Showing posts with label Servers. Show all posts
Showing posts with label Servers. Show all posts

Thursday, July 13, 2017

Intel debuts its Xeon Scalable platform - Part 2

Intel described the launch of its Xeon Scalable Platform as the biggest data centre announcement in the past 10 years. Wall Street's reaction was fairly muted, perhaps because Intel has already captured nearly the entire market for server CPUs and there was not much to suggest that any innovations in the chip architecture would significantly expand the overall market or the company's margins. However, a broad ecosystem of cloud providers, telecom carriers, server vendors, network equipment suppliers, storage specialists and systems integrators were lined-up for the big Xeon unveiling with press releases of their own. As an industry milestone, it is certain that the next wave of cloud data centre infrastructure will be built on Xeon Scalable processors.

Highlights of Intel's Xeon ecosystem momentum

Amazon Web Services

AWS has listed Intel as a strategic partner for over a decade. It is certainly a major customer. It’s been claimed that every day AWS enough servers to power a Fortune 500 enterprise. AWS launched a C5 instance family in November 2016 powered by a custom version of the Xeon Scalable Platform with hardware acceleration capability. Amazon EC2 C5 instances based on Xeon Scalable processors with AVX-512 now offer up to 72 vCPUs - twice that of previous generation compute-optimised instances - and 144 GB of memory. AWS also said it is working with Intel to optimise deep learning engines. AWS reports over a 100x boost in inference performance and is also using the new Xeon for high performance computing (HPC) clusters supporting thousands or tens of thousands of EC2 instances. AWS provided a video testimonial for the launch event.

It should also be noted that AWS is now offering NVIDIA GPU instances. Like the other cloud giants, AWS will also build its own data centre gear whenever this is the fastest or cheapest path to deployment. This includes routers based on custom Broadcom silicon and bespoke network interface cards based on an in-house Annapurna ASIC. At its scale, AWS would surely consider all silicon options for its core platform. Intel and AWS seem to be working well together.

AT&T

The guest of honour at the Xeon launch event was John Donovan, AT&T's chief strategy officer and group president, technology and operations. ‎AT&T has been running the new Xeon processors for several months in its production network. Donovan reported a 25% boost in performance - good but maybe not overwhelmingly so. Still, AT&T is moving all its network functions into a cloud based on X86. AT&T said it has a strong collaborative relationship with Intel. Total cost of ownership for the entire network improves with each generation of Xeons.

Google

The first public cloud to deploy the new Xeon Scalable Platform processors is Google. End customers are reporting consistent performance improvements, in some cases of 30 to 50%. When the applications are tuned for the AVX-512 instructions, customers are reporting more than a 100% performance improvement.

Microsoft

The new Intel Xeon Scalable Platform processors will be the base for Microsoft Azure. Earlier this year at the Open Compute Project (OCP) Summit in San Jose, Microsoft announced Project Olympus, a next generation hyperscale cloud hardware design and a new model for open source hardware development with the OCP community. Rather than contributing a fully-completed design to OCP, with this new approach Microsoft will contribute its next generation cloud hardware designs when they are approximately 50% complete. The building blocks that Project Olympus will contribute consist of a new universal motherboard, high-availability power supply with included batteries, 1U/2U server chassis, high-density storage expansion, a new universal rack power distribution unit (PDU) for global data centre interoperability, and a standards compliant rack management card.

Although some saw this announcement as a potential opening for ARM processors in Azure, in a customer testimonial video this week Microsoft confirmed that Project Olympus is based on Xeon Scalable Platform processors and Intel FPGAs. Microsoft said this combination of Xeon processors, FPGAs and high-performance storage will be a powerful solution for AI. In fact, Azure anticipates the world's largest deployment of FPGAs to power the largest neural network to date.

Telefónica

In Spain, Intel has been collaborating with Telefónica since 2008. One big focus of development is network functions virtualisation (NFV) to simplify its network. Telefonica expects the Intel Xeon Scalable Platform processors will play a key role in its 5G network. This means that Telefónica is fully committed to x86 for the basis of its infrastructure. The new processors, which are currently in Telefónica’s labs, have been delivering a performance boost of approximately 67% over the previous Xeon E5 2600 chips.

6WIND

6WIND reports that its software running on Xeon Scalable Processors delivers a significant boost for IPsec. Specifically, 6WIND Turbo IPsec performance tests on Xeon Platinum servers demonstrate a 50% increase in processing power for common applications such as multi-site VPNs and backhaul security gateways.

Accton

Accton announced a combination server-switch hardware appliance based on dual-socket Intel Xeon Scalable processors, supporting up to 28 cores (56 threads) per socket. The switch system includes 48 SFP28 (25 GbE) and 6 QSFP28 (100 GbE) network ports, all contained within a single 1RU chassis form-factor. Accton said its Intel Xeon Purley platform increases CPU capacity and performance for virtual machine consolidation and density, as well as boosting memory bandwidth (six channels).

Advantech

Advantech has introduced two new platforms: a 2U dual socket network appliance and a single socket, short depth 1U server, both based on the new Intel Xeon Scalable Processors. The scalability of the dual socket appliance increases significantly, with up to 12 more cores per CPU than on the previous generation appliance. The company noted performance advances in the throughput of encrypted packets using the latest Intel QuickAssist Technology, now available in the chipset, to perform IPsec encryption and decryption. During tests at Intel Labs, a server configured with an Intel Xeon Platinum Processor 8160 showed an increase of up to 1.32 times higher performance, demonstrating what both platforms will be able to deliver to help meet demands for higher encrypted data throughput and VPN density while freeing up slots for more I/O and offload.

Cisco

Cisco launched a new generation of servers and software based on Intel's latest Xeon Scalable Platform processors and a unique Cisco system-level vision for the future of IT. The Cisco Unified Computing System (Cisco UCS) M5 generation seeks to extend the power and simplicity of unified computing for data-intensive workloads, applications at the edge, and the next generation of distributed application architectures. The latest UCS Director 6.5 management software allows data centre professionals to complete 80% of operational tasks from a single console. A Workload Optimization Manager, powered by Turbonomic and which is deeply integrated into the UCS hardware, uses intent-based analytics to continuously match workload demand to infrastructure supply across on premise and multi-cloud environments. The company says the Cisco UCS can reduce administration and management costs by up to 63% while accelerating the delivery of new application services by up to 83%.

Dell EMC

Dell EMC launched the 14th generation of its PowerEdge servers featuring the new processors and a cyber-resilient architecture with a deep root of trust, including cryptographically trusted booting.

Ericsson

Highlighting the new Intel Xeon Scalable processors, Ericsson published a whitepaper 'Industrialising Network Functions Virtualisation with Software-Defined Infrastructure'. Topics discussed include Data Plane Development Kit (DPDK), which is a set of software libraries for accelerating packet processing workloads on commodity off-the-shelf hardware platforms.

The Fast Data Project

FD.io or Fido, a collaborative open source project that aims to establish a high-performance IO services framework for dynamic computing environments, announced significant performance gains reaching terabit levels at multimillion route scale. Architectural improvement increases in latest Xeon Scalable processors - such as increased PCIe bandwidth - allow FD.io to double its performance at scale without modification to the software. FD.io said it is the only vSwitch for which performance scaling is IO bound rather than CPU bound.

Fujitsu

Fujitsu launched a multi-node server that combines the density of blade-like servers with the simplicity of rack-based systems. The newly-refreshed range of dual- and quad-socket PRIMERGY servers and octo-socket PRIMEQUEST business critical server systems are designed for the new Xeon Scalable processors. Technical features include enhanced DDR4 memory modules and up to 6 TB capacity in quad socket PRIMERGY server. Fujitsu said its PRIMEQUEST server pushes the performance envelope of SAP HANA up to 12 TB of the in-memory database.

Nokia

Nokia introduced a refreshed AirFrame Data Center solution based on the Xeon Scalable Processors. Nokia said it has worked closely with Intel over the past year during the Intel Xeon Scalable processor development process and has just completed its own benchmarking of the new design. The results show a performance improvement over the previous generation Intel Xeon processor E5-26xxv4, with an average gain of 40% in processor rate performance.

Radisys

Radisys announced support for the new Xeon Scalable processors in its DCEngine, which helps communication service providers to transform their central offices into hyperscale SDN-enabled virtualised data centres. Radisys said its DCEngine’s management software suite, delivered with Intel Rack Scale Design, simplifies data centre resource management by enabling an open management framework with dynamic resource allocation, intelligent policy profiling and real-time, granular insight into compute, storage and network resources. The company estimates that CSPs leveraging DCEngine in data centres can expect significant improvements in total cost of ownership through reduced real estate footprint by 55%, which can result in up to 35% cost savings over a period of three years, as well as substantial reduction in costs associated with power consumption, hardware and software support.

ZTE

ZTE has launched a 2-socket cloud application rack server R5300 G4, 4-socket high-reliability rack server R8500 G4, hyperconverged blade server E9000 and software-defined storage KS10000.

Wednesday, July 12, 2017

Cisco Launches its Latest Unified Computing System

Cisco launched a new generation of servers and software based on Intel's latest Xeon Scalable Platform processors and a unique Cisco system-level vision for the future of IT.

The Cisco Unified Computing System (Cisco UCS) M5 generation seeks to extend the power and simplicity of unified computing for data-intensive workloads, applications at the edge, and the next generation of distributed application architectures. The latest UCS Director 6.5 management software allows data center professionals to complete 80% of operational tasks from a single console. A Workload Optimization Manager, which is powered by Turbonomic and which is deeply integrated into the UCS hardware, uses intent-based analytics to continuously match workload demand to infrastructure supply across on premise and multi-cloud environments. The company says the Cisco UCS can reduce administration and management costs by up to 63 percent while accelerating the delivery of new application services by up to 83 percent.

Leveraging the new Intel Xeon Scalable processors, UCS M5 servers supports up to double the memory capacity of previous systems. Cisco said its lab testing reveals that UCS M5 servers deliver up to 86% higher performance over the previous generation of UCS.

The M5 generation of servers include:


  • Cisco UCS B200 M5 Blade Server: a half-width blade form factor for traditional multi-tier or distributed applications. It supports two GPUs.
  • Cisco UCS B480 M5 Blade Server: for workloads ranging from memory-intensive, mission-critical enterprise applications to distributed database virtualized workloads.
  • Cisco UCS C220 M5 Rack Server: aa high-density 2-socket rack server that delivers performance and efficiency for a wide range of workloads, including virtualization, collaboration, and bare-metal applications.
  • Cisco UCS C240 M5 Rack Server: a storage and I/O optimized enterprise-class rack server for big data analytics, software-defined storage and bare metal applications.
  • Cisco UCS C480 M5 Rack Server: featuring a modular architecture for flexible technology refreshes, the C480 delivers scale-up extensibility for in-memory databases, big data analytics, virtualization, VDI and bare metal applications. GPU support has tripled—with up to six supported—as has disk capacity, which now supports 32 drives.

“As organizations strive to become more competitive through real-time analytics and faster decision-making, new thinking around data center infrastructure is required,” said Liz Centoni, senior vice president and general manager, Cisco Computing Systems Product Group. “Our unique, unified system architecture delivers the agility our customers need to create a cloud experience on-prem, so that our new line of servers simply means faster applications with fewer complications.”

http://www.cisco.com

Tuesday, July 11, 2017

Huawei details Boundless Computing server strategy and solutions

Huawei announced in Beijing the launch of its Boundless Computing server strategy and series solutions, which focuses on industry requirements for digital transformation and outlines the company's 5-year innovation roadmap for computing.

During the launch event, Huawei delivered an overview of the server strategy and its business positioning, and also launched its V5 series solutions, which include the all-flash SAP HANA appliance solution, a big data application acceleration solution, edge computing for smart video analytics solution, and the G series heterogeneous computing platform.

Huawei's Boundless Computing vision encompasses optimising computing for applications and bringing computing power closer to data sources to help realise the potential of computing. It also includes progressing beyond servers and enabling data centre-level resource pooling and on-demand provisioning to improve the computing efficiency of data centres.

The strategy also involves going beyond the limits the of data centre to enable smart access, and expanding computing into the data sources to enhance the intelligence of data at the remote end.

At the release ceremony, Huawei, together with customers and partners including Industrial and Commercial Bank of China, Tencent, SAP and Microsoft, discussed the challenges to computing development and how they can be addresses. Huawei also released the FusionServer V5 delivering five key smart features.

Describing the strategy, Qiu Long, president, IT server product line at Huawei, said, "A fully connected world is unfolding and computing will be the pivotal force behind everything… the Boundless Computing strategy is about rethinking the road to a fully connected world, that includes unlocking the potential of computing, going beyond the boundary of servers, and extending further beyond the boundary of data centres".


Tuesday, June 13, 2017

Dell'Oro reports white box server shipments up 41% yr/yr in Q1

According to the latest Server Quarterly Report from Dell'Oro Group, white box server shipments continued to grow at a rapid pace in the first quarter, increasing 41% year on year, with the first quarter growth led principally by Google and Amazon, although Facebook and Microsoft are expected to increase their spending in the second quarter of 2017.

Highlights from Dell'Oro's server report for the first quarter of 2017 include:

1.         Overall cloud data centre expenditure is projected to remain strong for the remainder of the year, although it is forecast to be uneven during the year across the major cloud providers Google, Microsoft, Amazon and Facebook.

2.         The cloud providers are expected to continue to build-out data centres at a high rate and to invest in the latest server technologies based on the Intel Purley platform and 25 Gbit/s single-lane SerDes technology.

3.         Most of the major U.S.-based branded vendors, led by Hewlett-Packard Enterprise (HPE) and Dell Technologies, experienced quarter over quarter and year on year shipment declines due to a number of factors, including server migration from the enterprise/on premise to the cloud, typical first quarter weakness, and a pause in server purchases ahead of the Intel Purley server refresh cycle, which is expected in the second half of 2017.

Commenting on the report, Baron Fung, senior business analysis manager at Dell'Oro Group, noted, "Dell'Oro believes that most of the growth in the server market will come from cloud deployments… while the upcoming Intel Purley refresh cycle may spur overdue spending in enterprise, it will be the cloud providers that will set the market growth pace in 2017."

Friday, March 24, 2017

Microsoft's Project Olympus provides an opening for ARM

A key observation from this year's Open Compute Summit is that the hyper-scale cloud vendors are indeed calling the shots in terms of hardware design for their data centres. This extends all the way from the chassis configurations to storage, networking, protocol stacks and now customised silicon.

To recap, Facebook's newly refreshed server line-up now has 7 models, each optimised for different workloads: Type 1 (Web); Type 2 - Flash (database); Type 3 – HDD (database); Type 4 (Hadoop); Type 5 (photos); Type 6 (multi-service); and Type 7 (cold storage). Racks of these servers are populated with a ToR switch followed by sleds with either the compute or storage resources.

In comparison, Microsoft, which was also a keynote presenter at this year's OCP Summit, is taking a slightly different approach with its Project Olympus universal server. Here the idea is also to reduce the cost and complexity of its Azure rollout in hyper-scale date centres around the world, but to do so using a universal server platform design. Project Olympus uses either a 1 RU or 2 RU chassis and various modules for adapting the server for various workloads or electrical inputs. Significantly, it is the first OCP server to support both Intel and ARM-based CPUs. 

Not surprisingly, Intel is looking to continue its role as the mainstay CPU supplier for data centre servers. Project Olympus will use the next generation Intel Xeon processors, code-named Skylake, and with its new FPGA capability in-house, Intel is sure to supply more silicon accelerators for Azure data centres. Jason Waxman, GM of Intel's Data Center Group, showed off a prototype Project Olympus server integrating Arria 10 FPGAs. Meanwhile, in a keynote presentation, Microsoft Distinguished Engineer Leendert van Doorn confirmed that ARM processors are now part of Project Olympus.

Microsoft showed Olympus versions running Windows server on Cavium's ThunderX2 and Qualcomm's 10 nm Centriq 2400, which offers 48 cores. AMD is another CPU partner for Olympus with its ARM-based processor, code-named Naples.  In addition, there are other ARM licensees waiting in the wings with designs aimed at data centres, including MACOM (AppliedMicro's X-Gene 3 processor) and Nephos, a spin-out from MediaTek. For Cavium and Qualcomm, the case for ARM-powered servers comes down to optimised performance for certain workloads, and in OCP Summit presentations, both companies cited web indexing and search as one of the first applications that Microsoft is using to test their processors.

Project Olympus is also putting forward an OCP design aimed at accelerating AI in its next-gen cloud infrastructure. Microsoft, together with NVIDIA and Ingrasys, is proposing a hyper-scale GPU accelerator chassis for AI. The design, code named HGX-1, will package eight of NVIDIA's latest Pascal GPUs connected via NVIDIA’s NVLink technology. The NVLink technology can scale to provide extremely high connectivity between as many as 32 GPUs - conceivably 4 HGX-1 boxes linked as one. A standardised AI chassis would enable Microsoft to rapidly rollout the same technology to all of its Azure data centres worldwide.

In tests published a few months ago, NVIDIA said its earlier DGX-1 server, which uses Pascal-powered Tesla P100 GPUs and an NVLink implementation, were delivering 170x of the performance of standard Xeon E5 CPUs when running Microsoft’s Cognitive Toolkit.

Meanwhile, Intel has introduced the second generation of its Rack Scale Design for OCP. This brings improvements in the management software for integrating OCP systems in a hyper-scale data centre and also adds open APIs to the Snap open source telemetry framework so that other partners can contribute to the management of each rack as an integrated system. This concept of easier data centre management was illustrated in an OCP keynote by Yahoo Japan, which amazingly delivers 62 billion page views per day to its users and remains the most popular website in that nation. The Yahoo Japan presentation focused on an OCP-compliant data centre it operates in the state of Washington, its only overseas data centre. The remote data centre facility is manned by only a skeleton crew that through streamlined OCP designs is able to perform most hardware maintenance tasks, such as replacing a disk drive, memory module or CPU, in less than two minutes.

One further note on Intel’s OCP efforts relates to its 100 Gbit/s CWDM4 silicon photonics modules, which it states are ramping up in shipment volume. These are lower cost 100 Gbit/s optical interfaces that run over up to 2 km for cross data centre connectivity.

On the OCP-compliant storage front not everything is flash, with spinning HDDs still in play. Seagate has recently announced a 12 Tbytes 3.5 HDD engineered to accommodate 550 Tbyte workloads annually. The company claims MTBF (mean time between failure) of 2.5 million hours and the drive is designed to operate 24/7 for five years. These 12 Tbyte enable a single 42 U rack to deploy over 10 Pbytes of storage, quite an amazing density considering how much bandwidth would be required to move this volume of data.


Google did not make a keynote appearance at this year’s OCP Summit, but had its own event underway in nearby San Francisco. The Google Cloud Next event gave the company an even bigger stage to present its vision for cloud services and the infrastructure needed to support it.

Thursday, February 9, 2017

Cisco Offers Integrated Azure Stack in its UCS Platform

Cisco will begin offering Microsoft Azure Stack on its Unified Computing System platforms. The integrated, validated system enables organizations to deliver Microsoft Azure services from their on-premises data center.

“Cisco and Microsoft are coming together to offer a hybrid cloud solution built on the power of UCS and Microsoft Azure,” said Liz Centoni, senior vice president and general manager, Computing Systems Product Group, Cisco. “Through our joint engineering efforts, application developers and IT managers will have a turnkey solution that is easy to deploy, manage and scale.”

“Microsoft and Cisco are proven innovators and trusted technology partners, giving customers the confidence their IT environments can be supported and secure. Microsoft Azure Stack provides services and application programming interfaces (APIs) compatible with the Azure public cloud, allowing developers to do their best work while giving them the agility to deploy their applications to public, private or hosted clouds,” said Mike Neil, corporate vice president, Azure Infrastructure & Management, Microsoft Corporation.

https://newsroom.cisco.com/press-release-content?type=press-release&articleId=1819842

Thursday, December 1, 2016

IDC: Worldwide Server Sales Decline 7% in Q3

Vendor revenue in the worldwide server market declined 7.0% year over year to $12.5 billion in the third quarter of 2016 (3Q16), according to the International Data Corporation (IDC) Worldwide Quarterly Server Tracker. Server demand across enterprise portfolios was soft for the quarter, and demand for high-end systems experienced a year-over-year revenue decline of 25.0% to $1.1 billion.

IDC said overall server market growth had recently slowed in part due to a slowdown in hyperscale datacenter growth and continued drag from declining high-end server sales. In addition, the robust enterprise refresh cycle of 2015 has created difficult comparisons in 2016 to the prior year's quarterly results. Worldwide server shipments decreased 4.6% to 2.38 million units in 3Q16 when compared with the same year-ago period.

"The server market suffered a difficult quarter as previously healthy volume server growth faltered, suggesting that weakness in enterprise demand was more pronounced than expected," said Kuba Stolarski, research director, Computing Platforms at IDC. "While cloud datacenter buildouts by key hyperscalers helped in part to prop up the quarterly results, the overwhelming downward trend was difficult to overcome. It remains to be seen whether hyperscale can drive enough demand to keep the market positive going into the home stretch of 2016."

Some highlights:

  • Hewlett Packard Enterprise (HPE) retained the number 1 spot in the worldwide server market with 25.9% market share in vendor revenue for 3Q16, as revenue decreased 12.1% year over year to $3.2 billion. 
  • Dell Technologies maintained its number 2 position in the worldwide server market with 17.8% of vendor revenue for the quarter, while revenue decreased 8.7% year over year to $2.2 billion. 
  • Lenovo and Cisco both moved up into a three-way tie* for the third market position with IBM, with 7.9%, 7.4%, and 6.9% revenue share, respectively. Lenovo's revenue declined 7.4% to $986 million, while Cisco grew its revenue 4.8% to $928 million. IBM's revenue decreased 32.9% year over year to $864 million in 3Q16.


http://www.idc.com/getdoc.jsp?containerId=prUS41969816

Monday, October 31, 2016

Microsoft Announces Project Olympus - OCP Hardware Designs

Microsoft, in collaboration with the Open Compute Project (OCP), announced Project Olympus – a next generation hyperscale cloud hardware design and a new model for open source hardware development with the OCP community.

With Project Olympus, Microsoft said it hopes to foster a model of open source collaboration that has been embraced for software but has historically been at odds with the physical demands of developing hardware. Rather than contributing a fully-completed design to OCP, with this new approach, Microsoft will contribute its next generation cloud hardware designs when they are approximately 50% complete.  This is intended to encourage community involvement in the iterative design process.

“Microsoft is opening the door to a new era of open source hardware development. Project Olympus, the re-imagined collaboration model and the way they’re bringing it to market, is unprecedented in the history of OCP and open source datacenter hardware,” said Bill Carter, Chief Technology Officer, Open Compute Project Foundation.

The building blocks that Project Olympus will contribute consist of a new universal motherboard, high-availability power supply with included batteries, 1U/2U server chassis, high-density storage expansion, a new universal rack power distribution unit (PDU) for global datacenter interoperability, and a standards compliant rack management card.

Microsoft noted that over 90% of the servers it currently purchases are based on OCP contributed specifications.

https://azure.microsoft.com/en-us/blog/microsoft-reimagines-open-source-cloud-hardware/

Sunday, October 16, 2016

OpenCAPI Looks to Redefine Server Architecture Beyond PCIe

Major industry vendors announced their support for OpenCAPI, a new standard that 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. The idea is to re-architect servers to remove system bottlenecks, putting the compute power closer to the data -- and to do so with an open (non-Intel) design.

Backers of the newly formed OpenCAPI Consortium include AMD, Dell EMC, Google, Hewlett Packard Enterprise, IBM, Mellanox Technologies, Micron, NVIDIA and Xilinx.

OpenCAPI said its high bandwidth, low latency open interface is capable of 25 Gbps, outperforming the current PCIe specification which offers a maximum data transfer rate of 16 Gbps.

Several companies announced plans to introduce and deploy OpenCAPI enabled products, including:

  • IBM plans to introduce POWER9-based servers that leverage the OpenCAPI specification in the second half of 2017. Additionally, IBM will enable members of OpenPOWER Foundation to introduce OpenCAPI enabled products in the second half 2017.
  • 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.
  • Mellanox plans to enable the new specification capabilities in its future products.
  • Xilinx plans to support OpenCAPI enabled FPGAs.


The OpenCAPI consortium said it intends to make the OpenCAPI specification fully available to the public at no charge before the end of the year.

IBM first introduced CAPI technology to the industry in 2014 with our POWER8 processor and made it available to our OpenPOWER partners. Since then, the industry has embraced and validated its potential as a game-changing technology for the most important modern workloads including artificial intelligence, advanced data analytics and deep learning,” said Brad McCredie, IBM Fellow and Vice President of POWER Development. “As a result of this initial success, IBM has decided to double down on our commitment to open standards and enablement of industry innovation by opening up access to our CAPI technology to the entire industry. With the support of our OpenCAPI co-founders, we have created a new OpenCAPI specification that tremendously improves performance over our prior specification and IBM will be among the first to implement it with our POWER9 products expected in 2017.”

http://www.opencapi.org

Monday, September 19, 2016

IDC: Worldwide Server Market Revenue Declines 0.4% in Q2

Vendor revenue in the worldwide server market declined 0.4% year over year to $13.4 billion in the second quarter of 2016 (2Q16), according to the International Data Corporation (IDC) Worldwide Quarterly Server Tracker.

IDC attributed the slowing market to a pause in hyperscale datacenter expansion and the continued drag from high-end server sale declines. In addition, the robust enterprise refresh cycle of 2015 will create difficult comparisons in 2016 to the prior year’s quarterly results.

Some highlights:

  • Worldwide server shipments increased 2.6% to 2.4 million units in 2Q16 when compared with the same year-ago period.
  • On a year-over-year basis, volume system revenue increased 5.3% and midrange system demand increased 12.7% in 2Q16 to $10.6 billion and $1.3 billion, respectively. 
  • Hewlett Packard Enterprise (HPE) retained the number 1 spot in the worldwide server market with 25.4% market share in vendor revenue for 2Q16, as revenue decreased 0.3% year over year to $3.4 billion. 
  • HPE's year-over-year growth rate as reported by IDC was impacted by the start of the H3C partnership in China that began in May of 2016; as a result, a portion of HPE-designed servers were rebranded as H3C for the China market. Had these systems been branded as HPE servers, their worldwide server market share would have been 26.6% in vendor revenue for the quarter as revenue increased 4.2% year over year to $3.6 billion. 
  • Dell maintained its number 2 position in the worldwide server market, building on server revenue growth of 10.0% year over year to $2.6 billion, resulting in 19.3% vendor revenue market share in 2Q16. IBM retained the number 3 position with 9.8% share for the quarter as revenue decreased -34.0% year-over-year to $1.3 billion in 2Q16, as both POWER systems and system z mainframes experienced double-digit declines. 
  • Lenovo and Cisco tied for the number 4 position for the second consecutive quarter with 7.2% and 6.4% market shares, respectively. Lenovo earned $969 million in revenues following an increase of 2.1%, while Cisco's revenues declined 0.7% year over year to $860 million.
  • ARM sales have yet to make an impact on the server market.


"The server market is progressing exactly as expected, with close to flat growth in the second quarter, following a difficult first quarter, but growth in volume servers is still healthy, which is a good sign for the market moving forward," said Kuba Stolarski, research director, Computing Platforms at IDC. "As we prepare for the second half of 2016, expect to see market growth led by cloud datacenter buildouts from key hyperscalers. Looking out further, the market will be impacted by digital transformation initiatives, including the Internet of Things and cognitive computing, and by a continuing shift towards software-defined infrastructure."

http://www.idc.com

Tuesday, July 19, 2016

LinkedIn's Open19 Project Aims for New Rack/Server Spec

LinkedIn is launching a new Open19 project that aims to establish a new open standard for servers based on a common form factor.

LinkedIn believes a new spec could lead to lower cost per rack, lower cost per server, and optimized power utilization in its hyperscale, cloud data centers. The project is open and industry participation is welcomed.

The Open19 platform is based on standard building blocks with the following specifications:

  • Standard 19-inch 4 post rack;
  • Brick cage;
  • Brick (B), Double Brick (DB), Double High Brick (DHB);
  • Power shelf—12 volt distribution, OTS power modules;
  • Optional Battery Backup Unit (BBU);
  • Optional Networking switch (ToR);
  • Snap-on power cables/PCB—200-250 watts per brick;
  • Snap-on data cables—up to 100G per brick;
  • Provides linear growth on power and bandwidth based on brick size.


https://engineering.linkedin.com/blog/2016/07/open19--a-new-vision-for-the-data-center-
http://open19.org/

LinkedIn Acquisition Brings More Cloud Services and Traffic


Microsoft agreed to acquire LinkedIn for $26.2 billion in cash, giving it the world’s largest social network for professional contacts. LinkedIn highlights: 19 percent growth year over year (YOY) to more than 433 million members worldwide 9 percent growth YOY to more than 105 million unique visiting members per month 49 percent growth YOY to 60 percent mobile usage 34 percent growth YOY to more than 45 billion quarterly member page views 101 percent...

LinkedIn Develops its Own Data Center Switch


LinkedIn's engineering team has developed its own data center switch to keep up with the rapidly growing traffic demands of its professional, social network. The new switch, dubbed "Pigeon", is a 3.2 Tbps switching platform that can be used as a leaf or spine switch. It uses Broadcom's latest Tomahawk silicon (32X100G) and switch software developed in house. In a blog post, Zaid Ali Kahn describes why the company decided to take on the difficult...


Thursday, July 7, 2016

Skyport Interoperates with Cisco ACI

Skyport Systems, a start-up offering secure infrastructure solutions, announced interoperability between its SkySecure platform and Cisco’s Application Centric Infrastructure (ACI) solution.

The goal is to provide application-layer and system-level security and policy controls needed to extend the trust boundary from a system-level root-of-trust to the network edge. Skyport said its interoperability with Cisco ACI also mobilizes security policies, enabling them to follow workloads throughout their lifecycles, and lets users deploy and maintain secure administrative workstations, jump hosts and multi-zone DMZ architectures as an integral part of an overall security framework.

Skyport's SkySecure converged system brings together zero trust compute, virtualization and a full stack of security technologies. It logs all traffic at a forensically auditable level, enabling users to see where traffic originates, where it is headed, whether it was allowed or not, what policy allowed or blocked it, and when and who put that policy into action. Remote management capability allows users to easily secure branch infrastructure without firewalls, proxies, MPLS or other security measures.

“SkySecure interoperability with Cisco ACI extends policy inward to the root of trust, providing truly end-to-end application-layer security for all assets, no matter where they are deployed,” said Art Gilliland, CEO of Skyport Systems. “This builds on the work we’ve done to secure Microsoft Active Directory and other highly valuable resources, and furthers our mission to help organizations ensure security of their most critical IT assets.”

https://www.skyportsystems.net/

Wednesday, June 1, 2016

IDC: Server Sales Drop in Q1 Due to Hyperscale Slowdown

Vendor revenue in the worldwide server market decreased 3.6% year over year to $12.4 billion in the first quarter of 2016 (1Q16), according to IDC's freshly updated Worldwide Server Tracker. The research firm attributed the decline to a pause in hyperscale server deployments as well as a clear end to the enterprise refresh cycle. IDC said worldwide server shipments decreased 3.0% to 2.2 million units in 1Q16 when compared with the same year-ago period.

"As expected, server growth slowed in the first quarter, with a clear end to the Intel-led enterprise refresh, a pause in hyperscale cloud expansion, and a very difficult year-on-year comparison in the high end of the market, coming off of a major mainframe refresh from IBM one year ago," said Kuba Stolarski, Research Director, Computing Platforms at IDC. "Now that the cyclical refresh has comes to an end, the market focus is shifting towards software-defined infrastructure, hybrid environment management, and next-gen IT domains such as the Internet of Things (IoT), robotics, and cognitive analytics. In the short term, IDC expects the second half of 2016 to re-energize hyperscale cloud infrastructure expansion with existing data centers filling out and new cloud data centers standing up across the globe."

Some highlights:

  • On a year-over-year basis, volume system revenue increased 1.8% and midrange system demand increased 8.3% in 1Q16 to $9.8 billion and $1.1 billion, respectively. 
  • Midrange systems were helped by enterprise investment in scalable systems for virtualization and consolidation, as well as increases in x86-based mission critical systems. 
  • 1Q16 demand for high-end systems experienced a year-over-year revenue decline of 33.4% to $1.4 billion on a difficult compare to the prior year, in which a major IBM system z upgrade drove a spike in mainframe system refresh.
  • Demand for x86 servers improved in 1Q16 with revenues increasing 2.6% year over year in the quarter to $10.6 billion worldwide while unit shipments declined 2.9% to 2.2 million servers. HPE led the market with 29.7% revenue share based on 5.5% revenue growth over 1Q15. Dell retained second place, securing 21.5% revenue share following a 1.8% year-over-year revenue decline.
  • Non-x86 servers experienced a revenue decline of 28.7% year over year to $1.8 billion, representing 14.7% of quarterly server revenue. IBM leads the segment with 62.7% revenue share despite a 32.9% revenue decline when compared with the first quarter of 2015. IDC also continued to track falling revenue from ARM server sales in 1Q16, with the HP Moonshot system deployments representing the largest single component.


http://www.idc.com

Monday, May 23, 2016

Netronome Integrates P4 and C Programming on Production Server NICs

Netronome introduced a P4 and C compliant Integrated Development Environment (IDE) for dynamically programming new networking capabilities on its Agilio CX and LX family of intelligent server adapters (ISAs).

The news is significant because bringing SDN capabilities into a server NIC could help identify and resolve tenant application performance bottlenecks rapidly, enabling cloud service providers to maintain high levels of user experience.

For telco NFV deployments, Netronome said its solution enables a significantly higher degree of dynamic data center traffic observability, helping telco operators to pinpoint issues related to call drops or poor call and video quality in 4G and 5G networks. AT&T and Netronome are presenting and demonstrating this use case at the P4 Language Consortium workshop this week at Stanford University.

The P4 Language Consortium, of which Netronome is an active member, is currently developing specifications for the P4 programming language and associated compilers.The Netronome IDE leverages the Consortium’s open source P4 compiler to deliver 10 Gbps to 100 Gbps performance for popular data center networking functions using the Agilio server networking platform. Extensions developed by  Netronome also enable integration with optional C-based programming for sophisticated functions such as stateful processing.

“Server-based networking has evolved as the most widely deployed form of SDN; its fundamental tenets are feature velocity and control - important requirements for data center operators,” said Sujal Das, senior vice president and general manager, marketing and corporate strategy. “As a pioneer in hardware-accelerated, server-based networking solutions, we take great pride in being the first in the industry with shipping products that can truly help customers realize the value of integrated P4 and C programming for their data center applications.”

A beta release of the Netronome IDE with Programmer Studio v6.0 featuring P4 and C programming on Agilio CX and LX ISAs is available.

http://www.netronome.com
http://www.open-nfp.org
http://www.p4.org

Netronome Brings Hardware-Acceleration to OpenStack Networking

Netronome has tuned its Agilio Server Networking Platform for delivering hardware-acceleration for OpenStack networking, allowing data centers to accelerate applications such as network virtualization, security, load balancing and telemetry using different data plane options suitable for use cases spanning traditional IT to IaaS and Telco NFV workloads. Netronome's own testing has found a 5X boost in VM performance when network functions are offloaded to its Agilio interface cards.

At this week's OpenStack Summit in Austin, Netronome, in collaboration with Ericsson and Mirantis, is showcasing acceleration of open source datapath implementations, specifically, Open vSwitch (OVS), Stateful Firewall (Connection Tracking) and OpenContrail vRouter using Agilio CX intelligent server adapters. The company said this approach will be incorporated as an enhanced OpenStack networking plug-in architecture specification. As a result, critical networking functions that would otherwise hamper performance of the OpenStack implementation are offloaded to the Agilio platform, accommodating significantly more virtual machines per server leading to up to 6X lower TCO and higher services revenue per server compared to traditional NICs.
http://www.netronome.com


Netronome's Agilio Server Networking Accelerates Cloud Data Centers

Netronome introduced its Agilio Server Networking Platform for transparently offloading server-based networking data paths, such as open virtual switch (OVS), Juniper Networks Contrail vRouter, and Linux firewall.

The company said its hardware and software-based Agilio platform delivers up to 5X higher throughput while reducing CPU requirements by up to 80 percent compared to traditional NICs and server-based networking implemented in software.

Server-based networking is being widely deployed in cloud data centers to handle virtualization, firewalls, load balancing, telemetry, zero-trust security using micro-segmentation, virtual network functions (VNFs) and application-based analytics. The big cloud providers (AWS, Microsoft Azure, Google) are using server-based networking in their mega data centers. Netronome's Agilio solution accelerates such server-based networking functions by offloading compute-intensive flow and tunnel processing from the CPUs.

The Agilio CX intelligent server adapters (ISAs) are based on Netronome's own flow processing silicon (NFP-4000) and software architecture (Agilio Software). The Agilio ISAs use onboard memory to support up to two million security policies, and deliver 28Mpps of throughput using hardware-based acceleration.

Wednesday, April 13, 2016

Everspin Samples Highest Density MRAM Non-Volatile Memory

Everspin Technologies has begun sampling a 256Mb ST-MRAM Storage Class Memory (SCM) - the highest density commercial MRAM currently on the market. The expects to sample a 1Gb product based on its proprietary perpendicular magnetic tunnel junction (pMTJ) spin torque technology (ST-MRAM) later this year.

Everspin cited the following advantages for it ST-MRAM:

  • Supports 100,000 times faster write speeds than NAND flash
  • Operates on the DDR3/DDR4 DRAM memory interface
  • Requires no wear leveling
  • Provides the highest endurance of currently available non-volatile memories
  • Delivers low power operation
  • Enables instant on/off functionality

“We continue to bring the fastest non-volatile products to our customers, expanding our offering with a high density 1Gb DDR4 pMTJ ST-MRAM. This will provide new and innovative approaches to the way non-volatile memory solutions can be architected,” said Everspin CEO Phill LoPresti.

http://www.everspin.com

Wednesday, April 6, 2016

OpenPOWER Advances in HyperScale Data Center Race

Since its founding two years ago, the OpenPOWER Foundation, which is an open development alliance based on IBM's POWER microprocessor architecture, has grown to more than 200 participating companies and organizations. The goal is to build advanced server, networking, storage and GPU-acceleration technology for next-generation, hyperscale data centers.

At the second annual OpenPOWER Summit held in San Jose this week, more than 50 new infrastructure and software innovations, spanning the entire system stack, including systems, boards, cards and accelerators are showcased.

Some highlights:

  • New Servers for High Performance Computing and Cloud Deployments – Foundation members introduced more than 10 new OpenPOWER servers, offering expanded services for high performance computing and server virtualization.
  • Google is developing a next-generation OpenPOWER and Open Compute Project form factor server. Google is working with Rackspace to co-develop an open server specification based on the new POWER9 architecture, and the two companies will submit a candidate server design to the Open Compute Project.
  • Rackspace announced that “Barreleye” has moved from the lab to the data center. Rackspace anticipates “Barreleye” will move into broader availability throughout the rest of the year, with the first applications on the Rackspace Public Cloud powered by OpenStack. Rackspace and IBM collectively contributed the “Barreleye” specifications to the Open Compute Project in January 2016.
  • IBM, in collaboration with NVIDIA and Wistron, plans to release its second-generation OpenPOWER server, which includes support for the NVIDIA Tesla Accelerated Computing platform. The server will leverage POWER8 processors connected directly to the new NVIDIA Tesla P100 GPU accelerators via the NVIDIA NVLink high-speed interconnect technology. Early systems will be available in Q4 2016. Additionally, IBM and NVIDIA plan to create global acceleration labs to help developers and ISVs port applications on the POWER8 and NVIDIA NVLink-based platform.
  • Expanded use of CAPI for Acceleration Technology – Foundation members, including Bittware, IBM, Mellanox and Xilinx, unveiled more than a dozen new accelerator solutions based on the Coherent Accelerator Processor Interface (CAPI). Alpha Data also unveiled a Xilinx FPGA-based CAPI hardware card at the Summit. These new accelerator technologies leverage CAPI to provide performance, cost and power benefits when compared to application programs running on a core or custom acceleration implementation attached via non-coherent interfaces. This is a key differentiator in building infrastructure to accelerate computation of big data and analytics workloads on the POWER architecture.
  • A Continued Commitment to Genomics Research – Following successful collaborations with LSU and tranSMART, OpenPOWER Foundation members continue to develop new advancements for genomics research. Edico Genome announced the DRAGEN Genomics Platform, a new appliance that enables ultra-rapid analysis of genomic data, reducing the time to analyze an entire genome from hours to just minutes, allowing healthcare providers to identify patients at higher risk for cancer before conditions worsen.
“To meet the demands of today’s data centers, businesses need open system design that provides greater f1exibility and speed at a lower cost,” said Calista Redmond, President of the OpenPOWER Foundation and Director of OpenPOWER Global Alliances, IBM. “The innovations introduced today demonstrate OpenPOWER members’ commitment to building technology infrastructures that provide customers with more choice, allowing them to leverage increased data workloads and analytics to drive better business outcomes.”

https://cloudplatform.googleblog.com/2016/04/Google-and-Rackspace-co-develop-open-server-architecture-based-on-new-IBM-POWER9-hardware.html
http://openpowerfoundation.org/

Thursday, March 31, 2016

HPE Pushes Ahead with Persistent Memory

Hewlett Packard Enterprise (HPE) introduced new compute platforms with built-in support for Persistent Memory, a technology that combines the performance of high-speed memory and the persistence of storage to deliver new levels of application performance. The technology will be available for new HPE ProLiant Gen9 servers.

Some highlights:

HPE Persistent Memory. The first product in the HPE Persistent Memory portfolio is a an 8GB NVDIMM that is designed to accelerate database and analytic workloads. The HPE 8GB NVDIMM is designed around industry-standard NVDIMM-N technology, working with standards bodies such as JEDEC and SNIA, and includes back-up power from the HPE Smart Storage Battery, which supports up to 16 NVDIMMs for moving data from DRAM to Flash when power is lost.

New Intel Xeon platform. Designed to support up to 22 cores and memory speeds of up to 2400MT/s, the new Intel Xeon E5-2600 v41 processor offers up to 25 percent performance gains2 for HPE ProLiant Gen9 servers. The Intel Xeon E5-2600 v4 processors include virtualization enhancements, added security and improved orchestration capabilities to help customers better manage shared platform resources.

State of the art solid state drives (SSDs). HPE NVMe SSDs are compact, economical and offer up to 2TB of storage in a flexible package that includes Express Bay for front access to drives that are designed for big-ticket jobs, including online transaction processing, business intelligence and Big Data analytics.

Smart authentication. Adding TCG Trusted Platform Module (TPM) 2.0 specification 1.16 to HPE ProLiant Gen 9 servers provides a tamper-resistant environment to prevent unauthorized access to servers. TPM supports Microsoft BitLocker, which securely stores authentication elements, such as passwords and encryption keys.

HPE Application Migration to Cloud Solution. Secure, tested and validated reference architecture delivered by HPE Technology Services experts to help customers migrate on-premises applications to a private cloud.

http://www.hpe.com

Dell Releases 13th Gen PowerEdge Servers

Dell launched its 13th generation of PowerEdge 13th generation rack, tower, blade and converged infrastructure architecture servers. The major improvements include over 20 percent improved performance with differentiated air-cooled support and over 12 percent enhanced memory bandwidth aligned to Intel Xeon processor E5-2600 v4 updates.

“Customers are driving the rise of the software defined data center, using workload-oriented solutions that are increasingly compute-centric,” said Ashley Gorakhpurwalla, vice president and general manager, Dell Server Solutions. “Dell’s global x86 leadership gains, particularly in blade servers, are a terrific indicator of how we deliver on these customer needs. Dell PowerEdge 13th generation servers include practical innovations, based on product knowledge that spans our 20-year history, to deliver the right functionality to enable customers’ future-ready datacenters.”

http://www.dell.com/learn/us/en/04/campaigns/poweredge-13g-server

Tuesday, March 15, 2016

Skyport Raises $30 Million from GV and Cisco

Skyport Systems announced a $30 million round of funding led by GV (formerly known as Google Ventures), with participation from Cisco Investments, Thomvest Ventures, Northgate Capital and InstantScale, as well as existing investors Index Ventures, Sutter Hill Ventures and Intel Capital. This Series C round brings total Skyport funding to $67 million.

Skyport, which is based in Mountain View, California, specializes in secure infrastructure for protecting IT environments from attacks while providing total visibility into all traffic and administrative changes. Skyport SkySecure is the first commercial Hyper-Secure Infrastructure architected from the ground up to provide continuous validation to ensure system integrity and remote management to ensure auditability.

“Security leaders have been saying for decades that security needs to be built in from the ground up yet most solutions just bolt on or around. If organizations are serious about protecting their information they need to consider that now is the time to re-platform for security.” said Art Gilliland, CEO of Skyport Systems. “Skyport Systems’ approach delivers powerful security protections in a pre-integrated easy-to-use system saving customers money and helping them achieve a high level of security and compliance.”

http://www.skyportsystems.com


  

Tuesday, February 23, 2016

Skyport Offers Hardened Servers for Microsoft Active Directory.

Skyport Systems announced a turnkey solution to deliver a hardened implementation of Microsoft Active Directory.

Through a partnership with Ascent Solutions, Skyport SkySecure delivers bundles for data center Active Directory production forests, highly secure ‘Red Forest’ administrative zones and cloud access DMZ authentication services.  Skyport said this provides a clean source computing platform with secure boot and ongoing malware and rootkit prevention and detection.

As part of this solution, Skyport Systems is announcing new SkySecure capabilities specifically designed to help secure the Active Directory environment. These include:

  • Kerberos ticket inspection to mitigate fraudulent administrator log-ins, ‘golden ticket’ attacks, and unacceptable use of older NTLM protocol versions
  • Authorized/unauthorized administrative access enforcement and accounting of all logon sessions and attempted sessions into and out of secure administrative environments
  • Application-layer microsegmentation that enables secured communications only between participating servers in the architecture
  • Active audit reports to validate the on-going operation and continuous monitoring of the architecture and its consistency with ongoing best practices evolution
  • Continuous validation of the clean source status for the computing platform including all components, software and updates that are admitted into the secure enclave

“Working with Ascent Solutions will greatly simplify a critical area of enterprise security for our customers,” said Art Gilliland, CEO of Skyport Systems. “Skyport Systems’ clean source, zero-trust infrastructure makes critical IT assets such as credential management systems secure by default, making it an ideal system to use for implementing Microsoft’s most recent guidance on securing privileged access.”

http://www.ascentclouds.com
http://www.skyportsystems.com

See also