Sindhu is CEO and Co-Founder of Fungible, a Santa Clara-based startup providing at-scale, next-generation solutions for the data center, cloud and IT industries. He has been at the forefront of the network and processing industry for over three decades.
As the co-founder and CTO of Juniper Networks, he played a central role in the architecture, design and development of Juniper’s M40 router – the M series was the first of its kind, offering the industry true decoupling of the control plane and the forwarding plane.
Prior to Juniper, he was a Principal Scientist and Distinguished Engineer at the Computer Science Lab at Xerox’s Palo Alto Research Center (PARC) pushing the envelope on what silicon could do for networking and processing.
He is passionate about new ways to support our growing data-centric world with the right combination of hardware and software to build the infrastructure our future needs.