search.noResults

search.searching

note.createNoteMessage

search.noResults

search.searching

orderForm.title

orderForm.productCode
orderForm.description
orderForm.quantity
orderForm.itemPrice
orderForm.price
orderForm.totalPrice
orderForm.deliveryDetails.billingAddress
orderForm.deliveryDetails.deliveryAddress
orderForm.noItems
high-performance computing


clusters deployed in Top500 companies. Te deep learning appliance is based on MPI


optimized Caffe frame developed by Inspur. It is a soſtware/hardware integrated solution with MPI parallel and multiple GPU accelerators for big data processing. Inspur concentrates on accelerated development and efficient application of deep learning – from the perspective of hardware infrastructure, system optimisation and parallel framework. Meanwhile, with unique soſtware and


hardware technologies in the three major fields of heterogeneous computing, namely GPU, MIC and FPGA, Inspur has become China’s biggest server supplier in deep learning and the core supplier for Baidu and Alibaba. www.inspursystems.com


Learn about Self-Service Cloud Computing and EMC’s 2 TIERS at the Omnibond (booth 941) exhibition during ISC. Te company will feature its CloudyCluster, a tool that simplifies the self-service process of launching HPC clusters on AWS, complete with scheduler, compute and storage based on OrangeFS, EFS, and S3. CloudyCluster comes with many HPC libraries


and applications pre-installed. CCQ, a part of CloudyCluster, enables Elastic HPC, which can help optimise EC2 usage during job execution. Visit the booth to engage in discussion about your HPC objectives, or opt for a personal demo highlighting ease of setup and flexible use cases for cloud computing on AWS with CloudyCluster. Omnibond will also showcase one of its


partners, EMC, at its booth during ISC this year. EMC is demonstrating 2 TIERS, a burst buffer technology leveraging OrangeFS as the fast flash tier and S3 as the object store capacity tier, inside


Calyos (booth 1223) is a provider of Advanced 2-Phase Cooling solutions for electronic components. Based upon its unique and extensive expertise in Loop Heat Pipe (LHP) technologies, Calyos supplies a comprehensive range of high performance, pumpless, passive platform cooling solutions for High Performance Computing (HPC) and Power Electronics (PE). Calyos technology significantly reduces


the total cost of ownership (TCO) of its final users by enabling cleaner, more reliable, more powerful and more energy efficient customer applications. With state-of-the-art design tools (2-Phase Models, CFD–FlothermXT, ANSYS), manufacturing (porous media) and test capabilities (high-end laboratory testing), Calyos offers a wide range of services, from design to mass production, through prototyping, tests, and qualification. www.calyos-tm.com


www.scientific-computing.com l


Let NetApp (booth 1231) accelerate your analytics, shared file systems, and soſtware defined storage with price-performance optimised storage systems all produced and maintained within a DevOps environment. Check out the 0.5PB Ceph TCO model, for


cost per TB against your configuration and see if your current storage can measure up. Te company will also showcase its low latency flash and hybrid cloud solutions. As of May 10, 2016, the company has systems with the number 1 SPC-2 price-performance ranking using SSDs and the number 3 ranking with HDDs. Investigate HPC, analytics, technical


of CloudyCluster on AWS. Learn how the EMC ECS and DSSD lines can also serve as the tiers for on-premise solutions. www.omnibond.com


Storage for HPC is faced with seemingly contradicting requirements – users want fast, parallel storage yet require long-term data availability and don’t tolerate data loss or corruption. Quobyte (booth 1000) delivers the solution: its soſtware turns standard server hardware into a reliable and highly available datacentre file system. Built around a high-performance parallel file


system core, Quobyte supports all workloads from classical file system use cases like HPC,


computing and additional solutions at our booth as well as NetApp’s StorageGRID Webscale application and appliance for managing, moving, and storing billions of securely encrypted objects across widely distributed geographies within or outside of the cloud. www.netapp.com


region, drawing on NCI’s success building the Australian Geoscience Data Cube using Landsat satellite data. Multispectral high-resolution photography,


radar and temperature observations will empower organisations within the region to generate improved weather forecasts and will help scientists better understand the effects of climate change. Te NCI HPC Development and Innovations


filers and archival to high-performance block storage for virtual machines and databases. Data is kept safe and available with end-to-end checksumming, replication and erasure coding, and is accessible via local mount point for Linux and Windows, NFS, HDFS or S3. Admins benefit greatly from Quobyte’s automation capabilities that enable lights-out operations and make excessive maintenance overhead a thing of the past. www.quobyte.com/hpc


NCI Australia (booth 815): specialists in integrating HPC and HPD to deliver world class outcomes. During ISc this year NCI will showcase several projects including: Te Copernicus Project, a collaboration


with ESA and EUMETSAT to ensure satellite meteorological data from the Sentinel satellite program will be accessible across the Asia Pacific


@scwmagazine


team are preparing for next-generation technologies by increasing scalability of NOAA’s Modular Ocean Model (MOM). Results include upscaling from 2,000 to 20,000 cores, as well as a 7.5-fold reduction in computation (wall clock) time. www.nci.org.au


GPGPU Programming with GOOPAX (booth 515). Video cards have an enormous potential for high performance computing. Tey are used to speed up applications in many areas, such as simulations, image recognition, CAD, or AI. Te problem is oſten the programming. GOOPAX brings a new concept to GPGPU,


language-embedded programming. Tis leads to a number of advantages including: perfect integration of the GPU kernels into the host code; programs compiled with a standard C++ compiler; shorter programs due to code- reusability; significantly higher performance due to meta-programming, profiling, and just-in-time compilation; more reliability – race conditions and other programming errors are detected


JUNE/JULY 2016 19





Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44