Our 10^th annual Persistent Memory + Computational Storage Summit is right around the corner on May 24 and 25, 2022.  We remain virtual this year, and hope this will offer you more flexibility to watch our live-streamed mainstage sessions, chat online, and catch our always popular Computational Storage birds-of-a-feather session on Tuesday afternoon without needing a plane or hotel reservation! This year, the Summit agenda expands knowledge on computational storage and persistent memory, and also features new sessions on computational memory, Compute Express Link ^TM (CXL)^TM, NVM Express, SNIA Smart Data Accelerator Interface (SDXI), and Universal Chiplet Interconnect Express (UCIe). We thank our many dynamic speakers who are presenting an exciting lineup of talks over the two days, including:

• Yang Seok Ki of Samsung on Innovation with SmartSSD for Green Computing
• Charles Fan of MemVerge on Persistent Memory Breaks Through the Clouds
• Gary Grider of Los Alamos National Labs on HPC for Science Based Motivations for Computation Near Storage
• Alan Benjamin of the CXL Consortium on Compute Express Link (CXL): Advancing the Next Generation of Data Centers
• Cheolmin Park of Samsung on CXL and The Universal Chiplet Interconnect Express (UCIe)
• Stephen Bates and Kim Malone of NVM Express on NVMe Computational Storage – An Update on the Standard
• Andy Walls of IBM on Computational Storage for Storage Applications

Our full agenda is at www.snia.org/pm-summit. We’ll have great networking opportunities, a virtual reception, and the ability to connect with leading companies including Samsung, MemVerge, and SMART Modular who are sponsoring the Summit. As David McIntyre of Samsung, the 2022 PM+CS Summit chair, says in his 2022 Summit Preview Video, “You won’t want to miss this event!” Complimentary registration is now available at https://www.snia.org/events/persistent-memory-summit/pm-cs-summit-2022-registration.  We will see you there! The post Dynamic Speakers on Tap for the 2022 SNIA Persistent Memory + Computational Storage Summit first appeared on SNIA Compute, Memory and Storage Blog.

Our “Storage Life on the Edge” webcast series continued on March 22, 2022 where our expert panelists, Stephen Bates, Bill Martin, Mayank Saxena and Tong Zhang highlighted several real-world edge use cases, the implications for storage, and the benefits of computational storage standards. You can access the on-demand session and the presentation slides at the SNIA Educational Library. The panel answered several questions during the live event. We only had time to get to a handful. As promised, here are answers to all of them.

Q.  I have heard NVMe® is developing an open and vendor-neutral standard for computational storage devices. How important do you think standards like this one are for mass adoption of these types of devices on the edge and why?

A. Yes, NVMe is working to develop an architectural model for NVMe-based computational storage devices. The specifics of this are under development, but it will lead to new commands in NVMe that pertain to computation. Standards like this are of vital importance to the adoption of computational storage at the edge since it will lead to a rich ecosystem of software and allow for the multi-sourcing of computational storage devices from multiple vendors.

Q.  Computation storage devices come in three main forms. Computational storage processor, computational storage drive and computational storage array. How do you see each of these being deployed on the edge and why?

A. I think we can expect to see all three types of computational storage devices in the edge. Computational storage drives combine the storage of an SSD with compute power. This will be very useful in the edge where physical space is a very real constraint. That said, computational storage processors will also have a role as they separate the compute element from the storage while providing peer-to-peer communication between the compute element and storage at the edge, and that can be desirable in certain instances. Finally, the computational storage array is appealing because it is a plug and play solution for computational storage that can be inserted into a 1U or 2U rack space and consumed via standards based APIs.

Q. What percentage of data at the edge have you experienced to be compressible? Can you provide some examples of edge use cases which have a high percentage of compressible data and some examples which have low percentages, and comment on the specific percentages? How does this affect the capacities of storage devices in these use cases?

A. Except image/video, most other data at edge tend to have decent compressibility. Experience shows that we may expect 2:1~4:1 compression ratio in general. Example edge use cases with highly compressible data are time series data from various IoT devices, and most edge database and data analytics systems. Typically low compressibility is caused by the use of special-purpose compression (e.g., JPEG and H.264) before data storage. By leveraging the good runtime data compressibility, computational storage drives with built-in transparent compression could very well contribute to lowering the TCO and power consumption of edge infrastructure.

Q. Will applications push encrypt/decrypt keys to the computational storage processor? Or is there pre-configuration and storage of keys?

A. It can support both models. In the traditional PKI model, keys can be stored in trusted platform module (TPM) at the edge server following certificate signing request (CSR) process, tied to some root certificate, which can be revoked when needed. There can also be an encryption key per IO, and these keys can be managed and rotated by hosts. Notably, there are a lot of innovations happening in the field of data security benefiting the edge security directly e.g. ICN (Information-Centric Network). With ICN, data can be secured at packet level with ephemeral keys agnostic to transport protocol. Computational storage can perform such encryptions near to data without involving CPU, increasing data sanctity and performance.

Q. Given the heterogeneity nature of the edge data and system, how can computational storage be a value add?

A. Heterogeneity is indeed the central nature of edge, which is very important to understand. At the edge, data is at the heart - everything else is just peripheral. There are always two primary things to consider i.e. TCO & compute for data. It is becoming more apparent for edge servers and gateways that data processing compute should be done at the edge where data is ingested. Offloading of repetitive data-intensive processing tasks can help reduce the cost and improve the ecosystem for protocol processing and governance in these heterogenous environments.

Now with this, one can have storage with a standard interface for everyday data-intensive tasks, serving varied use cases, which can be plugged into any compute entity i.e. from Rasberry Pi to 1U server in the cloudlet datacenter. That’s powerful.

Q.  Would it make sense to use a computational storage drive (CSD) for general-purpose programmable computation for edge? If yes, would using embedded CPUs inside CSDs be more efficient than using external CPUs?

A. Yes, compared with external host CPUs, embedded processors inside computational storage drives tend to be much less powerful and have much less cache memory. So it does not make much sense if we only want to off-load some computation-intensive tasks into the embedded processors on a computational storage drive. However, because the computational storage drive could integrate customized hardware engines for functions like compression, encryption, and data filtering, it still makes sense to off-load certain programmable computation into the computational storage drive if it involves certain pre- or post-processing that could leverage those customized hardware engines.

Q. What could a computation storage drive do to seamlessly contribute to reducing power consumption in edge environments?

A. The low-hanging fruit here is for the computational storage drive to carry out internal transparent lossless data compression. By reducing the data volume through compression, we will write much a smaller amount of data into NAND flash memory. We know that writing data into NAND flash memory is the most energy-consuming operation inside of a storage drive. So in-storage transparent compression could seamlessly reduce the power consumption.

Remember, this is a series. If you missed the introduction “Storage Life on the Edge: Managing Data from the Edge to the Cloud and Back,” you can view it on-demand here. I also encourage you to register for the next session in this series on April 27, 2022 “Storage Life of the Edge: Security Challenges” where our security experts will discuss the multitude of security challenges created by the edge. I hope you’ll join us.

As applications continue to increase in complexity and users demand more from their workloads, there is a trend to again deploy dedicated accelerator chips to assist by offloading work from the main CPU.  These new accelerators (xPUs) have multiple names such as SmartNIC (Smart Network Interface Card), DPU, IPU, APU, NAPU. How are these different than GPU, TPU and the venerable CPU? xPUs can accelerate and offload functions including math, networking, storage functions, compression, cryptography, security and management.

It’s a topic that the SNIA Networking Storage Forum will spotlight in our 3-part xPU webcast series. The first webcast on May 19, 2022 “SmartNICs to xPUs – Why is the Use of Accelerators Accelerating?” will cover key topics about, and clarify questions surrounding, xPUs, including…

1. xPU Definition: What is an xPU (SmartNIC, DPU, IPU, APU, NAPU), GPU, TPU, CPU? A focus on high-level architecture and definition of the xPU.

• Trends and Workloads: What is driving the trend to use hardware accelerators again after years of software-defined everything? What types of workloads are typically offloaded or accelerated?  How do cost and power factor in? 

• Deployment and Solutions: What are the pros and cons of dedicated accelerator chips versus running everything on the CPU?  

• Market landscape Who provides these new accelerators—the CPU, storage, networking, and/or cloud vendors? 

Register here to join us on May 19th to get the answers to these questions. Part 2 of this series will take a deep dive on accelerator offload functions and Part 3 will focus on deployment and solutions. Keep an eye on this blog and follow us on Twitter @SNIANSF for details and dates for the future sessions.

As applications continue to increase in complexity and users demand more from their workloads, there is a trend to again deploy dedicated accelerator chips to assist by offloading work from the main CPU.  These new accelerators (xPUs) have multiple names such as SmartNIC (Smart Network Interface Card), DPU, IPU, APU, NAPU. How are these different than GPU, TPU and the venerable CPU? xPUs can accelerate and offload functions including math, networking, storage functions, compression, cryptography, security and management. It’s a topic that the SNIA Networking Storage Forum will spotlight in our 3-part xPU webcast series. The first webcast on May 19, 2022 “SmartNICs to xPUs – Why is the Use of Accelerators Accelerating?” will cover key topics about, and clarify questions surrounding, xPUs, including…

1. xPU Definition: What is an xPU (SmartNIC, DPU, IPU, APU, NAPU), GPU, TPU, CPU? A focus on high-level architecture and definition of the xPU.

• Trends and Workloads: What is driving the trend to use hardware accelerators again after years of software-defined everything? What types of workloads are typically offloaded or accelerated?  How do cost and power factor in?

• Deployment and Solutions: What are the pros and cons of dedicated accelerator chips versus running everything on the CPU?

• Market landscape Who provides these new accelerators—the CPU, storage, networking, and/or cloud vendors?

Register here to join us on May 19th to get the answers to these questions. Part 2 of this series will take a deep dive on accelerator offload functions and Part 3 will focus on deployment and solutions. Keep an eye on this blog and follow us on Twitter @SNIANSF for details and dates for the future sessions.

The complex and changeable structure of edge computing, together with its network connections, massive real-time data, challenging operating environment, distributed edge cloud collaboration, and other characteristics, create a multitude of security challenges. It’s a topic the SNIA Networking Storage Forum (NSF) will take on as our "Storage Life on the Edge" webcast series continues. Join us on April 27, 2022 for “Storage Life on the Edge: Security Challenges” where I’ll be joined by security experts Thomas Rivera, CISSP, CIPP/US, CDPSE and Eric Hibbard, CISSP-ISSAP, ISSMP, ISSEP, CIPP/US, CIPT, CISA, CDPSE, CCSK as they explore these challenges and wade into the debate as to whether existing security practices and standards are adequate for this emerging area of computing. Our discussion will cover:

• Understanding the key security issues associated with edge computing
• Identify potentially relevant standards and industry guidance (e.g., IoT security)
• Offer awareness of new security initiatives focused on edge computing

Register today and bring your questions. Eric and Thomas will be on-hand to answer them. And if you’re interested in the other “Storage Life on the Edge” presentations we’ve done. You can find them in the SNIA Educational Library.

The complex and changeable structure of edge computing, together with its network connections, massive real-time data, challenging operating environment, distributed edge cloud collaboration, and other characteristics, create a multitude of security challenges. It’s a topic the SNIA Networking Storage Forum (NSF) will take on as our “Storage Life on the Edge” webcast series continues. Join us on April 27, 2022 for “Storage Life on the Edge: Security Challenges” where I’ll be joined by security experts Thomas Rivera, CISSP, CIPP/US, CDPSE and Eric Hibbard, CISSP-ISSAP, ISSMP, ISSEP, CIPP/US, CIPT, CISA, CDPSE, CCSK as they explore these challenges and wade into the debate as to whether existing security practices and standards are adequate for this emerging area of computing. Our discussion will cover:

• Understanding the key security issues associated with edge computing
• Identify potentially relevant standards and industry guidance (e.g., IoT security)
• Offer awareness of new security initiatives focused on edge computing

Register today and bring your questions. Eric and Thomas will be on-hand to answer them. And if you’re interested in the other “Storage Life on the Edge” presentations we’ve done. You can find them in the SNIA Educational Library.

The confluence of 5G networks, AI and machine learning, industrial IoT, and edge computing are driving the fourth industrial revolution – Industry 4.0. The impact of the industrial edge and how it is being transformed were among the topics at our SNIA Cloud Storage Technologies Initiative (CSTI) webcast “5G Industrial Private Network and Edge Data Pipelines.” If you missed it, you can view it on-demand along with the presentation slides in the SNIA Educational Library. In this blog, we are sharing and clarifying answers to some of the intriguing questions from the live event. Q. What are some of the key challenges to support the agility and flexibility requirements of Industry 4.0? A. The fourth industrial revolution aka Industry 4.0 aspires to fundamentally transform the flexibility, versatility and productivity of future smart factories. Key attributes of this vision include complex workloads to enable remote autonomous operation, which involves autonomous mobile robots and machines, augmented reality aided connected workers, wireless sensors, actuators and remote supervisory control systems, as shown in the diagram below. Machines in smart factories will no longer be stationary. To enable quick response to supply demand changes and enable mass customization (“batch size of one”), factory lines need to be quickly reconfigurable and need machines to move within a certain range. These AI-based, mobile autonomous robots and machines require high data through-put wireless networks and highly reliable sub-second latency for machine-to-machine control communications.

Q. What are some of the new 5G capabilities that are important to enable Industry 4.0? A. Although cellular technology (2G through 4G) was primarily targeted to serve consumers via massive public networks, 5G enables standalone private networks and is designed to meet the needs of vertical industries. Not only does 5G provide faster data rates (up to 10x faster than 4G), but 5G also supports delivery of massive amounts of concurrent machine-to-machine connections. With 5G private networks, users can tune the network based on custom requirements of the factory. Providing enhanced design flexibility, network slicing establishes multiple logical/virtual networks to handle a wide variety of use cases, all coexisting on the same physical infrastructure. Here are a few of the transformational 5G developments, as shown in the diagram below.

• Enhanced Mobile Broadband (eMBB) supports extremely high data rates (up to several Gb/s) and offers enhanced coverage beyond existing networks
• Massive Machine Type Communication (mMTC) supports wide-area coverage, signal penetration through indoor structures, ubiquitous connectivity enabling hundreds of thousands of IoT devices per square kilometer and support for battery-saving low energy operation
• Ultra-reliable Low Latency Communications (URLLC) supports high reliability applications requiring low-latency end-to-end communications

Q. What does this all mean for storage? A. There is a huge shift now that 50% of data is being created and processed at the edge. It’s really putting us at a tipping point (as demonstrated by the chart below). By the time we get to the year 2040, it is projected that there will be 364 times the amount of storage growth at the edge compared to data centers. Our mission as storage professionals is to start looking at how we place our technology and how we think about data and data movement within our organizations.

The bottom line: Storage and data strategies must include the edge.

The second webcast in our Storage Life on the Edge series is coming up on March 22, 2022 at 10:00 am Pacific time.  This panel, moderated by Bill Martin, SNIA Compute, Memory, and Storage Initiative Chair, takes a deeper dive to focus on edge use cases in the computational storage space. Our panelists Mayank Saxena from Sansung, Stephen Bates from Eideticom, and Tong Zhang from ScaleFlux will discuss edge to cloud use cases where storage and compute resources need to be deployed in practical topologies that deliver the very best in application performance. They’ll examine high performance edge data needs, database acceleration solutions, meeting retail chain challenges, and more. You won’t want to miss their panel discussion and the chance to ask your questions live. Register here to attend. We’ll look forward to seeing you! The post Our Storage Life on the Edge Webcast Series Continues…. first appeared on SNIA Compute, Memory and Storage Blog.

The SNIA Networking Storage Forum (NSF) kicked off our “Storage Life on the Edge” webcast series with a session on managing data from the edge to the cloud and back. We were fortunate to have a panel of experts, Dan Cummins, John Kim and David McIntyre to explain key considerations when managing and processing data generated at the edge. If you missed this introductory session, it’s available on-demand, along with the presentation slides at the SNIA Educational Library.

Our presenters spent a good percentage of time answering questions from our live audience. Here are answers to them all.

Q. Could an application be deployed simultaneously at near-edge, far edge and functional edge?

A. [Dan] Many of the applications are the outcomes that customers need depending on the vertical market; whether that's manufacturing, retail or and gas. They require processing that's distributed at each of these locations so absolutely if we go back to that computer vision

use case you can see that part of the application or the outcome includes an IoT stack that is deployed at the far right. That's ingesting the data from the cameras (and/or sensors) as well as an AI/ML streaming framework that in runtime is deployed to process the model at the near edge. Also, applications do the retraining up in the cloud. So, yes absolutely many of the outcomes actually are distributed applications that are deployed simultaneously across the edge, the core, and the cloud.

Q. Can the cloud ever be considered to be at the edge?

A. [Dan] “The edge” has a different meaning to many people. A cloud is an edge. One of the trends that we're seeing is what's called the “functional edge” or some people like to refer to that as the “IoT edge,” and then you have the “far edge” and then something we defined as a “mirror edge,” (a coordinated center in a cloud), but that cloud is an edge. Now, what we're seeing is that the onset of private wireless or 5G for example has the ability to be able to connect that far edge or that IoT edge directly to a cloud or directly to a data center, but each of those eliminates the edge computing locations in between. You can think of it like an always-on world with the speed and the bandwidth that you would get with 5G, as it becomes ubiquitous and allows you to connect processing in a cloud or core data center directly to the IoT edge which is pretty compelling, but yes, cloud is an edge.

Q. If I’m using a tablet inside a connected car where is the edge? Is it the tablet, the car or a nearby cellular base station?

A. [John] All of those could be different parts of the edge. The tablet could be the functional edge, and the car may also be the functional edge because they both have a sort of constricted or restricted domain in terms of the hardware which is fairly fixed. You can update the software and use it as your fairly dedicated functional processes, which don't really have any other applications going on. And then the cellular base station could probably be considered the far edge and you could also have a telco office acting as a traffic processing center or small data center that could be the near-edge. Or this information from the functional and far edge could then flow into the cloud and the cloud could be that near-edge data center before some of the data ultimately goes back to a core data center that's run by the enterprise or hosted in a colocation facility.

[Dan] There is no one edge. What we're really talking about is edge compute or where does processing of data take place and it takes place everywhere and the applications are the outcomes that you need for that processing. If you're in manufacturing, you need overall equipment effectiveness. If you’re in retail you need fraud detection. Where to produce that outcome, you're going to need to be able to operate in multiple locations and so I really would define edge as the point where data is being acted on by edge compute.

Q. How do edge storage needs differ from cloud or data center storage needs?

A. [Dan] We touched a little bit on this. I was trying to convey that depending on the location, much of the data that's generated from the IoT edge is mostly streaming data and they have to get it to a point where they can process the data. The streaming architectures are prevalent because as you're transporting data between locations, processed data could have an intermittent connectivity or a low bandwidth situation so typically you see either a streaming data architecture or some sort of architecture that can handle that disconnect and then re-establish and continue. Most of the data that's coming in at the far edge is usually because of the streaming. It’s a store forward and most of it is unstructured. When you start to get into upstream, where you need to do more with the data like that near edge, I had explained that you have kind of a mix of both these edge workloads which is working on this unstructured data, as well as a mix of structured data for business applications. So, you have a mix of edge and IT workloads. All of those are in that data processing pipeline that is needed to provide a near real-time response. It's not really out of band data, it's in-band data and then usually with a core data center or cloud is where you're usually going to be operating on data that is out of band that requires deep storage. So, the data center will continue to have deep storage as well as the cloud where you need to expand and you need longer term storage for in-home or for training models and things like that. Typically, the further you go up the edge, locations all the way up to the core, the more storage that you're going to need.

[David] One needs to be concerned from an application standpoint on a balancing of compute and storage resources or memory resources as well. So, latency inherent delays especially as performance requirements increase with applications require localized compute and storage resources at the point of creation of the data. The heavy lift of processing will still be done at the cloud where you can balance out racks and racks of compute resources along with arrays and racks of solid-state drives. However, as we expand out to the edge having point compute and storage resources that are tailored for specific applications perhaps we should call them edge aggregation points, basically collecting all that IoT data and you want to provide some level of real-time processing and analytics and decision-making out in the field, having those aggregation points allows you to do so. The other part of this, is how to optimize the performance against that data through caching, through providing persistent memory layer or higher performance storage flash memory. That's actually worth another discussion at a separate time. But you can start getting deep on how to optimize compute and storage resources and memory resources at the edge.

[Dan] One thing that is not obvious to folks trying to build out edge solutions is that customers care very much about cost. If you take a look at the amount of compute with the growth of compute at the edge, there's in aggregate more compute at the edge than there is in a core data center or cloud and if you want to reduce transport fees or if you want to reduce infrastructure sprawl you really want to be able to act on that data near the point of generation. John talked about how you would distribute the edge processing for AI and ML out to the edge. Doing so helps you filter the data so you don't have to move all the data to a cloud or core data center, therefore reducing your infrastructure sprawl and also reducing your cost for transport. You get the added benefit of more of a real-time response. This is why you see new technologies that are coming out that promote acting on data near the point of generation. If you take a look at AWS lambda functions, for example, or even some of the data management applications that are basically tagging the data as it comes in at the edge and they're caching it at the edge. Then they're using a centralized repository or distributed ledger where somebody can query that ledger and then distribute that query out to where the data exists.

Q. With that topic in mind does AI training ever happen at any of the edge points or is this only reserved for cloud?

A. [John] The traditional answer would be no. AI training only happens either in the core data center or in a cloud data center and at the edge you only have inference. However, I don't think that's completely true now. That's generally still true, because the training requires the most compute power, the most CPUs or GPUs, the most storage, and networking bandwidth, but I think increasingly there is more and more AI training that can happen or is happening out there beyond the core data centers and clouds, especially at near edge or the far edge.

If you're training your phone to recognize your fingerprint or your face, I’m not sure if all of that has to go back to the data center in order for the training models to be done. Everyone knows that the actual inference for face or fingerprint recognition once you’ve trained it, is done completely on the phone—it doesn’t need to contact the cloud or core data centers to do that. Many of these phones have small GPUs built into their chipset and they can recognize your fingerprint interface even if they don't have any connectivity going at all - no network connectivity. But I would say traditionally, most or all the training was in the data center. But some of it has moved out to the near edge or the far edge.

[Dan] The only thing I would add on top of that is some customers are disconnected from public clouds. Especially some government and even some retailers. They have their own local data centers and they do a form of federated learning in their edges.

Q. I believe there are other applications but we're just talking about AI here. What are some of these other applications besides artificial intelligence that are used in this environment?

A. [Dan] The big one would be streaming analytics that's non-video to preserve safety or to preserve production or to take action. You want to take action where the data is being generated. In manufacturing we see this quite a bit where a manufacturing system is taking telemetry in from a set of sensors running analytics on it and then modifying their action based on those analytics. With respect to storage that's very small unstructured amounts of data that's highly compressible and doesn't require a lot of storage processing. But yes, real-time analytics.

[David] AI can encompass video stream and camera captures for security purposes and that’s an additional application for smart cities and any deployment or mass deployment of video for security. Another one that is interesting is genomic sequencing where instead of sending the batch data up to the cloud for processing it can actually be done localized to the doctor's office. That's an emerging trend, where we're seeing a tremendous amount of interest especially for analyzing in near real time patient data and keeping that data private and localized where decision making can be made to benefit that patient versus sending that data across the network.

[John] I would say there are a lot of apps. The most famous apps that we've talked about are AI or use AI, but there are a lot of other apps that run at the edge. A lot of them are for accessing information, sharing information, or otherwise utilizing information. For people it could be as simple as navigation which may include some AI elements, but navigation by itself does not necessarily use AI for the basic navigation, nor do the shopping apps for entering information ordering food. These are all things that can run partly at the edge. Other examples would include doing diagnostics, such as automotive diagnostics, factory diagnostics, or robot diagnostics, or social media apps. Those are things with edge apps that may or may not use AI at the edge, though they often still use AI at the core or in the cloud.

Q. We're seeing a lot of movement towards repatriation of apps from cloud to edge data centers or even far edge compute locations. Do you think part of that repatriation is being driven by not getting the storage locations right and are we perhaps aiming at the wrong problem by repatriating the app to an edge?

A. [Dan] The fundamental reason people are repatriating their edge applications is to get that processing near the point of data generation to improve overall response. Now the second half of that, is the way that applications were developed 10 years ago is completely different than applications developed today. You have a cloud native microservices container-based application environment with rich APIs and some sort of DevOps pipeline for delivery and continuous integration. The rise of containers and virtualization in cloud native application architectures are making it easier to repatriate as well, right? So, I think it's both those things.

Q. Do you ever see CapEx versus OpEx as part of that decision making as well?

A. [Dan] Absolutely 110% and that's the point that I was trying to make earlier. There are two things I kept saying throughout this webcast. The first is don't overlook generating real-time responses. Work for your outcomes is obviously important, but customers are running businesses. The second is they're looking for ways to reduce costs. So, if you're pushing your processing out to your edge you're doing a number of things. You're actually reducing CapEx because you're now filtering the data or doing all the local processing and making decisions locally and taking actions locally and reducing the infrastructure for shipping all that data up to some centralized location. That reduces your capital expenditures because it's reducing your infrastructure sprawl.

In terms of OpEx and making it simple, that's a more complicated response. But reducing operational expenses comes in many forms. At the edge is one of them. It could be through how do you manage your applications through the edge. Leverage of containers and Kubernetes for example, we see the hyperscalers like Amazon, Azure and Google, AKS EKS and GKE with these managed Kubernetes services in multi-cluster management they can repatriate those container applications and move them using the same common tool sets to the edge. So, things like that help reduce OpEx.

[John] I think a lot of the movement to the cloud and then the subsequent repatriation has to do with balancing of OpEx and CapEx. A lot of people started out looking at CapEx, and move to the cloud where there's no CapEx, it's all OpEx, so initially it is much cheaper for your first year or two to move things to the cloud because you're saying “I don't have to buy these servers, I just pay monthly for what I’m using.” But then after you either build up enough data or you have enough traffic or enough compute power or enough data ingress and egress, then the monthly charges add up and grow as you grow the amount of data or compute. And then suddenly people look and say “wow, if I could repatriate this data and build a relatively efficient infrastructure on premises, the total cost of CapEx and OpEx combined would be lower than keeping it in the public cloud.” There are also some security or privacy concerns because you can say well in the cloud perhaps, I can't control which country it's in or which data center. I can't prove who has access or who doesn't have access so that's another reason to possibly repatriate.

[Dan] This is something that's often overlooked. I told the story earlier where we were talking to a customer who has self-driving vehicles. They took a cloud-first strategy where they were doing all of their inferencing. So, they're collecting all the sensor information from the vehicle, including the video and shipping that to the cloud doing the infrastructure in the cloud, then they’re processing and inferencing from the cloud back down to the edge. We said to them “that's going to cost you a lot of money” and they said “yes and it costs a lot of bandwidth for us to send all this video upstream too.”  So, what they are having to do is transcode their video to a lower frame rate so that they could save on transport fees. We convinced them they should probably take a hybrid approach. You still do training and everything up in the cloud, but move your inferencing on board with something you can use to filter the data. That way you don't have to re-transcode the data so that you can maintain the fidelity of your video images because you're only going to be sending about 30 percent of that upstream and if you're going to send it upstream since you're over a cellular network why don't you send that to some co-location provider or local data centers where you have more points of presence. We want to look at helping design solutions for their age, but really take a look at how they improve their business outcomes, while also reducing CapEx and OpEx.

Q. Is the edge inherently less secure than the data center?

A.  [Dan] If you take a look at the compute outside the data that are not protected by the whole data center then inherently it is less secure. I read an article where it said 30% of all security breaches are at the far edge or through some external port. So, this is infrastructure that can be moved to a room, it could be spoofed, it could be tampered with. When you're deploying edge compute outside the walls of an IT data center, out there in the wild, you really need to pay attention to zero trust architectures. Around how do I provide my hardware attestation as well as software attestation. Can I provide cryptographic network isolation, protected transports and everything else? It is definitely a top concern.

Remember I said this was a series? I encourage you to register for next two live Storage Life of the Edge webcasts:

• March 22, 2022: Storage Life on the Edge: Use Cases
• April 27, 2022: Storage Life on the Edge: Security Challenges

We hope to see you there!

The SNIA Networking Storage Forum (NSF) kicked off our “Storage Life on the Edge” webcast series with a session on managing data from the edge to the cloud and back. We were fortunate to have a panel of experts, Dan Cummins, John Kim and David McIntyre to explain key considerations when managing and processing data generated at the edge. If you missed this introductory session, it’s available on-demand, along with the presentation slides at the SNIA Educational Library. Our presenters spent a good percentage of time answering questions from our live audience. Here are answers to them all. Q. Could an application be deployed simultaneously at near-edge, far edge and functional edge? A. [Dan] Many of the applications are the outcomes that customers need depending on the vertical market; whether that’s manufacturing, retail or and gas. They require processing that’s distributed at each of these locations so absolutely if we go back to that computer vision use case you can see that part of the application or the outcome includes an IoT stack that is deployed at the far right. That’s ingesting the data from the cameras (and/or sensors) as well as an AI/ML streaming framework that in runtime is deployed to process the model at the near edge. Also, applications do the retraining up in the cloud. So, yes absolutely many of the outcomes actually are distributed applications that are deployed simultaneously across the edge, the core, and the cloud. Q. Can the cloud ever be considered to be at the edge? A. [Dan] “The edge” has a different meaning to many people. A cloud is an edge. One of the trends that we’re seeing is what’s called the “functional edge” or some people like to refer to that as the “IoT edge,” and then you have the “far edge” and then something we defined as a “mirror edge,” (a coordinated center in a cloud), but that cloud is an edge. Now, what we’re seeing is that the onset of private wireless or 5G for example has the ability to be able to connect that far edge or that IoT edge directly to a cloud or directly to a data center, but each of those eliminates the edge computing locations in between. You can think of it like an always-on world with the speed and the bandwidth that you would get with 5G, as it becomes ubiquitous and allows you to connect processing in a cloud or core data center directly to the IoT edge which is pretty compelling, but yes, cloud is an edge. Q. If I’m using a tablet inside a connected car where is the edge? Is it the tablet, the car or a nearby cellular base station? A. [John] All of those could be different parts of the edge. The tablet could be the functional edge, and the car may also be the functional edge because they both have a sort of constricted or restricted domain in terms of the hardware which is fairly fixed. You can update the software and use it as your fairly dedicated functional processes, which don’t really have any other applications going on. And then the cellular base station could probably be considered the far edge and you could also have a telco office acting as a traffic processing center or small data center that could be the near-edge. Or this information from the functional and far edge could then flow into the cloud and the cloud could be that near-edge data center before some of the data ultimately goes back to a core data center that’s run by the enterprise or hosted in a colocation facility. [Dan] There is no one edge. What we’re really talking about is edge compute or where does processing of data take place and it takes place everywhere and the applications are the outcomes that you need for that processing. If you’re in manufacturing, you need overall equipment effectiveness. If you’re in retail you need fraud detection. Where to produce that outcome, you’re going to need to be able to operate in multiple locations and so I really would define edge as the point where data is being acted on by edge compute. Q. How do edge storage needs differ from cloud or data center storage needs? A. [Dan] We touched a little bit on this. I was trying to convey that depending on the location, much of the data that’s generated from the IoT edge is mostly streaming data and they have to get it to a point where they can process the data. The streaming architectures are prevalent because as you’re transporting data between locations, processed data could have an intermittent connectivity or a low bandwidth situation so typically you see either a streaming data architecture or some sort of architecture that can handle that disconnect and then re-establish and continue. Most of the data that’s coming in at the far edge is usually because of the streaming. It’s a store forward and most of it is unstructured. When you start to get into upstream, where you need to do more with the data like that near edge, I had explained that you have kind of a mix of both these edge workloads which is working on this unstructured data, as well as a mix of structured data for business applications. So, you have a mix of edge and IT workloads. All of those are in that data processing pipeline that is needed to provide a near real-time response. It’s not really out of band data, it’s in-band data and then usually with a core data center or cloud is where you’re usually going to be operating on data that is out of band that requires deep storage. So, the data center will continue to have deep storage as well as the cloud where you need to expand and you need longer term storage for in-home or for training models and things like that. Typically, the further you go up the edge, locations all the way up to the core, the more storage that you’re going to need. [David] One needs to be concerned from an application standpoint on a balancing of compute and storage resources or memory resources as well. So, latency inherent delays especially as performance requirements increase with applications require localized compute and storage resources at the point of creation of the data. The heavy lift of processing will still be done at the cloud where you can balance out racks and racks of compute resources along with arrays and racks of solid-state drives. However, as we expand out to the edge having point compute and storage resources that are tailored for specific applications perhaps we should call them edge aggregation points, basically collecting all that IoT data and you want to provide some level of real-time processing and analytics and decision-making out in the field, having those aggregation points allows you to do so. The other part of this, is how to optimize the performance against that data through caching, through providing persistent memory layer or higher performance storage flash memory. That’s actually worth another discussion at a separate time. But you can start getting deep on how to optimize compute and storage resources and memory resources at the edge. [Dan] One thing that is not obvious to folks trying to build out edge solutions is that customers care very much about cost. If you take a look at the amount of compute with the growth of compute at the edge, there’s in aggregate more compute at the edge than there is in a core data center or cloud and if you want to reduce transport fees or if you want to reduce infrastructure sprawl you really want to be able to act on that data near the point of generation. John talked about how you would distribute the edge processing for AI and ML out to the edge. Doing so helps you filter the data so you don’t have to move all the data to a cloud or core data center, therefore reducing your infrastructure sprawl and also reducing your cost for transport. You get the added benefit of more of a real-time response. This is why you see new technologies that are coming out that promote acting on data near the point of generation. If you take a look at AWS lambda functions, for example, or even some of the data management applications that are basically tagging the data as it comes in at the edge and they’re caching it at the edge. Then they’re using a centralized repository or distributed ledger where somebody can query that ledger and then distribute that query out to where the data exists. Q. With that topic in mind does AI training ever happen at any of the edge points or is this only reserved for cloud? A. [John] The traditional answer would be no. AI training only happens either in the core data center or in a cloud data center and at the edge you only have inference. However, I don’t think that’s completely true now. That’s generally still true, because the training requires the most compute power, the most CPUs or GPUs, the most storage, and networking bandwidth, but I think increasingly there is more and more AI training that can happen or is happening out there beyond the core data centers and clouds, especially at near edge or the far edge. If you’re training your phone to recognize your fingerprint or your face, I’m not sure if all of that has to go back to the data center in order for the training models to be done. Everyone knows that the actual inference for face or fingerprint recognition once you’ve trained it, is done completely on the phone—it doesn’t need to contact the cloud or core data centers to do that. Many of these phones have small GPUs built into their chipset and they can recognize your fingerprint interface even if they don’t have any connectivity going at all – no network connectivity. But I would say traditionally, most or all the training was in the data center. But some of it has moved out to the near edge or the far edge. [Dan] The only thing I would add on top of that is some customers are disconnected from public clouds. Especially some government and even some retailers. They have their own local data centers and they do a form of federated learning in their edges. Q. I believe there are other applications but we’re just talking about AI here. What are some of these other applications besides artificial intelligence that are used in this environment? A. [Dan] The big one would be streaming analytics that’s non-video to preserve safety or to preserve production or to take action. You want to take action where the data is being generated. In manufacturing we see this quite a bit where a manufacturing system is taking telemetry in from a set of sensors running analytics on it and then modifying their action based on those analytics. With respect to storage that’s very small unstructured amounts of data that’s highly compressible and doesn’t require a lot of storage processing. But yes, real-time analytics. [David] AI can encompass video stream and camera captures for security purposes and that’s an additional application for smart cities and any deployment or mass deployment of video for security. Another one that is interesting is genomic sequencing where instead of sending the batch data up to the cloud for processing it can actually be done localized to the doctor’s office. That’s an emerging trend, where we’re seeing a tremendous amount of interest especially for analyzing in near real time patient data and keeping that data private and localized where decision making can be made to benefit that patient versus sending that data across the network. [John] I would say there are a lot of apps. The most famous apps that we’ve talked about are AI or use AI, but there are a lot of other apps that run at the edge. A lot of them are for accessing information, sharing information, or otherwise utilizing information. For people it could be as simple as navigation which may include some AI elements, but navigation by itself does not necessarily use AI for the basic navigation, nor do the shopping apps for entering information ordering food. These are all things that can run partly at the edge. Other examples would include doing diagnostics, such as automotive diagnostics, factory diagnostics, or robot diagnostics, or social media apps. Those are things with edge apps that may or may not use AI at the edge, though they often still use AI at the core or in the cloud. Q. We’re seeing a lot of movement towards repatriation of apps from cloud to edge data centers or even far edge compute locations. Do you think part of that repatriation is being driven by not getting the storage locations right and are we perhaps aiming at the wrong problem by repatriating the app to an edge? A. [Dan] The fundamental reason people are repatriating their edge applications is to get that processing near the point of data generation to improve overall response. Now the second half of that, is the way that applications were developed 10 years ago is completely different than applications developed today. You have a cloud native microservices container-based application environment with rich APIs and some sort of DevOps pipeline for delivery and continuous integration. The rise of containers and virtualization in cloud native application architectures are making it easier to repatriate as well, right? So, I think it’s both those things. Q. Do you ever see CapEx versus OpEx as part of that decision making as well? A. [Dan] Absolutely 110% and that’s the point that I was trying to make earlier. There are two things I kept saying throughout this webcast. The first is don’t overlook generating real-time responses. Work for your outcomes is obviously important, but customers are running businesses. The second is they’re looking for ways to reduce costs. So, if you’re pushing your processing out to your edge you’re doing a number of things. You’re actually reducing CapEx because you’re now filtering the data or doing all the local processing and making decisions locally and taking actions locally and reducing the infrastructure for shipping all that data up to some centralized location. That reduces your capital expenditures because it’s reducing your infrastructure sprawl. In terms of OpEx and making it simple, that’s a more complicated response. But reducing operational expenses comes in many forms. At the edge is one of them. It could be through how do you manage your applications through the edge. Leverage of containers and Kubernetes for example, we see the hyperscalers like Amazon, Azure and Google, AKS EKS and GKE with these managed Kubernetes services in multi-cluster management they can repatriate those container applications and move them using the same common tool sets to the edge. So, things like that help reduce OpEx. [John] I think a lot of the movement to the cloud and then the subsequent repatriation has to do with balancing of OpEx and CapEx. A lot of people started out looking at CapEx, and move to the cloud where there’s no CapEx, it’s all OpEx, so initially it is much cheaper for your first year or two to move things to the cloud because you’re saying “I don’t have to buy these servers, I just pay monthly for what I’m using.” But then after you either build up enough data or you have enough traffic or enough compute power or enough data ingress and egress, then the monthly charges add up and grow as you grow the amount of data or compute. And then suddenly people look and say “wow, if I could repatriate this data and build a relatively efficient infrastructure on premises, the total cost of CapEx and OpEx combined would be lower than keeping it in the public cloud.” There are also some security or privacy concerns because you can say well in the cloud perhaps, I can’t control which country it’s in or which data center. I can’t prove who has access or who doesn’t have access so that’s another reason to possibly repatriate. [Dan] This is something that’s often overlooked. I told the story earlier where we were talking to a customer who has self-driving vehicles. They took a cloud-first strategy where they were doing all of their inferencing. So, they’re collecting all the sensor information from the vehicle, including the video and shipping that to the cloud doing the infrastructure in the cloud, then they’re processing and inferencing from the cloud back down to the edge. We said to them “that’s going to cost you a lot of money” and they said “yes and it costs a lot of bandwidth for us to send all this video upstream too.”  So, what they are having to do is transcode their video to a lower frame rate so that they could save on transport fees. We convinced them they should probably take a hybrid approach. You still do training and everything up in the cloud, but move your inferencing on board with something you can use to filter the data. That way you don’t have to re-transcode the data so that you can maintain the fidelity of your video images because you’re only going to be sending about 30 percent of that upstream and if you’re going to send it upstream since you’re over a cellular network why don’t you send that to some co-location provider or local data centers where you have more points of presence. We want to look at helping design solutions for their age, but really take a look at how they improve their business outcomes, while also reducing CapEx and OpEx. Q. Is the edge inherently less secure than the data center? A.  [Dan] If you take a look at the compute outside the data that are not protected by the whole data center then inherently it is less secure. I read an article where it said 30% of all security breaches are at the far edge or through some external port. So, this is infrastructure that can be moved to a room, it could be spoofed, it could be tampered with. When you’re deploying edge compute outside the walls of an IT data center, out there in the wild, you really need to pay attention to zero trust architectures. Around how do I provide my hardware attestation as well as software attestation. Can I provide cryptographic network isolation, protected transports and everything else? It is definitely a top concern. Remember I said this was a series? I encourage you to register for next two live Storage Life of the Edge webcasts:

• March 22, 2022: Storage Life on the Edge: Use Cases
• April 27, 2022: Storage Life on the Edge: Security Challenges

We hope to see you there!