Three Industry Firsts: How HPE ProLiant Gen13 Sets a New Server Standard

More drives, memory, and GPUs now sit in each server, so one mistake or one failure carries a higher cost. That makes always-on security and reliability increasingly critical as infrastructure density increases.

On the road to HPE Discover Barcelona 2026, Patrick Moorhead, CEO and Chief Analyst at Moor Insights & Strategy, and Daniel Newman, CEO of The Futurum Group, are joined by Krista Satterthwaite, SVP and GM of HPE Compute at HPE. They discuss how HPE built security, intelligent management, flexibility, and reliability into ProLiant Gen13.

HPE describes three iLO 8 security advances as industry firsts, based on its own competitive research: automatic self-encrypting drive protection from first boot, multi-person authorization for high-impact actions, and post-quantum cryptography that extends beyond firmware. Satterthwaite says the aim is to automate protection so IT teams have fewer things to remember, since so much data center risk comes from human error. For ongoing operations, HPE Compute Ops Management gives centralized visibility across a fleet wherever it sits.

Key Takeaways Include:

🔹 Automated security reduces the risk of human error. Satterthwaite explains how iLO 8 verifies components, including third-party hardware, requires two-person approval for critical changes, expands quantum-resistant protections, and automatically enables self-encrypting drive security without relying on manual configuration.

🔹 Centralized management makes it easier to keep servers up to date. Updates often get delayed because they're difficult to manage. HPE Compute Ops Management provides visibility across server fleets, regardless of location, and allows partners to manage systems remotely. Satterthwaite cites an HPE-commissioned Forrester Total Economic Impact study that modeled an 80% reduction in unplanned downtime and a 209% ROI for a composite organization.

🔹 Four new platforms address different compute requirements. Built on AMD EPYC 9006 processors, the lineup includes the dense 1U DL525 for AI workloads, the eight-GPU DL585a for agentic AI, and a 2U enclosure that supports either four dense servers or two HPC-focused servers for workloads such as EDA. Satterthwaite emphasizes that no two data centers have the same requirements.

🔹 Higher server density raises the stakes for reliability. As more drives, memory, and GPUs are packed into each server, a single failure can have greater consequences. Satterthwaite notes that 81% of surveyed customers cite reliability as their primary reason for choosing ProLiant. HPE backs that focus with more than 1,000 tests and 10,000 hours of testing for each generation.

‍

Automating protection, centralizing operations, and testing for reliability reduces the number of things IT teams have to remember as server density and AI workloads grow.

Watch the full video at sixfivemedia.com, and subscribe to our YouTube channel so you never miss an episode.

Learn more about HPE.

Disclaimer: Six Five Media is for information and entertainment purposes only. Over the course of this video, we may discuss companies that are publicly traded, and we may reference their equity share prices. Nothing discussed during this webcast should be considered investment advice or a recommendation to buy or sell any security. We are not investment advisors, and you should not rely on this content as financial advice. Six Five Media collaborates with technology companies and industry leaders to produce research-driven interviews and multimedia programming for enterprise technology audiences.

Patrick Moorhead:

Hey everybody, welcome to Six FIve On The Road. I'm Patrick Moorhead here with Daniel Newman, my bestie. We are On The Road, headed to HPE Discover Barcelona. And Daniel, as we have seen, as AI scales, the servers underneath have to do a lot more than just run fast. And quite frankly, they're doing a lot more things than I think three years ago we thought it would do. I'm here with Krista Satterthwaite, SVP and GM, HPE Compute, and longtime Six Five guests, which we super appreciate. Great to see you, Krista.

‍

Krista Satterthwaite:

Great to see you, too. Thanks for having me.

‍

Daniel Newman:

Yeah, good to have you back. Road to Discover is here, and I'm sure you are. You know, I think I said to one of your colleagues recently, I said, you know, it's always amazing with big, big companies when you have these big tentpole events. It is the whole world within that company for like a month. It's like we can't do anything because we're planning for Discover. It's like, obviously there are people behind the scenes keeping all the lights on, but there's like a whole cohort of people that the whole world is just the event. So this is going to be a big one. I'm sure Six Five is excited. Yeah, 6.5 is excited to be there. We love heading out, and the team loves being in Barcelona. What Pat was saying, though, about scaling AI- let's start there. Infrastructure is becoming more and more critical. It's becoming more complicated to secure and protect. And of course, the right technology can still be exposed to human error. How is that sort of shaping how you're thinking about building your ProLiant Gen13?

‍

Krista Satterthwaite:

Yeah. So with ProLiant Gen13, now, you know, we've had a big focus on security for many, many, many years. We've talked about it many times, and we feel like we have a real advantage there. And this generation, what we wanted to do was make it easier for people, easier, more automated. So there's a few things that we introduced. Number one, when it comes to our latest iLO, iLO 8, it actually does more component verification. That means if you put something in the server, iLO is going to make sure that that's supposed to be in the server. And we're doing that not just for components that we have, but also third-party components. So that's number one. Number two is if there's something very serious that gets changed, it requires two people to change it. So that helps when it comes to mistakes or someone who's doing something that they shouldn't be doing. So we're excited about that because so much is human error when it comes to issues in the data center. Number three, we've been working on quantum protection. We've expanded that quantum protection in this generation. And then also with our drives, SED drives, that is going to be turned on automatically. That security is going to be turned on automatically in this generation. So no one has to remember to turn on that protection. So we're trying to make it a little easier, a little bit more automated for people so that it's, you know, there's a million things for IT to worry about. And we were trying to take some of those things off of their plate.

‍

Patrick Moorhead:

Yeah, it's been great, Krista, to watch what you've been doing with security. It's funny, I can even track back to probably 2009, but we won't go all the way back there. But most recently, I was on stage for the announcement of Gen 12, talking about your security. We did some research. For you as well. So really leading with security as a spike feature. But beyond getting security right at deployment, how do you keep that going? Once they're installed and productive, and in multiple years, the fleet is working. How do you make that easier for them to keep up with everything that they need to, because the outside world is changing even faster now than it did 10, 20, 3 years ago?

‍

Krista Satterthwaite:

Yeah, well, managing infrastructure can be a challenge. So we want to make that easier to and more automated. And we've got HPE ComputeOps management for that. It can see everything, no matter where it is in the world. And you can control things from very centrally. We're excited because we just had a study which we interviewed the people that are using our HPE ComputeOps management. And they reported to us they're seeing an 80% reduction in unplanned downtime. They keep things up to date. It's much easier to keep things up to date. It's funny because when people don't keep things up to date, the reason why they don't is because it's too hard to do. This makes it easier. And also, they're seeing a 209 percent return on investment. One of the things that even our partners are telling us is that it's easier for them to manage things on their customers' behalf because they can do so much more remotely. They don't have to travel to get things done, and they can see it faster. And when you can see it faster, you can intercept it faster. So we're excited about that. And we know that too much time is spent managing infrastructure, and we're tackling that, making sure that we're saving them time.

‍

Daniel Newman:

Pat, did you do that study, or maybe I did that study? Yeah, you may have. We never miss a chance, Chris, to do a little sliding, a little promo for something we may have done, or take credit for something we may not have. So as those teams, as the support becomes more demanding, there's more AI, there's more business applications, and now you've got power, cooling, space, all these constraints. What is the optionality that this new generation gives customers as they grow?

‍

Krista Satterthwaite:

Yeah, so in this generation, we launched four brand new platforms and brand new, meaning they've never been done before. And part of the reason for that is because everyone's data center looks different. What they're trying to do with it is different than they've done before. So the four platforms we have: we have a DL 525, which is an AI-targeted platform. It's very dense. It's only one GPU. We've got a 585A, which is much larger and accepts eight GPUs and great for agentic AI. And then we have an extremely dense solution, which accepts two different types of servers. It's a 2U enclosure, and it either accepts four very dense servers or two servers. And that's for HPC. So think EDA. And those are all leveraging AMD EPYC's 9006 series processors that just announced.

‍

Patrick Moorhead:

So Krista, one of the attributes that goes back to probably the first server mainframe mini, I mean, it's about reliability, right? And the definition of reliability, and whether we want to call this the agentic age or whatever, how has this definition of reliability- just customers needed to get all their work done, has that changed? And if it has, how has it changed?

‍

Krista Satterthwaite:

Yeah, what I would say is that it's amazing how much people are putting in one server these days. So there's a lot of eggs in one basket.

‍

Patrick Moorhead:

Density.

‍

Krista Satterthwaite:

Yes, density, the number of drives, how much memory they're putting in, how many GPUs they're putting in. So there's a lot in every server and more and more. And so what happens is it becomes more critical to stay up and running. And ProLiant has been known for reliability for a long time. As a matter of fact, year after year after year, we survey our customers, and they 81% tell us that reliability is the main reason they buy ProLiant and that it's one of our key differentiators. So we do over a thousand tests for every generation and over 10,000 hours of testing. So we make sure that we're comfortable with it. And it's funny, years ago, I was a product manager, and I went out, and I would talk to customers, and I'd interview them, and I'd say, okay, rate how important performance is, rate how important efficiency is, rate how important reliability is. And one of the customers just stopped me, and he said, Without that, none of this other stuff matters. And that's what we're, you know, that's what we see more and more and more, because more and more is being put into these servers.

‍

Patrick Moorhead:

Yeah, Dan, I'm going to flex again.

‍

Daniel Newman:

Reliability matters. I mean, it's why HPE has the market position it has in servers. It's, you know, kind of as a joke, Pat; it's kind of why mainframes never really go away. You know, it's like in certain instances, people really care. Does this thing work all the time? And That's been a big part of what's helped build your business. I did want to make a joke on the way out about your 10,000 hours, because I was like, hey, that server's got 10,000 hours. I'm like, so can it speak a few languages now or master? They say about that. But it was a little late to the joke, but I was still insistent on trying to find a way to squeeze it in here before I said goodbye. But I just want to thank you so much. It's been a lot of fun having you on. You are becoming a bit of a regular. You know, I hope the fame and fortune that comes with being on the six five is is paying off really well. And we appreciate you chatting with us all the time. Of course, the road to HPE Discover Barcelona is just ahead of us. And we're going to have a lot more coverage coming there from the show floor. So be part of our community. Hit subscribe. Follow us on all the channels. And of course, check out our coverage on Six Five media dot com. See you next time. 

,