In this video from the 2013 HPC User Forum, Scott Schultz from Mellanox presents an overview of Mellanox and HPC.

Download the slides (PDF) or check out the HPC User Forum Video Gallery.

Related posts:

• Video: SGI Update from HPC User Forum
• Recent Advances in Overcoming the Red Shift for CFD Simulation Analytics
• Video: IDC HPC Market Update

The post Video: An Overview of Mellanox in HPC appeared first on insideHPC.

Operating networks at 100 Gigabit per second rates and higher requires careful integration between all parts of the network. We believe that silicon photonics is an important component in the development of 100 Gigabit InfiniBand and Ethernet solutions, and that owning and controlling the technology will allow us to develop the best, most reliable solution for our customers,” said Eyal Waldman, president, CEO and chairman of Mellanox Technologies. “We expect that the proposed acquisition of Kotura’s technology and the additional development team will better position us to produce 100Gb/s and faster interconnect solutions with higher-density optical connectivity at a lower cost. We welcome the great talent from Kotura and look forward to their contribution to Mellanox’s continued growth.”

Read the Full Story.

Related posts:

• Kotura helping Sun with nanophotonics work
• Slidecast: Kotura Low-Power 100 Gb/s Optical Engine
• Mellanox to Acquire Voltaire

The post Mellanox to Acquire Kotura appeared first on insideHPC.

2013 HPC User Forum Video Gallery (site under construction)

• Ubercloud – Paving the way to HPC as a Service
• Notur II Norwegian HPC infrastructure
• IBM-DOME Microserver Demonstrator
• SGI Update from HPC User Forum
• Overview of Mellanox in HPC
• Future Directions for IA … and more
• Big Data Use Cases: “The Size of the Data does not define Big Data”
• HPC in Astrophysics
• High-Performance Data Analysis: HPC Meets Big Data
• Henry Newman Presents: Today’s I/O Challenges for Big Data Analysis
• Petascale Supernova Simulation
• 2013 IDC HPC Market Update
• Apixio – Knowledge-driven Outcomes for Healthcare
• The Big Data Paradigm Shift – Insight Through Automation
• Engineering for the Mars Science Laboratory
• Applying New Computing Techniques to Numerical Astrophysics
• Recent Advances in Overcoming the Red Shift for CFD Simulation Analytics
• 3D Electronic Model-Based Design at Gulfstream

Slides from the HPC User Forum are now available for download.

Related posts:

• Video: SGI Update from HPC User Forum
• HPC User Forum, April 5-7, Houston, TX
• HPC User Forum in Tucson to Focus on Disruptive Innovation and Big Data

The post 2013 HPC User Forum Video Gallery appeared first on insideHPC.

This week the University of Florida unveiled HiPerGator, the state’s most powerful supercomputer with 157 Teraflops of peak performance.

UF worked with Dell, Terascala, Mellanox and AMD to build a machine that makes supercomputing power available to all UF faculty and their collaborators and spreads HiPerGator’s computing power over multiple simultaneous jobs instead of focused on a single task at warp speed. HiPerGator features the latest in high-performance computing technology from Dell and AMD with 16,384 processing cores; a Dell Terascala HPC Storage Solution (DT-HSS 4.5) with the industry’s fastest open-source parallel file system; and Mellanox’s FDR 56Gb/s InfiniBand interconnects that provide the highest bandwidth and lowest latency. Together these features provide UF researchers unprecedented computation and faster access to data to quickly further their research.

Read the Full Story or check out the Fact Sheet on HiPerGator.

Related posts:

• Mellanox FDR 56Gb/s InfiniBand Powers Fastest Supercomputer in India
• Mellanox FDR InfiniBand Powers Stampede Supercomputer
• Dell Taps Mellanox to Accelerate Blade Performance

The post HiPerGator Debuts as Florida’s Most Powerful Supercomputer appeared first on insideHPC.

In this video from the 2013 Open Fabrics Developer Workshop, Paul Grun from Cray leads a panel discussion on Scaling with PGAS Languages.

Panelists:

• Howard Pritchard, Cray (slides)
• Mirko Rahn, Fraunhofer Institute
• DK Panda, OSU (slides)
• Rich Graham, Mellanox
• Robert Woodruff, Intel

You can check out more OFA videos at our Open Fabrics Workshop Video Gallery.

Related posts:

• Video: Challenges of Scale & MPI/PGAS APIs
• Video: OFS for the Intel Xeon Phi
• Video: Ethernet over InfiniBand (EoIB)

The post Video: Panel Discussion on Scaling with PGAS Languages appeared first on insideHPC.

We try to keep this page up to date, but you can always find our latest works on our RichReport YouTube Channel.

2013 Event Coverage:

• Open Fabrics Developer Workshop
• Lustre User Group Video Gallery
• Moabcon 2013 Video Gallery
• National HPCC Conference
• HPC Advisory Council Switzerland Conference

SC12 Videos (Alphabetical by Vendor Name):

Adaptive Computing

• Big Data Debate at SC12. In this video, Adaptive Computing hosts a Big Data Debate at SC12 in Salt Lake City.
• Interview: Adaptive Computing CEO on HPC, Clouds and Big Data. Robert A.Clyde describes how the company’s system management software helps customers manage the world’s largest HPC clusters and private Clouds.
• Moab HPC Suite Remote Visualization Software Speeds Innovation at SC12. Moab HPC Suite Remote Visualization Edition enables you to create easy, centralized access to shared visualization compute, application and data resources.
• Adaptive Computing Enhances Moab Cloud Suite 7.2. Brady Kimball from Adaptive Computing describes enhancements to the Moab Cloud Suite, an intelligent cloud management end-to-end platform. The suite provides touchless cloud service optimization across the full cloud service life cycle including agility, cost savings and service performance.
• Adaptive Computing Leverages Torque to Manage Intel Xeon Phi Resources. Nick Ihli from Adaptive Computing demonstrates how the company’s Torque resource manager works with Intel Xeon Phi. By relaying Intel Xeon Phi instrumentation such as memory availability to the company’s Moab workload manager, the system is able to schedule coprocessor resources efficiently.
• Adaptive Computing Enhances Moab HPC Suite at SC12. Brady Kimball describes enhancements to the Moab Compute Manager 7.2 suite.

Adaptive Computing SC12 Booth Theater

• Overview of Warewulf Node Health Check Software. Michael Jennings Jackie Scoggins from LBNL describe Warewulf Node Health Check software.
• Community HPC Clusters at Purdue University. Andrew Howard from Purdue discuss has the community cluster program has moved forward with the help of Moab software at the Rosen Center for Advanced Computing.
• What’s New in Moab HPC Suite 7.2? Brady Kimball describes enhancements to the company’s resource management software.
• COSMOS – Fundamental Cosmology, Dark Energy, and the Cosmic Microwave Sky. The COSMOS Supercomputer Consortium, founded by Stephen Hawking and part of the Science and Technology Facilities Council DiRAC High Performance Computing facility, has chosen Moab HPC Suite 7.2 to manage its groundbreaking scientific computing workloads.
• Moab/TORQUE Support for Intel Xeon Phi. The latest version of Moab was designed to recognize and work with the new Intel Xeon Phi coprocessors, including the ability to automatically detect coprocessors and determine their location and availability.
• Intel Xeon Phi Coprocessor Overview at SC12. Mike Haedrich from Intel presents an overview of the Intel Xeon Phi coprocessor.
• HPC Cloud ROI and Opportunities Cloud Brings to HPC. Brady Kimball from Adaptive Computing presents on the Moab Cloud Suite.
• Moab HPC Suite – Remote Visualization Edition at SC12. With Moab HPC Suite — Remote Visualization Edition, you can improve the productivity, collaboration and security of the design and research process by only transferring pixels instead of data to users to do their simulations and analysis.
• Using Moab Node-sets to Improve Job Scheduling. Gabriel Mateescu from Virginia Tech presents how Node-sets work to improve scheduling efficiency.
• Configuring Moab to Fairly Share a Supercomputer while Preventing Starvation in a University Setting. Jenett Tillotson from Indiana University presents this talk on Moab.
• Demo: Adaptive Computing All-Spark Cube at SC12. Ian Nate from Adaptive demonstrates the company’s resource management software through a custom-built All Spark cube.
• Realizing Energy Efficient Scheduling in a Network of Datacenters. Dr. Bastian Koller from the HPC Center in Stuttgart presents this talk on Moab at HLRS.
• The Technical Cloud: When Remote 3D Visualization Meets HPC. Andrea Rodolico from NICE Software presents on remote visualization.
• HPC at ACC Cyfronet. Lukasz Fils from Cyfronet presents a talk on Moab at Cyfronet in Poland.
• NCRC Scheduling Environment. Frank Indiviglio from NOAA describes how Moab software is used for job scheduling.

Aeon

• Aeon Computing Showcases Award-Winning Data Oasis at SC12. Doug Johnson from Aeon Computing describes the company’s innovative Data Oasis technology powered by the Lustre file system.

Allinea

• Allinea Helps Scientists Run their Applications Faster and Better. Allinea CTO David Lecomber describes the company’s powerful tools for debugging at scale.
• Demo: Allinea MAP Profiling Tool. Mark O’Connor from Allinea demonstrates the company’s new MAP performance profiler tool, a unique offering with extremely low overheard.

Altair

• Interview: SGI Teams with Altair on the Road to Exascale. Paul Kinyon from SGI’s product management team describes how the company is working with partners like Altair to solve customer’s toughest computational challenges. The company is looking at a range of technologies that could enbable Exascale computing capabilities at a practical level of power consumption.
• Altair Speeds RADIOSS at SC12 Using Intel Xeon Phi. James Reinders and Paresh Pattani from Intel discuss how the new Intel Xeon Phi is already powering engineering applications like RADIOSS. Altair was able to port both the explicit and implicit versions of the RADIOSS code in short order.
• Altair PBS Pro Steps up with Support for Intel Xeon Phi Coprocessors. Altair’s Mary Bass describes the company’s PBS Pro system management software, now with support for the new Intel Xeon Phi coprocessor.
• Demo: Altair RADIOSS Finite Element Analysis on Intel Xeon Phi at SC12. Eric Lequiniou, Director of High Performance Computing at Altair demonstrates a port of RADIOSS to the new Intel Xeon Phi that uses both explicit and implicit solvers.

AMD

• AMD Powers Penguin Computing at SC12. Penguin Computing CTO Phil Pokorney describes the company’s full range of power-efficient integrated cluster solutions for HPC.
• Supermicro Showcases AMD Opteron Solutions for HPC. Don Clegg from Supermicro describes the company’s wide array of HPC solutions powered by AMD Opteron.

Asetek

• Asetek Reinvents the Datacenter with Innovative Hot Water Cooling at SC12. Asetek founder & CEO André Eriksen describes how CPUs are liquid cooled with the company’s proprietary liquid cooling while a liquid-to-air heat exchanger inside the server cools the inside server air.

Bull

• New Bull Supercomputer Blades Featuring Intel Xeon Phi. Pascale Bernier-Bruna from Bull describes the company’s new hpc blade offerings with the Intel Xeon Phi coprocessor.
• French Supercomputer Vendor Bull Optimizes Apps for Intel Xeon Phi. In this video from SC12, Mathieu Dubois from Bull discusses the company’s application optimization efforts on the new Intel Xeon Phi Coprocessor.

CAPS-Enterprise

• Caps-Enterprise Steps up with Support for Intel Xeon Phi. Caps-Enterprise CTO François Bodin describes the company’s programming tools for new Intel Xeon Phi.
• CAPS-Enterprise Tops Off Accelerators for Accelerators with OpenACC. Caps-Enterprise CTO François Bodin describes the company’s tools with support for programming Directives with OpenACC.

Colfax International

• Colfax Offers Powerhouse Xeon Phi Server and Code Optimization Course at SC12. Mike Fay from Colfax International describes the company’s new CXP9000 server with up to eight Intel Xeon Phi coprocessors. After that, Vardim Karpusenko provides an overview of the company’s new training courses on optimizing code for Xeon Phi.

Cycle Computing

• Cycle Computing Spins up HPC in the Cloud. Jason Stowe from Cycle Computing describes how the company helps customers maximize the utilization of existing supercomputing infrastructure and bridge the gap between traditional data centers and on-demand utility supercomputing.
• Demo: Cycle Computing Spins Up Big AWS Clusters on-the-fly at SC12. Cycle Computing CEO Jason Stowe demonstrates how easy it is to use the company’s software to provision large compute instances on the AWS cloud.

DDN

• DDN Powers Genomics at the Virginia Bioinformatics Institute. Dr. Harold (Skip) Garner from the Virginia Bioinformatics Institute describes how Big Data I/O is required to crunch Genomics data in the fight against cancer.
• DDN Ramps Up for Exascale at SC12. Jeff Denworth from Data Direct Networks describes the company’s high performance storage solutions for HPC. Used by 60 percent of the TOP100 supercomputers in the works, DDN recently announced a $100 Million dollar investment in Exascale technologies.
• Steve Simms on the Data Capacitor II at Indiana University. Steve Simms from Indiana University describes a recent upgrade to the Data Capacitor project, a high-speed, high-capacity storage facility for very large data sets. With 5 PB of storage, Data Capacitor II will support big data applications used in computational research. IU partnered with DDN to develop Data Capacitor II, which is scheduled to be installed in the IU Data Center in spring 2013.

Dell

• Dell Powers Genomics Research Computing and Personalized Medicine at SC12. Glen Otero from Dell discusses his Birds of Feather session on Personalized Medicine at SC12. The company is working with researchers to enable faster, more cost-effective genome sequencing to enable better healthcare for us all.
• Dell HPC Keeps Focus on Helping Researchers. Tim Carroll from Dell discusses the company’s recent Stampede supercomputer installation at the Texas Advanced Computing Center and how the company focuses on helping researchers.

Gnodal

• Gnodal Showcases Fully Adaptive Load Balancing Ethernet Fabric at SC12. Fred Homewood from Gnodal describes escribes the company’s high bandwidth, low latency 40 GigE Ethernet switch solutions for HPC and the Enterprise.

HPC Advisory Council

• HPC Advisory Council Announces Student Cluster Teams for ISC’12. Gilad Shainer, Tong Liu, and Pak Lui from the HPC Advisory Council revue the organization’s outreach efforts for the past year and look forward to 2013. The council is an active sponsor of international Student Cluster Competitions that encourage young people to learn parallel programming skills.

IBM

• IBM Platform HPC Speeds Applications with Intel Xeon Phi. Jie Wu from IBM Platform Computing describes how the company’s Platform HPC software manages computing resources from the new Intel Xeon Phi.

IDC

• IDC HPC Market Update from SC12. Did you know that 3Q2012 was the biggest quarter of revenue in the history of HPC? In this video from SC12, Earl Joseph from IDC presents the latest on the supercomputing market.

Inktank

• Inktank Boosts Open Source Ceph File System. Neil Levine from Inktank describes the company’s efforts to commercialize and support the Ceph open source file system. With high reliability and nearly unlimited scalability, Ceph has great potential for Big Data applications as well as an enabling technology for Exascale computing.

Intel

• TACC Stampede Supercomputer Comes in at #7 on the TOP500 with Intel Xeon Phi. Lars Koesterke from the Texas Advanced Computing Center describes how hundreds of science applications are being ported to the the new Stampede supercomputer powered by the Intel Xeon Phi.
• Altair Speeds RADIOSS at SC12 Using Intel Xeon Phi. James Reinders and Paresh Pattani from Intel discuss how the new Intel Xeon Phi is already powering engineering applications like RADIOSS. Altair was able to port both the explicit and implicit versions of the RADIOSS code in short order.
• Colfax Offers Powerhouse Xeon Phi Server and Code Optimization Course at SC12. Mike Fay from Colfax International describes the company’s new CXP9000 server with up to eight Intel Xeon Phi coprocessors. After that, Vardim Karpusenko provides an overview of the company’s new training courses on optimizing code for Xeon Phi.
• Intel Xeon Phi Adds Smarts to SGI UV. SGI’s Chief Marketing Office Franz Aman describes the company’s full range of solutions featuring the new Intel Xeon Phi coprocessor for HPC.
• Intel Xeon Phi at the University of Tokyo. Professor Kei Hiraki from the University of Tokyo discusses the historical development of accelerator technology that has culminated in the new Intel Xeon Phi coprocessor.
• Rogue Wave Steps up with HPC Programming Tools for Intel Xeon Phi. Scott Lasica from Rogue Wave software describes the company’s Totalview debugger for the new Intel Xeon Phi.
• IBM Platform HPC Speeds Applications with Intel Xeon Phi. Jie Wu from IBM Platform Computing describes how the company’s Platform HPC software manages computing resources from the new Intel Xeon Phi.
• Caps-Enterprise Steps up with Support for Intel Xeon Phi. Caps-Enterprise CTO François Bodin describes the company’s programming tools for new Intel Xeon Phi.
• NAG Programming Tools for Intel Xeon Phi. David Cassell from NAG describes the company’s programming environment for the new Intel Xeon Phi.
• New Bull Supercomputer Blades Featuring Intel Xeon Phi. Pascale Bernier-Bruna from Bull describes the company’s new hpc blade offerings with the Intel Xeon Phi coprocessor.
• James Reinders on Exploiting Parallelism with the Intel Xeon Phi. Intel’s James Reinders describes the new Intel Xeon Phi and how scientists can exploit parallelism in its many cores to speed their HPC applications.
• Seneca Accelerates HPC Apps with Intel Xeon Phi and Nvidia Kepler K20X Side by Side. Bret Stouder from Seneca describes the company’s latest contract with Jefferson Labs for the first-ever hybrid servers with Intel Xeon Phi coprocessors and Nvidia Kepler K20X accelerators running side by side.
• Intel Parallel Studio XE Demo at SC12. Steve Lionel from Intel demonstrates the Intel Parallel Studio XE. Available for Linux and Windows, the studio suite eases application development for Xeon CPUs and Intel Xeon Phi coprocessors.
• Intel Cluster Studio XE Demo at SC12. Gergana Slavova from Intel demonstrates the Intel Cluster Studio XE, an integrated tool suite for HPC development.
• Demo: Intel Advisor XE 2013 Transforms Serial Code for Intel Xeon Phi at SC12. In this video from SC12, David R. Mackay from Intel demonstrates the Intel Advisor XE 2013, a design tool that helps you to transform serial code to run well on multicore hardware (such as the Intel Xeon Phi) by forecasting what might happen if the code executes in parallel.

Intersect360 Research

• The Effect of HPC on Everyday Lives. Addison Snell from Intersect360 Research presents at the SC12 Opening Press Conference.

NAG

• NAG Programming Tools for Intel Xeon Phi. David Cassell from NAG describes the company’s programming environment for the new Intel Xeon Phi.

Nirvana

• Nirvana Large-scale Data Federation Technology at SC12. As a division of General Atomics, Nirvana commercializes data grid technology originally developed at the San Diego Supercomputer Center (SDSC)

Numascale

• Numascale Aggregates Big Memory SMPs from Commodity Servers at SC12. Einar Rustad from Numascale describes the company’s hardware-based server aggregation platform that enables large shared-memory systems to be built from commodity servers.

Nvidia

• Nvidia GPU Technology Theater at SC12. Livestreamed from the show, the complete theater shedule from SC12 features terrific talks on science and engineering.
• Introducing Nvidia Kepler K20X – the GPU that Powers the World’s Fastest Supercomputer. Nvidia’s Sumit Gupta describes the 64-bit Kepler K20 architecture for HPC applications.
• Buddy Bland on How the #1 Titan Supercomputer will Power Science. As a hybrid system, Titan derived 100 percent of its LINPACK performance from NVIDIA K20X  accelerators.

Mellanox

• Mellanox Breaks Performance Records, Dominates TOP500 at SC12. Todd Wilde from Mellanox describes the company’s recent advancements in high speed InfiniBand interconnects. Infiniband recently InfiniBand has become the leading interconnect on the TOP500 with 224 clusters and the Connect-IB dual-port 56Gb/s FDR InfiniBand adapter recently achieved the industry’s highest throughput of more than 100Gb/s utilizing PCI Express 3.0 x16 and over 135 million messages per second, 4.5X higher than previous or competing solutions.

OpenSFS & EOFS

• OpenSFS and EOFS Foster the Lustre Community at SC12. Norm Morse from OpenSFS and Hugo Falter from the European EOFS discuss the latest developments in the Lustre community.

Panasas

• Panasas Showcases ActiveStor 14 at SC12. By accelerating small file and metadata performance with Solid State Drive (SSD) technology, ActiveStor 14 delivers extreme performance, for the technical computing and big data workloads commonly found in HPC environments.
• Panasas Chief Scientist on Where HPC Meets Big Data and Hadoop. Panasas ActiveStor not only accelerates product design and scientific discovery applications, but will perform seamless Hadoop analyses, ensuring that customers can extract maximum value from their existing big data infrastructure.

Penguin Computing

• AMD Powers Penguin Computing at SC12. Penguin Computing CTO Phil Pokorney describes the company’s full range of AMD Opteron integrated cluster solutions for HPC.

Rogue Wave Software

• Rogue Wave Steps up with HPC Programming Tools for Intel Xeon Phi. Scott Lasica from Rogue Wave software describes the company’s Totalview debugger for the new Intel Xeon Phi.
• TotalView Debugger Stands Above with Support for Blue Gene/Q. Scott Lasica from Rogue Wave Software discusses the company’s new Totalview programming tools for IBM BlueGene/Q supercomputers with a million processing cores or more.

Samplify

• Samplify APAX: Lowering the Cost of Big Science, Big Data, and Cloud Computing. APAX accelerates the performance of multicore CPU-based applications bound by memory, I/O, and storage bottlenecks.
• Slidecast: Samplify APAX Compression Lowers Cost of Big Science. APAX is the only solution that accelerates the throughput DDRx, SAS/SATA, SSD, PCIe, Ethernet, and Infiniband, by up to six times.

SC12 Committee

• SC12 Press Conference with Jeff Hollingsworth. In this video, SC12 General Chair Jeff Hollingsworth opens the show press conference in Salt Lake City. This year there were a record number of exhibitors have booths at the show. Recorded Nov. 12, 2012.

Scalable Informatics

• Scalable Informatics at SC12 – A Keen Eye on Real Storage Performance. Joe Landmand from Scalable Informatics describes the company’s latest storage technologies for HPC.

Seneca

• Seneca Accelerates HPC Apps with Intel Xeon Phi and Nvidia Kepler K20X Side by Side. Bret Stouder from Seneca describes the company’s latest contract with Jefferson Labs for the first-ever hybrid servers with Intel Xeon Phi coprocessors and Nvidia Kepler K20X accelerators running side by side.

SGI

• Interview: SGI Teams with Altair on the Road to Exascale. Paul Kinyon from SGI’s product management team describes how the company is working with partners like Altair to solve customer’s toughest computational challenges. The company is looking at a range of technologies that could enbable Exascale computing capabilities at a practical level of power consumption.
• Intel Xeon Phi Adds Smarts to SGI UV. SGI’s Chief Marketing Office Franz Aman describes the company’s full range of solutions featuring the new Intel Xeon Phi coprocessor for HPC.

Solarflare

• Solarflare ApplicationOnLoad Engine – HPC Processing on a “Bump in the Wire”. With their ApplicationOnLoad Engine (AOE) the company is enabling applications to be processed on the fly right on the NIC server adapter.
• Slidecast: Solarflare Processing NICs Do HPC Custom Compute. Solarflare President & CEO Russell Stern describes how the company develops network interface software and hardware to transform the way applications use networks, providing industry-leading application acceleration for the most demanding scale-out compute environments.

Spectra Logic

• Spectra Logic Tape Storage Technologies Taking Off at SC12. Molly Rector from Spectra Logic describes the latest advancements in the company’s tape-based storage technologies. Along the way, she debunks the myth that Amazon’s AWS Glacier offering will be the death of tape.

Supermicro

• Supermicro Showcases AMD Opteron Solutions for HPC. Don Clegg from Supermicro describes the company’s wide array of HPC solutions powered by AMD Opteron.

Sugon

• Chinese Supercomputer Vendor Sugon Sponsors SC12 Student Cluster Competition. Sha Chaoqun from Sugon describes the company’s products for high performance computing. As a leading Chinese server vendor, Sugon helped sponsor the SC12 Student Cluster Challenge.

Texas Instruments

• Texas Instruments Offers System on a Chip for HPC. Based on its award winning KeyStone architecture, TI’s SoCs are designed to revitalize cloud computing, inject new verve and excitement into pivotal infrastructure systems and, despite their feature rich specifications and superior performance, actually reduce energy consumption.
• Slidecast: Texas Instruments SoC’s Increase Performance and Reduce Power Consumption. Arnon Friedmann from TI presents details on the the company’s new SoCs, which now have the capability to boot Linux and run conventional HPC software.

The Portland Group

• PGI’s Michael Wolfe on OpenACC Directives for GPUs. Michael Wolfe from The Portland Group discusses the origins of the OpenACC standard for programming directives in GPUs. He also weighs in on the recent OpenMP 4.0 technical report, which proposed to incorporate OpenACC directives into OpenMP 4.0 sometime in 2013.

VMware

• Interview: Josh Simons on HPC Cloud Trends at SC12. Josh Simons from the VMware CTO office describes recent trends in Cloud Computing for HPC. The company is looking at how virtualization technologies could benefit supercomputing on the road to Exascale.

Xyratex

• Xyratex Announces OEM Deals with Dell and HPC at SC12. Mike Stoltz from Xyratex describes the company’s ClusterStor products for HPC. The company recently announced that HP and Dell will resell ClusterStor to power their advanced HPC clusters.

Related posts:

• Video: Moab/TORQUE Support for Intel Xeon Phi
• Adaptive Computing Enhances Moab HPC Suite with Version 7.2 at SC12
• Video: What’s New in Moab HPC Suite 7.2?

The post insideHPC Video Archive appeared first on insideHPC.

Video Gallery: HPC Advisory Council Switzerland Workshop

• Hands-on Training: Know Your Cluster Bottlenecks and Maximize Performance
• DDN: Big Data Evolution
• The DEEP Project: Developing a Novel, Exascale-enabling Supercomputing Platform
• LRZ SuperMUC – One year of Operation
• GPU Computing with NVIDIA’s new Kepler Architecture
• KernelGen — Next-generation Compiler Platform for Accelerating GPUs
• A Generic Methodology for Optimizing an HPC Storage System
• Direct MPI from NVIDIA Tesla and Intel Xeon Phi Accelerator Memories on an InfiniBand Cluster
• Modular HPC, Exascale Block by Block
• Xyratex at HPC Advisory Council Switzerland Workshop
• GPFS CACHE over 200 Km
• Introducing Panasas ActiveStor 14
• Overview of AMD in HPC
• Accelerating Big Data with Hadoop (HDFS, MapReduce and HBase) and Memcached
• Fast Deadlock-Free Routing for InfiniBand Networks
• The UberCloud HPC Experiment – Paving the Way to HPC as a Service
• CPU Alternatives for Future High-performance Systems
• Mellanox: The Foundation for Scalable Computing
• The Future of Network-based Storage
• Who can Beat x86? How to reduce your power footprint and more…
• Building a Cost-Effective and High-Performing Public Cloud
• Programming Models and their Designs for Exascale Systems (Part II)
• Management of large-scale GPU Clusters
• Experiences from the Deployment of TACC’s Stampede System
• Scaling Storage from Seismic Depths to Sequoia Heights
• Programming Models and their Designs for Exascale Systems (Part I)
• HP’s Data-Centric Datacenters for Exascale and Big Data
• HPC Advisory Council Overview from Switzerland HPC Conference 2013
• HPC at Swiss CSCS

Related posts:

• HPC Advisory Council Opens Switzerland Workshop
• HPC Advisory Council Switzerland Workshop, March 13-15, 2012
• HPC Advisory Council Workshop Comes to Switzerland March 21-23, 2011

The post Video Gallery: HPC Advisory Council Switzerland Workshop appeared first on insideHPC.

In this video from the 2013 Open Fabrics Developer Workshop, Sreev Doddabalapur from Mellanox presents: Accelerating Big Data over RDMA.

You can check out more OFA videos at our Open Fabrics Workshop Video Gallery.

Related posts:

• High Performance RDMA-based Design for Big Data and Web 2.0 memcached
• Video: RSOCKETS – RDMA for Dummies
• Video: Ethernet over InfiniBand (EoIB)

The post Video: Accelerating Big Data over RDMA appeared first on insideHPC.

In this video from the 2013 Open Fabrics Developer Workshop, Ali Ayoub from Mellanox presents: Ethernet over InfiniBand (EoIB).

Download the slides (PDF). You can check out more OFA videos at our Open Fabrics Workshop Video Gallery.

Related posts:

• Video: InfiniBand Scalable Subnet Administration
• Video: InfiniBand Fabric Administration for Linux
• Video: Update on Lustre, OpenSFS, and FastForward InfiniBand

The post Video: Ethernet over InfiniBand (EoIB) appeared first on insideHPC.

On plain old CPUs, RDMA allows CPUs running in one node to reach out through an InfiniBand network and directly read data from another node’s main memory, or push data to that node’s memory without having to go through the operating system kernel and the CPU memory controller. If you prefer 10 Gigabit Ethernet links instead, there is an RDMA over Converged Ethernet, or RoCE, wrapper that lets RDMA run on top of Ethernet – as the name suggests. With GPUDirect, which is something that InfiniBand server adapter and switch maker Mellanox Technologies has been crafting with Nvidia for many years, the idea is much the same. Rather than having a GPU go back to the CPU and out over the network to get data that has been chewed on by another GPU, just let the GPUs talk directly to each other over InfiniBand (or Ethernet with RoCE) and get the CPU out of the loop.

GE's IPN251 hybrid computing card marries a Core i7, a Xilinx FPGA, and an Nvidia Kepler GPU with a PCI switch

Read the Full Story.

Related posts:

• Mellanox FDR InfiniBand Pushes PCI-Express 3.0 to the Limits
• HP Taps Mellanox for Low Latency Blade Switch
• InfiniBand Trade Association announces RDMA over Converged Ethernet

The post Hybrid CPU-GPU Chips Plus RDMA and PCI-Express Make for Screamin’ Iron appeared first on insideHPC.

The InfiniBand network was easy to deploy and delivers incredible application performance on a consistent basis,” said Tommy Minyard , director of Advanced Computing Systems, TACC. “Utilizing Mellanox FDR 56Gb/s InfiniBand provides us with extremely scalable, high performance — a critical element as Stampede is designed to support hundreds of computationally- and data-intensive science applications from around the United States and the world.”

Stampede supports national scientific research into weather forecasting, climate modeling, drug discovery and energy exploration and production. Read the Full Story.

Related posts:

• Mellanox FDR 56Gb/s InfiniBand Powers Fastest Supercomputer in India
• Video: Intel Xeon Phi Powers #7 TACC Stampede Super
• Video: Mellanox Tips the Scales on the TOP500 with FDR InfiniBand

The post Mellanox FDR InfiniBand Powers Stampede Supercomputer appeared first on insideHPC.

In this video from the HPC Advisory Council Switzerland Conference, Dan Waxman from Mellanox provides a hands-on training for InfiniBand entitled: Hands-on Training: Know Your Cluster Bottlenecks and Maximize Performance.

Depending on the application of the user’s system, it may be necessary to modify the default configuration of the network adapters and the system/chipset configuration. This slide deck describes common tuning parameters, settings & procedures that can improve performance of the network adapter. Different Server & NIC vendors may have different recommendations for the values to be set – but the general tuning approach should be similar. For the hands-on demo we will utilize Mellanox ConnectX adapters – thus we will implement the recommended settings issued by Mellanox.

Download the Slides (PDF).

Related posts:

• Developers: Get Hands-on Open Fabrics Training with RDMA
• Video: Mellanox Breaks Performance Records, Dominates TOP500 at SC12
• Video: Hands-On InfiniBand Clustering Contest

The post Video: Hands-on Training: Know Your Cluster Bottlenecks and Maximize Performance appeared first on insideHPC.

Over the last few years, we’ve seen a steadily growing buzz surrounding the use of ARM chips in PCs, servers, and supercomputers. Here at GTC 2013, that buzz is even more pronounced due to NVIDIA’s upcoming Project Denver, and advances in their GPU technology that result in even less dependency on having a fast and powerful (read: Xeon) processor feeding the GPU number-crunching beasts. Our pal Rik Myslewski penned a great article on GTC 2013 ARM chatter here.

While most everyone has been debating and speculating about what it would be like to combine ARM processors and GPU accelerators, one organization has put together some hardware in order to separate the theoretical from the real. The Barcelona Supercomputer Center (from the Barcelona in Spain, not the other one) is building clusters to explore the potential advantages that might arise from combining low power ARM processors with fast number-crunching GPUs.

Their first attempt, the Tibadabo, was a proof of concept to determine whether it’s possible to build an all-ARM-based cluster. Could they really put together a cluster based on cell phone processors? And, if they could build it, could they find or adapt enough software for it to do useful work?

They were able to construct a two-rack cluster containing 32 blades, 256 nodes, and a total of 512 Tegra 2 ARM cores. They were able to port 11 scientific apps over to ARM with little difficulty, although they did need to fiddle around with the memory hierarchy to optimize some of the apps.

The performance wasn’t all that great. The total system turned out 512 GFLOPs while consuming 3.4 KW, yielding .015 GGLOPs/watt. For context, the best systems on the most recent Green500 list come in around 2.4 or 2.5 GFLOPs/watt, while the systems at the end of the list are rated at .033 GFLOPs/watt.

So they went back to the drawing board and, using NVIDIA’s CARMA development box, clustered 16 of them together as a learning experience they called Pedraforca v1. This system did much better than the ARM-only Tibadabo on energy efficiency, yielding .78 GFLOPs/watts on DGEMM and 5.04 in SGEMM (matrix multiply double and single precision), so they were making progress.

Limitations in the platform (PCIe max of 400 MB/s plus inability to overlap computation and data transfers) meant it couldn’t be scaled up very well. However, it did lead them to a new breakthrough in their thinking for their next system, which they’ve dubbed Pedraforca V2.

They’ve decided the key to building a highly efficient system isn’t to build an accelerated cluster but to build a cluster of accelerators. While there isn’t much difference in the words, there’s a world of difference between the meanings. With Pedraforca v2, they will be de-coupling the CPUs from the GPUs, meaning that the ratio of CPU-GPU can be changed to fit the workloads. They will also be using direct GPU-GPU data transfers via Mellanox’s ConnectX-3 Infiniband interconnects.

This will take a huge amount of latency out of the system and, accordingly, reduce the amount of work the CPU needs to do to orchestrate GPU communications. The prototype system will have 64 nodes which will utilize a quad-core Tegra 3 CPU that will slide into a 4x PCIe slot on a Mini-ITX carrier. In this configuration, the CPU will only be managing boot and MPI communications, plus minimal traffic cop duty for the GPUs. The point is that you don’t need a hugely fast and powerful processor to fulfill these requirements.

However, Pedraforca v2 will have some processing power in the form of Kepler-based NVIDIA K20 GPUs that can deliver 1,170 GFLOP/s through a PCIe Gen3 slot. The GPUs will be able to communicate with each other at 40 Gb/s via the aforementioned Mellanox-fueled Infiniband interconnect.

Both presenters pointed out that this isn’t a general purpose HPC system – it is intended as a host for apps that are GPU-optimized. While they didn’t discuss any FLOPs/watt estimates or performance predictions, it’s safe to say that this system should be an eye opener when it comes to energy efficiency and even cost per FLOP. It’s definitely a project worth watching.

Related posts:

• AMD shares Barcelona results
• Dell and the Barcelona Opterons
• AMD Delays Barcelona Ramp-Up to Q1 2008

The post GTC 2013: ARM + GPU = GPU’riffic, says Barcelona SCC appeared first on insideHPC.

This system is a powerful compute resource for all researchers in the region of East Westphalia and Lippe, and our partners in Germany and Europe,” Prof.Dr. Holger Karl, head of the PC² board.

With a system interconnect powered by Mellanox QDR InfiniBand, the Paderborn cluster uses Dell PowerVault MD3200 storage components powered by the FraunhoferFS FhGFS the parallel file- system. Read the Full Story.

Related posts:

• GWDG Fires Up New Magny-Cours Super in Germany
• ClusterVision Partners to Deploy Minerva Supercomputer at the University of Nottingham
• NCSA Fires Up Heterogeneous Forge Super

The post ClusterVision Fires Up 200 Teraflop Super at University of Paderborn appeared first on insideHPC.

In this video from the HPC Advisory Council Switzerland Conference, Colin Bridger presents: Mellanox: The Foundation for Scalable Computing.

Download the Slides (PDF).

Related posts:

• Video: Scalable Cluster Computing with Nvidia GPUs
• Video: Gnodal Ethernet Solutions for High Performance Computing
• Video: Intro to 3D Torus Architectures

The post Video: Mellanox – The Foundation for Scalable Computing appeared first on insideHPC.

Today NetApp announced the new NetApp E5500 storage system for Big Data and HPC applications. Derived from Engenio technology acquired from LSI, the seventh-generation E-Series is a high-density platform with record per-spindle throughput.

The SGI InfiniteStorage 5600, which is an OEM version of the NetApp E5500, has produced a new SPC-2 result confirming the performance and cost efficiency of the new E5500; it showcases the performance possibilities the E5500 unlocks for HPC and big data organizations. The audited, peer-reviewed SPC-2 result demonstrates the highest throughput per spindle by more than 2.5 times over the nearest non-NetApp published result.

Read the Full Story.

In related news, SGI rolled out the InfiniteStorage 5600 storage system today, noting that the flexibility of the platform enables users to push the limit without breaking their budget.

inShare

Comment on this story by Ralph on Mar 6
Advertisement
Accelerate x64 Applications on GPUs Using the Most Trusted HPC Compilers: The Portland Group.
The Unknowns that come with Exascale
Posted in Exascale, HPC

Over at Reed’s Ruminations, Dan Reed writes that the road to Exascale will come complete with the unknowns that make up any change that involves orders of magnitude.

All currently envisioned exascale systems would require parallelism at unprecedented scale, and barring new, energy efficient memory technologies; they would be memory starved relative to current systems, even under a 20 MW system design point; and multilevel fault tolerance would be required to achieve acceptable systemic mean time to failure (MTBF). Extraordinary parallelism, unprecedented data locality and adaptive resilience: these are daunting architecture, system software and application challenges for exascale computing.

Read the Full Story.

inShare

Comment on this story by Ralph on Mar 6
Video: Supercomputer Modelling of a Complete Human Viral Pathogen
Posted in HPC, Video, Visualization

In this video, researchers perform a reconstruction and simulation of the poliovirus using the BlueGene/Q supercomputer at the Victorian Life Sciences Computation Initiative. The poliovirus model is being used as a basis for understanding antiviral drugs, virus infection and helps us to learn how to model related viruses such as Enterovirus 71.

Read the Full Story.

inShare

Comment on this story by Rich Brueckner on Mar 6
Sponsored Post: OpenFabrics Software Events Coming to Monterey in April
Posted in Events, HPC, HPC Hardware, HPC Software, Network, Open Fabrics, Open Fabrics Workshop, Sponsored Post

Be a part of the OpenFabrics Alliance’s OpenFabrics Software events in Monterey, CA.

The OFA User Workshop, April 18-19, provides opportunities to share experiences and learn from a community of OFS users.
The International Developer’s Workshop, April 21-24, will focus on the development and improvement of OFS as well as major developments in RDMA, etc. Agenda and more information is available on OpenFabrics.org.
Registration for the two events is now open. For more details, check out the OFA Newsletter.

inShare

Comment on this story by Rich Brueckner on Mar 5
Video: Enterprise HPC in the Cloud – Fortune 500 Use Cases
Posted in Cloud HPC, Events, Video

Over at the Compute Cycles Blog, Jason Stowe from Cycle Computing writes that the recent AWS: reInvent conference featured a series of talks on Enterprise Use Cases of HPC in the Cloud. In this video, Stowe introduces Cloud HPC talks from Johnson & Johnson, Pacific Life, Hartford Insurance, and Life Technologies.

Read the Full Story.

inShare

Comment on this story by Rich Brueckner on Mar 5
Benchmarking Intel Xeon Phi vs. Sandy Bridge
Posted in Co-processors, Compute, HPC, HPC Hardware

Intel has been careful to label the Xeon Phi as a coprocessor, something that always pairs with a Xeon CPU. But how does their performance compare on real applications? Over at the Xcelerit Blog, Paul Sutton benchmarks both devices using an optimized parallel version of the Monte-Carlo LIBOR swaption portfolio pricer.

It is executed once on the host CPUs (the Sandy Bridge processors), and again on the Xeon Phi co-processor in offload mode. The execution time of the full application is measured, including data transfers, random number generation, and reduction. All these steps are running on the target processor.

As we can see, from about 100K paths onwards, the Intel Xeon Phi becomes faster than the Sandy Bridge processors, reaching nearly 3x at 1M paths. With lower numbers of paths, the Sandy Bridge outperforms the Phi. This can be explained by the added data transfers and the comparably low level of parallelism for a low number of paths (considering both vectorization and multi-threading). The setup time for the random number generator also becomes more dominant on the Xeon Phi when there is relatively little computation performed.

Read the Full Story.

inShare

Comment on this story by Ralph on Mar 5
Podcast: Student Cluster Competition Comes to South Africa, Winners off to ISC’13
Posted in Events, HPC, ISC13, Podcast, Rich Report

In this podcast, Happy Sithole from CHPC and Gilad Shainer from Mellanox discuss the first-ever Student Cluster Competition in South Africa, which wrapped up in December. The winning team will be traveling to compete in the ISC’13 Student Cluster Competition in Leipzig this June.

Download the MP3 or Subscribe on iTunes.

In related news, you can now follow all the major worldwide Student Cluster Competitions at their new home site.

inShare

Comment on this story by Rich Brueckner on Mar 5
1 Terabyte/sec File Systems Enable Big Fast Data
Posted in HPC, HPC Hardware, Storage

Over at the new Cray Blog, VP of Storage Barry Bolding writes that Big Data at the company is synonymous with very fast data access. As evidenced by the Lustre-powered Terabyte/sec file system on Blue Waters, the time for Big Fast Data has come.

Success was achieved on Oct. 7, 2012 when Cray and NCSA measured 1.037 TB/sec of performance to a single Lustre filesystem and 1.137 TB/sec of simultaneously to all three Lustre filesystems. To put this achievement into mass media perspective, 1TB/sec is equivalent to downloading about 125 copies of Dead Space 3 per second, or about 250,000 songs through Spotify per second. This is a milestone for parallel filesystems, a milestone for Lustre, a milestone for Cray and a milestone for our customer at NCSA. Best of all this the technology is being put to good use by a cadre of National Science Foundation users in solving some of the most challenging scientific problems facing our world today.

Here is the leader board script we are using:

and

Here is the side banner script we are using:

and

Related posts:

• Video: Interview with Whamcloud CTO Eric Barton
• Video: Whamcloud Test and Validation Toolset for Lustre
• insideHPC Launches SC11 Featured Video Page

The post Ad Test Page appeared first on insideHPC.

In this podcast, Happy Sithole from CHPC and Gilad Shainer from Mellanox discuss the first-ever Student Cluster Competition in South Africa, which wrapped up in December. The winning team will be traveling to compete in the ISC’13 Student Cluster Competition in Leipzig this June.

Download the MP3 or Subscribe on iTunes.

In related news, you can now follow all the major worldwide Student Cluster Competitions at their new home site.

Related posts:

• Podcast: Radio Free HPC Looks at the Student Cluster Competition
• Podcast: Radio Free HPC Reviews the SC12 Student Cluster Competition
• Podcast: How Taiwan’s NIST Won the SC10 Student Cluster Competition

The post Podcast: Student Cluster Competition Comes to South Africa, Winners off to ISC’13 appeared first on insideHPC.

Who says that HPC folks don’t know how to have fun? Our Video Sunday feature continues with this Mellanox rendition of the Harlem Shake, an Internet meme that is apparently all the rage at the moment.

I had to look it up, but the Harlem Shake is a recent phenomenon, with versions performed by diverse groups including the Norwegian Army, Dallas Mavericks, and the Swansea City football team.

The videos last between 30 and 32 seconds and feature an excerpt from the song “Harlem Shake” by electronic musician Baauer. Usually, a video begins with one person (often helmeted or masked) dancing to the song alone for 15 seconds, surrounded by other people not paying attention or unaware of the dancing individual. When the bass drops, the video cuts to the entire crowd doing a crazy convulsive dance for the next 15 seconds.

I’m wondering if someone could simulate the spread of this kind of thing? As of February 15, about 40,000 Harlem Shake videos had been uploaded, totalling 175 million views.

Related posts:

• Video: Optimizing for the Intel Xeon Phi Coprocessor
• Video: EMC Lustre Contributions
• Video: Current and Future Lustre Developments at CEA

The post Video: Harlem Shake Comes to HPC appeared first on insideHPC.

If you’ll recall, the True Scale architecture replaces traditional Verbs-based MPI libraries with the Performance Scaled Messaging (PSM) layer. Designed specifically with HPC performance in mind, this approach does not require address lookups, which gives you the goodness of lower latency. In large deployments such as those in the Tri-Labs, True Scale has delivered impressive scalability as described in Sandia’s report entitled: Unprecedented Scalability and Performance of the New NNSA tri-lab Linux Capacity Cluster 2, which is part of the SC12 Proceedings.

The performance gains that Sandia users are experiencing with their applications on the new TLCC2 Chama has resulted in many positive feedbacks from happy users…. As pointed out in the introduction, to the scales we have benchmarked on Chama, we are seeing unprecedented performance and scalability of many key Sandia applications.

So how did Intel get True Scale to scale so well? They use something called QDR-80 to double-up 40Gbps QDR ports, thus delivering 80Gbps. While this is a neat trick in itself, Intel has paired this with lower pricing than FDR alternatives. The net-net of this is that Intel is offering low latency interconnects for less money, a persuasive message indeed for supercomputer buyers who would love to take that extra cash and use it to buy more cores.

Watch this space as Intel continues to beef up its portfolio on its journey to Exascale computing. Compute is just one element of a performing, balanced architecture. As Intel brings fabrics (Cray Aries, True Scale, and Fulcurm) and storage (Lustre expertise and SSDs) to bear, the company is building a formidable platform for the future of HPC.

Related posts:

• New Whitepaper: Intel True Scale Fabric Architecture for Enhanced HPC Performance
• Intel MPI Library for Intel Xeon Phi-based Clusters & MVAPICH2 for Intel MIC
• Interview: Sandia’s Experimental Intel MIC Cluster Hails from Appro

The post How Intel’s True Scale QDR-80 IB Scales for Less appeared first on insideHPC.

For customers currently running Infiniband networks, the appeal of being able to collapse their data requirements onto a single network has always been tempered by the lack of support for Remote Direct Memory Access (RDMA) on Ethernet networks. Again, HP and Mellanox lead the way in blade switches. The SX1018HP supports RDMA over Converged Ethernet (RoCE) allowing those RDMA tuned applications to work across both Infiniband and Ethernet networks. When coupled with the recently announced HP544M 40Gb Ethernet/FDR Infiniband adapter, customers can now support RDMA end to end on either network and begin the migration to a single Ethernet infrastructure.

Read the Full Story.

Related posts:

• Mellanox Forges Switch-hitting ConnectX-3 Adapters
• Dell Taps Mellanox to Accelerate Blade Performance
• Dell Goes with Mellanox VPI Combo Cards for IB and 10 GigE

The post HP Taps Mellanox for Low Latency Blade Switch appeared first on insideHPC.