Page 2,527«..1020..2,5262,5272,5282,529..2,540..»

Scale-out processors: Bridging the efficiency gap between servers and emerging cloud workloads

To support the growing popularity and continued expansion of cloud services, providers must overcome the physical space and power constraints that limit the growth of data centers. Problematically, the predominant processor micro-architecture is inherently inefficient for running these demanding scale-out workloads, which results in low compute density and poor trade-offs between performance and energy. Continuing the current trends for data production and analysis will further exacerbate these inefficiencies.

Improving the clouds computational resources whilst operating within physical constraints requires server efficiency to be optimized in order to ensure that server hardware meets the needs of scale-out workloads.

To this end, the team of HiPEAC member Babak Falsafi, a Professor in the School of Computer and Communication Sciences at EPFL, the director of the EcoCloud research center at EPFL (founded to innovate future energy-efficient and environmentally friendly cloud technologies), presented Clearing the Clouds: A Study of Emerging Workloads on Modern Hardware, which received the best paper award as ASPLOS 2012. ASPLOS is a flagship international computer systems venue with a high citation index.

While we have been studying and tuning conventional server workloads (such as transaction processing and decision support) on hardware for over a decade, we really wanted to see how emerging scale-out workloads in modern datacenters behave. says Falsafi. To our surprise, we found that much of a modern server processors hardware resources including the cores, caches and off-chip connectivity are overprovisioned when running scale-out workloads leading to huge inefficiencies.

Mike Ferdman, a senior PhD student team member explains: efficiently executing scale-out workloads requires optimizing the instruction-fetch path for up to a few megabytes of program instructions, reducing the core complexity while increasing core counts, and shrinking the capacity of on-die caches to reduce area and power overheads.

Scale-out Processors

The insights from the evaluation are now driving us to develop server processors tuned to the demands of scale-out workloads, says Boris Grot a postdoctoral team member. In a paper that will appear in the flagship computer architecture conference, ISCA, this year, our team proposes the Scale-Out Processor, a processor organization that unlike current industrial chip design trends does away with power-hungry cores and much of on-die cache capacity and network fabric to free area and power for a large number of simple cores built around a streamlined memory hierarchy. Not only do these improvements lead to greater performance and efficiency at the level of each processor chip, they also enable a net reduction in the total cost of ownership in datacenters.

Provided by EuroCloud

Read this article:
Scale-out processors: Bridging the efficiency gap between servers and emerging cloud workloads

Read More..

Racemi Joins Rackspace Cloud Tools Program

ATLANTA, March 21, 2012 (GLOBE NEWSWIRE) -- Racemi, provider of technology that accelerates migrations to cloud computing, today announced it has joined the Cloud Tools Network with Rackspace(R) Hosting, (NYSE: RAX - News), the world's leading specialist in the hosting and cloud computing industry.

Through this joint collaboration , Rackspace Cloud customers can seamlessly migrate existing applications using Racemi Cloud Path, which migrates applications in their current tested and proven configuration without requiring server rebuilds or additional technology stacks.

Rackspace Cloud Tools is a showcase site for the company's strategic partners and independent developers to work with Rackspace Cloud in order to share tools, applications and services.

"Cloud Path users tell us that they love the speed of migrations, our Zero Risk licensing plan, and that our technology doesn't require any on-premises infrastructure," said James Strayer, vice president of product management, Racemi.

Racemi Cloud Path is a Software as a Service (SaaS) offering that allows businesses to migrate their existing applications into the cloud quickly, without costly professional services or rebuilding servers. The Cloud Path technology moves the entire server "stack" - operating system, applications and configuration.

"Migrating existing applications can be time-consuming, often requiring in-house or consulting personnel to rebuild servers from scratch," said Bob Bardwell, business development manager at Rackspace. "We are pleased to be working with an innovative company like Racemi that is addressing these migration challenges."

About Racemi

Racemi has been named a "Cool Vendor" and has received other industry awards.

Racemi builds server imaging and cloud migration technology allowing companies to quickly capture and move their existing server images to, from and between cloud providers and across data centers. Racemi enables OEM partners to automate private data centers by leveraging its market-leading server imaging technology to rapidly provision servers in any automated use case including rapidly deploying enterprise images to cloud computing resources. For MSPs (managed service providers), Racemi is the fastest and best method for on-boarding customers to their cloud.

For more information, visit

Go here to read the rest:
Racemi Joins Rackspace Cloud Tools Program

Read More..

OpenStack-Powered Cloud Solution is Fast, Easy and Available Now – Video

20-03-2012 03:53 The OpenStack-Powered Cloud Solution is fast, easy, and available now. With Dell-developed Crowbar software, you can stand up an OpenStack cloud in minutes. Its modular framework eases ongoing maintenance and evolution of your cloud infrastructure. And, it's available now, with a reference architecture and deployment guide.

View post:

OpenStack-Powered Cloud Solution is Fast, Easy and Available Now - Video

Read More..

MachPanel Demo for Enterprise Web Hosting – SaaS and Cloud Hosting Control Panel – Video

20-03-2012 04:05 MachSol ( provides MachPanel -- SaaS enabled hybrid control panel supporting Exchange 2010 SP2, SharePoint 2010, CRM 2011, Lync 2010, BlackBerry Enterprise & Express servers -- Virtualization and Cloud Automation Solutions by MachSol Inc. Get Special Discount and Offers Today! Act Now on http

Originally posted here:

MachPanel Demo for Enterprise Web Hosting - SaaS and Cloud Hosting Control Panel - Video

Read More..

Cloud Hosting Your Website: Cloud Hosting Providers – Video

20-03-2012 09:01 Cloud Web Site Hosting can make your website faster, more robust and even save you money, compared with other premium hosting options such as Dedicated and Virtual Private Servers (VPS) Web Hosting. Cloud web hosting solutions offer considerable advantages for your web site or business, but finding the right cloud website hosting provider can be difficult, especially if you aren't already familiar with server configuration and management. Cloud Hosting Providers help you choose the best web hosting for your needs, with detailed comparisons of leading Australian Cloud Web Hosting services. For more information, visit

Here is the original post:

Cloud Hosting Your Website: Cloud Hosting Providers - Video

Read More..

Understanding the Cloud Computing Stack: SaaS, PaaS and IaaS | CloudU – Video

19-03-2012 14:47 In this installment of the CloudU video series, CloudU curator Ben Kepes, discusses the different components of the Cloud Computing stack: software-as-service, platform-as-a-service and infrastructure-as-service. CloudU is a vendor-neutral and totally free Cloud Computing curriculum and certificate program. Watch more videos and learn more at

Follow this link:

Understanding the Cloud Computing Stack: SaaS, PaaS and IaaS | CloudU - Video

Read More..

ServiceMesh Makes the Enterprise Cloud More Reliable, Governed and Secure

SANTA MONICA, CA--(Marketwire -03/20/12)- ServiceMesh, provider of the market-leading enterprise cloud platform for Global 2000 companies, today announced the availability of the Agility Platform version 7.4, with new features to help enterprises transform their costly and constrained IT services delivery approach into an application-centric, agile IT operating model that quickly aligns to business needs. The ServiceMesh Agility Platform is the only enterprise-grade solution on the market that accelerates this transformation by managing the lifecycle of cloud applications independent of the underlying infrastructure while maintaining compliance, security and governance through flexible policy definition and enforcement. The result is a significant reduction in the cost, complexity, and time to market for application solution delivery.

Global 2000 customers are seeking ways to extend the benefits of cloud computing to more business-critical applications and data, but these organizations require stringent control over service-level performance, reliability, and governance. Agility Platform 7.4 satisfies these needs with new capabilities that include advanced disaster recovery, failover, and high-availability features for cloud applications and services. In addition, new policy-driven security and configuration management capabilities make it easier to enforce standardization and compliance requirements, while expanded support for VMware vCloud Director enables the Agility Platform to extend its governance and lifecycle management capabilities to all vCloud Director deployments.

The Industry's Only Enterprise Cloud Governance and Lifecycle Management Solution

The ServiceMesh Agility Platform has helped Global 2000 enterprises unlock the business value of cloud computing by governing, managing and securing enterprise-grade portfolios of platforms and applications across hybrid clouds. Global 2000 companies, from top five global banks to leaders in pharmaceuticals and consumer products, are using the Agility Platform to transform their IT operating models to deliver significant cost and time to market advantages:

Agility Platform 7.4 extends these benefits with new product capabilities including:


"Enterprise customers are continuing the evolution of their initial private cloud initiatives into more production rollouts," said Cameron Haight, Research Vice President, Gartner. "Given the increasing importance of the services that are being provided, IT organizations should ensure that their cloud management platforms provide increasingly robust policy-driven governance and automated configuration management to meet the business' need for scale and workload optimization."

"Agility Platform customers want to extend the benefits of a more agile and cost effective IT operating model directly to their business-critical applications, enabling more strategic competitive advantages in terms of adaptability and speed," said Frank Martinez, CTO of ServiceMesh. "The Agility Platform ensures that cloud operational excellence is inherent in an organization's business-critical workloads, enabling real-time, business-level IT requests to be aligned to the optimal underlying IT services and infrastructure with full governance, control, visibility, and security."

Learn more about the ServiceMesh Agility Platform.

Request a demonstration of the Agility Platform in action.

Visit link:

ServiceMesh Makes the Enterprise Cloud More Reliable, Governed and Secure

Read More..

AMD releases Opteron 3200 chips optimised for cloud

Advanced Micro Devices is expected to announce new Opteron 3200 series chips for low-end servers, which the company hopes will give it a competitive edge over Intel in the cloud server market.

The three Opteron 3200 chips are for use in single-socket servers for web hosting and cloud applications, according to a company presentation. The chips have up to eight processor cores, clock speeds of up to 3GHz, and draw between 45 watts and 65 watts of power.

The new chips are based on the Bulldozer processor architecture, which is also in the Opteron 6200 16-core processors and FX-series gaming chips. The Opteron 3200 launch comes after AMD in late February announced it would to acquire SeaMicro, which offers dense and power-efficient servers for cloud computing environments.

AMD's chips will likely compete against Intel's Xeon E3 series chips, which are used in SeaMicro's SM10000-XE server. Intel worked with SeaMicro on the server, but analysts have said that AMD will ultimately swap Intel's chips with its own chips.

AMD is pitching the Opteron 3200 as a "low-cost-per-core" product. The chips are priced between $99 and $129 (60-80), while Intel's E3 chips are priced between $189 and $885 (120-560). MSI, Tyan, Fujitsu and Dell are expected to launch web servers and dense systems based on the chips.

AMD's expanded product line provides an entry point to new markets, said Jim McGregor, chief technology strategist at In-Stat.

But the Opteron 3200 could be a misfit in servers if competing on price versus performance-per-watt, McGregor said. There is a growing interest in deploying low-power servers in data centres to cut energy costs, but the Opteron 3200 chips are comparatively power-hungry for such installations.

A better match would be AMD's low-power Bobcat cores, which are used in low-power PCs, McGregor said. But the company instead had to push the bigger Opteron cores for ECC memory and data protection. AMD also has not built a dedicated low-power chip for servers.

AMD's microserver strategy is unclear, but the company has to move quickly to establish a presence in the market, McGregor said. The company faces challenges from Intel, which is ahead in processor and manufacturing technology, and ARM, whose smartphone and tablet processors are being tested in servers.

Intel's low-power Atom chips are already being used in servers, and HP is scheduled to make an ARM-based dense server available for testing in the second quarter.

Here is the original post:

AMD releases Opteron 3200 chips optimised for cloud

Read More..