Turbotodd

Ruminations on tech, the digital media, and some golf thrown in for good measure.

Posts Tagged ‘data center

Nvidia’s New Chips

leave a comment »

Nvidia announced its largest-ever acquisition today, offering $6.9 billion for data center chip technology maker, Mellanox.

Bloomberg is reporting that Mellanox beat out rivals that included Intel in a bidding process for the American-Israeli company, one which its founder, Jensen Huang, built in under three years by “persuading owners of data centers that his graphics chips are the right solution for processing the increasingly large amounts o information needed for artificial intelligence work, such as image recognition.”

The growing reams of data generated means work on AI and large databases needs to be split between multiple computers. Simply using a faster processor isn’t enough, Huang said. To deal with this, data centers in future will be built as though they are single giant computers “with tens of thousands of compute nodes,” requiring inter-connections that let them work in parallel. Nvidia will use its newly acquired technology to make those giant warehouses full of machinery more efficient and effective, he said.

The deal may signal a resumption of consolidation in the $470 billion semiconductor industry, which has been reshaped over the past five years as companies combined to gain scale while battling rising costs and shrinking customer lists.

The deal will require regulatory approval.

ZDNet’s take

Nvidia’s purchase of Mellanox for $6.9 billion will translate into a broader data center play for beyond the graphics and high performance computing markets.

  • Nvidia’s rivalry with Intel hits a new stage.
  • Nvidia gets more revenue diversification and data center sales.
  • Mellanox gives Nvidia more entries into high performance computing and the data center.
  • As artificial intelligence workloads become the norm, Nvidia with Mellanox be more an architecture play.

And SiliconANGLE spoke with analyst Patrick Moorhead about the deal:

“Both Nvidia and Mellanox are big in the high performance computing, machine learning, automotive, public cloud and enterprise data center markets, and could bring even more value to customers when [their technologies are] combined.”

“Scale and diversification is everything in the chip business, and Nvidia gets both with this acquisition,” added Holger Mueller, principal analyst and vice president of Constellation Research Inc. “It allows the company to scale and diversify from its existing graphics, gaming and AI use cases. Getting in the data center is vital with the overall move to the public cloud, so if this goes through, it means Nvidia will become more relevant for both executives and developers alike.”

The financial spin: Nvidia is paying a 15% premium to Mellanox’s Friday closing level, and indicated the purchase would be immediately accretive to earnings, margins and cash flows.

Written by turbotodd

March 11, 2019 at 2:03 pm

Softer Networking

leave a comment »

The Turbo radar sensed more disruption on the technology M&A front overnight.

Actually, it was my RSS feed reader, but hey, close enough for jazz.

VMWare, the virtualization technology provider owned by storage technology stalwart, EMC, bought Andreessen Horowitz-backed Nicira for $1.05 billion buckaroos.

Nicira is an open source software developer for network virtualization, and has been adopted by VMWare most likely for its development of “software defined data centers.”

Historically, data communications controls have been managed by proprietary software sold in combination with hardware (think Cisco, Juniper, etc.)

With Nicira, control functions are separated and moved down the stack, so to speak, so they can be run on a variety of servers and not just proprietary hardware.

According to Wall Street Journal’s coverage of the announcement, VMWare CEO Paul Maritz “predicts that nearly all of the hardware in current computer rooms will be replaced by software running on commodity-style servers.”

The software-defined data center. Veddy interesting.

It’ll be even more interesting to see how Cisco and the other networking hardware vendors respond…or not.

Written by turbotodd

July 24, 2012 at 3:08 pm

Flying Through Your Data Center

leave a comment »

After my recent visit to the Bahamas, and my first ever flight in a small aircraft, I decided I was going to take up flying.  Well, virtually, anyhow.

My buddy Steve recommended I buy a copy of Microsoft Flight Simulator X, along with a remote USB yoke and throttle control, to do some initial simulation and learn some of the basic flying requirements on the safety of my computer.

Click to expand image. The IBM Smarter Computing Workload Simulator is designed to give busy chief information officers a fast and easy way to view areas of potential savings and efficiency through the lens of IBM Smarter Computing systems and technologies. I was able to create this simulation in less than a minute!

I’m all about simulating while I learn the basics of flying.  I figure it’s much safer for me on the ground than in the air!

But simulations are no longer limited simply to learning how to fly.

Sometimes, the best way to demonstrate the benefits of new technology is, actually, through more technology.

Like an online simulator for IT data center ROI, for example.

The kind of tool that allows people to punch in information and variables and receive instant feedback on possible alternatives.

So, enter the new IBM Smarter Computing Workload Simulator.

This new online simulation tool is designed to give busy CIOs a fast and easy to way to view areas of potential savings and efficiency through lens of IBM Smarter Computing systems and technologies.

If you’re not familiar with IBM’s Smarter Computing approach to IT earlier this year, IBM introduced it as a way for organizations to realize greater efficiencies, improved reliability, and better performance, and all at lower costs.

The strategy centers around three fundamental aspects:

  • Leveraging analytics to exploit vast amounts of data for business goals
  • Utilizing optimized systems that are designed for specific tasks
  • Managing as much of the IT as possible with cloud-computing technologies.

The new simulator, then, starts by asking the visitor to select either IBM Power Systems or IBM System z to compare to their own IT infrastructure.

It then asks for the type of industry they’re in, the type of workload to be compared, and the number and types of systems to compare – including those based on Intel Itanium, Intel x86, and/or Sun SPARC.

As the systems are identified, graphical images of servers begin to populate a simulated data center floor.

When the visitor finishes and hits the “Next” button, an alternative data center floor immediately pops up and populates with IBM systems and a breakdown of estimated costs and savings.

Visitors can drill down for charts and analysis on operating and strategic costs of their infrastructures, and the potential costs and savings of the IBM alternative.

For even greater analysis, visitors can click on the IBM System Consolidation and Evaluation Tool at the end of the simulation that provides a more comprehensive and detailed comparison.

IBM will expand the tool, which went live in mid-October, to include support for System x in the first half of 2012.

You can check out the IBM Smarter Computing Workload simulator here.

New Z, Smarter Data Center

leave a comment »

Today’s a big day.

It’s my birthday.  No gifts, please.

But it’s also the day IBM has announced the birth of the new zEnterprise mainframe, complete with a system design overhaul, that allows workloads on mainframe, POWER7, and System x servers to share resources and be managed as a single, virtualized system.

All that for my birthday!  Woo hoo!  Can I put one of those suckers in my home office? (Then I could really live up to my nickname.)

All birthday hilarity aside, this new system represents a major investment and a lot of blood, sweat, and tears on the part of IBM employees, particularly up in our Poughkeepsie plant.

There, IBM added a new, 56,000-square-foot, $30 million production floor to manufacture the new zEnterprise. 

And overall, it represents some U.S. $1.5 billion in R&D investment and a three-year, 24-hour development cycle that spanned three continents and involved more than 5,000 IBMers working a total of 31 million hours.

image

IBM employees Einar Norman, (left) Plattekill, N.Y. and Richard Lane, Rosendale, N.Y., prepare IBM’s new zEnterprise System Mainframe for shipment in the company’s Poughkeepsie, N.Y. plant.

Following are a few speeds and feeds and a whole bunch of details about the new system (Hang on to your raised floor railings, bay-bey!):

  • Industry first: IBM mainframe governance and management benefits extended to select POWER7, System x environments
  • New technology boosts complex analytics performance up to 10X, delivering insight from business data in minutes versus hours
  • zEnterprise is the most powerful, scalable mainframe server ever –- up to 60% faster than System z10 for new workloads
  • Most energy efficient mainframe — more than 100,000 virtualized servers can be managed as a single system;  60% more capacity than z10 while using same amount of energy

The new systems design combines IBM’s new zEnterprise mainframe server with new technology — the IBM zEnterprise BladeCenter Extension and the IBM zEnterprise Unified Resource Manager — that enable it to manage workloads running across System z, and select POWER7 and System x servers. 

As a result, customers can integrate the management of zEnterprise System resources as a single system and extend mainframe qualities, such as governance and manageability, to workloads running on select IBM POWER7 and System x blade servers.

With the ability to manage workloads across systems as one, the zEnterprise System can drive up to 40% lower acquisition costs and reduce cost of ownership by 55%.

IBM designed the zEnterprise System to address an important issue for corporate data centers — the jumble of disparate technologies added over time to run specific applications and which operate in silos, sometimes unable to communicate with each other in real time and requiring separate staff and software tools to manage.

This long-standing challenge for customers is aggravated  by dramatic increases in cost and complexity amid a rising tide of sophisticated, data-intensive workloads.

IBM zEnterprise BladeCenter Extension

The IBM zEnterprise BladeCenter Extension allows supports purpose IBM POWER7 and System x BladeCenter systems as well as blades optimized for specific workloads, such as analytics and managing Web infrastructure.

IBM blade servers inside the IBM zEnterprise BladeCenter Extension — which can be managed like mainframe resources — integrate with System z and can run tens of thousands of off-the-shelf applications. 

Later this year, IBM will deliver the zEnterprise BladeCenter Extension with support for IBM POWER7 blades running AIX, IBM’s UNIX operating system.  IBM is also introducing the IBM Smart Analytics Optimizer to accelerate the performance of complex analytic workloads at a lower cost per transaction. 

Next year, IBM plans to announce additional general purpose blades for the IBM zEnterprise BladeCenter Extension including select IBM System x-based blades running Linux.  Additional workload optimized blades are planned to include IBM DataPower for improving website and network performance.

IBM zEnterprise Unified Resource Manager

New IBM Systems Software called Unified Resource Manager is first-of-its-kind firmware — software that controls how the hardware functions — that integrates multiple platform resources as a single virtualized system and provides unified management for zEnterprise. 

More than 100,000 virtualized servers can be managed as a single system on a fully-configured cluster of zEnterprise Systems.

The zEnterprise Unified Resource Manager is the key to using mainframe quality of service attributes, including security and reliability, to benefit workloads running on select Power and System x BladeCenter systems. 

For example, the Unified Resource Manager can identify system bottlenecks or failures among disparate systems. If a failure occurs on a System x blade server, the Unified Resource Manager can instantaneously move the affected application to another System x blade to keep it running. 

At the same time, the Unified Resource Manager automatically sends an electronic message to IBM to initiate a service call. The Unified Resource Manager can also help prioritize compute workloads  in line with changing business priorities. 

Additionally, the zEnterprise Unified Resource Manager improves network security across applications spanning the complete zEnterprise system, including workloads on IBM POWER7 and System x blades.  This helps reduce complexity and the need for additional encryption and firewall security software within the zEnterprise environment. 

The New zEnterprise 196

From a performance standpoint, the zEnterprise System is the most powerful IBM system ever. The core server in the zEnterprise System — called zEnterprise 196 — contains 96 of the world’s fastest, most powerful microprocessors running at 5.2Ghz, capable of executing more than 50 billion instructions per second. 

image

IBM technician Asia Dent, Poughkeepsie, tests two multi-chip modules that will each power one of IBM’s new zEnterprise System mainframes. Each ceramic module forms the central processing unit of the new computer and packs 96 of the world’s fastest microprocessors (5.2 Ghz) together to give the new mainframe 60% faster performance than its predecessor, while using the same amount of electricity. Each module is capable of executing 50 billion instructions per second.

This new IBM microprocessor technology has new software to optimize performance of data-heavy workloads, including up to a 60% improvement in data intensive and Java workloads. Increased levels of system performance in turn increases software performance, which can reduce software license costs. 

The new system offers 60% more capacity than its predecessor, the System z10, and uses about the same amount of electricity.  For clients selecting Linux on System z, a single virtualized server can be created and deployed for less than $1 per day.  It costs 74% less to run comparative Oracle workloads on the zEnterprise 196 compared to x86 systems.

Energy efficiencies were achieved through advances in microprocessor design, 45nm silicon technology, more efficient power conversion and distribution, as well as advanced sensors and cooling control firmware that monitors and makes adjustments based on environmental factors such as temperature and humidity levels and even air density.

A water cooling option is also available for the z196 that can reduce energy use by up to 12%.  In a normal data center environment, water cooling reduces the required system air flow by more than 20%, while removing more than 70% of the system air heat load. 

This can be particularly beneficial for data centers with hot spots, or limited power and cooling capacity. Water cooling on the z196 is designed to connect directly to typical data center chilled water systems and does not require an external water conditioning unit.

The new z196 builds on the IBM System z industry leading security features.  IBM System z servers are the only commercial system to achieve Evaluation Assurance Level 5 security classification.

The z196 can be configured to include up to 80 specialty engines to further reduce costs and increase performance including the System z Application Assist Processor (zAAP) for integrating Java workloads with core business applications, the System z Integrated Information Processor (zIIP) designed to help free-up computing capacity and lower IT costs, and the Integrated Facility for Linux (IFL) to optimize Linux workloads running on the mainframe.

Smart Analytics Optimizer

IBM is also announcing the new IBM Smart Analytics Optimizer — created by IBM Research — an accelerator for analytic workloads integrated to the new mainframe through the BladeCenter Extension. 

With the hybrid features of the new zEnterprise system and the Smart Analytics Optimizer customers can analyze data to anticipate emerging business trends, capture new opportunities and avoid risks up to 10 times faster.

Using zEnterprise with DB2 10 for z/OS (currently in beta), Cognos Business Intelligence and SPSS Predictive Analytics, clients will have a single platform for unprecedented insight across their most critical core information resulting in increased productivity.

New IBM Software

The unique value of zEnterprise System is the synergy among the range of IBM hardware and software.  New software has been optimized for the zEnterprise and finely tuned to work cross platform when used in conjunction with the new Blade Center Extension. 

New Tivoli integrated service management for zEnterprise software helps provide visibility, control, and automation for applications, business services, infrastructure, and data resources.  And the new Tivoli security manager for zEnterprise software will allow clients to report and analyze security events associated with Linux on System z and include these reports in the mainframe reporting and analysis, as well as easily enroll and manage federated user access for zEnterprise and Linux on System z.

The new IBM Rational Developer for System z multi-platform environment for building, testing and deploying zEnterprise applications now offers a new Rational Developer for System z Unit Test feature.

This feature improves zEnterprise development productivity by off-loading mainframe application development and testing to a workstation, which frees the mainframe to run high-value core business applications.

New compilers also announced today help customers update applications designed to work on older systems to take advantage of the zEnterprise architecture.  The new IBM Rational C++ compiler, for example, can boost overall application performance by as much as 60%, when combined with new zEnterprise systems.

The new CICS deployment assistance for z/OS provides comprehensive reporting and improved change management facilities for CICS, helping further reduce ongoing IT infrastructure costs. 

IBM Information Management System (IMS) 11, which drives a high percentage of today’s transaction intensive workloads, extends its ability to easily interconnect with other applications using extended web services and connectivity for SOA. 

IMS runs 50 billion transactions every day on System z with real-time operational access from any application or platform.

The new Lotus collaborative tools on Linux on System z combine the productivity boost of collaboration with enterprise grade processor speed, scalability, and reliability to help people inside and outside an organization connect and collaborate faster and more reliably — accelerating business processes and driving growth.  

New versions of IBM Lotus Quickr and IBM Lotus Sametime join other products in the IBM Lotus software portfolio in empowering globally distributed and mobile employees with highly scalable communications and collaboration capabilities.

IBM is also announcing a new z/OS Distributed Data Backup feature for its flagship DS8000 storage system that can help lower data protection and disaster recovery costs by consolidating cross platform disaster recovery environments on to the z196.  Clients can now back up vital data from multi-platform workloads over high performance connections with the unmatched reliability and security of the mainframe.

Visit here to learn more about the new zEnterprise.

Written by turbotodd

July 22, 2010 at 2:40 pm

%d bloggers like this: