Inside HPC & AI News | High-Performance Computing & Artificial Intelligence

“Analytics applied over complex, many-to-many data relationships hit the ‘Graph Cache Thrash’ bottleneck and grind to a halt, failing to deliver good performance or to operate at scale,” said Brad Bebee, SYSTAP CEO. “GPU hardware provides a compelling performance increase for data-intensive, predictive analytic applications. With Blazegraph and our new GPU products, users can harness the computing power comparable to what was only available from supercomputers, such as a Cray, at a fraction of the cost.”The post Video: Blazegraph Accelerates Graph Computing with GPUs appeared first on insideHPC.

On December 18, Oracle closed an agreement to acquire StackEngine, an Austin-based startup focused on Docker automation. All StackEngine employees will be joining Oracle as part of Oracle Public Cloud.The post Oracle Acquires StackEngine Startup to Automate Docker appeared first on insideHPC.

In this video, David Bolton from Slashdot Media looks at the costs of running high-powered servers in the Cloud from three providers: AWS, Google and Microsoft. The Cloud computing services are compared by price, capability and available features.The post How Much Does it Cost to Run an HPC Server in the Cloud? appeared first on insideHPC.

Intel is seeking an HPC Solutions Architect in our Job of the Week.The post Job of the Week: HPC Solutions Architect at Intel appeared first on insideHPC.

Scientists from the Heat and Mass Transfer Technological Center (CTTC) at the Technical University of Catalonia in Spain have harnessed the extreme performance of the Mira supercomputer with their in-house multi-physics CFD code as a result of collaboration on scalable debugging for the high-end system between Allinea Software and Argonne National Laboratory.The post Enabling New Frontiers in CFD Research at Argonne with Allinea DDT appeared first on insideHPC.

In this video, David Keyes (KAUST) and Torsten Hoefler (ETH Zurich) discuss the new papers track at the PASC16 conference. After issuing their Call for Papers, the event will be held June 8-10, 2016 in Lausanne, Switzerland.The post Video: Seeking Submissions for New Papers Track at PASC16 appeared first on insideHPC.

The 2016 ASC Student Supercomputer Challenge (ASC16) in China has issued its Call for Participation. As one of the largest Student Cluster Competitions in the world, the ASC16 initiative provides a unique opportunity for organizations and individuals to test their mettle in High Performance Computing. Student Teams and Potential Hosting Institutions are invited to apply.The post Call for Participation: ASC16 Student Supercomputer Challenge appeared first on insideHPC.

John Stone from the University of Illinois presented this talk at the Intel HPC Developer Conference at SC15. "VMD is designed for modeling, visualization, and analysis of biological systems such as proteins, nucleic acids, lipid bilayer assemblies, etc. It may be used to view more general molecules, as VMD can read standard Protein Data Bank (PDB) files and display the contained structure."The post Visualizing Biomolecular Complexes on x86 and KNL Platforms: Integrating VMD and OSPRay appeared first on insideHPC.

The fifth Irish Supercomputer List was released today with a full ranking of the nation's HPC systems. Launched in November 2013 to raise the profile of High Performance Computing in Ireland and abroad, the list is updated twice annually with a continuous open call for participation from users and maintainers of Irish HPC installations.The post Irish Supercomputer List Reflects HPC Growth appeared first on insideHPC.

"At SC15, IBM, in turn, announced new offerings centered "on the tight integration of IBM’s Power processors with accelerators." But it was an announcement about IBM’s interest in FPGAs that attracted attention. It has concluded a multi-year strategic collaboration with Xilinx to develop FPGA-enabled workload acceleration on Power-based systems. Through a private commercial agreement as well as by collaboration through the Open Power Foundation, the two companies are teaming up to develop open acceleration infrastructures, software, and middleware.The post Is the Future CPU+GPU or CPU+FPGA? appeared first on insideHPC.

Today ClusterVision and UberCloud formally announced the integration of UberCloud Application Containers with Trinity, ClusterVision’s private cloud solution. Trinity provides a complete HPC cluster manager on top of a cloud platform capable of managing HPC, general IT, and Big Data, bringing the flexibility of Platform-as-a-Service to HPC.The post ClusterVision Trinity Private Cloud Moves to UberCloud HPC Application Containers appeared first on insideHPC.

"The goal of each hackathon is for current or prospective user groups of large hybrid CPU-GPU systems to send teams of at least 3 developers along with either (1) a (potentially) scalable application that needs to be ported to GPU accelerators, or (2) an application running on accelerators which needs optimization. There will be intensive mentoring during this 5-day hands-on workshop, with the goal that the teams leave with applications running on GPUs, or at least with a clear roadmap of how to get there. Our mentors come from national laboratories, universities and vendors, and besides having extensive experience in programming with OpenACC/CUDA, many of them develop the GPU-capable compilers and help define the OpenACC standard."The post 2016 Hackathons Seeking Team Applications appeared first on insideHPC.

ISC 2016 has announced their keynote speakers. The event takes place June 19-23 in Frankfurt, Germany.The post ISC 2016 Announces Keynote Speakers appeared first on insideHPC.

"Applications in diverse industries such as the hospitality and retail industry, social networks and surveillance can benefit from real time image recognition. Parallelism at the system level can be divided into two main areas. First, at the database level and second at the image recognition level. The compute load per thread on the host system can just be calculated as the total number of images in the database divided by the number of threads. The image matching algorithms can then be parallelized on the coprocessor."The post Image Recognition with Coprocessors appeared first on insideHPC.

Nvidia's Jen-Hsun Huang and Ian Buck presented this talk at SC15. "Supercomputing has swept rapidly from the far edges of science to the heart of our everyday lives. And propelling it forward – bringing it into the mobile phone already in your pocket and the car in your driveway – is GPU acceleration, Nvidia CEO Jen-Hsun Huang told a packed house at a rollicking event kicking off this week’s SC15 annual supercomputing show in Austin. The event draws 10,000 researchers, national lab directors and others from around the world."The post Accelerated Computing: The Path Forward appeared first on insideHPC.

Graduate students and postdoctoral scholars from institutions in Canada, Europe, Japan and the United States are invited to apply for the seventh International Summer School on HPC Challenges in Computational Sciences, to be held June 26 to July 1, 2016, in Ljubljana, Slovenia. The summer school is sponsored by the Extreme Science and Engineering Discovery Environment (XSEDE) with funds from the U.S. National Science Foundation, Compute/Calcul Canada, the Partnership for Advanced Computing in Europe (PRACE) and the RIKEN Advanced Insti­tute for Computational Science (RIKEN AICS).The post Apply for International Summer School on HPC Challenges in Slovenia appeared first on insideHPC.

Baidu Research has unveiled new research results from its Silicon Valley AI Lab (SVAIL). Results include the ability to accurately recognize both English and Mandarin with a single learning algorithm. The results are detailed in a paper: Deep Speech 2: End-to-End Speech Recognition in English and Mandarin.The post Deep Learning System Replaces Hand-Engineered Components With Neural Networks appeared first on insideHPC.

Bill Nitzberg from Altair presented this talk at the Intel HPC Developer Conference at SC15. "Everyone benefits from faster, more resilient infrastructure - the small, the medium, and the really big. This talk will cover how job management software like PBS connect applications with system resources and present optimal paths for application execution."The post Video: Job Launching – Keeping Pace with Expanding Complexities appeared first on insideHPC.

Today Allinea released version 6.0 of their HPC development tools suite Allinea Forge and Performance Reports. Building on their commitment to serving the scientific HPC community, Allinea demonstrated the new features at SC15 last month in Austin.The post New Allinea 6.0 HPC Developer Tools Suite appeared first on insideHPC.

In this video from the CHPC National Meeting in South Africa, participants in the Student Cluster Competition discuss what they learned in their race to build the fastest HPC cluster. "The students received a unique opportunity to learn, experience and demonstrate how high-performance computing influence our world and day-to-day learning. As an integral part of the CHPC National Meeting, the Student Cluster Competition is designed to introduce the next generation of students to the high performance computing world and community."The post Lessons Learned from the CHPC Student Cluster Competition appeared first on insideHPC.

In this NICS podcast, Scott Gibson discusses how the Earth was formed with Wladimir Lyra, an assistant professor at California State University at Northridge, Department of Physics and Astronomy. Lyra is using XSEDE supercomputing resources to explore this age-old question.The post Podcast: XSEDE Powers Search for How the Earth was Formed appeared first on insideHPC.

Today IBM's Cleversafe announced its software defined/hardware aware storage approach to enable organizations with massive-scale data demands to easily take advantage of software defined storage (SDS) with a solution that integrates with industry-standard hardware. The Cleversafe approach reduces cost and complexity by enabling enterprises to manage their storage hardware and software from a single management system. The company also announced newly certified hardware platforms, giving enterprise customers even greater deployment flexibility.The post Cleversafe takes Software Defined Storage to Industry Standard Hardware appeared first on insideHPC.

"This talk will discuss the plans to use OpenStack to manage and automate dynamically changing an environment to provide users a highly re-configurable software environment with access to a large number of operating systems and software packages on the “Bridges system.” It will feature elements of OpenStack related to bare-metal booting, network provisioning, container management, storage, and scheduling nodes to match the workloads of the users."The post Using OpenStack to Manage a Data Analytics HPC Cluster at PSC appeared first on insideHPC.

In many HPC environments, the storage system is an afterthought. While the main focus is on the CPU’s the selection and implementation of the storage hardware and software is critical to an efficient and productive overall HPC environment. Without the ability to move data quickly into and out of the CPU system, the HPC users would not be able to obtain the performance that is expected.The post Enterprise HPC Storage System appeared first on insideHPC.

The XSEDE16 conference has issued its Call for Participation. With a conference theme of Diversity, Big Data, Science at Scale: Enabling the Next-Generation of Science and Technology, the conference takes place July 17-21, 2016 in Miami.The post Call for Participation: XSEDE16 Conference in Miami appeared first on insideHPC.

In this TACC podcast, the Thomas Jordan from the University of Southern California describes how he uses the computational resources of XSEDE, the Extreme Science and Engineering Discovery Environment, to model earthquakes and help reduce their risk to life and property. Dr. Jordan was invited to speak at SC15 on the Societal Impact of Earthquake Simulations at Extreme Scale.The post Podcast: Societal Impact of Earthquake Simulations at Extreme Scale appeared first on insideHPC.

Buddy Bland from ORNL presented this talk at SC15. "Summit will deliver more than five times the computational performance of Titan’s 18,688 nodes, using only approximately 3,400 nodes. Each Summit node will contain multiple IBM POWER9 CPUs and NVIDIA Volta GPUs all connected together with NVIDIA’s high-speed NVLink and a huge amount of memory."The post Buddy Bland Presents an Update on the Summit Supercomputer appeared first on insideHPC.

SC15 has released results from the Supercomputing conference in Austin. This year, the conference drew a record 12,868 attendees, including 4,829 who registered for the six-day Technical Program of invited speakers, technical papers, research posters, tutorials, workshops and more.The post SC15 Announces Attendance Record & Awards Roundup appeared first on insideHPC.

Today Mellanox announced the Defense Information Systems Agency (DISA) has approved the Mellanox SwitchX series of 10/40 Gigabit Ethernet switches for use on U.S. Department of Defense (DoD) networks. This move comes as a direct result of the DISA awarding Mellanox Federal Systems the Unified Capabilities Approved Product List (UC APL) certification for the Mellanox SwitchX series of Ethernet switches.The post Mellanox 10/40 Gig Ethernet Switches Approved for DoD Networks appeared first on insideHPC.

In this video from the Intel HPC Developer Conference at SC15, David Pellerin, HPC Business Development Principal at Amazon Web presents: Use-Cases and Methods for Scalable Enterprise HPC in the Cloud.The post Use-Cases and Methods for Scalable Enterprise HPC in the Cloud appeared first on insideHPC.

This week Flow Science released a new version of FLOW-3D Cast, its software specially-designed for metal casters. FLOW-3D Cast v4.1 offers powerful advances in modeling capabilities, accuracy and performance.The post Flow Science Adds Active Simulation Control to FLOW-3D Cast appeared first on insideHPC.

In this video from SC15, Bryan Catanzaro, senior researcher in Baidu Research's Silicon Valley AI Lab describes AI projects at Baidu and how the team uses HPC to scale deep learning. Advancements in High Performance Computing are enabling researchers worldwide to make great progress in AI.The post Video: Bryan Catanzaro on HPC and Deep Learning at SC15 appeared first on insideHPC.

"OpenHPC is a collaborative, community effort that initiated from a desire to aggregate a number of common ingredients required to deploy and manage High Performance Computing Linux clusters including provisioning tools, resource management, I/O clients, development tools, and a variety of scientific libraries. Packages provided by OpenHPC have been pre-built with HPC integration in mind with a goal to provide re-usable building blocks for the HPC community."The post Video: Working Together on Frameworks for HPC Systems with OpenHPC appeared first on insideHPC.

Penguin Computing in Portland is seeking a Python Software Engineer in our Job of the Week.The post Job of the Week: Python Software Engineer at Penguin Computing in Portland appeared first on insideHPC.

In this TACC podcast, Niall Gaffney from the Texas Advanced Computing Center discusses the Wrangler supercomputer for data-intensive computing. "We went to propose to build Wrangler with (the data world) in mind. We kept a lot of what was good with systems like Stampede, but then added new things to it like a very large flash storage system, a very large distributed spinning disc storage system, and high speed network access to allow people who have data problems that weren't being fulfilled by systems like Stampede and Lonestar to be able to do those in ways that they never could before."The post Podcast: Big Data on the Wrangler Supercomputer appeared first on insideHPC.

In this video from SC15, Brian Sparks from Mellanox presents an overview of the HPC Advisory Council. "The HPC Advisory Council’s mission is to bridge the gap between high-performance computing (HPC) use and its potential, bring the beneficial capabilities of HPC to new users for better research, education, innovation and product manufacturing, bring users the expertise needed to operate HPC systems, provide application designers with the tools needed to enable parallel computing, and to strengthen the qualification and integration of HPC system products."The post Video: Introduction to the HPC Advisory Council appeared first on insideHPC.

Today the Society of HPC Professionals announced the formation of the HPC in Cybersecurity Center of Performance located in Washington, D.C. "The HPC in Cybersecurity Center of Performance (CoP) is an educational chapter focused on bringing together members of the private sector, government and academia engaged in the intersecting technologies of HPC and cybersecurity,” said Maryam Rahmani, CoP Director.The post New Cybersecurity Center of Performance Launches from SHPCP appeared first on insideHPC.

In this video from the Intel HPC Developer Conference at SC15, Kent Millfield from TACC presents: OpenMP and the Intel Compiler. "The OpenMP standard has recently been extended to cover offload and SIMD. The Intel compiler has provided its own implementations of offload and SIMD for some time before the extensions to the OpenMP standard was approved, and that standard is still evolving. This talk describes what you can do with the Intel compiler that you cannot yet do in OpenMP including some where gaps are getting closed soon, and some which will remain for a while. The talk will also highlight where things are done differently between the language interfaces of the Intel compiler and the OpenMP standard. The talk is relevant both to those who seek to port existing code to the OpenMP standard, and to those who are starting afresh."The post Video: OpenMP and the Intel Compiler appeared first on insideHPC.

In this special guest feature, Kristin Hansen, Chief Marketing Officer at Bright Computing writes that HPC doesn't need to be held back by commonly held misconceptions.The post HPC Myths Need Not Hamper the Technology’s Growth appeared first on insideHPC.

In this video from SC15, Brian Connors of Lenovo and Charlie Wuischpard of Intel Lenovo discuss how their company's are partnering to drive innovation in high performance computing. “We’re excited to collaborate with Lenovo in their new Beijing Center for HPC, cloud and data analytics,” said Charles Wuischpard, vice president and general manager of HPC Platform Group at Intel. “As with the current Innovation Center in Germany, the new center in Beijing gives clients early access to a broad range of ever-advancing technology and scale, including full support of the Intel Scalable System Framework — allowing users of all sizes to experience its benefit.”The post Video: Lenovo and Intel Partner on HPC Innovation at SC15 appeared first on insideHPC.

Today Nvidia announced that Facebook will power its next-generation computing system with Tesla GPUs, enabling a broad range of new machine learning applications.The post GPUs Power Facebook’s New Deep Learning Machine appeared first on insideHPC.

"How can quants or financial engineers write financial analytics libraries that can be systematically efficiently deployed on an Intel Xeon Phi co-processor or an Intel Xeon multi-core processor without specialist knowledge of parallel programming? A tried and tested approach to obtaining efficient deployment on many-core architectures is to exploit the highest level of granularity of parallelism exhibited by an application. However, this approach may require exploiting domain knowledge to efficiently map the workload to all cores. Using representative examples in financial modeling, this talk will show how the use of Our Pattern Language (OPL) can be used to formalize this knowledge and ensure that the domains of concerns for modeling and mapping the computations to the architecture are delineated. We proceed to describe work in progress on an Intel Xeon Phi implementation of Quantlib, a popular open-source quantitative finance library."The post Video: Designing Parallel Financial Analytics Libraries Using a Pattern Oriented Approach appeared first on insideHPC.

One of the highlight of the annual SC conference is the Student Cluster Competition, where student teams race to build the fastest HPC cluster. For SC16, the conference is looking for your help improve the application benchmark suite.The post Help Improve the SC16 Student Cluster Competition appeared first on insideHPC.

"In this video from SC15, Amar Shan describes how the the Cray CS-Storm takes GPUs to new levels of scalability. Systems like the CS-Storm have propelled Cray to power 50 percent of the TOP500 supercomputers. While the Cray CS-Storm started out successfully in government sectors, the systems have gained traction in various commercial sectors including Oil & Gas."The post Cray CS-Storm Takes GPUs to New Levels of Scalability at SC15 appeared first on insideHPC.

"Modal is a cosmological statistical analysis package that can be optimized to take advantage of a high number of cores. The inner product computations with Modal can be run on the Intel Xeon Phi coprocessor. As a base, the entire simulation took about 6 hours on the Intel Xeon processor. Since the inner calculations are independent from each other, this lends to using the Intel Xeon Phi coprocessor."The post Cosmic Microwave Background Analysis with Intel Xeon Phi appeared first on insideHPC.

"Just as representative benchmarks like HPCG are set to replace Linpack, so a focus on software is taking over. From industry analysts to users at SC15 we heard that software is the number one challenge and the number one opportunity to have world-class impact."The post Four Reasons that Software Development is in the HPC Driving Seat for 2016 appeared first on insideHPC.

"In July, Intel announced plans for the HPC Scalable System Framework - a design foundation enabling wide range of highly workload-optimized solutions. This talk will delve into aspects of the framework and highlight the relationship and benefits to application development and execution."The post Video: Diving into Intel’s HPC Scalable System Framework Plans appeared first on insideHPC.

Today CoolIT Systems announced that the company has been named 2015 Exporter of the Year by the Canadian Manufacturers & Exporters (CME) and JuneWarren-Nickle’s Energy Group (JWE) in Calgary.The post CoolIT Systems Named Alberta’s Exporter of the Year appeared first on insideHPC.

"Modeling and simulation have been the primary usage of high performance computing (HPC). But the world is changing. We now see the need for rapid, accurate insights from large amounts of data. To accomplish this, HPC technology is repurposed. Likewise the location where the work gets done is not entirely the same either. Many workloads are migrating to massive cloud data centers because of the speed of execution. In this panel, leaders in computing will share how they, and others, integrate tradition and innovation (HPC technologies, Big Data analytics, and Cloud Computing) to achieve more discoveries and drive business outcomes."The post Dell Panel on the Convergence of HPC, Big Data, and Cloud appeared first on insideHPC.