High-Performance Computing News Analysis | insideHPC

In this podcast, the Radio Free HPC team looks at the latest developments in processor technology coming out of the recent Hot Chips conference. "The HOT CHIPS conference typically attracts more than 500 attendees from all over the world. It provides an opportunity for chip designers, computer architects, system engineers, press and analysts, as well as attendees from national laboratories and academia to mix, mingle and see presentations on the latest technologies and products."The post Radio Free HPC Looks at Hot Chips for 2018 appeared first on insideHPC.

Over at The UberCloud, Wolfgang Gentzsch writes that researchers are using HPC in the Cloud in a revolutionary new way for the design of bioreactors. "It’s amazing to think of all the products created in bioreactors. The medications we take, the beer we drink and the yogurt we eat are all made in bioreactors optimized for the manufacturing of these products. Unfortunately, optimizations take a lot of work and data. In a new HPC Cloud project, engineers from ANSYS with support from UberCloud performed an extensive Design of Experiments in Microsoft’s Azure Cloud."The post UberCloud Works with ANSYS and Azure to Optimize Bioreactors appeared first on insideHPC.

Valentin Clement from the Center for Climate System Modeling in Switzerland gave this talk at PASC18. 'In order to profit from emerging high-performance computing systems, weather and climate models need to be adapted to run efficiently on different hardware architectures such as accelerators. This is a major challenge for existing community models that represent very large code bases written in Fortran. We introduce the CLAW domain-specific language (CLAW DSL) and the CLAW Compiler that allows the retention of a single code written in Fortran and achieve a high degree of performance portability."The post The CLAW DSL: Abstractions for Performance Portable Weather and Climate Models appeared first on insideHPC.

Berkeley Lab is seeking a Computer Science Postdoctoral Scholar in our Job of the Week. "Berkeley Lab’s Computational Research Division has an opening for a Computer Science Postdoctoral Scholar. Develop performance modeling and analytical capabilities and tools for manycore and GPU-accelerated supercomputers and apply them to distributed memory Office of Science applications running on such platforms."The post Job of the Week: Computer Science Postdoctoral Scholar at Berkeley Lab appeared first on insideHPC.

"We invite researchers and professionals to take part in this workshop to discuss the challenges of Machine Learning, AI and HPC, and share their insights, use cases, tools and best practices. HPML is held in conjunction with the 30th edition of SBAC-PAD. SBAC-PAD is an international conference on High Performance Computing started in 1987 in which scientists and researchers present recent findings in the fields of parallel processing, distributed computing and computer architecture."The post Agenda Published: High Performance Machine Learning Workshop in France appeared first on insideHPC.

Emma Haruka gave this talk at Google Next. "Google Cloud Platform (GCP) is ready for High Performance Computing (HPC) applications. Google Compute Engine (GCE) offers flexible network and virtual machine (VM) configuration options to run HPC workloads. This session explores why GCP is a good place to run HPC applications and save money. Topics will include CPU, GPU, and memory offerings, as well as underlying network architecture, preemptible VMs, and storage options. You will also learn how Google designs their cloud infrastructure and why it works for HPC workloads."The post Video: Introduction to HPC on the Google Cloud Platform appeared first on insideHPC.

SYCL is an open standard developed by the Khronos Group that enables developers to write code for heterogeneous systems using standard C++. Developers are looking at how they can accelerate their applications without having to write optimized processor specific code. SYCL is the industry standard for C++ acceleration, giving developers a platform to write high-performance code in standard C++, unlocking the performance of accelerators and specialized processors from companies such as AMD, Intel, Renesas, and Arm.The post Codeplay Releases First Fully-Conformant SYCL 1.2.1 Solution for C++ appeared first on insideHPC.

Etienne Lyard from the University of Geneva, Switzerland presents: Handling and Processing Data from the Cherenkov Telescope Array.

Dan Rosplock from Virginia Tech writes that Large-scale simulations could shed light on the 'dark' elements that make up most of our cosmos. By reverse engineering the evolution of these elements, they could provide unique insights into more than 14 billion years of cosmic history.The post Supercomputing Dark Matter appeared first on insideHPC.

Today the Society of Women Engineers (SWE) announced the recipients of its annual awards program. SWE Awards recognize individuals who have proven to be innovators and leaders in their local communities, the STEM community and the future generation of STEM. SWE award recipients include professionals and collegiates from influential businesses, corporations and universities across the globe who play an integral role in the support and advancement of women in engineering. "The men and women recognized today have broken boundaries in their careers and personal lives,” said Penny Wirsing, president of SWE. “They are leaders paving the way to empower and inspire future women engineers across the globe.”The post SWE Awards Recognize Engineers in the STEM Community appeared first on insideHPC.

Susan Bates from NCAR gave this talk at the Blue Waters Summit. "For the past five years, the Blue Waters Project has provided an invaluable platform for research in the fields of atmospheric science, climate, and weather. The computationally intensive numerical models running on Blue Waters push the limits of model resolution and/or capability in first-of-their-kind simulations."The post Advances in the Fields of Atmospheric Science, Climate, and Weather appeared first on insideHPC.

This guest article from Kingston Technology covers how NVMe SSDs and DRAM are being used for high performing mixed workloads.The post NVMe SSDs and DRAM for High Performing Mixed Workloads appeared first on insideHPC.

Today D-Wave Systems published a milestone study demonstrating a topological phase transition using its 2048-qubit annealing quantum computer. This complex quantum simulation of materials is a major step toward reducing the need for time-consuming and expensive physical research and development.The post D-Wave Demonstrates First Large-Scale Quantum Simulation of Topological State of Matter appeared first on insideHPC.

In this video, Tate Cantrell from Verne Global describes how the company is taking advantage of the nearly unlimited power and cooling available in Iceland for their datacenters running HPC workloads. "Whether deployed as stand-alone compute or used as an extension to existing in-house HPC infrastructure, hpcDIRECT from Verne Global offers a top specification (x86 and ARM), bare metal solution combining best-in-class design and an HPC optimised, low cost environment and location."The post Video: Moving HPC Workloads to Verne Global in Iceland appeared first on insideHPC.

Today Fujitsu published specifications for the A64FX CPU to be featured in the post-K computer, a future machine designed to be 100 times faster than the legendary K computer that dominated the TOP500 for years. "A64FX is the world's first CPU to adopt the Scalable Vector Extension (SVE), an extension of Armv8-A instruction set architecture for supercomputers. Building on over 60 years' worth of Fujitsu-developed microarchitecture, this chip offers peak performance of over 2.7 TFLOPS, demonstrating superior HPC and AI performance."The post Fujitsu Unveils Details on Post-K Supercomputer Processor Powered by ARM appeared first on insideHPC.

In this video, Mike Bernhardt sits down with Doug Kothe from the Exascale Computing Project for a quick update and a look ahead. "As we traverse the second half of the 2018 calendar year, the Exascale Computing Project (ECP) continues to execute confidently toward our mission of accelerating the delivery of a capable exascale computing ecosystem* to coincide with the nation’s first exascale platforms in the early 2020s."The post Video: An Update on the Exascale Computing Project appeared first on insideHPC.

VMware explores the concepts of virtual throughput clusters and CPU overcommitment with VMware vSphere to create multitenant and agile virtual HPC computing environments.The post Virtualization Adds Value, Benefits to HPC Environments appeared first on insideHPC.

In today's Startup news, HPC elder James Cuff has joined a new company called Witnix. Most recently at The Next Platform, James spent most of his career at the HPC center at Harvard before he retired a couple of times. Just ask him. "We love working with new and established advanced technology organizations alike. When you find you have a scaling issue, want to grow, deliver results and build profits even faster, let’s talk about how our approach will help you."The post HPC Elder James Cuff Joins Witnix Startup appeared first on insideHPC.

In this Chip Chat podcast, Lisa Spelman from Intel summarizes the recent Intel Data Centric Innovation Summit. In this interview, Spelman discusses Intel's view of data-centric computing and how our broad portfolio of silicon solutions will help customers move faster, store more, and process everything.The post Podcast: Lisa Spelman on Intel Data-Centric Solutions appeared first on insideHPC.

In this video from PASC18, Dan Jacobson from ORNL describes the highlights from the conference and why scientists and engineers should consider attending PASC19 in Zurich. "Next year, PASC19 happens the week before the ISC 2019 conference in Germany. Be sure to catch both shows!"The post Interview: Dan Jacobson from ORNL on Why PASC19 will be The Show to Attend Next Year appeared first on insideHPC.

In this video from the Dell EMC HPC Community Meeting, Robert Dildy from Dell EMC describes how the company powers HPC for the Oil & Gas industry. "The Dell EMC HPC Community is a worldwide technical forum that fosters the exchange of ideas among researchers, computer scientists, technologists, and engineers and promotes the advancement of innovative, powerful HPC solutions."The post How Dell EMC Powers HPC for the Oil & Gas industry appeared first on insideHPC.

Today CoolIT Systems announced it has appointed STULZ ANZ as its master distributor for Rack DCLC products in the Australasian region. "As a business who prides itself on our innovations and future gazing approach, partnering with CoolIT ensures we can provide the latest liquid cooling technology to our portfolio of solutions, and ensure we remain at the forefront of our industry as it rapidly changes year by year.”The post CoolIT Systems Teams with STULZ for Liquid Cooling Down Under appeared first on insideHPC.

In this slidecast, Trish Damkroger from Intel presents: Technology Trends Driving HPC. "HPC is now critical for more use cases, complex workloads, and data-intensive computing than ever before. From AI and visualization to simulation and modeling, Intel provides the advantage of one platform for any workload by integrating world-class compute with powerful fabric, memory, storage, and acceleration. You can move your research and innovation forward faster to solve the world’s most complex challenges."The post Slidecast: Technology Trends Driving HPC appeared first on insideHPC.

In this podcast, the Radio Free HPC team looks at the new Eagle supercomputing under construction at NREL. "The new machine from HPE will run more detailed models that simulate complex processes, systems, and phenomena to advance early research and development on energy technologies across fields including vehicle, wind power, and data sciences."The post Radio Free HPC Looks at NREL’s new Eagle Supercomputer appeared first on insideHPC.

This fall, the Intel Extreme Performance Users Group (IXPUG) will host a free conference focused on key high-performance computing, artificial intelligence, and cloud computing topics.This guest post from Intel explores how AI and HPC are converging and and how the two areas of technology — as well as cloud computing — are converging.The post Exploring the Convergence of AI, HPC & More appeared first on insideHPC.

A new effort from the Visual Genomes Foundation (VGF) looks to move visual artificial intelligence forward in big way. The first step: learn and record exabytes of visual DNA features from millions of images in a collaborative effort that is open to industry, academia, and government partners. “Nobody has ever created a working model of the entire human visual system – a true synthetic vision system. We have a first generation model working now that will only get better over time."The post Visual Genomes Foundation Looks to Exascale for Ai appeared first on insideHPC.

In this video from the Blue Waters 2018 Symposium, Maxim Belkin presents a tutorial on Containers: Shifter and Singularity on Blue Waters. "Container solutions are a great way to seamlessly execute code on a variety of platforms. Not only they are used to abstract away from the software stack of the underlying operating system, they also enable reproducible computational research. In this mini-tutorial, I will review the process of working with Shifter and Singularity on Blue Waters."The post Containers: Shifter and Singularity on Blue Waters appeared first on insideHPC.

Brian O'Shea from Michigan State University gave this talk at the Blue Waters Summit. "Astronomy, astrophysics, and space sciences are fields that are inundated with data, and involve physical phenomena that are complex and cannot be explored via experiments on Earth. As a result, sophisticated simulation tools are required to make theoretical progress in understanding these phenomena, and large-scale computing is required to both analyze observational data and to execute the necessary simulations. In this talk, I will highlight some of the most important advances made in astronomy, astrophysics, and space sciences using Blue Waters, including a variety of figures and animations contributed by the user community."The post Video: Exploring the Universe with Blue Waters appeared first on insideHPC.

Intel is seeking a Research Scientist for their Extreme Scale Computing team in Oregon in our Job of the Week. "In this position, you will be responsible for conceiving, researching, and prototyping new parallel and distributed computing algorithms and frameworks, with special emphasis on machine learning and graph analytics, and you will develop relevant software and hardware technologies with the goal of converting these into products and fueling Intel's growth. You will use your strong knowledge of scientific principles to identify and research promising technologies typically 3-5 years prior to product development. This requires a good understanding of state-of-the-art techniques in parallel computing, machine learning, distributed computing, optimization of algorithms, and bench-marking, along with a strong understanding of computer architecture."The post Job of the Week: Research Scientist at Intel appeared first on insideHPC.

Vasileios Karakasis from CSCS gave this talk at the the Directive Based GPU Programming Workshop. "Directives-based programming facilitates the task of parallelizing your application by letting you focus on its parallel logic rather than on the very details and the low-level intricacies of the GPU architecture. In this course, we will introduce the OpenACC programming paradigms for the GPU. We will cover the parallel execution model and how it can be used to leverage parallelism, the memory model and how this differs from the classic CPU paradigm."The post Video: Introduction to OpenACC appeared first on insideHPC.

This week at the Hot Chips conference, Tachyum CEO Dr. Radoslav Danilak described how the company's its Prodigy Universal Processor Chip combines the best attributes of CPU, GPU and TPU architectures to overcome HPC challenges. "I look forward to sharing with attendees at HOT CHIPS how a new approach is needed to overcome the challenges faced by all those in the hyperscale datacenter, HPC and AI markets.”The post Tachyum Touts Benefits of Universal Processor at HOT CHIPS appeared first on insideHPC.

Today the Women in High Performance Computing (WHPC) group announced the launch of a Chapters and Affiliates Program to bring its vision and mission to the worldwide community and assist those passionate about diversity and inclusion in bringing about positive change in their localities. The pilot programme consists of six chapters and three affiliates across Europe and North America, and will allow WHPC to assess how a worldwide network of such chapters and affiliates might operate.The post Women in HPC Launches Chapters and Affiliates Pilot Program appeared first on insideHPC.

In this video from the DDN User Group at ISC 2018, James Coomer from DDN presents: A3I - Accelerated Any-Scale Solutions from DDN. "Engineered from the ground up for the AI-enabled data center, DDN’s A3I solutions are fully optimized to handle the spectrum of AI and DL activities concurrently: data ingest and preparation, training, validation, and inference. The DDN A3I platform is easy to deploy and manage, highly scalable in both performance and capacity, and represents a highly efficient and resilient solution for all of your current and future AI requirements."The post Video: Accelerated Any-Scale Ai Solutions from DDN appeared first on insideHPC.

In this Conversations with Dez podcast, Dez Blanchfield sits down with Jack Wells from ORNL to talk about about his personal & professional life journey, his role at Oak Ridge National Lab, how Artificial Intelligence is being deployed & leveraged in HPC, and the role IBM’s POWER9 solution is playing in supporting Oak Ridge and its mission. Jack Wells is the Director of Science for the Oak Ridge Leadership Computing Facility.The post Podcast: From Here to Ai with Jack Wells from Oak Ridge appeared first on insideHPC.

SC18 continues its series of Invited Talk previews with this quick look at "Brain-Inspired Massively-Parallel Computing” by Stephen Furber. "The SpiNNaker (Spiking Neural Network Architecture) platform is an example of a highly flexible digital neuromorphic platform, based upon a massively-parallel configuration of small processors with a bespoke interconnect fabric designed to support the very high connectivity of biological neural nets in real-time models. Although designed primarily to support brain science, it can also be used to explore more applications-oriented research."The post SC18 Preview: Steve Furber on Brain-Inspired Massively-Parallel Computing appeared first on insideHPC.

Today ACM announced that Linda Gesenhues of the Federal University of Rio de Janeiro and Markus Höhnerbach of RWTH Aachen University are the recipients of the 2018 ACM-IEEE CS George Michael Memorial HPC Fellowships. "The ACM-IEEE CS George Michael Memorial HPC Fellowship is endowed in memory of George Michael, one of the founding fathers of the SC Conference series. The fellowship honors exceptional PhD students throughout the world whose research focus is on high performance computing applications, networking, storage or large-scale data analytics using the most powerful computers that are currently available."The post Linda Gesenhues and Markus Höhnerbach to receive George Michael Memorial HPC Fellowships appeared first on insideHPC.

Tiziana DiMatteo from Carnegie Melon University gave this talk at the 2018 Blue Waters Symposium. "The first billion years is a pivotal time for cosmic structure formation. The galaxies and black holes that form then shape and influence all future generations of stars and black holes. Understanding and detecting the the first galaxies and black holes is therefore one of the main observational and theoretical challenges in galaxy formation."The post Video: Massive Galaxies and Black Holes at the Cosmic Dawn appeared first on insideHPC.

By working with a manufacturer of DRAM products that deliver a diversity of components, data center operators can be assured that they will not have a patchwork of suppliers to work with. This guest post from Kingston Technology explores different storage structures and why DRAM performance is so crucial to data center success.The post Why the Choice of DRAM in the Data Center is so Critical appeared first on insideHPC.

The Ohio Supercomputer Center Statewide Users Group (SUG) has issued its Call for Participation. Featuring a talk on OSC's pending Pitzer cluster, the event takes place Oct. 4 in Columbus, Ohio. The purposes of the SUG conference are to foster connections, update OSC’s user base on OSC’s direction, highlight new scientific developments produced using OSC resources, and obtain constructive feedback as to the future of OSC and our role in supporting science across Ohio. "We will have a flash talk and poster session to highlight the research and emerging ideas from OSC clients. Talks and posters will be selected from abstracts submitted via the registration form. We encourage posters by students just starting their work, to show creative ideas on how high-performance computing will enhance their research."The post Call for Participation: OSC Statewide User Group Conference in October appeared first on insideHPC.

Today the OpenFabrics Alliance (OFA) unveiled an expanded mission to accelerate the development and adoption of advanced fabric technologies. This is a significant expansion of its original mission from 2004, which was to facilitate the rapid adoption of an emerging network technology, known as the InfiniBand Architecture. The new mission expands its scope to include software for the entirety of the advanced networks landscape, including the InfiniBand Architecture. "

In this Chip Chat podcast, Jim Jeffers from Intel describes his team's three important open source libraries for data center rendering that deliver rasterization and ray tracing with high performance on Intel Xeon processors. Jim discusses the new Intel Select Solutions for Professional Visualization that package up key software capabilities with the power of high performance computing to provide stunning visualizations.The post Podcast: Bringing Complex Data To Life with Intel Select Solutions appeared first on insideHPC.

Hatem Ltaief from KAUST gave this talk at PASC18. "The real-time correction of telescopic images in the search for exoplanets is highly sensitive to atmospheric aberrations. The pseudo-inverse algorithm is an efficient mathematical method to filter out these turbulences. We introduce a new partial singular value decomposition (SVD) algorithm based on QR-based Diagonally Weighted Halley (QDWH) iteration for the pseudo-inverse method of adaptive optics. The pseudo-inverse simulation code will be deployed on-sky for the Subaru telescope during observation nights scheduled early 2018."The post Extreme Computing for Extreme Adaptive Optics: The Key to Finding Life Outside our Solar System appeared first on insideHPC.

Intel will host the Intel eXtreme Performance User Group (IXPUG) event Sept. 25-28 in Hillsboro, Oregon. "This IXPUG conference is focused on all aspects of employing and adopting many-core processing technologies and techniques for optimal application execution, including topics that cover system hardware beyond the processor (memory, interconnect, etc.), software tools, programming models, new workloads (visualization, data analytics, machine learning, etc.) and more. The conference will provide an interactive experience focused on key topics associated with high-performance computing, artificial intelligence, data analytics, cloud computing, and more."The post Intel to Host IXPUG eXtreme Performance User Group Sept. 25-28 in Oregon appeared first on insideHPC.

Today HPE announced it is building a new supercomputer for the National Renewable Energy Laboratory (NREL) that is more energy efficient and 3.5 times more powerful than its existing system. The new development is part of a long-standing collaboration between HPE and the U.S. Department of Energy (DOE) to apply advanced supercomputing and HPC solutions to accelerate research across various DOE agencies. The new, fast-performing system, which NREL has named Eagle, will run more detailed models that simulate complex processes, systems, and phenomena to advance early research and development on energy technologies across fields including vehicle, wind power, and data sciences.The post HPE Eagle Supercomputer to Triple Performance and Enhance Energy Efficiency at NREL appeared first on insideHPC.

Today at SIGGRPAH, NVIDIA announced its newest GPUs based on the new Turing architecture. "

In this video from ISC 2018, Rick Koopman from Lenovo describes the company's latest HPC innovations including their new Neptune liquid cooling technology. Lenovo is the world’s largest TOP500 supercomputing provider measured by the number of systems ranked on the TOP500 list. 117 of the 500 most powerful supercomputers included in the TOP500 are Lenovo installations, meaning nearly one out of every four systems (23.4 percent) on the prestigious list is a Lenovo solution.The post Lenovo Takes the TOP500 with Liquid Cooling at ISC 2018 appeared first on insideHPC.

Today One Stop Systems introduced the Magma ExpressBox 3T-V3-eGPU, a new external graphics card solution with Thunderbolt 3. The ExpressBox 3T-V3-eGPU can transform both computers and laptops with Thunderbolt 3 connections into powerful workstations. "We’re committed to providing mobile professionals with the latest technologies for performing AI, CAE and rendering applications,” said Steve Cooper, CEO of OSS. “Our new ExpressBox 3T-V3-eGPU, like all of our Magma ExpressBox expansion products, enables professionals to remain mobile without sacrificing office workstation performance, but now takes it to a whole new level with NVIDIA technology.”The post One Stop Systems rolls out Magma ExpressBox eGPU with Thunderbolt 3 appeared first on insideHPC.

Gul Rukh Khattak from CERN gave this talk at PASC18. "We use a dataset composed of the energy deposition from electron, photons, charged and neutral hadrons in a fine grained digital calorimeter. The training of these models is quite computing intensive, even with the help of GPGPU, and we propose a method to train them over multiple nodes and GPGPU using a standard message passing interface. We report on the scalings of time-to-solution."The post Training Generative Adversarial Models over Distributed Computing Systems appeared first on insideHPC.

The NVIDIA blog points us to this story on how Fast.ai just completed a new deep learning benchmark milestone. Using NVIDIA V100 GPUs on AWS with PyTorch, the company now has the ability to train ImageNet to 93% accuracy in just 18 minutes. "DIU and fast.ai will be releasing software to allow anyone to easily train and monitor their own distributed models on AWS, using the best practices developed in this project,” said Jeremy Howard, a founding researcher at fast.ai. “We entered this competition because we wanted to show that you don’t have to have huge resources to be at the cutting edge of AI research, and we were quite successful in doing so.”The post Fast.AI Achieves Record ImageNet performance with NVIDIA V100 Tensor Core GPUs appeared first on insideHPC.

"The panelists will discuss the critical challenges facing key HPC application areas in the next 5-10 years, based on a mix of knowledge and speculation. They will explore whether we need to make radical changes to our practices, methods, tools, and techniques to be able to use modern resources and make faster and bigger progress on our scientific problems."The post PASC18 Panel Discussion Big Data vs. Fast Computation appeared first on insideHPC.