Posts Tagged ‘IBM’

IBM 3Q16 Results Telegraph a New z System in 2017

October 27, 2016

DancingDinosaur usually doesn’t like to read too much into the statements of IBM suits at financial briefings. This has been especially true since IBM introduced a new presentation format this year to downplay its platform business and emphasize its strategic imperatives. (Disclaimer: DancingDinosaur is NOT a financial analyst but a technology analyst.)

But this quarter the CFO said flat out: “Our z Systems results reflect a product cycle dynamic, seven quarters into the z13 cycle; revenue was down while margins continue to expand. We continue to add new clients to the platform and we are introducing new technologies like block chain. We announced new services to make it easier to build and test block chain networks in a secure environment as we build our block chain platform it’s been engineered to run on multiple platforms but is optimized for scale, security and resilience on both the IBM mainframe and the IBM cloud.”

linuxone-emperorLinuxONE Emperor

If you parse the first sentence–reflect a product cycle dynamic–he is not too subtly hinting that IBM needs a z System refresh if they want to stop the financial losses with z. You don’t have to be a genius to expect a new z, probably the z14, in 2017. Pictured above is the LinuxONE Emperor, a z optimized to run Linux. The same suit said “We’ve been shifting our platform to address Linux, and in the third quarter Linux grew at a double digit rate, faster than the market.” So based on that we can probably guess that the z14 (or whatever it will be called) will run z/OS, followed shortly by a LinuxONE version to further expand the z System’s Linux footprint.

Timothy Prickett Morgan picked that up too and more. He expects a z14 processor complex will be announced next year around the same time that the Power9 chip ships. In both cases, Power and z customers who can wait will wait, or, if they are smart, will demand very steep discounts on current Power8 hardware to make up for the price/performance improvements that are sure to accompany the upcoming Power9 and z machines.

When it comes to revenue 3Q16 was at best flat, but actually was down again overall. The bright spot again was IBM’s strategic imperatives. As the suit stated: in total, we continue to deliver double-digit revenue growth in our strategic imperatives led by our cloud business. Specifically, cognitive solutions were up 5% and, within that, solution software was up 8%.

Overall, growth in IBM’s strategic imperatives rose 15%. Over the last 12 months, strategic imperatives delivered nearly $32 billion in revenue and now represent 40% of IBM. The suit also emphasized strong performance in IBM’s cloud offerings which increased over 40%, led by the company’s as-a-service offerings. IBM ended the third quarter with an as-a-service run rate of $7.5 billion, up from $6.7 billion last quarter. Most of that was attributed to organic growth, not acquisitions. Also strong was IBM’s revenue performance in security and mobile. In addition, the company experienced growth in its analytic offerings, up 14% this quarter with contributions from the core analytics platform, especially the Watson platform, Watson Health, and Watson IoT.

IBM apparently is convinced that cognitive computing, defined as using data and adding intelligence into products and services to help companies make better decisions, is the wave of the future. As the company sees it, real value lies in providing cognitive capabilities via the IBM cloud. A critical element of its strategy is IBM’s industry focus. Initially industry platforms will address two substantial opportunity areas, financial services and block chain solutions. You can probably add healthcare too.

Blockchain may emerge as the sleeper, although DancingDinosaur has long been convinced that blockchain is ideal for z shops—the z already handles the transactions and delivers the reliability, scalability, availability, and security to do it right.  As IBM puts it, “we believe block chain has the potential to do for trusted transactions what the Internet did for information.” Specifically, IBM is building a complete block chain platform and is now working with over 300 clients to pioneer block chain for business, including CLS, which settles $5 trillion per day in the currency markets, to implement a distributed ledger in support of its payment netting service, and Bank of Tokyo Mitsubishi, for smart contracts to manage service level agreements and automate multi party transactions.

Says Morgan: “IBM is very enthusiastic about using Blockchain in commercial transaction processing settings, and has 40 clients testing it out on mainframes, but this workload will take a long time to grow. Presumably, IBM will also push Blockchain on Power as well.”  Morgan may be right about blockchain coming to Power, but it is a natural for the z right now, whether as a new z14 or a new z-based LinuxONE machine.

DancingDinosaur is Alan Radding, a veteran information technology analyst, writer, and ghostwriter. Please follow DancingDinosaur on Twitter, @mainframeblog. See more of his IT writing at and here.


OpenCAPI, Gen-Z, CCIX Initiate a New Computing Era

October 20, 2016

The next generation data center will be a more open, cooperative, and faster place judging from the remarkably similar makeup of three open consortia, OpenCAPI , Gen-Z, and CCIX. CCIX allows processors based on different instruction set architectures to extend their cache coherency to accelerators, interconnect, and I/O.

OpenCAPI provides a way to attach accelerators and I/O devices with coherence and virtual addressing to eliminate software inefficiency associated with the traditional I/O subsystem, and to attach advanced memory technologies.  The focus of OpenCAPI is on attached devices primarily within a server. Gen-Z, announced around the same time, is a new data access technology that primarily enables read and write operations among disaggregated memory and storage.


Rethink the Datacenter

It’s quite likely that your next data center will use all three. The OpenCAPI group includes AMD, Dell EMC, Google, Hewlett Packard Enterprise, IBM, Mellanox Technologies, Micron, NVIDIA and Xilinx. Their new specification promises to enable up to 10X faster server performance with the first products expected in the second half of 2017.

The Gen-Z consortium consists Advanced Micro Devices, Broadcom, Huawei Technologies, Red Hat, Micron, Xilinx, Samsung, IBM, and Cray. Other founding members are Cavium, IDT, Mellanox Technologies, Microsemi, Seagate, SK Hynix, and Western Digital. They plan to develop a scalable computing interconnect and protocol that will enable systems to keep with the rapidly rising tide of data that is being generated and that needs to be analyzed. This will require the rapid movement of high volumes of data between memory and storage.

The CCIX initial members include Amphenol Corp., Arteris Inc., Avery Design Systems, Atos, Cadence Design Systems, Inc., Cavium, Inc., Integrated Device Technology, Inc., Keysight Technologies, Inc., Micron Technology, Inc., NetSpeed Systems, Red Hat Inc., Synopsys, Inc., Teledyne LeCroy, Texas Instruments, and TSMC.

The basic problem all three address revolves around how to make the volume and variety of new hardware forge fast communications and work together. In effect each group, from its own particular perspective, aims to boost the performance and interoperability of data center servers, devices, and components engaged in generating and handling myriad data and tasked with analyzing large amounts of that data. This will only be compounded as IoT, blockchain, and cognitive computing ramp up.

To a large extent, this results from the inability of Moore’s Law to continue to double the number of processors indefinitely. Future advances must rely on different sorts of hardware tweaks and designs to deliver greater price/performance.

Then in Aug. 2016 IBM announced a related chip breakthrough.  It unveiled the industry’s first 7 nm chip that could hold more than 20 billion tiny switches or transistors for improved computing power. The new chips could help meet demands of future cloud computing and Big Data systems, cognitive computing, mobile products and other emerging technologies, according to IBM.

Most chips today in servers and other devices use microprocessors between 14 and 22 nanometers (nm). The 7nm technology represents at least a 50 percent power improvement. IBM intends to apply the new chips to analyze DNA, viruses, and exosomes. IBM expects to test this lab-on-a-chip technology starting with prostate cancer.

The point of this digression into chips and Moore’s Law is to suggest the need for tools and interfaces like Open CAPI, Gen-Z, and CCIX. As the use cases for ultra fast data analytics expands along with the expected proliferation of devices speed becomes critical. How long do you want to wait for an analysis of your prostate or breast cells? If the cells are dear to you, every nanosecond matters.

For instance, OpenCAPI provides an open, high-speed pathway for different types of technology – advanced memory, accelerators, networking and storage – to more tightly integrate their functions within servers. This data-centric approach to server design puts the compute power closer to the data and removes inefficiencies in traditional system architectures to help eliminate system bottlenecks that significantly improve server performance.  In some cases OpenCAPI enables system designers to access memory with sub-500 nanosecond latency.

IBM plans to introduce POWER9-based servers that leverage the OpenCAPI specification in the second half of 2017. Similarly, expect other members of OpenPOWER Foundation to introduce OpenCAPI enabled products in the same time frame. In addition, Google and Rackspace’s new server under development, codenamed Zaius and announced at the OpenPOWER Summit in San Jose, will leverage POWER9 processor technology and plans to provide the OpenCAPI interface in its design. Also, Mellanox plans to enable the new specification capabilities in its future products and Xilinx plans to support OpenCAPI enabled FPGAs

As reported at the Gen-Z announcement, “The formation of these new consortia (CCIX, OpenCAPI, and Gen-Z), backed by more than 30 industry-leading global companies, supports the premise that the datacenter of the future will require open standards. We look forward to collaborating with CCIX and OpenCAPI as this new ecosystem takes shape,” said Kurtis Bowman, Gen-Z Consortium president. Welcome to the 7nm computing era.

DancingDinosaur is Alan Radding, a veteran information technology analyst, writer, and ghostwriter. Please follow DancingDinosaur on Twitter, @mainframeblog. See more of his IT writing at and here.


Compuware Triples Down on Promised Quarterly z System Releases

October 14, 2016

Since Jan 2015 Compuware has been releasing enhancements to its mainframe software portfolio quarterly.  The latest quarterly release, dated Oct. 3, delivers REST APIs for ISPW source code management and DevOps release automation; Integration of Compuware Abend-AID with Syncsort Ironstream to create their own custom cross-platform DevOps toolchains; and a new Seasoft Plug-In for Topaz Workbench. The Seasoft plug-in will help less skilled IBM z/OS developers to manage mainframe batch processing along with other z platform tasks


Compuware’s point is to position the mainframe at the heart of agile DevOps computing. As part of the effort, it needs to deliver slick, modern tools that will appear to the non-mainframers who are increasingly moving into multi-platform development roles that include the mainframe. These people want to work as if they are dealing with a Windows or Linux machine. They aren’t going to wrestle with arcane mainframe constructs like Abends or JCL.  Traditional mainframe dev, test and code promotion processes are simply too slow to meet the demands of today’s fast-moving markets. The new dev and ops people who are filling out data center ranks haven’t the patience to learn what they view as antiquated mainframe concepts. They need intelligent tools that visualize the issue and let them intuitively click, drag, drop, and swipe their way through whatever needs to be done.

This is driven by the long-expected attrition of veteran mainframers and the mainframe knowledge and application insight they brought. Only the recession that began in 2008 slowed the exit of aging mainframers. Now they are leaving; one mainframe credit card processor reportedly lost 50 mainframe staff in a month.  The only way to replace this kind of experience is with intelligent and easy to learn tools and expert automation.

Compuware’s response has been to release new tools and enhancements every quarter. It started with Topaz in 2015. DancingDinosaur covered it Jan. 2015 here.  The beauty of Topaz lies in its graphical ease-of-use. Data center newbies didn’t need to know z/OS; they could understand what they were seeing and do meaningful work. With each quarterly release Compuware, in one way or another, has advanced this basic premise.

The most recent advances are streamlining the DevOps process in a variety of ways.  DevOps has emerged as critical with mainframe shops scrambling to remain relevant and effective in a rapidly evolving app dev environment. Just look at Bluemix if you want to see where things are heading.

In the first announcement, Compuware extended mainframe DevOps innovation with REST APIs for ISPW SCM and release automation. The new APIs enable large enterprises to flexibly integrate their numerous other mainframe and non-mainframe DevOps tools with ISPW to create their own custom cross-platform DevOps toolchains. Part of that was  the acquisition of the assets associated with Itegrations’s source code management (SCM) migration practice and methodology, which will  enable Compuware users to more easily migrate their SCM systems from Agile-averse products such as CA Endevor, CA Panvalet, CA Librarian, and Micro Focus/Serena ChangeMan as well as internally developed SCM systems—to ISPW

According to Compuware, these DevOps toolchains are becoming increasingly important for two reasons:

  • Enterprises must aggressively adopt DevOps disciplines in their mainframe environments to fulfill business requirements for digital agility. Traditional mainframe dev, test and code promotion processes are simply too slow to meet the demands of today’s fast-moving markets to counter new, digitally nimble market disruptors.
  • Data centers need to better integrate the toolchains that support their newly adopted mainframe DevOps workflows with those that support DevOps across their various other platforms. This is because mainframe applications and data so often function as back-end systems-of-record for front-end web and mobile systems-of-engagement in multi-tier/cross-platform environments.

In the second announcement Compuware integrated Abend-AID and Syncsort’s Ironstream to give fast, clear insight into mainframe issues. Specifically, the integration of Abend-AID and Ironstream \ enables IT to more quickly discover and act upon correlations between application faults and broader conditions in the mainframe environment. This is particularly important, notes Compuware, as enterprises, out of necessity, shift operational responsibilities for the platform to staffs with limited experience on z/OS. Just put yourself into the shoes of a distributed system manager now dealing with a mainframe. What might appear to be a platform issue may turn out to be software faults, and vice versa.  The retired 30-year mainframe veterans would probably see it immediately (but not always). Mainframe newcomers need a tool with the intelligence to recognize it for them.

With the last announcement Compuware and Software Engineering of America (SEA) introduced the release of SEA’s JCLplus+ Remote Plug-In and $AVRS Plug-In for Compuware’s Topaz Workbench mainframe IDE. Again think about mainframe neophytes. The new plug-ins for Topaz significantly ease challenging JCL- and output-related tasks, according to Compuware, effectively enabling both expert and novice IT staff to perform those tasks more quickly and more accurately in the context of their other mainframe DevOps activities.

An encouraging aspect of this is that Compuware is not doing this alone. The company is teaming up with SEA and with Syncsort to make this happen. As the mainframe vendors work to make mainframe computing easier and more available to lesser trained people it will be good for the mainframe industry as a whole and maybe even help lower the cost of mainframe operations.

DancingDinosaur is Alan Radding, a veteran information technology analyst, writer, and ghostwriter. Please follow DancingDinosaur on Twitter, @mainframeblog. See more of his IT writing at and here.


Put your z System at the Center of Blockchain

October 6, 2016

The zSystem has been a leading platform for the world’s top banks for decades and with blockchain the z could capture even more banking and financial services data centers. Two recent IBM Institute for Business Value (IBV) studies show commercial blockchain solutions are rapidly being adopted throughout banking and financial markets dramatically faster than initially expected, according to an IBM announcement late in Sept.  Of course, not every blockchain deployment runs on z but more should be.


Copyright William Mougayer

According to an IBV study, more than 70 percent of early adopters are prioritizing blockchain efforts in order to break down current barriers to creating new business models and reaching new markets. IBV analyst report the respondents are better positioned to defend themselves against competitors, including those untraditional disruptors like non-bank startups. The majority of respondents are focusing their blockchain efforts on four areas: clearing and settlement, wholesale payments, equity and debt issuance, and reference data.

But blockchain isn’t just a financial services story. Mougayer identifies government services, healthcare, energy, supply chains, and world trade as blockchain candidates. IoT will also be an important area for blockchain, according to a new book on IoT by Maciej Kranz, an IoT pioneer.

As Kranz explains: blockchain has emerged as a technology that allows a secure exchange of value between entities in a distributed fashion. The technology first appeared on most IT radar screens a few years ago in the form of Bitcoin, a virtual currency that relies on blockchain technology to ensure its security and integrity. Although Bitcoin’s future is still uncertain, blockchain is a completely different story.

Blockchain is attracting considerable attention for its ability to ensure the integrity of transactions over the network between any entities. Automobile companies are considering the technology to authenticate connected vehicles in the vehicle-to-vehicle (V2V) environment, notes Kranz. Still others are looking at blockchain to trace the sources of goods, increase food safety, create smart contracts, perform audits, and do much more. Blockchain also provides a natural complement to IoT security in a wide variety of use cases.

The z and especially the newest generation of z Systems is ideal for blockchain work. Zero downtime, industry-leading security, massive I/O, flexibility, high performance at scale, and competitive price/performance along with its current presence in the middle of most transactions, especially financial transactions, makes z a natural for blockchain.

A key driver for blockchain, especially in the banking and financial services segment is the Linux Foundation’s HyperLedger project. This entails a collaborative, open source effort to establish an open blockchain platform that will satisfy a variety of use cases across multiple industries to streamline business processes. Through a cross-industry, open standard for distributed ledgers, virtually any digital exchange of value, such as real estate contracts, energy trades, even marriage licenses can securely and cost-effectively be tracked and traded.

According to Linux Foundation documents, “the Hyperledger Project has ramped up incredibly fast, a testament to how much pent-up interest, potential, and enterprise demand there is for a cross-industry open standard for distributed ledgers.” Linux Foundation members of the Hyperledger Project are moving blockchain technology forward at remarkable speed. IBM has been an early and sizeable contributor of code to the project. It contributed 44,000 lines of code as a founding member.

That it is catching on so quickly in the banking and financial services sector shouldn’t be a surprise either.  What blockchain enables is highly secure and unalterable distributed transaction tracking at every stage of the transaction.  Said Likhit Wagle, Global Industry General Manager, IBM Banking and Financial Markets, when ticking off blockchain advantages: To start, first movers are setting business standards and creating new models that will be used by future adopters of blockchain technology. We’re also finding that these early adopters are better able to anticipate disruption and fight off new competitors along the way.

It is the larger banks leading the charge to embrace blockchain technology with early adopters twice as likely to be large institutions with more than a hundred thousand employees. Additionally, 77 percent of these larger banks are retail banking organizations.

As the IBV surveys found, trailblazers expect the benefits from blockchain technology to impact several business areas, including reference data (83 percent), retail payments (80 percent) and consumer lending (79 percent). When asked which blockchain-based new business models could emerge, 80 percent of banks surveyed identified trade finance, corporate lending, and reference data as having the greatest potential.

IBM is making it easy to tap blockchain by making it available through Docker containers, as a signed and certified distribution of IBM’s code submission to Hyperledger, and through Bluemix services. As noted above, blockchain is a natural fit for the z and LinuxOne. To that end, Bluemix Blockchain Services and a fully integrated DevOps Tool is System z- and IoT-enabled.

DancingDinosaur is Alan Radding, a veteran information technology analyst, writer, and ghostwriter. Please follow DancingDinosaur on Twitter, @mainframeblog. See more of his IT writing at and here.


IBM z System and Power Fuel Hybrid Cloud

September 30, 2016

DancingDinosaur has been cheerleading the z as a cloud player since 2011 and even before, mainly as an ideal vehicle for private clouds. So it should be no surprise to readers that last week IBM announced z and Power cloud-ready systems, services, and solutions for the hybrid cloud environment. My only question: What took them so long?


Power and z accelerate transformation to hybrid cloud

The world, indeed, is changing fast, and IT data centers especially have to scramble to keep up as they try to blend public cloud, private cloud, and traditional IT data centers and integrate it all seamlessly. “Today’s business environment is very dynamic and filled with disruption. A hybrid cloud model enables clients to continuously adapt while also optimizing on-premises investments and delivering the flexibility clients need across IBM Systems and the cloud,” according to Tom Rosamilia, senior vice president, IBM Systems.

At the heart of the IBM’s systems for what it calls the hybrid cloud era are three technologies we should be generally already familiar:

  • z Systems for cloud. IBM z Systems Operational Insights is a new SaaS-based offering that provides analytic insights on cloud operations for new levels of efficiency and application performance. It allows users to make better business and application decisions based on trends and embedded expertise on performance data through a GUI dashboard. This accompanies IBM OMEGAMON Application Performance Management, which provides quick identification of problem components through end-to-end visibility for clients’ hybrid workloads that include z Systems applications.  In addition, the newly available IBM Common Data Provider enables z Systems operational data to be efficiently consumed in near real time by the clients’ cloud or local enterprise operational analytics platform. An OK start, but you can quibble with OMEGAMON as IBM’s performance analysis and management choice. At its core, this is old technology. DancingDinosaur would prefer, say, Watson.
  • Power Systems for cloud. With integrated OpenStack-based cloud management and elastic consumption models, according to IBM, these new enterprise-class IBM Power Systems enable organizations to transform their IT infrastructure to a local cloud for AIX, IBM i and Linux workloads and extend them with rapid access to compute services in the IBM Cloud. DancingDinosaur covered the new LC here.
  • IBM Spectrum Copy Data Management and Protect. This brings a new solution that drives operational and development agility and efficiency across new and traditional applications that allow detailed, easy management of data copies.  Additionally, IBM Spectrum Protect has expanded its extensive hybrid cloud solution integration with cloud object storage options for use in hybrid cloud deployments.

About the only thing missing above is LinuxONE but that will come up below when IBM gets to openness, which is critical to hybrid clouds. In its announcement, IBM also promised a series of new and expanded collaborations with IBM Systems for hybrid cloud environments, including:

  • Canonical: Canonical and IBM are extending their ongoing alliance to make Ubuntu OpenStack available today on LinuxONE, z Systems, Power Systems, and OpenPOWER-based systems, including the new line of LC servers. This enables organizations to leverage Canonical’s portfolio across the three platforms with simplified and automated OpenStack management.
  • Hortonworks: IBM and Hortonworks,  a Hadoop platform, are jointly entering the marketplace to make Hortonworks Hadoop distribution available on POWER. Whoopee, Hadoop already runs native on z.
  • Mirantis: Mirantis and IBM are collaborating to develop reference architectures enabling Mirantis OpenStack to manage compute nodes hosted on IBM Power Systems servers, and to validate a host of core applications to run its OpenStack private cloud. With this integration, Mirantis will now bring its OpenStack based private cloud management to the POWER platform. This enables organizations to leverage the efficiency of IBM Power Systems for data-driven workloads in a seamless and compatible way for their data center through Mirantis’ OpenStack cloud management.
  • NGINX: NGINX’s application delivery platform now supports servers based on IBM’s POWER architecture with the latest release of its commercial load balancer and web accelerator software, NGINX Plus R10. The combination of NGINX Plus and POWER brings new agility to enterprises, allowing them to scale their infrastructure and application delivery solutions across any environment – public, private, and hybrid cloud; containers; and bare metal – providing a consistent user experience.
  • Red Hat: Red Hat and IBM are expanding their long-standing alliance to better help organizations embrace hybrid cloud. Through joint engineering and deeper product collaboration, the two companies plan to deliver solutions built on key components of Red Hat’s portfolio of open source products, including Red Hat Enterprise Linux, (RHEL)., By the way, RHEL is the #2 Linux distro on the z. RHEL also enables IBM Power Systems as a featured component of Red Hat’s hybrid cloud strategy spanning platform infrastructure located both on and off an enterprise’s premises.

There is enough openness to enable you to do what you need so DancingDinosaur has no real complaints with IBM’s choices above. Just wish it was more z- and LinuxONE-centric.

DancingDinosaur is Alan Radding, a veteran information technology analyst and writer and mainframe bigot. Please follow DancingDinosaur on Twitter, @mainframeblog. See more of his IT writing at and here.


IBM Applies Fit-For-Purpose to Accelerating Hybrid Cloud Adoption

September 16, 2016

Almost every company is using the cloud, but not for everything, according to a recently announced study from IBM’s Institute of Business Value (IBV). Although 78 percent of the executives surveyed reported cloud initiatives as coordinated or fully integrated, almost half of computing workloads are expected to remain on dedicated, on-premises servers. This forces IT managers to consider applying IBM’s old server fit-for-purpose methodology to the cloud era, something mainframe shops haven’t seen since 2009-2010 with the arrival of hybrid mainframes.


Given cloud evolution, notes the study researchers, it is imperative that organizations determine and regularly re-assess which combination of traditional IT, public cloud, and private cloud best suits their needs. This sounds eerily similar to IBM’s fit-for-purpose mantra that it used to steer buyers between the company’s various server offerings: enterprise mainframes, midrange machines, and entry level PC servers. Only in today’s cloud era, the choices are on-premises private clouds, off-premises public clouds, and hybrid clouds.

Picking up the fit-for-purpose mantra, IBM’s Marie Wieck said:  “Enterprises are moving to the cloud, especially hybrid cloud, faster than anyone expected to support their digital transformation, drive business model innovation and fuel growth.” She concludes by rephrasing the old server fit-for-purpose pitch for the cloud era: “Successful clients have integrated plans to place workloads where they fit best, and IBM’s hybrid cloud strategy provides this on-ramp for flexibility and growth.”

DancingDinosaur has no problem with the fit-for-purpose approach.  It has proven immeasurably useful to me over the years when pressed to explain differences between IBM platforms. That the company is starting to apply it to various ways of deploying cloud computing seems both fitting and ironic. It was the emergence of the Internet in the first place as a forerunner to the cloud that saved IBM from the incompatibilities of its myriad platforms. This was after IBM’s internal effort to make its systems at least interoperate in some rudimentary way, no matter how kludgy, failed. This happened under an initiative called Systems Application Architecture (SAA), which started in the late 1980s and was gone and forgotten by 2000. Vestiges of SAA actually may still linger in some systems. Read about it here.

It should be no surprise that the cloud has emerged as a strategic imperative for IBM. In addition to being where the revenue is heading, it is doing good things for its customers. The latest study finds that the top reasons executives cite for adopting hybrid cloud solutions are: lowering total cost of ownership (54 percent), facilitating innovation (42 percent), enhancing operational efficiencies (42 percent), and enabling them to more readily meet customer expectations (40 percent).

Furthermore, the researchers found that organizations are steadily increasing their use of cloud technologies to address wide-ranging requirements. Specifically companies reported undertaking cloud initiatives that enabled them to expand into new industries (76 percent), create new revenue sources (71 percent), and create and support new business models (69 percent).

Given the widely varying possible cloud starting points from which any company might begin its cloud journey the fit-for-purpose approach makes even more send. As the researchers noted: The particular needs and business conditions of each enterprise help define its optimal hybrid solution: most often, a blend of public cloud, private cloud, and traditional IT services. Finding the right cloud technology mix or deployment approach starts with deciding what to move to the cloud and addressing the challenges affecting migration. In the study, executives achieved the strongest results by integrating cloud initiatives company-wide, and by tapping external resources for access to reliable skills and greater efficiency.

Cloud computing undeniably is hot. According to IDC, worldwide spending on public cloud services is expected to grow from $96.5 billion this year to more than $195 billion in 2020. Even as cloud adoption matures and expands, organizations surveyed expect that about 45 percent of their workloads will continue to need on-premises, dedicated servers – nearly the same percentage as both today and two years ago. Clearly organizations are reluctant to give up the control and security they retain by keeping certain systems on-premises, behind their own firewalls.

Hybrid cloud solutions promise a way to move forward incrementally. Hybrid clouds by definition include a tailored mix of on-premises and public cloud services intended to work in unison and are expected to be widely useful across industries. Each organization’s unique business conditions and requirements will define its optimal hybrid technology landscape. Each organization’s managers will have to balance cost, risk, and performance considerations with customer demands for innovation, change, and price along with its own skills and readiness for change. Sounds like fit-for-purpose all over again.

DancingDinosaur is Alan Radding, a veteran information technology analyst and writer. Please follow DancingDinosaur on Twitter, @mainframeblog. See more of his IT writing at and here.


Revamped IBM Power Systems LC Takes on x86

September 9, 2016

To hear IBM, its revamped and refreshed Power Systems LC lineup will undermine x86 (Intel), HPE, Dell/EMC, and any other purveyor of x86-based systems. Backed by accelerators provided by OpenPower community members, IBM appears ready extend the x86 battle to on premises, in the cloud, and the hybrid cloud. It promises to deliver better performance at lower cost for all the hot workloads too: artificial intelligence, deep learning, high performance data analytics, and compute-heavy workloads.


Two POWER8 processors, 1U config, priced 30% less than an x86 server

Almost a year ago, Oct. 2015, DancingDinosaur covered IBM previous Power Systems LC announcement here. The LC designation stands for Linux Community, and the company is tapping accelerators and more from the OpenPower community, just as it did with its recent announcement of POWER9 expected in 2017, here.

The new Power LC systems feature a set of community delivered technologies IBM has dubbed POWERAccel, a family of I/O technologies designed to deliver composable system performance enabled by accelerators. For GPU acceleration the NVDIA NVLink delivers nearly 5x better integration between POWER processors and the NVIDIA GPUs.  For FPGA acceleration IBM tapped its own CAPI architecture to integrate accelerators that run natively as part of the application.

This week’s Power Systems LC announcement features three new machines:

  • S821LC (pictured above)—includes 2 POWER8 sockets in a 1U enclosure and intended for environments requiring dense computing.
  • S822LC—brings 2 POWER8 sockets for big data workloads and adds big data acceleration through CAPI and GPUs.
  • S822LC—intended for high performance computing, it incorporates the new POWER8 processor with the NVDIA NVLink to deliver 2.8x the bandwidth to GPU accelerators and up to 4 integrated NVIDIA Pascal GPUs.

POWER8 with NVLink delivers 2.8 x the bandwidth compared to a PCle data pipe. According to figures provided by IBM comparing the price-performance of the Power S822LC for HPC (20-core, 256 GB, 4x Pascal) with a Dell C4130 (20-core, 256 GB 4xK80) and measured by total queries per hour (gph) the Power System delivered 2.1x better price-performance.  The Power Systems server cost more ($66,612) vs. the Dell ($57,615) but the Power System delivered 444 qph vs. Dell’s 185 qph.

The story plays out similarly for big data workloads running MongoDB on the IBM Power S8221LC for big data (20-core, 128 GB) vs. an HP DL380 (20-core, 128 GB). Here the system cost (server, OS, MongoDB annual subscription) came to $24,870 for IBM Power and $29,915 for HP.  Power provided 40% more performance at a 31% lower hardware/maintenance cost.

When it comes to the cloud the new IBM Power Systems LC offerings get even more interesting from a buyer’s standpoint. IBM declared the cloud a strategic imperative about 2 years ago and needs to demonstrate adoption that can rival the current cloud leaders; AWS, Google, and Microsoft (Azure). To that end IBM has started to tack on free cloud usage.

For example, during the industry analyst launch briefing IBM declared: Modernize your Power infrastructure for the Cloud, get access to IBM Cloud for free and cut your current operating costs by 50%. Whether you’re talking on-premises cloud or hybrid infrastructure the freebies just come. The free built-in cloud deployment service options include:

  • Cloud Provisioning and Automation
  • Infrastructure as a Service
  • Cloud Capacity Pools across Data Centers
  • Hybrid Cloud with BlueMix
  • Automation for DevOps
  • Database as a Service

These cover both on-premises, where you can transform your traditional infrastructure with automation, self-service, and elastic consumption models or a hybrid infrastructure where you can securely extend to Public Cloud with rapid access to compute services and API integration. Other freebies include open source automation, installation and configuration recipes, cross data center inventory, performance monitoring via the IBM Cloud, optional DR as a service for Power, and free access and capacity flexibility with SolfLayer (12 month starter pack).

Will the new LC line and its various cloud freebies get the low cost x86 monkey off IBM’s back? That’s the hope in Armonk. The new LC servers can be acquired at a lower price and can deliver 80% more performance per dollar spent over x86-based systems, according to IBM. This efficiency enables businesses and cloud service providers to lower costs and combat data center sprawl.

DancingDinosaur has developed TCO and ROI analyses comparing mainframe and Power systems to x86 for a decade, maybe more.  A few managers get it, but most, or their staff, have embedded bias and will never accept non-x86 machines. To them, any x86 system always is cheaper regardless of the specs and the math. Not sure even free will change their minds.

The new Power Systems LC lineup is price-advantaged over comparatively configured Intel x86-based servers, costing 30% less in some configurations.  Online LC pricing begins at $5999. Additional models with smaller configurations sport lower pricing through IBM Business Partners. All but the HPC machine are available immediately. The HPC machine will ship Sept. 26.

DancingDinosaur is Alan Radding, a veteran information technology analyst and writer. Please follow DancingDinosaur on Twitter, @mainframeblog. See more of his IT writing at and here.


Meet the POWER9 Chip Family

September 2, 2016

When you looked at a chip in the past you primarily were concerned with two things: the speed of the chip, usually expressed in GHz, and how much power it consumed. Today the IBM engineers preparing the newest POWER chip, the 14nm POWER9, are tweaking the chips for the different workloads it might run, such as cognitive or cloud, and different deployment options, such as scale-up or scale-out, and a host of other attributes.  EE Times described it in late August from the Hot Chips conference where it was publicly unveiled.

ibm power9 bandwidth


IBM describes it as a chip family but maybe it’s best described as the product of an entire chip community, the Open POWER Foundation. Innovations include CAPI 2.0, New CAPI, Nvidia’s NVLink 2.0, PCle Gen4, and more. It spans a range of acceleration options from HSDC clusters to extreme virtualization capabilities for the cloud. POWER9 is not just about high speed transaction processing; IBM wants the chip to interpret and reason, ingest and analyze.

POWER has gone far beyond the POWER chips that enabled Watson to (barely) beat the human Jeopardy champions. Going forward, IBM is counting on POWER9 and Watson to excel at cognitive computing, a combination of high speed analytics and self-learning. POWER9 systems should not only be lightning fast but get smarter with each new transaction.

For z System shops, POWER9 offers a glimpse into the design thinking IBM might follow with the next mainframe, probably the z14 that will need comparable performance and flexibility. IBM already has set up the Open Mainframe Project, which hasn’t delivered much yet but is still young. It took the Open POWER group a couple of years to deliver meaningful innovations. Stay tuned.

The POWER9 chip is incredibly dense (below). You can deploy it as either a scale-up or scale-out architecture. You have a choice of two-socket servers with 8 DDR4 ports and another for multiple chips per server with buffered DIMMs.

power9 chip

IBM POWER9 silicon layout

IBM describes the POWER9 as a premier acceleration platform. That means it offers extreme processor/accelerator bandwidth and reduced latency; coherent memory and virtual addressing capability for all accelerators; and robust accelerated compute options through the OpenPOWER community.

It includes State-of-the-Art I/O and Acceleration Attachment Signaling:

  • PCIe Gen 4 x 48 lanes – 192 GB/s duplex bandwidth
  • 25G Link x 48 lanes – 300 GB/s duplex bandwidth

And robust accelerated compute options based on open standards, including:

  • On-Chip Acceleration—Gzip x1, 842 Compression x2, AES/SHA x2
  • CAPI 2.0—4x bandwidth of POWER8 using PCIe Gen 4
  • NVLink 2.0—next generation of GPU/CPU bandwidth and integration using 25G Link
  • New CAPI—high bandwidth, low latency and open interface using 25G Link

In scale-out mode it employs direct attached memory through 8 direct DDR4 ports, which deliver:

  • Up to 120 GB/s of sustained bandwidth
  • Low latency access
  • Commodity packaging form factor
  • Adaptive 64B / 128B reads

In scale-up mode it uses buffered memory through 8 buffered channels to provide:

  • Up to 230GB/s of sustained bandwidth
  • Extreme capacity – up to 8TB / socket
  • Superior RAS with chip kill and lane sparing
  • Compatible with POWER8 system memory
  • Agnostic interface for alternate memory innovations

POWER9 was publicly introduced at the Hot Chips conference last spring. Commentators writing in EE Times noted that POWER9 could become a break out chip, seeding new OEM and accelerator partners and rejuvenating IBM’s efforts against Intel in high-end servers. To achieve that kind of performance IBM deploys large chunks of memory—including a 120 Mbyte embedded DRAM in shared L3 cache while riding a 7 Tbit/second on-chip fabric. POWER9 should deliver as much as 2x the performance of the Power8 or more when the new chip arrives next year, according to Brian Thompto, a lead architect for the chip, in published reports.

As noted above, IBM will release four versions of POWER9. Two will use eight threads per core and 12 cores per chip geared for IBM’s Power virtualization environment; two will use four threads per core and 24 cores/chip targeting Linux. Both will come in two versions — one for two-socket servers with 8 DDR4 ports and another for multiple chips per server with buffered DIMMs.

The diversity of choices, according to Hot Chips observers, could help attract OEMs. IBM has been trying to encourage others to build POWER systems through its OpenPOWER group that now sports more than 200 members. So far, it’s gaining most interest from China where one partner plans to make its own POWER chips. The use of standard DDR4 DIMMs on some parts will lower barriers for OEMs by enabling commodity packaging and lower costs.

DancingDinosaur is Alan Radding, a veteran information technology analyst and writer. Please follow DancingDinosaur on Twitter, @mainframeblog. See more of his IT writing at and here.




IBM Taps PCM to Advance Neuron-based Cognitive Computing

August 19, 2016

Just a couple of months ago DancingDinosaur reported a significant IBM advance in phase change memory (PCM). Then earlier this month IBM announced success in creating randomly spiking neurons using phase-change materials to store and process data. According to IBM, this represents a significant step toward achieving energy-efficient, ultra-dense, integrated neuromorphic technologies for application in cognitive computing.

IBM Phase Change Neurons

Phase Change Neurons

This also represents big step toward a cognitive computer. According to IBM, scientists have theorized for decades that it should be possible to imitate the versatile computational capabilities of large populations of neurons as the human brain does. With PCM it appears to be happening sooner than the scientists expected. “We have been researching phase-change materials for memory applications for over a decade, and our progress in the past 24 months has been remarkable,” said IBM Fellow Evangelos Eleftheriou.

As the IBM researchers explain: Phase-change neurons consist of a chip with large arrays of phase-change devices that store the state of artificial neuronal populations in their atomic configuration. In the graphic above individual devices are accessed by means of an array of probes to allow for precise characterization, modeling and interrogation. The tiny squares are contact pads that are used to access the nanometer-scale, phase-change cells (not visible). The sharp probes touch the contact pads to change the phase configuration stored in the cells in response to the neuronal input. Each set of probes can access a population of 100 cells. The chip hosts only the phase-change devices that are the heart of the neurons. There are thousands to millions of these cells on one chip that can be accessed (in this particular graphic) by means of the sharp needles of the probe card.

Not coincidentally, this seems to be dovetailing with IBM’s sudden rush to cognitive computing overall, one of the company’s recent strategic initiatives that has lately moved to the forefront.  Just earlier this week IBM was updating industry analysts on the latest with Watson and IoT and, sure enough, cognitive computing plays a prominent role.

As IBM explains it, the artificial neurons designed by IBM scientists in Zurich consist of phase-change materials, including germanium antimony telluride, which exhibit two stable states, an amorphous one (without a clearly defined structure) and a crystalline one (with structure). These artificial neurons do not store digital information; they are analog, just like the synapses and neurons in our biological brain, which is what makes them so tempting for cognitive computing.

In the published demonstration, the team applied a series of electrical pulses to the artificial neurons, which resulted in the progressive crystallization of the phase-change material, ultimately causing the neurons to fire. In neuroscience, this function is known as the integrate-and-fire property of biological neurons. This forms the foundation for event-based computation and, in principle, is similar to how our brain triggers a response when we touch something hot.

Even a single neuron can exploit this integrate-and-fire property to detect patterns and discover correlations in real-time streams of event-based data. To that end, IBM scientists have organized hundreds of artificial neurons into populations and used them to represent fast and complex signals. Moreover, the artificial neurons have been shown to sustain billions of switching cycles, which would correspond to multiple years of operation at an update frequency of 100 Hz. The energy required for each neuron update was less than five picojoule and the average power less than 120 microwatts (for comparison, 60 million microwatts power a 60 watt lightbulb).

The examples the researchers have provided so far seem pretty conventional.  For example, IoT sensors can collect and analyze volumes of weather data collected at the network edge for faster forecasts. Artificial neurons could be used to detect patterns in financial transactions that identify discrepancies. Even data from social media can be used to discover new cultural trends in real time. To make this work, large populations of these high-speed, low-energy nano-scale neurons would most likely be used in neuromorphic coprocessors with co-located memory and processing units, effectively mixing neuron-based cognitive computing with conventional digital computing.

Makes one wonder if IBM might regret spending millions to dump its chip fabrication capabilities.  According to published reports Samsung is very interested in this chip technology and wants to put the new processing power to work fast. The processor, reportedly dubbed TrueNorth by IBM, uses 4,096 separate processing cores to form one standard chip. Each can operate independently and are designed for low power consumption. Samsung hopes  the chip can help with visual pattern recognition for use in autonomous cars, which might be just a few years away. So, how is IBM going to make any money from this with its chip fab gone and commercial cognitive computers still off in the future?

DancingDinosaur is Alan Radding, a veteran information technology analyst and writer. Please follow DancingDinosaur on Twitter, @mainframeblog. See more of his IT writing at and here.


IBM Discounts z/OS Cloud Activity

August 12, 2016

The latest iteration of IBM’s z/OS workload pricing aims at to lower the cost of running cloud workloads.  In a recent announcement, z Systems Workload Pricing for Cloud (zWPC) for z/OS seeks to minimize the impact of new public cloud workload transaction growth on Sub-Capacity license charges. IBM did the same thing with mobile workloads when they started driving up the 4-hour workload averages on the z. As more z workloads interact with public clouds this should start to add up, if it hasn’t already.

bluemix garage -ni_5554516560

Bluemix Garages in the Cloud

As IBM puts it: zWPC applies to any organization that has implemented Sub-Capacity pricing via the basic AWLC or AEWLC pricing mechanisms for the usual MLC software suspects. These include z/OS, CICS, DB2, IMS, MQ and WebSphere Application Server (WAS).  An eligible transaction is one classified as Public Cloud-originated, connecting to a z/OS hosted transactional service and/or data source via a REST or SOAP web service.  Public cloud workloads are defined as transactions processed by named Public cloud application transactions identified as originating from a recognized Public Cloud offering, including but not limited to, Amazon Web Services (AWS), Microsoft Azure, IBM Bluemix, and more.

IBM appears to have simplified how you identify eligible workloads. As the company notes: zWPC does not require you to isolate the public cloud work in separate partitions, but rather offers an enhanced way of reporting. The z/OS Workload Manager (WLM) allows clients to use WLM classification rules to distinguish cloud workloads, effectively easing the data collection requirements for public cloud workload transactions.

So how much will you save? It reportedly reduces eligible hourly values by 60 percent. The discount produces an adjusted Sub-Capacity value for each reporting hour. What that translates into on your monthly IBM software invoice once all the calculations and fine print are considered amounts to a guess at this point. But at least you’ll save something. The first billing eligible under this program starts Dec. 1, 2016.

DancingDinosaur expects IBM to eventually follow with discounted z/OS workload pricing for IoT and blockchain transactions and maybe even cognitive activity. Right now the volume of IoT and blockchain activity is probably too low to impact anybody’s monthly license charges. Expect those technologies ramp up in coming years with many industry pundits projecting huge numbers—think billions and trillions—that will eventually impact the mainframe data center and associated software licensing charges.

Overall, Workload License Charges (WLC) constitute a monthly software license pricing metric applicable to IBM System z servers running z/OS or z/TPF in z/Architecture (64-bit) mode.  The driving principle of WLS amounts to pay-for-what-you-use, a laudable concept. In effect it lowers the cost of incremental growth while further reducing software costs by proactively managing associated peak workload utilization.

Generally, DancingDinosaur applauds anything IBM does to lower the cost of mainframe computing.  Playing with workload software pricing in this fashion, however, seems unnecessary. Am convinced there must be simpler ways to lower software costs without the rigmarole of metering and workload distribution tricks. In fact, a small mini-industry has cropped up among companies offering tools to reduce costs, primarily through various ways to redistribute workloads to avoid peaks.

A modification to WLC, the variable WLC (VWLC) called AWLC (Advanced) and the EWLC (Entry), aligns with most of the z machines introduced over the past couple of years.  The result, according to IBM, forms a granular cost structure based on MSU (CPU) capacity that applies to VWLC and associated pricing mechanisms.

From there you can further tweak the cost by deploying Sub-Capacity and Soft Capping techniques.  Defined Capacity (DC), according to IBM, allows the sizing of an LPAR in MSU such that the LPAR will not exceed the designated MSU amount.  Group Capacity Limit (GCL) extends the Defined Capacity principle for a single LPAR to a group of LPARs, allowing MSU resources to be shared accordingly.  BTW, a potential downside of GCL is that is one LPAR in the group can consume all available MSUs due to a rogue transaction. Again, an entire mini industry, or maybe no so mini, has emerged to help handle workload and capacity pricing on the z.

At some point in most of the conference pricing sessions the eyes of many attendees glaze over.  By Q&A time the few remaining pop up holding a copy of a recent invoice and ask what the hell this or that means and what the f$#%@#$ they can do about it.

Have to admit that DancingDinosaur did not attend the most recent SHARE conference, where pricing workshops can get quite energetic, so cannot attest to the latest fallout. Still, the general trend with mobile and now with cloud pricing discounts should be lower costs.

DancingDinosaur is Alan Radding, a veteran information technology analyst and writer. Please follow DancingDinosaur on Twitter, @mainframeblog. See more of his IT writing at and here.


%d bloggers like this: