Data Centre


Superdome X gets pumped on Skylake to become Superdome Flex

HPE's big honking server and memory box

By Chris Mellor


HPE has upgraded its Superdome X server to use Skylake CPUs, bragging that it's the world's most scalable and modular in-memory computing platform.

Superdome is HP's line of mission-critical, highly available servers that used Intel Itanium processors and have moved to using Xeons. The Superdome X takes x86 Xeon E7 v4 CPUs.

Superdome Flex is an x86-based system, not an Itanium one. The thing comes in a 5U enclosure, which supports four sockets and 6TB of memory (64GB DIMMS).

Superdome Flex

But only configurations of one or two chassis are supported at the initial release.

It has a modular design featuring:

Superdome Flex 4-socket blade

The processors are from the Xeon Platinum and Gold families, with up to 28 cores per socket. Processor cache ranges from 16.6MB, through 19.25MB and 24.75MB to 38.5MB. There are 48 DIMM slots of memory per chassis and 12 DIMMS per CPU.

For networking it has 2 x 10 GbitE ports per chassis and 2 x 1 GbitE ports per chassis. A chassis has four drive bays, 16 x PCIe slots and four USB ports.

Every Superdome Flex system starts with one 4-socket Base Chassis (with boot support). An Expansion Chassis can be added to expand the system from 4-sockets to 8.

There are are two focused markets; in-memory databases, such as SAP HANA, Oracle Database In-Memory and Microsoft SQL Server, and real-time analytics. HPE says approximately 50 per cent of all SAP HANA server deployments are on HPE systems.

It claims that Superdome Flex is the highest performing platform on the 16P two-tier SAP Sales and Distribution (SD) standard application benchmark. It has, HPE says, a 45 per cent lower TCO than Oracle Exadata and a 41 per cent lower one than IBM POWER.

Get specs here. Superdome Flex comes with a three-year warranty and is available now. There is no word on pricing. ®

Sign up to our NewsletterGet IT in your inbox daily


More from The Register

Architects? Power-hungry GPU fiends? HP has something for you

Venerable PC maker emits bunch of graphics powerhouses

After Microsoft calls out HP Inc over stalled Windows 10 logins, HP bounces back with a fix

Shove this tool into your PC if it's getting stuck during startup

Nvidia adds nine nifty AI supercomputing containers to the cloud

Now you can splash out on tons of GPUs if you really need to

AI caramba! Nvidia devs get a host of new kit to build smart systems

Kubernetes for GPUs, a PyTorch extension, TensorRT 4, and much, much more

'Self learning' Intel chips glimpsed, Nvidia emits blueprints, AMD and Tesla rumors, and more

AI roundup A quick guide to this week's reveals

Google ramping up AI in China, Nvidia's Titan V, Intel's hip-hop misstep

Roundup And more in your machine-learning news summary

AI, AI, Pure: Nvidia cooks deep learning GPU server chips with NetApp

Pure Storage's AIRI reference architecture probably a bit jelly

AMD, Intel hate Nvidia so much they're building a laptop chip to spite it

Analysis Just months after Chipzilla trashed its new best friend as an 'unreliable supplier'

Black screen of death after Win10 update? Microsoft blames HP

OEM factory images create 'incorrect registry keys'

Nvidia quickly kills its AMD-screwing GeForce 'partner program' amid monopoly probe threat

GPU giant rails against rumors of stiffing sellers