Taneja Group | HPC
Join Newsletter
Forgot
password?
Register
Trusted Business Advisors, Expert Technology Analysts

Items Tagged: HPC

Profiles/Reports

Voltaire Adds 10G

In the 2nd quarter of 2007, Voltaire plans to add 10GbE capabilities to its director-class Grid Director, making Grid Director the first switch platform to support 20Gb InfiniBand, Fibre Channel, and 10GbE in a single switch. This new release of multi-service Grid Director will provide interoperable switching across multiple fabrics in both LAN/WANs and SANs.

Publish date: 02/01/07
news

InfiniBand networking for storage and converged data centers

InfiniBand networking has expanded from its high-performance computing roots to take on emerging, more mainstream use cases in today's enterprise data center.

  • Premiered: 10/29/12
  • Author: Jeff Byrne
  • Published: TechTarget: SearchStorage.com
Topic(s): TBA InfiniBand TBA Jeff Byrne TBA Data Center TBA high-performance computing TBA HPC TBA Networking TBA Storage
news

Extreme Enterprise Applications Drive Parallel File System Adoption

With the advent of big data and cloud-scale delivery, companies are racing to deploy cutting-edge services. “Extreme” applications like massive voice and image processing or complex financial analysis modeling that can push storage systems to their limits. Examples of some high visibility solutions include large-scale image pattern recognition applications and financial risk management based on high-speed decision-making. These ground-breaking solutions, made up of very different activities but with similar data storage challenges, create incredible new lines of business representing significant revenue potential.

  • Premiered: 04/30/13
  • Author: Mike Matchett
  • Published: www.infostor.com
Topic(s): TBA Big Data TBA Cloud Computing TBA HPC TBA analytics TBA scale-out TBA Cloud Storage TBA cluster computing TBA HDFS TBA Data protection
Profiles/Reports

Extreme Applications in the Enterprise Drive Parallel File System Adoption

With the advent of big data and cloud-scale delivery, companies are racing to deploy cutting-edge services that include “extreme” applications like massive voice and image processing or complex fi-nancial analysis modeling that can push storage systems to their limits. Examples of some high visi-bility and big market impacting solutions include applications based on image pattern recognition at large scale and financial risk management based on decision-making at high speed.

 
These ground-breaking solutions, made up of very different activities but with similar data storage challenges, create incredible new lines of business representing significant revenue potential. Every day here at Taneja Group we see more and more mainstream enterprises exploring similar “extreme service” opportunities. But when enterprise IT data centers take stock of what it is required to host and deliver these new services, it quickly becomes apparent that traditional clustered and even scale-out file systems - of the kind that most enterprise data centers (or cloud providers) have racks and racks of - simply can’t handle the performance requirements.

 
There are already great enterprise storage solutions for applications that need either raw throughput, high capacity, parallel access, low latency, or high availability – maybe even for two or three of those at a time. But when an “extreme” application needs all of those requirements at the same time, only supercomputing type storage in the form of parallel file systems provides a functional solution. The problem is that most commercial enterprises simply can’t afford or risk basing a line of business on an expensive research project.


The good news is that some storage vendors have been industrializing former supercomputing storage technologies, hardening massively parallel file systems into commercially viable solutions. This opens the door for revolutionary services creation, enabling mainstream enterprise datacenters to support the exploitation of new extreme applications.  
 

Publish date: 05/03/13
news

What does the next big thing in technology mean for the data center?

There are plenty of technologies touted as the next big thing. Big data, flash, high-performance computing, in-memory processing, NoSQL, virtualization, convergence, software-defined whatever all represent wild new forces that could bring real disruption but big opportunities to your local data center.

  • Premiered: 03/19/14
  • Author: Mike Matchett
  • Published: Tech Target: Search Data Center
Topic(s): TBA data TBA Data Center TBA Big Data TBA Storage TBA Flash TBA SSD TBA HPC TBA High Performance Computing TBA NoSQL TBA Virtualization TBA convergence TBA software-defined TBA Hadoop TBA scale-out TBA Apache TBA analytics TBA scalability TBA Converged Infrastructure TBA hyper convergence TBA Platform as a Service TBA PaaS TBA Hypervisor TBA Hybrid
news

IBM N Series dropped from NetApp OEM deal, E Series stays

IBM this week went public with its plans to stop rebranding NetApp FAS arrays as the IBM N Series, although it will continue to sell NetApp E Series storage.

  • Premiered: 05/29/14
  • Author: Taneja Group
  • Published: Tech Target: Search Storage
Topic(s): TBA Arun Taneja TBA IBM TBA NetApp TBA SAN TBA NAS TBA Storwize TBA HPC TBA SONAS
Profiles/Reports

Fibre Channel: The Proven and Reliable Workhorse for Enterprise Storage Networks

Mission-critical assets such as virtualized and database applications demand a proven enterprise storage protocol to meet their performance and reliability needs. Fibre Channel has long filled that need for most customers, and for good reason. Unlike competing protocols, Fibre Channel was specifically designed for storage networking, and engineered to deliver high levels of reliability and availability as well as consistent and predictable performance for enterprise applications. As a result, Fibre Channel has been the most widely used enterprise protocol for many years.

But with the widespread deployment of 10GbE technology, some customers have explored the use of other block protocols, such as iSCSI and Fibre Channel over Ethernet (FCoE), or file protocols such as NAS. Others have looked to Infiniband, which is now being touted as a storage networking solution. In marketing the strengths of these protocols, vendors often promote feeds and speeds, such as raw line rates, as a key advantage for storage networking. However, as we’ll see, there is much more to storage networking than raw speed.

It turns out that on an enterprise buyer’s scorecard, raw speed doesn’t even make the cut as an evaluation criteria. Instead, decision makers focus on factors such as a solution’s demonstrated reliability, latency, and track record in supporting Tier 1 applications. When it comes to these requirements, no other protocol can measure up to the inherent strengths of Fibre Channel in enterprise storage environments.

Despite its long, successful track record, Fibre Channel does not always get the attention and visibility that other protocols receive. While it may not be winning the media wars, Fibre Channel offers customers a clear and compelling value proposition as a storage networking solution. Looking ahead, Fibre Channel also presents an enticing technology roadmap, even as it continues to meet the storage needs of today’s most critical business applications.

In this paper, we’ll begin by looking at the key requirements customers should look for in a commercial storage protocol. We’ll then examine the technology capabilities and advantages of Fibre Channel relative to other protocols, and discuss how those translate to business benefits. Since not all vendor implementations are created equal, we’ll call out the solution set of one vendor – QLogic – as we discuss each of the requirements, highlighting it as an example of a Fibre Channel offering that goes well beyond the norm.

Publish date: 02/28/14
news

GridGain In-Memory Computing Platform Enjoys Broad Adoption as a Result of its Recent Open Source

GridGain Systems (GridGain.com), provider of the leading open source In-Memory Computing (IMC) Platform, announced that since its open source announcement on March 3, customer interest in its products has significantly accelerated and product downloads have increased by more than 900 percent in the last four months.

  • Premiered: 07/31/14
  • Author: Taneja Group
  • Published: Broadway World
Topic(s): TBA GridGain TBA Mike Matchett TBA HPC TBA Big Data TBA analytics
news

HP adds StoreVirtual, EVO: RAIL hyper-converged appliances

HP rolled out three hyper-converged appliances aimed at the SMB market, including a box that conforms to VMware EVO: RAIL specs.

  • Premiered: 10/16/14
  • Author: Taneja Group
  • Published: Tech Target: Search Virtual Storage
Topic(s): TBA HP TBA VMWare TBA EVO:RAIL TBA StoreVirtual TBA StoreVirtual VSA TBA ConvergedSystem TBA vSphere TBA Hypervisor TBA Virtual SAN TBA VSAN TBA Storage TBA scale-out TBA Virtualization TBA hybrid storage TBA High Performance TBA HPC TBA hyperconverged TBA hyperconvergence TBA Microsoft TBA Hyper-V TBA Arun Taneja
news

Hyperconvergence Makes Virtualization a Cinch for Businesses

Small business IT teams that want to wholeheartedly embrace server virtualization but are perhaps intimidated by getting up to speed on the technology may welcome a solution that ensures all integrated components work together automatically and transparently in the background.

  • Premiered: 11/24/14
  • Author: Taneja Group
  • Published: BizTech Magazine
Topic(s): TBA Arun Taneja TBA Virtualization TBA hyperconvergence TBA hyperconverged TBA LUN TBA Storage TBA HPC TBA High Performance TBA SimpliVity TBA OmniCube TBA SAN TBA Deduplication TBA Compression TBA WANO TBA WAN Optimization TBA HP TBA IBM TBA Scale Computing TBA Nutanix
news / Blog

InfiniBand Updates Specs Preparing for 10000 Node Exascale Clusters

We've long been fans of InfiniBand, watching as new generations of enterprise class scale-out clusters and storage solutions learn from the HPC world how to achieve really high-speed interconnection. InfiniBand itself may never win the popular market race against Ethernet, but newer generations of Ethernet are looking more and more like InfiniBand. And parts of the IB world, namely RDMA and RoCE, have swept into datacenters almost unaware (e.g. look under the hood of SMB 3.0).

  • Premiered: 03/10/15
  • Author: Mike Matchett
Topic(s): InfiniBand IBTA Exascale Networking HPC RoCE RDMA
news

IT pros get a handle on machine learning and big data

Despite its benefits, machine learning can also go very wrong. Beginners need to understand their input data, project scope and purpose, and the machine learning algorithms at work.

  • Premiered: 07/15/15
  • Author: Mike Matchett
  • Published: TechTarget: Search Data Center
Topic(s): TBA IT TBA Mike Matchett TBA Big Data TBA Machine Learning TBA predictive modeling TBA Optimization TBA scale-out TBA Apache TBA Apache Mahout TBA Apache Madlib TBA High Performance TBA High Performance Computing TBA HPC TBA storage architecture TBA Storage TBA In-Memory TBA Microsoft TBA Microsoft Azure TBA AI TBA Artificial Intelligence
news

Big data analytics applications impact storage systems

Analytics applications for big data have placed extensive demands on storage systems, which Mike Matchett says often requires new or modified storage structures.

  • Premiered: 09/03/15
  • Author: Mike Matchett
  • Published: TechTarget: Search Storage
Topic(s): TBA Mike Matchett TBA Big Data TBA analytics TBA Storage TBA Primary Storage TBA scalability TBA Business Intelligence TBA BI TBA AWS TBA Amazon AWS TBA S3 TBA HPC TBA High Performance Computing TBA High Performance TBA ETL TBA HP Haven TBA HP TBA Hadoop TBA Vertica TBA convergence TBA converged TBA IOPS TBA Capacity TBA latency TBA scale-out TBA software-defined TBA software-defined storage TBA SDS TBA YARN TBA Spark
news

The Need for Modern Day Scale-Out NAS Products

Today, storage architectures are undergoing yet another makeover, and the once dominant legacy products are being overtaken.

  • Premiered: 11/12/15
  • Author: Jeff Kato
  • Published: InfoStor
Topic(s): TBA InfoStor TBA Network Attached Storage TBA NAS TBA Storage TBA File Storage TBA SAN TBA scale-out TBA Scale out NAS TBA Cloud TBA EMC TBA NetApp TBA ONTAP TBA Cleversafe TBA Caringo TBA object storage TBA HPC TBA Big Data TBA High Performance TBA High Performance Computing TBA Performance TBA Flash TBA SSD TBA IOPS TBA Metadata TBA scalability TBA software-defined TBA Saas TBA Software-as-a-Service TBA open API TBA API
news

Can your cluster management tools pass muster?

The right designs and cluster management tools ensure your clusters don't become a cluster, er, failure.

  • Premiered: 11/17/15
  • Author: Mike Matchett
  • Published: TechTarget: Search Data Center
Topic(s): TBA cluster TBA Cluster Management TBA Cluster Server TBA Storage TBA Cloud TBA Public Cloud TBA Private Cloud TBA Virtual Infrastructure TBA Virtualization TBA hyperconvergence TBA hyper-convergence TBA software-defined TBA software-defined storage TBA SDS TBA Big Data TBA scale-up TBA CAPEX TBA IT infrastructure TBA OPEX TBA Hypervisor TBA Migration TBA QoS TBA Virtual Machine TBA VM TBA VMWare TBA VMware VVOLs TBA VVOLs TBA Virtual Volumes TBA cloud infrastructure TBA OpenStack
news

Scale-out NAS design now rivals object storage

Jeff Kato takes a closer look at ideal scale-out NAS design principles and vendors that are emerging with modern scale-out NAS designs.

  • Premiered: 02/12/16
  • Author: Jeff Kato
  • Published: TechTarget: Search Storage
Topic(s): TBA scale-out TBA NAS TBA scale-out NAS TBA Block Storage TBA File Storage TBA Storage TBA Oracle TBA Fibre Channel TBA FC TBA scalability TBA web-scale TBA web-scale storage TBA object storage TBA High Performance TBA HPC TBA High Performance Computing TBA Flash TBA SSD TBA data-aware TBA Metadata TBA IOPS TBA Performance TBA NetApp TBA EMC TBA software-defined TBA Virtual Machine TBA VM TBA Public Cloud TBA Cloud TBA hyperscale
news / Blog

Hyperconverged Supercomputers For the Enterprise Data Center

Last month NVIDIA, our favorite GPU vendor, dived into the converged appliance space. In fact we might call their new NVIDIA DGX-1 a hyperconverged supercomputer in a 4U box. Designed to support the application of GPU's to Deep Learning (i.e. compute intensive deeply layered neural networks that need to train and run in operational timeframes over big data), this beast has 8 new Tesla P100 GPUs inside on an embedded NVLink mesh, pre-integrated with flash SSDs, decent memory, and an optimized container-hosting deep learning software stack. The best part? The price is surprisingly affordable, and can replace the 250+ server cluster you might otherwise need for effective Deep Learning.

  • Premiered: 05/12/16
  • Author: Mike Matchett
Topic(s): NVIDIA hyperconvergence Big Data HPC
news / Blog

Scaling All Flash to New Heights - DDN Flashscale All Flash Array Brings HPC to the Data Center

It's time to start thinking about massive amounts of flash in the enterprise data center. I mean PBs of flash for the biggest, baddest, fastest data-driven applications out there. This amount of flash requires an HPC-capable storage solution brought down and packaged for enterprise IT management. Which is where Data Domain Networks (aka DDN) is stepping up. Perhaps too quietly, they have been hard at work pivoting their high-end HPC portfolio into the enterprise space. Today they are rolling out a massively scalable new flash-centric Flashscale 14KXi storage array that will help them offer complete, comprehensive single-vendor big data workflow solutions - from the fastest scratch through the biggest throughput parallel file systems into the largest distributed object storage archives.

  • Premiered: 05/17/16
  • Author: Mike Matchett
Topic(s): DDN HPC Big Data SSD Flash SAN Lustre GPFS
news

Delving into neural networks and deep learning

Deep learning and neural networks will play a big role in the future of everything from data center management to application development. But are these two technologies actually new?

  • Premiered: 06/16/16
  • Author: Mike Matchett
  • Published: TechTarget: Search IT Operations
Topic(s): TBA deep learning TBA datacenter management TBA Data Center TBA Datacenter TBA Big Data TBA Machine Learning TBA big data analytics TBA Artificial Intelligence TBA Compute TBA neural networks TBA Cloud TBA scale-out TBA scale-out architecture TBA High Performance Computing TBA High Performance TBA HPC TBA NVIDIA TBA Mellanox TBA DataDirect Networks TBA 4U appliance TBA Google TBA Google AlphaGo TBA network TBA Mike Matchett
news

Spark speeds up adoption of big data clusters and clouds

Infrastructure that supports big data comes from both the cloud and clusters. Enterprises can mix and match these seven infrastructure choices to meet their needs.

  • Premiered: 07/19/16
  • Author: Mike Matchett
  • Published: TechTarget: Search IT Operations
Topic(s): TBA Apache Spark TBA Spark TBA Mike Matchett TBA Cloud TBA cloud cluster TBA cluster TBA Big Data TBA big data analytics TBA MapReduce TBA Business Intelligence TBA BI TBA MLlib TBA High Performance TBA hadoop cluster TBA HDFS TBA Hadoop Distributed File System TBA IBM TBA Hortonworks TBA Cloudera TBA capacity management TBA Performance Management TBA API TBA SAN TBA storage area networks TBA CAPEX TBA DataDirect Networks TBA HPC TBA Lustre TBA Virtualization TBA VM