Univa HPC Job Bank
HPC in the Cloud


Dedicated to covering high-end cloud computing
in science, industry and the datacenter

Language Flags

ScaleMP Announces vSMP Foundation 5


CUPERTINO, Calif., Nov. 8 – ScaleMP, a leading provider of virtualization solutions for high-end computing, today announced the newest version of its server virtualization for aggregation software platform, vSMP Foundation 5. This latest release from ScaleMP includes new technologies that broaden the technical and business environments that can benefit from vSMP Foundation.

“The new functionality in vSMP Foundation 5 will help ScaleMP broaden its reach into more end users, including rapidly expanding application areas like Big Data,” said Addison Snell, CEO of Intersect360 Research. “For analytics and MapReduce types of applications, users want ease of programming and management over a scalable memory or I/O space, and vSMP Foundation gives them an opportunity to have that.”

New features available with vSMP Foundation 5

Extended hardware options:

  • Intel True Scale HCAs support - vSMP Foundation 5 supports the latest Intel True Scale Fabric 7300 Series Host Adapter as a system interconnect. By supporting this new Intel InfiniBand adapter, vSMP Foundation allows for cost-effective, high-performance VMs designed from the ground up for the Intel ecosystem.
  • 10GigE network adapters - vSMP Foundation 5 is providing customers with more choice when it comes to designing their 10GigE fabrics. This new version supports Emulex OneConnect 10GbE network adapters and the Broadcom NetXtreme II BCM578x0 family of network controllers.
  • Processor support - vSMP Foundation 5 expands processor support for the Intel Xeon Processor E5-4600 family and the AMD Opteron 6300 series – providing support for the latest generation of processors for the most demanding workloads.
  • Intel Xeon Phi coprocessor support - vSMP Foundation 5 supports the recently announced Intel Xeon Phi coprocessor, Intel’s latest entry for high performance computing in two modes: processor-virtualized mode and coprocessor-aggregated mode. Under the processor-virtualized mode, vSMP Foundation virtualizes the entire platform, both the host CPU and memory with the Intel Xeon Phi coprocessor cores and memory. Thus, any application that runs on an existing IA host system will seamlessly run on the Intel Xeon Phi coprocessor based system. Applications which are scalable will see an immediate performance gain due to having over 50 cores available running in one instance of the operating system. With a coprocessor-aggregated mode, vSMP Foundation 5 supports traditional coprocessor operational mode allowing for offloading and native execution when aggregating multiple servers to a larger virtual SMP.

New solutions:

  • Large memory solution for big-data and analytics - vSMP Foundation for Memory Expansion (MEX) is a cost and performance optimized solution for users seeking to create very large memory VMs from industry standard systems. vSMP Foundation for Memory Expansion gives applications the ability to address all of the memory available from multiple servers while running just one instance of the operating system. Terabytes (TB) of memory can be easily accessed from a collection of inexpensive servers. Its unique cost structure makes this solution appealing for big-data, genomics and analytics customers.
  • Hosted VM mode - Version 5 of vSMP Foundation will run on top of a virtual machine, in addition to physical servers. This allows cloud customers to expand memory from one VM into another VM on a different physical node. Hosted VM mode will initially support KVM (Kernel Virtual Machine) and will be expanded to additional hypervisors in the future.
  • Ethernet connectivity for Hosted VM mode - hosted VM mode allows VMs to be created using standard Ethernet adapters. By supporting Ethernet as a system interconnect for a virtualized environment in addition to InfiniBand, vSMP Foundation can now run on a cost-effective infrastructure, appealing to a more diverse set of users and service providers.

Performance:

  • Batched I/O - vSMP Foundation 5 dramatically improves the I/O performance by batching I/O operations between system boards and executing scattered I/O commands in one transfer. I/O performance improvement depends on the device type. Typical network speed improvement could be up to 5x, and disk performance as much as 2x.

Provisioning:

  • IBM Platform HPC Integration - vSMP Foundation 5 has now been integrated with IBM Platform HPC. This allows for organizations to automate the workflow for a range of application requirements. Applications that need the CPU or memory resources not immediately available in a cluster at the time of job submission will now be able to have IBM Platform HPC create virtual SMPs as needed, and release the servers back to the cluster when the workload changes.


“vSMP Foundation 5 is a significant release from ScaleMP. We are broadening our reach by extending both the infrastructure we work with as well as our integration with workload management systems,” said Shai Fultheim, founder and CEO of ScaleMP. “We are enabling very large memory systems to be created, allowing for even more massive datasets to be analyzed, through our expansion of capabilities. Big Data analytics will benefit directly from the large memory offerings we are creating with our partners.”

Pricing & Availability

vSMP Foundation 5 is offered under the ScaleMP licensing model with prices starting as low as $400 per socket. The per-socket pricing model allows for greater simplicity when it comes to selecting platforms for vSMP Foundation. It provides customers peace of mind by focusing on the virtual SMP size and capabilities rather than on the nodes size and model. Additionally, vSMP Foundation is now available with floating licenses, allowing customers to reuse the same license for future hardware generations. Floating licenses provide the best ROI from vSMP Foundation licenses. General availability of vSMP Foundation 5 is expected in 1Q2013 and will be available for early access in December.
About vSMP Foundation

vSMP Foundation aggregates multiple industry-standard off-the-shelf x86 servers into a single virtual high-end system. vSMP Foundation provides customers with an alternative to traditional expensive symmetrical multiprocessing (SMP) systems and also offers simplified clustering infrastructure with a single operating system. It supports aggregation of up to 128 servers into a single virtual SMP system, providing customers with:

  • Up to 256 TB of shared memory for large memory requirements;
  • Up to 32,768 cores virtual SMP, proven scalability and record-breaking memory bandwidth;
  • Ease of use and lowest total cost of ownership (TCO) for clusters coupled with simplified storage architecture;
  • On-demand SMP with support for most common provisioning systems, allowing for increased datacenter utilization with consolidated architecture;

About ScaleMP

ScaleMP is the leader in virtualization for high-end computing, providing maximum performance and lower total cost of ownership (TCO). The innovative Versatile SMP (vSMP) architecture aggregates multiple independent systems into a single virtual system, delivering an industry-standard, high-end symmetric multiprocessing (SMP) computer. Using software to replace custom hardware and components, ScaleMP offers a new, revolutionary computing paradigm.

-----

Source: ScaleMP

Most Read Blogs


Feature Articles

CometCloud: Using a Federated HPC-Cloud to Understand Fluid Flow in Microchannels

The ever-growing complexity of scientific and engineering problems continues to pose new computational challenges. Thus, we present a novel federation model that enables end-users with the ability to aggregate heterogeneous resource scale problems. The feasibility of this federation model has been proven, in the context of the UberCloud HPC Experiment, by gathering the most comprehensive information to date on the effects of pillars on microfluid channel flow.
Read more...

CERN, Google, and the Future of Global Science Initiatives

Large-scale, worldwide scientific initiatives rely on some cloud-based system to both coordinate efforts and manage computational efforts at peak times that cannot be contained within the combined in-house HPC resources. Last week at Google I/O, Brookhaven National Lab’s Sergey Panitkin discussed the role of the Google Compute Engine in providing computational support to ATLAS, a detector of high-energy particles at the Large Hadron Collider (LHC).
Read more...

Avoiding Scientific Computing Bottlenecks in the Cloud

Frank Ding, engineering analysis & technical computing manager at Simpson Strong-Tie, discussed the advantages of utilizing the cloud for occasional scientific computing, identified the obstacles to doing so, and proposed workarounds to some of those obstacles.
Read more...

Short Takes

Running Computational Fluid Dynamics in the Cloud

May 16, 2013 | When it comes to cloud, long distances mean unacceptably high latencies. Researchers from the University of Bonn in Germany examined those latency issues of doing CFD modeling in the cloud by utilizing a common CFD and its utilization in HPC instance types including both CPU and GPU cores of Amazon EC2.
Read more...

In Support of Cloud-based Rendering

May 10, 2013 | Australian visual effects company, Animal Logic, is considering a move to the public cloud.
Read more...

Internet2 Awards Program Seeks Innovative Applications

May 10, 2013 | Program provides cash awards up to $10,000 for the best open-source end-user applications deployed on 100G network.
Read more...

Sponsored Whitepapers

Best Practices in Big Data Storage

05/10/2013 | Cleversafe, Cray, DDN, NetApp, & Panasas | From Wall Street to Hollywood, drug discovery to homeland security, companies and organizations of all sizes and stripes are coming face to face with the challenges – and opportunities – afforded by Big Data. Before anyone can utilize these extraordinary data repositories, however, they must first harness and manage their data stores, and do so utilizing technologies that underscore affordability, security, and scalability.

Exploring the Potential of Heterogeneous Computing

04/02/2012 | AMD | Developers today are just beginning to explore the potential of heterogeneous computing, but the potential for this new paradigm is huge. This brief article reviews how the technology might impact a range of application development areas, including client experiences and cloud-based data management. As platforms like OpenCL continue to evolve, the benefits of heterogeneous computing will become even more accessible. Use this quick article to jump-start your own thinking on heterogeneous computing.

Sponsored Multimedias

Newsletters

Stay informed! Subscribe to HPC in the Cloud email Newsletters.

HPC in the Cloud Update
HPCwire Weekly Update
Digital Manufacturing Report
Datanami
HPCwire Conferences & Events
Job Bank
HPCwire Product Showcases



HPC Job Bank


Featured Events



  • June 16, 2013 - June 20, 2013
    ISC'13
    Leipzig,
    Germany

  • June 17, 2013 - June 18, 2013
    Forecast 2013
    San Francisco, CA
    United States




HPC in the Cloud Conferences & Events