In-Air Drop Encapsulation Apparatus (IDEA)
IDEA is a groundbreaking advanced manufacturing tool that increases the production rate of traditionally hard-to-make specialty microcapsules by two to three orders of magnitude and reduces the production-associated waste by up to 99% due to the elimination of the continuous phase. This invention solves the material availability bottleneck for novel capsule developments.
MetaLitho3D: Metaoptics-Enabled Large-Scale 3D Nanolithography
MetaLitho3D is a parallel 3D nanolithography platform that employs over 100,000 high-contrast metalenses to perform wafer-scale two-photon lithography. Compared to current commercial solutions, it fundamentally changes the way 3D nanolithography is performed, providing a thousandfold improvement to fabrication throughput, better quality, unlimited scalability, and applicability.
Monolithic Telescopes
Monolithic Telescopes combine multiple reflective and refractive optics into a single fused-silica optic. This compact optic excels in the outer space environment by eliminating misalignment risks, increasing durability, and minimizing impacts of thermal distortions. Monolithic Telescopes streamline mission development by fitting existing designs and supporting new, modular housings.
Time-Resolved Diffraction for NIF
The Flexible Imaging Diffraction Diagnostic for Laser Experiments (FIDDLE) captures nanosecond-resolution x-ray diffraction “movies” of material phase transitions during laser-driven compression. Using ultrafast hybrid CMOS sensors, it delivers detailed atomic-scale insights into materials response while increasing data efficiency and ensuring reliability in high-energy density experiments.
EXUDE Elite
“EXtreme-power, Ultra-low-loss, Dispersive Element” (EXUDE) technology makes use of Spectral Beam Combining (SBC) of fiber lasers to achieve higher power, exploiting the broad gain bandwidth to enable large numbers of fiber laser channels to be combined with near diffraction-limited beam quality. In the original EXUDE technology, many incoherent laser beams, each with a slightly different wavelength, are superimposed onto a single beam by reflection off of a delicate grating structure. The power in the resulting beam is the sum of the powers of the individual beams.
UMap
Supercomputer applications face large, complex dataset problems from both the system (complex hierarchy, memory, and storage) and the workload. UMap is an open source user-level library that acts as a tier between the application, the complex datasets, and the system hierarchy.
UMap uniquely exploits the prominent role of complex memories in today’s servers and offers new capabilities to directly access large memory-mapped datasets. For high performance, UMap provides flexible configuration options to customize page handling to each application.
Winners: LLNL: Maya Gokhale (PI), Ivy Peng (now at KTH Royal Institute of Technology), Marty McFadden, Elena Green, Roger Pearce, Keita Iwabuchi, Karim Youssef
UnifyFS
The UnifyFS file system enables HPC science applications to perform I/O operations many times faster than they could with traditional methods. UnifyFS is an ephemeral (or temporary) file system that utilizes fast storage tiers on supercomputers to quickly store and access application data so that applications can produce their results in less time.
Winners: LLNL: Kathryn Mohror (PI), Cameron Stanavige, Chen Wang, Hariharan Devarajan, Ned Bass, Tony Hutter
ORNL: Sarp Oral (PI), Michael Brim, Ross Miller, Seung-Hwan Lim, Feiyi Wang, Swen Boehm, Jenna DeLozier
NCSA: Celso Mendes, Craig Steffen
Former LLNL: Adam Moody, Danielle Sikich
Former ORNL: Hyogi Sim, Joseph Moore
CANDLE: CANcer Distributed Learning Environment
CANDLE is an artificial intelligence-based computer code that brings together machine learning, deep learning, and cancer research to accelerate the discovery of new cancer therapies and treatments.
Winners: Argonne National Laboratory: Rick Stevens, Tom Brettin, Justin Wozniak, Emily Dietrich;
Lawrence Livermore National Laboratory: Fred Streitz, Brian Van Essen;
Oak Ridge National Laboratory: Gina Tourassi, John Gounley;
Los Alamos National Laboratory: Tanmoy Bhattacharya, Jamal Mohd Yusof; Frederick
National Laboratory for Cancer Research: Eric Stahlberg
Variorum: Vendor-Agnostic Computing Power Management
Pushing supercomputers to their limits requires a deeper understanding of power and energy than standard software and operating systems allow. Variorum provides robust interfaces that measure and optimize computation at the physical level: temperature, cycles, energy, and power. With Variorum, administrators and users can efficiently and effectively use computing resources.
Learn more: Variorum
Winners: LLNL: Tapasya Patki, Stephanie Brink, Barry Rountree, Eric Green, Kathleen Shoga, Aniruddha Marathe.
ZFP: Fast, Accurate Data Compression for Modern Supercomputing Applications
The zfp software library provides a comprehensive solution to both lossy and lossless data compression. zfp reduces the storage space of high-precision floating-point data without sacrificing accuracy. It was designed to be a compact number format for storing data arrays in-memory in compressed form while supporting high-speed random access.
Learn more: ZFP
Winners: LLNL: Peter Lindstrom, Danielle Asher, Stephen Herbein, Matthew Larsen, Mark Miller, Markus Salasoo
