The development is called the SeaMicro SM10000-XE. Needless to say, it’s the first fabric-based Xeon microserver ever made.

It’s also supposed to be the most energy-efficient, highest-density, highest-bandwidth Xeon server now available, period.

A single SM10000-XE replaces 32 dual-socket servers, but draws half the power and takes up a third the space without any changes to operating systems, applications or management tools.

It eliminates layers of Ethernet switches, server management devices and expensive load balancers.

Because it’s Xeon-based it can run heavyweight scale out workloads while the Atom-based SM10000-HD is meant for the highly parallel workloads found in the web tier. That means that microservers can capture a bigger piece of the data center. SeaMicro says the microserver will go mainstream running Apache Hadoop, real-time analytics, Java apps, PHP, Memcached and NoSQL.

The widget is built around the Xeon E3-1260L based on Sandy Bridge architecture and Samsung’s new low-power 1.35V Green DDR3 DRAM memory. Since it’s breakthrough, Intel and Samsung were both at its launch Tuesday when SeaMicro CEO Andrew Feldman announced it was shipping in volume.

Microservers are all about density, space and power. The Xeon E3-1260L has a 45W TDP envelope, providing 30% better performance per watt than processors from Intel’s previous generation, and SeaMicro has invented a new technology called TIO, short for Turn It Off, that lets it power-optimize the parts by turning off unnecessary CPU and chipset functions.

The chip’s four cores run at 2.4GHz CPU core. The clock can be throttled to 3.3GHz with Intel’s Turbo Boost Technology 2.0 and it’ll support eight threads with Intel Hyper-Threading Technology.

The SM10000-XE contains 64 CPUs for 256 2.4GHz cores in a 10U or 1,024 cores in a standard rack. It delivers 10 gigabits of bandwidth to each quad-core processor, which SeaMicro says sets a high watermark for bandwidth per unit compute.

It supports up to 32GB of DRAM per socket for a system total of 2.04TB.

The processors are tied together by SeaMicro’s Freedom Supercompute Fabric, which delivers 12 times the bandwidth per unit compute of a traditional server.

The XE also supports up to 16 10-gigabit Ethernet uplinks or 64 one-gigE uplinks. And unlike other microservers, it can support up to 64 SATA hard disks or solid-state disks without reducing computational density.

SeaMicro’s boards are Spartan in their minimalism consisting of only the processor, Samsung’s DDR3 and SeaMicro’s new Fabric ASIC, reportedly the industry’s first second-generation fabric ASIC, capable of supporting both large cores like the Xeon’s and small cores like the Atom’s.

SeaMicro figures eventually it’ll be able to design systems using Atoms and Xeons together in the same enclosure.

The XE’s austerity derives from SeaMicro’s Input/Output Virtualization Technology which reduces the component count, shrinks the motherboard and reduces power, cost and space.

The Freedom Supercompute Fabric is built of multiple Freedom ASICs working together, creating a 1.28 terabits a-second fabric that ties together 64 of the power-optimized mini-motherboards at low latency.

Samsung’s small high-density 30nm Green DDR3 is supposed to achieve more than a 70% power savings over 1Gb 1.5V 50nm class DDR3, improving SeaMicro’s TCO.

The SM10000-XE lists for $138,000 for a base configuration.

CompSec, which works with the US intelligence community, has adopted the widgetry in mission-critical applications to deliver huge amounts of compute power to remote and hard-to-access locations. It says it “greatly reduces response times, provides faster and more in-depth analysis, and helps to advance their mission.”

Mozilla is also on board. Matthew Zeier, director of IT infrastructure and operations, says that between the Atom boxes and the Xeon boxes “SeaMicro is able to meet the computational needs of our entire data center while driving down operating expenses by saving us power and space. We are a very happy customer.”

Intel has previously acknowledged that microservers could represent 10% of the server market by 2016. Its data center unit general manager Jason Waxman explained Tuesday that that forecast included both Atom and Xeon widgetry. Intel may be somewhat conservative considering the Xeon chip SeaMicro is using costs less than $300.

SeaMicro expects the next Atom generation to move chipset functions into the SoC, which will save more power and give it more real estate for processors.

SeaMicro rival Calxeda is building ARM chips into microservers.

In their place Egnyte (given the silly way we spell things you’re supposed to say ignite) proposes its HybridCloud, a next-generation storage, file-sharing and backup scheme originally targeted at SMBs that lately – at least in the last three quarters – has been attracting large accounts, including 30 departments in the Fortune 1000.

It’s thought to resolve a psychological barrier to cloud adoption by reassuringly keeping copies of what’s in the cloud on-premise. That’s obviously why they call it HybridCloud. Companies aren’t supposed to feel they’re losing control of their data.

Large accounts are also comfortable using FTP, which can move large amounts of data up and down. That’s why Egnyte has come up with the unified FTP and single sign-on capabilities that are supposed make separate FTP servers obsolete.

The start-up has 5,000 active trials going on all the time and says a third of them are FTP-related. According to CEO Vineet Jain “We know that two major pain points for IT are FTP and the ability to allow users to have a single sign-on when accessing services.”

With an FTP (or FTPES) transfer option integrated into the HybridCloud file server, users have a familiar way to securely upload large files directly into shared and private folders that are accessible from any device.

IT managers can set up and administer users directly from their Egnyte admin panel, using existing permission structures and eliminating those infernal special passwords.

For more complex or batch processes, scripting is supported, and all the files are accessible online or offline via Egnyte’s Office Local Cloud or Personal Local Cloud – the widgetry that keeps copies of files back in the office.

To streamline the process of using and maintaining user accounts while preserving security, Egnyte now supports the SAML protocol. End users can sign into their network once and automatically use Egnyte’s services without multiple passwords. They can also use Citrix Netscaler Cloud Gateway and OneLogin to go directly to Egnyte. IT managers can ensure Active Directory credentials are maintained within the firewall and integrate with existing SAML implementations, maintaining the critical extra security levels required in today’s cloud-infused world.

The start-up also argues – somewhat undeniably – that with cloud computing file server complexity and maintenance issues have increased dramatically and there are security issues galore.

It hired Forrester which did a study and found that 41% of employees at SMBs are using unauthorized cloud services in the workplace.

It says that means IT managers have to contend with a variety of consumer-grade products (presumably from its cloud storage competitors like Mozy and Box) that erode security, block IT from understanding what users are doing with critical company data and where they are storing it, ultimately impeding their company’s ability to collaborate and work effectively.

This time through Egnyte has expanded its syncing capabilities to include granular sub-folder level controls. The company, which figures nobody else has this kind of granularity – well, it did take nine months to develop – says serious cloud file-sharing means going beyond an easy-to-use interface and requires enterprise-grade security, IT administration tools, full auditing capabilities and syncing beyond a PC and Mac to include mobile devices, network attached storage (NAS) devices, storage area networks (SANs) and virtual servers.

Allowing cross-platform sync across a spectrum of devices is supposed to be the only way to make all employees, regardless of where they are, feel like they’re working from a single location.

So the widgetry now includes object-level integration with salesforce.com so users can collaborate with others regardless of whether or not they’re salesforce users, avoiding salesforce license fees. Access to salesforce files includes using iPad, iPhone, Android or some other mobile device. Salesforce.com users can work with files of any size, access virtually unlimited storage and share files directly within the salesforce.com interface. Team members who don’t have salesforce.com licenses can access the shared folders associated with salesforce objects through Egnyte.

Egnyte’s corporate plan covers 30 power users and 600 standard users and costs $228 a month when paid annually. That works out to $7.60 a power user a month.

Egnyte currently has a half-million users at what it says are thousands of companies representing over a billion shared files, taking advantage of a technology that offers the speed and security of local storage with the flexible accessibility of the cloud.

Egnyte is backed by $17 million from Kleiner Perkins, Floodgate Fund and Polaris Venture Partners.

The company has three data centers rented from Equinox in California, North Carolina and Amsterdam.

Flash’s future looks bleaker still considering Flex can build both desktop and mobile apps.

The Apache Foundation will have to vote on whether it will take Flex and its roadmap under its wing. Flex has been open source since 2008 but will have to shift out from under Adobe’s control and be managed as an independent project.

Adobe says it’s working on proposals for ASF to incubate both the core Flex SDK and BlazeDS, the messaging system for pushing data from a back-end Java EE server to a Flex application, as so-called “podlings.”

Adobe also means to contribute complete, but yet-to-be-released, Spark components, including ViewStack, Accordion, DateField, DateChooser and an enhanced DataGrid; Falcon, the next-generation MXML and ActionScript compiler currently under development; Falcon JS, an experimental cross-compiler from MXML and ActionScript to HTML and JavaScript; and Flex testing tools.

Apparently nothing will happen before November 29 when Flex 4.6 SDK is released.

Meanwhile, Flash might be hounded to an early grave by an upstart “Occupy Flash” movement bent on “ridding the world of the Flash Player plug-in.”

Intel hasn’t been able to break ARM’s deadly grip on the lucrative low-power mobile market. Conversely lack of a 64-bit chip has kept ARM out of desktops and servers although HP said Tuesday that it’s going to sell ARM servers based on the 32-bit quad-core silicon that the ARM-backed Texas start-up Calxeda has developed for energy-efficient web servers targeted at social media and the cloud.

ARM maintains that 32-bits is more than sufficient for most microservers.

That limitation, however, is about to disappear. ARM has done what AMD and Intel did with the 32-bit x86 and added 64-bit extensions to its 32-bit design, creating the first ARM architecture to include a 64-bit instruction set along with extended virtual addressing.

It has christened the thing the ARMv8 architecture and dubbed the new instruction set A64.

That means 32-bit code will run in the so-called AArch32 execution state and 64-bit code in the AArch64 execution state, which pushes existing memory limitations past 4GB. Two of the features from the 32-bit ARMv7 architecture that will carry over are TrustZone virtualization and NEON advanced SIMD.

There’s no silicon yet – ARM of course doesn’t make chips itself – it’s fabless – but one of its cloud-targeting OEMs, Applied Micro Circuits, aims to produce samples of a four-core 32-bit backward-compatible 64-bit ARM chip it calls the X-Gene by the second half of next year.

That feat would ostensibly put it ahead of Marvell, which bought Intel’s Xscale ARM business in 2006 and was assumed to have the 64-bit lead.

AppliedMicro will use Taiwan Semiconductor, its usual fabricator, to make its 64-bit ARM SoCs on 40nm and then 28nm processes. Each core will reportedly be good for 3GHZ and have L1 and L2 caches with a shared L3 cache.

The superscalar chip will support quad-issue out-of-order execution and include DDR3 main memory controllers, two Gigabit Ethernet ports, SATA storage and PCI Express controllers. Figure everything on the same die as the cores with each core reportedly requiring only two watts. Also figure the clock rate can be turbo-boosted and server makers will be able to tweak power and clock speed as needed.

The Register says X-Gene can be set up as a “baby symmetric multiprocessing server inside of a single chip” and that SMP can be extended across multiple X-Genes gluelessly so no extra chips are needed.

Until AppliedMicro materializes the chip, it will make a board simulating 128 ARMv8 cores crafted out of seven Xilinx Virtex FPGAs available to software developers starting in January so they can port data center software to the dingus.

The pre-silicon emulator reportedly runs the LAMP stack and responds to a C compiler. By January AppliedMicro is also promising to have a full suite of cloud computing applications driving various target workloads such as web, Memcached, Hadoop and web server along with tools and debuggers.

AppliedMicro is apparently months, if not years, ahead of ARM itself. ARM said its own v8 reference architecture specifications are now available to partners under license and that it will disclose other processors based on ARMv8 next year, with consumer and enterprise prototype systems expected in 2014, a long way off in Internet time.

ARM said its compiler and Fast Models with ARMv8 support have been made available to key ecosystem partners and that support for a range of open source operating systems, applications and third-party tools is in development.

Microsoft, which is already moving Windows to ARM, apparently has a piece of the action or at least an interest, but it hasn’t committed to porting Windows Server to ARM.

At the same time Intel will be moving to close the power and density gap to defend its precious server monopoly.

ARM chips have historically been made by companies such as Qualcomm, Nvidia, Samsung and TI. Apple designs its own and AMD, which appears to have observer status, may break ranks with Intel and join the crew.

The disk arrays would be replaced by Violin’s built-from-the-ground-up 6000 Series NAND flash Memory Arrays, which it calls the industry’s first all-silicon storage systems.

They’re supposed to have the reliability, performance and economics to be deployed as mission-critical primary storage. The 6000’s “Rack in a Box” skills extend to virtualization, private and public clouds, and Big Data initiatives.

The company says its approach to flash aggregation created a completely hot swappable platform that accelerates all business-critical applications, allowing them to be virtualized and deployed in private clouds.

Violin’s hardware and software, based on its own IP, are tightly integrated. Redundant Memory Gateways, which virtualize the flash resources and manage network connectivity, are integrated in the chassis and remove the need for an external device to connect to the network. All components are redundant and there is no single point of failure in the system.

Data on the Violin Integrated Memory Modules (VIMMs) is protected by hardware-based flash vRAID. Block or chip failures are handled on-the-fly and in the event of a VIMM failure, data is moved to a spare and the VIMM can be hot-swapped.

The widgetry, which comes in a 3U SAN-attached platform, promises an 80% reduction in cost per input/output operations per second (IOPS) and a 15:1 reduction in physical consolidation of hardware from a disk array vendor.

Deploying Tier 1 Memory Arrays is supposed to lead to extensive server compression and software license savings.

Violin can put more than 160TBs in a rack with 10 million IOPS and 40GB/s performance.

It claims one of its racks can replace 40 racks of EMC’s latest Tier 1 Symmetrix disk arrays, which need 9,600 disks to do the same job. It figures its users usually sees a 2x-3x reduction in both capex and opex.

Violin’s 6000 models are available based on either Single Level Cell (SLC) or Multi Level Cell (MLC) flash technology. Systems based on SLC are optimized for performance, supporting 16TBs per array and delivering one million raided IOPS with low latency. Systems based on MLC are optimized for capacity and support 32TBs per array and deliver 500,000 raided IOPS.

Violin’s unique patent-pending vRAID hardware-based approach is said to result in the fastest MLC Memory Array on the market. Multiple Memory Arrays can be clustered together scaling to petabytes of storage and tens of millions of IOPS.

Violin has also doubling the storage capacity of its 3200 Series to 20TB per 3U shelf with a new Violin 3220. It’s supposed to be good for 250,000 IOPS.

The 3220 is available now and the new 6000 series arrays are currently shipping to strategic partners in limited quantities with general availability set for Q1.

The widgetry supports Fibre Channel, Gigabit Ethernet and PCIe.

Violin’s flash comes from Toshiba, its largest investor. Juniper Network is also a backer as is a mystery OEM that may be IBM.

The six-year-old company, which is focused on the Global 5000, claims AOL, Revlon, Tagged.com, Oracle, Juniper and HP as customers. HP is putting together a Violin-based OLTP appliance like Oracle’s Exadata. Violin and IBM are working on joint sales.

CEO Don Basile, an émigré from Fusion-io where he was also CEO, expects Violin to IPO, like Fusion-io did, in Q1 or Q2 of next year if market conditions are favorable. Basile, however, remarks that the bad economy is working well for Violin. Customers are more cost-conscious. It helps that his widgetry plugs into existing fabrics.

Violin recently brought in close to $100 million in equity financing with $500 million in debt financing. Its revenues are reportedly about $100 million – or will be this year – and it only put its first product on the market 14 months ago, scoring a faster growth rate than 3Par or Isilon. It expects to double its 200-odd workforce by Christmas.

And Eucalyptus is already supposed to be the most widely deployed private and hybrid cloud platform, used by outfits like Puma, USDA, Plinga, Aerospace Corporation, InterContinental Hotels Group, Wetpaint and USASpending.gov.

It says at least 21 of the Fortune 100 have started a Eucalyptus cloud to get the service levels, security and compliance they can’t get with public clouds.

Anyway, the company’s been working on the new widgetry for the last 18 months and it doubles its lines of code.

High availability will appear in the company’s third-generation Eucalyptus 3, which should be out for trials, proofs-of-concept and production deployments in Q4.

Eucalyptus CEO Marten Mickos says, “High availability is one of the most sought-after and difficult features to implement in a private cloud platform.” It will be offered as a built-in standard feature in both the company’s supported and open source versions.

Eucalyptus 3 is architected to allow no single point of failure. If a system crashes for any reason – a failure in the disk drives, memory corruption or a network or power outage – Eucalyptus 3 will immediately trigger a failover to a “hot spare” service that’s running concurrently on a different physical machine.

The failover will be transparent to the outside world. Nobody’s slip will show even if hardware or network components fail. Service Level Agreements (SLAs) will be preserved.

Eucalyptus 3 also includes enhanced resource access controls (RAC) so cloud administrators can finely tune user group management, run in-depth cost tracking, and see details of cloud use throughout an enterprise. The admin can control which operations can run what and put limits on who’s eating up specific resources.

The upgrade supports the Amazon Web Services (AWS) Identity and Access Management (IAM) API. Eucalyptus 3 can also automatically map definitions from enterprise LDAP and Active Directory (AD) servers to Eucalyptus accounts, groups and users and includes expanded account and resource reporting interfaces for integration with existing data center chargeback and billing systems.

It’ll support an AWS boot from its own EBS SAN devices along with NetAPP and JBOD EBS SAN drivers, integrates with Active Directory (AD) and standard LDAP servers, and runs Windows, VMware 4.1, RHEL 6.0 and KVM images.

By the way, Gartner figures OpenStack is 18 months away from being production-ready.

The start-up’s got a way to make VMware’s vCenter manager natively support Microsoft’s Hyper-V, Citrix’s XenServer and Red Hat’s KVM hypervisors all at the same time without vCenter even knowing those outlanders aren’t its own ESXi.

The HotLink SuperVisor for VMware is meant to appeal to enterprises with heterogeneous widgetry, which must be just about everybody – well, two-thirds of them anyway – and let them mix and match hypervisors depending on cost, mission criticality, application support, performance, engineering and management requirements, SLAs and legacy imperatives.

HotLink already has enterprise customers, some even paying, and a calculator to figure out what they can save. One figured out that it could save $16.5 million over five years on licensing and support costs by not being locked in to VMware. Very persuasive that. And dangerous. It makes HotLink an acquisition target.

The start-up took a bottom-up architectural approach to the interoperability problem by plunging its mitts into the nasty guts of the databases in the hypervisors.

Out of messing with all that metadata was born HotLink’s patent-pending Transformation Engine, which decouples and abstracts the underlying hypervisors and workloads from the management layer so mixed virtual environments – free of the dependencies between the management tools and the virtual infrastructure – can be treated as unified and native objects inside the VMware infrastructure. Got that?

HotLink then combined its “platform transformation technology” – which translates hypervisor talk into messages vCenter can understand – with a plug-in architecture that provides extensions to the native management consoles to manage all the features of all the hypervisors.

Eureka! vCenter is extended to natively support XenServer, Hyper-V and KVM. No other management console is required; vCenter users can leverage their existing management investment and skills.

The start-up says its approach of unifying management and standardizing integration across all the virtual infrastructure avoids the overhead, complexity at scale, limited integration and constrained functionality of the top-down overlay approach other people have tried despite the limitations of mere APIs.

Done its way vCenter can be used for cross-platform management, orchestration and workflows.

The widgetry can do things like move workloads between hypervisors via hot or cold migration and configure local and remote storage for VMs across hypervisors. There’s health status and security management for all the virtual infrastructure, and policies and automation are uniformly and holistically applied across the disparate virtual platforms. There’s also seamless cross-platform snapshots, cloning and host format conversions.

HotLink also assumes not everything is virtualized and that some things run on bare metal.

The VMware product is HotLink’s first crack at the problem, an obvious choice since VMware is popular with the enterprise. There’ll be others. Microsoft’s System Center’s a likely next move. There’ll also be extensions to cloud platforms like Amazon and Rackspace.

HotLink was started by CEO Lynn LeBlanc and VP of engineering Richard Offer, who did FastScale Technology together. A cloudified software virtualization and provisioning start-up, FastScale was bought by EMC and then passed to VMware.

LeBlanc expects the $10 million HotLink got from Foundation Capital and Leapfrog will be the only outside money it’ll need.

It’s got two of seven customers willing to be identified: Informatica, which HotLink knows from FastScale days, and McAfee, a new account that’s proving to be its biggest. Aside from technology concerns, it says it’s also got customers in financial services, telecommunications and Internet search and an advisory board that hails from BMC, E*Trade, Citrix, eBay, Polycom as well as McAfee and Informatica.

HotLink is still in pilot phase but figure a starter kit running $25,000 for five concurrent hosts and one additional hypervisor besides ESXi when it’s out at the end of the month in time for VMworld. It’ll go through VARs, aiming to sign up the crème de la crème of the ones that have been majoring in virtualization.

It’s after the mid-sized and large enterprises, where Java lives, that want to develop and deploy Java apps in the cloud. And it’s not exactly going to turn away any enterprise-grade cloud vendors looking to offer their customers a Java Platform-as-a-Service.

Naturally, out in the wild it’ll encounter CloudBees’ RUN@Cloud, VMware’s Cloud Foundry, Red Hat’s OpenShift and Microsoft’s Azure.

The company was started a few months ago by Sun émigrés Rajesh Ramchandani and Laura Ventura, and has Java’s father James Gosling and former Sun CIO and Sun Federal president Bill Vass heading its Technical Advisory Board.

CumuLogic’s widgetry is IaaS-agnostic and users can build a PaaS on Amazon’s public cloud or VMware, Eucalyptus and the Citrix’ Cloud.com/Project Olympus private clouds – with OpenStack in the works.

CumuLogic’s contribution to cloud mania is to support the use of multiple clouds from multiple vendors at the same time, which is why it suits Gosling, who complains about the cloud’s lack of interoperability. The start-up’s got a management console that keeps track of what’s going on simultaneously in both the public and private clouds.

Ramchandani says, “CumuLogic is unique in that we are one of the first companies to emerge with a full Java PaaS for the federated cloud. Instead of rewriting applications to fit new platforms and essentially giving up standardized application components, we sought to create a product that would give users the flexibility to keep using those components, from application platforms to databases.”

Its trick is to keep all the images – with their necessaries – in a catalog that automatically updates and patches them when advised to do so.

Ramchandani imagines companies consolidating their applications into a single platform deployed across the enterprise on the same infrastructure like setting up an enterprise-wide master account on EC2 with access controls, quotas and hard/soft limits on cloud resources for users and departments to manage capacity, usage, security and compliance.

Immediately CumuLogic only supports CentOS, the Red Hat clone, on ESXi, Xen and KVM. Java, Ruby and PHP applications can access middleware and databases as services. Figure MySQL and DB2, JBoss and Websphere application servers and Apache 2.x and Nginx 0.9 web servers, and Tomcat to start.

In time Ramchandani, who’s VP of products, said to expect MongoDB, Cassandra NoSQL and Oracle databases, Hadoop and RabbitMQ.

CumuLogic’s product is based on a cloud application management platform and includes cloud services automation, auto-scaling, monitoring, resource management and user management.

It’s supposed to simplify things.

It includes features such as IaaS abstraction, policy-based workload deployment, and the ability to mix-and-match infrastructure software for deploying modern applications as well as consolidating legacy Java applications on a single platform, lowering the cost of managing multiple infrastructure assets.

By supporting multiple Java EE containers, CumuLogic says it alleviates the way users develop new applications or migrate existing applications to the cloud.

The beta version can be downloaded for free at http://www.cumulogic.com. It should GA in September or October. It’s been in limited beta on Amazon for a couple of months.

CumuLogic is an early-stage angel-funded start-up with expectations of going out for, say, $4 million-$5 million in venture funding soon.

Former NASA CTO Chris Kemp has started a company called Nebula after his NASA project that will field a customized turnkey OpenStack hardware appliance that’s supposed let businesses – and I quote – “easily, securely and inexpensively deploy large private cloud computing infrastructures from thousands of inexpensive computers with minimal effort.”

It claims the widget will shift the fundamental economics of computing.

Its black box is supposed to be able to configure a private cloud in minutes, even the massive clouds that used to be the private preserve of, well, NASA, that are capable of handling Big Data and running Big Analytics.

Nebula’s thinking IaaS and PaaS, as well as petabyte-scale storage, which will need software support, and partnerships with Hadoop and NoSQL concerns.

Its widget can control 20 compute and storage nodes. Customers are supposed to buy clutches of them at a time to stick between racks of commodity servers. No hint of pricing yet.

Andy Bechtolsheim, David Cheriton and Ram Shriram, the star-kissed Google early investor crew, have sprinkled their peculiar brand of angel dust over the start-up. It’s also gotten venture financing from the redoubtable Kleiner Perkins Caufield & Byers and Highland Capital Partners, but won’t talk about the size of bankroll. Kemp claims he turned down a king’s ransom.

According to John Doerr, Kleiner’s top partner, “Nebula will disrupt and democratize cloud computing. As original creators of OpenStack, this team has the unique expertise to deliver simplicity, scale, speed and low cost for enterprise cloud computing.”

The start-up even managed to get an atypical canned quote out of Bechtolsheim, who reached into his past and said, “Nebula embracing OpenStack today is similar to Sun embracing Berkeley Unix in the 1980s. Proprietary systems did not have a chance against open platforms. I see Nebula as the company that will bring OpenStack to the private enterprise cloud.”

Of course, somewhere in this whole thing there’s a slot for Andy’s Arista Networking 10GB switches.

Besides supporting garden-variety commodity servers, Nebula will support Facebook’s stripped-down energy-efficient Open Compute servers expected to start trickling out soon as motherboards from Synnex, the ODM.

Nebula will eventually certify reference architectures as Open Compute-compliant. Otherwise the reference architecture of the “hardware failure-tolerant” scale-out architecture is a Dell PowerEdge C server. Apparently HP will follow. Dell just launched an OpenStack effort of its own.

Product trials reportedly with energy, finance, biotech and media companies are expected to begin in Q4. Apparently Nebula is going to chase the Big Data folks like the American healthcare industry, Europe’s public sector and retail. One might expect optimization depending on use case like the genome.

Nebula’s co-founders include engineering VP Devin Carlen, the former CTO of Anso Labs, which wrote the Nova code to power NASA’s Nebula cloud, now OpenStack’s compute piece.

Nebula will compete against that other new OpenStack start-up Piston Cloud Computing run by Joshua McKenty, the cloud architect on NASA’s Nebula cloud infrastructure, which just got $4.5 million from Hummer Winblad, True Venture and Divergent Ventures as well as the newly Citrix-bought Cloud.com. But that’s just in its own backyard.