DENVER, Colo., Nov. 18, 2019 — HPCwire, the leading publication for news and information for the high performance computing industry, announced the winners of the 2019 HPCwire Readers’ and Editors’ Choice Awards at the Supercomputing Conference (SC19) taking place this week in Denver, CO. Tom Tabor, CEO of Tabor Communications Inc., unveiled the list of winners just before the opening gala reception.
“Every year it is our pleasure to connect with and honor the HPC community through our Readers’ and Editors’ Choice Awards, and 2019 marked an exceptional showing of industry innovation,” said Tom Tabor CEO of Tabor Communications, publisher of HPCwire. “Between our worldwide readership of HPC experts and an unparalleled panel of editors, the Readers’ and Editors’ Choice Awards represent resounding recognition throughout the industry. Our congratulations goes out to all of the winners.”
HPCwire has designated two categories of awards: (1) Readers’ Choice, where winners have been elected by HPCwire readers, and (2) Editors’ Choice, where winners have been selected by a panel of HPCwire editors and thought leaders in HPC. The process started with an open nomination process, with voting taking place throughout the month of September.
These awards, now in their 16th year, are widely recognized as being among the most prestigious recognition given by the HPC community to its own each year, and are the only awards that open voting to a worldwide audience of end users.
The 2019 HPCwire Readers’ and Editors’ Choice Award winners are:
Best Use of HPC in Life Sciences
Readers’ Choice: Stony Brook University researchers leveraged PSC’s Bridges and Bridges-AI systems to examine complex tumor tissue biology and build predictive models for patient-tailored treatment.
Editors’ Choice: CEA researchers, with a PRACE allocation of 24.1M core hours on GENCI’s Curie machine at TGCC, developed and implemented a new algorithm for the CAPITOL project that could lead to a breakthrough in breast cancer tumor detection.
Editors’ Choice: Researchers from the University of Michigan, SDSC, and TACC use an agent-based model (GranSim) to examine differences between 2D and 3D visualizations to better understand how Tuberculosis granulomas form and spread.
Best Use of HPC in Physical Sciences
Readers’ Choice: Argonne scientists ran three of the largest cosmological simulations to date, via a record-breaking transfer of nearly 3PB, to generate virtual universes on Oak Ridge‘s Summit supercomputer using Hardware/Hybrid Accelerated Cosmology Code (HACC) and Globus for data movement.
Editors’ Choice: Researchers create detailed 3D models of Perth’s groundwater aquifers by sending airborne electromagnetic survey measurements directly to Pawsey Supercomputing Center for near-real-time data processing to aid new plans for extraction and aquifer replenishment wells for the capital city of Perth.
Best Use of HPC in Manufacturing
Readers’ Choice: Glass bottle manufacturer O-I has used massive CFD and FEA simulation on TotalCAE HPC clusters to reduce physical testing and advance the state of the art in glass container manufacturing.
Editors’ Choice: Western Digital created a million-vCPU AWS cluster using Univa software to simulate crucial elements of upcoming head designs for its next-generation hard disk drives.
Best Use of HPC in Energy
Readers’ Choice: Total debuted the IBM-built Total Pangea 3 supercomputer, the highest-ranked industrial supercomputer, to treat more data and implement AI algorithms.
Editors’ Choice: UC San Diego engineers leveraged SDSC‘s Comet supercomputer to design new materials (“hybrid halide semiconductors”) for solar cells and LEDs, anticipating that these materials will provide excellent properties for those applications.
Editors’ Choice: LRZ used 6500 Lenovo SD650 nodes to construct 3D models of past tectonic plate and mantle changes, allowing better prediction of future changes and improving the safety and efficiency of extraction processes.
Best Use of HPC in Automotive
Readers’ Choice: Ducati engineers used Lenovo ThinkSystem servers to run advanced aerodynamic and fluid dynamic modeling calculations 20 percent faster while examining safety, handling and performance of motorbike design features.
Editors’ Choice: Aramco Research, Argonne National Laboratory and Convergent Science evaluated a new gasoline compression ignition engine by using an IBM Blue Gene/Q supercomputer to analyze thousands of high-fidelity engine designs in days rather months, improving fuel efficiency and emissions.
Best Use of HPC in Financial Services
Readers’ Choice: An investment bank used IBM Power9 AC922 servers (NVIDIA Tesla GPUS, IBM CPUs) and IBM Watson Machine Learning Accelerator software to train and run deep neural networks to bring greater efficiencies and accuracy to classification of operational risk incidents, fraud detection and assessment of unrated bonds using unstructured data.
Editors’ Choice: W.R. Hambrecht developed and refined a machine learning-based investment assessment system, running on AWS infrastructure, that the company says has improved its rate of picking successful start-ups by 3X.
Best Use of High Performance Data Analytics & Artificial Intelligence
Readers’ Choice: Tanmay Bakshi, the 15-year-old Canadian AI and ML systems architect, used IBM Power systems on the Nimbix Cloud to develop a neural network to create a new kind of biometric authentication — Heart ID — that identifies a person based on their heart’s unique electrical activity.
Editors’ Choice: Researchers at Mount Sinai Hospital developed an AI platform with Lenovo ThinkSystem SR670 servers, including GPUs, to detect neurodegenerative disease such as Alzheimer’s disease and chronic traumatic encephalopathy by leveraging machine learning techniques.
Best HPC Storage Product or Technology
Readers’ Choice: BeeGFS
Editors’ Choice: DDN SFA400NV
Best AI Product or Technology
Readers’ Choice: Nvidia V100 GPU
Editors’ Choice: Lenovo ThinkSystem SR670
Best Use of HPC in the Cloud
Readers’ Choice: Using AWS, the Ocean Conservancy performed over 75 50-year ocean simulations to understand stressors on the ocean and the intricate and potentially catastrophic effects climate change is having on our underwater ecosystems.
Editors’ Choice: AMD engineers executed the first physical verification of its largest 7nm chip design in just ten hours using Microsoft Azure cloud platform, powered by AMD’s own EPYC processors.
Editors’ Choice: Astera Labs used Six Nines and a 100% AWS cloud-based EDA workflow to design the industry’s first PCIe 5.0 retimer.
Best HPC Cloud Platform
Readers’ Choice: Amazon Web Services
Editors’ Choice: Microsoft Azure
Best HPC Server Product or Technology
Readers’ Choice: Nvidia DGX-2
Editors’ Choice: AMD 2nd-generation EPYC processors
Best HPC Programming Tool or Technology
Readers’ Choice: Singularity
Editors’ Choice: Cray Programming Environment for Arm
Best HPC Interconnect Product or Technology
Readers’ Choice: Mellanox HDR 200G InfiniBand
Editors’ Choice: Mellanox HDR 200G InfiniBand
Best HPC Collaboration (Academia/Government/Industry)
Readers’ Choice: HPE, Marvell, Mellanox, SUSE and Arm collaborated as part of the Catalyst UK program to accelerate adoption of supercomputer applications in the UK, support research into future architectures and software, and develop the ecosystem.
Editors’ Choice: NCSA, National Geospatial-Intelligence Agency, University of Minnesota and Ohio State University are collaborating to produce an elevation model of the entire Earth that will be publicly available and directly benefit activities such as community planning and environmental assessment.
Top Energy-Efficient HPC Achievement
Readers’ Choice: ORNL‘s Summit Supercomputer, built by IBM, NVIDIA and Mellanox, achieved the number two position on the Green500 (in addition to being ranked number one on the Top500).
Editors’ Choice: ORNL‘s Summit Supercomputer, built by IBM, NVIDIA and Mellanox, achieved the number two position on the Green500 (in addition to being ranked number one on the Top500).
Top HPC-Enabled Scientific Achievement
Readers’ Choice: SDSC, TACC and PSC enabled supercomputer simulations via the NSF’s XSEDE program to help reveal groundbreaking insight into gravitational waves, or invisible space ripples, by analyzing neutron star structures and mergers — with Perimeter Institute for Theoretical Physics (Ontario, Canada) and Theoretical Astrophysics Program (University of Arizona).
Editors’ Choice: The Event Horizon Telescope team crunched petabytes of data to produce never-before-seen images of the cosmos — most notably, the first-ever image of a black hole.
Top Supercomputing Achievement
Readers’ Choice: Cray swept all three US exascale-class supercomputer systems: Cray Shasta systems will be deployed at ANL, ORNL and LLNL.
Editors’ Choice: Cray swept all three US exascale-class supercomputer systems: Cray Shasta systems will be deployed at ANL, ORNL and LLNL.
Editors’ Choice: The NSF-backed Frontera supercomputer, built by Dell EMC using Intel CPUs and now operational at TACC, became the world’s largest academic supercomputer.
Top 5 New Products or Technologies to Watch
Readers’ Choice: Mellanox HDR 200G InfiniBand
Editors’ Choice: Cerebras Systems Wafer-Scale Engine
Elastic Fabric Adapter from AWS
Ayar Labs TeraPHY Electronic-Photonic Chiplet
Top 5 Vendors to Watch
Readers’ Choice: NVIDIA
Editors’ Choice: HPE/Cray
Workforce Diversity Leadership Award
Readers’ Choice: Women in IT Networking at SC (WINS) has funded 44 women (32 first-time participants and 12 returning participants) to contribute to SCinet since its inception in 2015.
Editors’ Choice: The PRACE Ada Lovelace Award is awarded annually to a female scientist who makes an outstanding contribution to and impact on HPC, both in Europe and globally, and serves as a role model for young women.
Outstanding Leadership in HPC
Readers’ Choice: Lisa Su, CEO at AMD, has led AMD’s charge back into the datacenter and steered the launch of the first 7nm server CPU.
Readers’ Choice: Peter Ungaro, President and CEO at Cray, has led Cray for 14 years, securing three US exascale contracts and guiding the transfer of Cray to HPE.
Editors’ Choice: Kathy Yelick, Assoc. Lab Director for Computing Sciences, Lawrence Berkeley National Laboratory, was NERSC Director from 2008 through 2012 and is widely recognized for contributions to parallel computing languages.
More information on these awards can be found at the HPCwire website at https://www.hpcwire.com/2019-hpcwire-awards-editors-choice/, or on Twitter through the hashtag: #HPCwireAwards.
HPCwire is the #1 news and information resource covering the fastest computers in the world and the people who run them. With a legacy dating back to 1986, HPCwire has enjoyed a history of world-class editorial and journalism, making it the news source of choice selected by science, technology and business professionals interested in high performance and data-intensive computing. Visit HPCwire at www.hpcwire.com
About Tabor Communications Inc.
Tabor Communications Inc. (TCI) is a media and services company dedicated to high-end, performance computing. As publisher of a complete advanced scale computing portfolio that includes HPCwire, Datanami, EnterpriseAI, and HPCwire Japan, TCI is the market-leader in online journalism covering emerging technologies within the high-tech industry, and a services company providing events, audience insights, and other services for companies engaged in performance computing in enterprise, government, and research. More information can be found at www.taborcommunications.com.