Featured Publication Summaries
All Featured Publication Summaries
Feature extraction and visualization algorithm improves functional memory and research outcomes in multiphase flow simulation analysis
By Galen Fader Oak Ridge National Laboratory A joint research team funded by the Department of Energy’s Exascale Computing Project (ECP) has created a novel end-to-end analytics and visualization program for solving domain-specific issues in multiphase flow simulations. The program operates alongside MFIX-Exa, a massively parallel CFD-DEM (computational fluid dynamics–discrete element model) code designed to […]
A team working on the ECP’s Exascale Atomistic Capability for Accuracy, Length, and Time (EXAALT) project has developed a task-level speculative method that maximizes parallelism and computational throughput at large scales by predicting whether task-level outputs will be used in subsequent executions.
Novel algorithm delivers flexibility, efficiency for sparse linear system solvers on HPC infrastructures
Researchers funded by the Exascale Computing Project (ECP) have extended the sparse direct solver STRUMPACK to GPU frameworks, providing more flexibility and efficiency for execution of large-scale sparse linear solvers on high-performance computing infrastructures.
A team funded by the Exascale Computing Project is preparing to release a new version of HPCToolkit, a suite of performance analysis tools that helps developers identify and diagnose performance bottlenecks on emerging exascale systems.
Cancer research inspires improved training models for natural language processing involving PII and other private data
The use of artificial intelligence/machine learning (AI/ML) methods to analyze health information brings great promise for learning about disease but also great risk to patient privacy.
ECP Data and Visualization lead offers viewpoint on the challenges and opportunities of exascale computing
The dawn of exascale computing will bring exciting new capabilities to bear on scientific investigation as well as unprecedented challenges that we should reframe as opportunities in order to find “exemplary solutions".
An Exascale Computing Project–funded team has developed MemHC, a GPU memory management framework that optimizes the many-body correlation function.
Scientists funded by the Exascale Computing Project have developed Metall, a persistent memory allocator that enables applications to allocate memory transparently into various nonvolatile random access memories (NVRAM) by leveraging the memory-mapped file mechanism (i.e., mmap system call).
A team of researchers working with the Exascale Computing Project has completed the first real-world demonstration of the effectiveness of Lagrangian analysis techniques for reducing data size and storage needs while ensuring accuracy for post hoc exploratory analysis and visualization of time-varying vector fields.
A team of scientists working with the ExaGraph Co-Design Center provided a review of work done under the Exascale Computing Project (ECP) to optimize combinatorial and graph algorithms and related software development for scaling to exascale applications.
Remote OpenMP Offloading strategy increases productive programmability, reduces complexity for real-world applications
Computer scientists working with the Exascale Computing Project (ECP) to advance LLVM compiler infrastructure have shown that OpenMP is an effective tool for remote accelerator offloading with more than a single compute node.
Work under ExaIO project introduces asynchronous I/O methods to improve data storage and operations for faster computation
Researchers working with the ExaIO project have developed an asynchronous input/output (I/O) framework for HDF5 (Hierarchical Data Format version 5), a popular parallel I/O library used by many Exascale Computing Project (ECP) applications across scientific domains.
Scientists working with the Exascale Computing Project (ECP) have developed Ginkgo, a sparse linear algebra library designed to increase portability of software among heterogeneous supercomputing architectures.
Researchers supporting the development of NWChemEx, an open-source, exascale software platform for high-performance quantum chemistry simulations, have demonstrated a novel modular software design solution that can be extended to future architectures with minimal software engineering effort and provides a sustainable pathway to software development with kernels that can be plugged into many high-level algorithms.
A team funded by the Exascale Computing Project (ECP) have ported and scaled WarpX, a particle-in-cell (PIC) code for solving the motion of relativistic, charged particles in the presence of electromagnetic fields, to GPU-based supercomputers such as Summit and the upcoming Aurora and Frontier machines.
Tusas, a novel open-source phase-field simulation framework, represents a superior tool for studying solidification dynamics and microstructure formation in heterogeneous metal alloys under extreme processing conditions such as additive manufacturing (AM).
With the latest Kokkos release, researchers with the Exascale Computing Project (ECP) continue to address the challenge of diverse programming models and heterogeneous architectures.
Researchers funded by the Exascale Computing Project have demonstrated an alternative to MPI, the de facto communication standard for high-performance computing (HPC), using NVIDIA’s library NVSHMEM to overcome the semantic mismatch between MPI and GPU asynchronous computation to enable the compute power needed for exascale computing.
New EFFIS framework optimizes WDMApp with support for code coupling and application performance monitoring
Researchers working with the nuclear fusion device simulation application WDMApp for the Exascale Computing Project have developed EFFIS, a workflow framework currently used in complex core-edge code coupling problems to automate visualizations of scientific, diagnostic, and performance results using a collaborative web-based dashboard.
Scientists working on the Exascale Computing Project’s ExaSMR project have developed a comprehensive simulation framework targeting the entire small modular reactor (SMR) core, resolving foreseeable roadblocks to scaling up coupled simulations to the full core, such as the reduced order modeling of spacer grids and mixing vanes.
The ExaStar project is developing a software ecosystem for exascale architectures that will support world-leading models of the mechanisms and observable consequences of a variety of stellar cataclysms.
The Exascale Computing Project’s (ECP’s) Co-design Center for Particle Applications (CoPA) aims to prepare particle applications for exascale computing.
A team of researchers has developed the Feature Tracking Kit (FTK), which uses simplicial spacetime meshing to simplify, scale, and deliver novel feature-tracking algorithms for in situ data analysis and scientific visualization. FTK delivers feature-tracking tools, scales feature-tracking algorithms in distributed and parallel environments, and simplifies development of new feature-tracking algorithms, enabling new analyses in greater detail than previously possible.
A team collaborating across national laboratories, universities, and industry has developed a new approach to runtime programming that enables scalable execution of implicitly parallel programs on large-scale machines using distributed dynamic dependence analysis for efficient, on-the-fly computation of dependences.
Researchers at the National Energy Technology Laboratory (NETL) and Lawrence Berkeley National Laboratory (LBNL) have developed MFIX-Exa, a massively parallel CFD-DEM (computational fluid dynamics-discrete element method) code, a high-fidelity computational tool that allows for simulating dense particle-laden flows in systems with complex geometries so high-performance computing (HPC) can be used in place of physical testing.
For the ExaWind challenge problem, decomposing the linear systems for each overset mesh offers several advantages by (1) allowing the use of rigorously coupled, separate CFD codes wherein optimal solvers can be chosen for their respective domains and (2) speeding up the linear solvers.
The analytical and computational methods developed in this work pave the way for future calculations in more complicated systems involving multiparticle and nuclear systems.
ArborX will speed up exascale applications for computational cosmology, multiphysics data transfer, computational mechanics, wind farm simulations, and other research areas.
Novel method combining machine learning and data partitioning benefits cancer records data extraction
A team of cancer researchers and computer scientists have applied machine learning (ML) ensemble techniques to reduce training time, mitigate task complexity, and improve accuracy and classification performance for information extraction with cancer pathology reports.
Scientists have demonstrated the value in two particle simulators of so-called rendezvous methods, which invoke a communication pattern useful when the processors sending and receiving information are unknown to each other.
Researchers supported by the Exascale Computing Project (ECP) conducted the first comprehensive review of research examining the usefulness of mixed-precision algorithms to power exascale computations.
This work extends the capabilities of exascale computing to fusion research and establishes the validity and scalability of the code-coupling approach for whole-device simulations.
A research team funded in part by the Exascale Computing Project has produced tools for assimilating high-resolution urban terrain into regional weather models, determining building-by-building meteorology, and for extremely fast generation of building simulations for energy use analysis.
Researchers have introduced ADEPT, a novel domain-independent parallelization strategy that optimizes the Smith-Waterman algorithm for DNA and protein sequencing on the heterogeneous architectures and GPUs of petascale. supercomputers.
Exascale Computing Project (ECP)–funded researchers have demonstrated a massively parallel, scalable system for simulating physical behaviors of materials undergoing complex topological changes, collisions, and large deformations using multi-GPU supercomputers such as Summit at Oak Ridge National Laboratory.
A team of researchers funded by the Exascale Computing Project demonstrated the efficacy of combining DRAM and high-density, byte-addressable nonvolatile memory (NVM) for accelerating high-performance computing (HPC) and enabling large problems at reasonable performance beyond the capabilities of DRAM and NVM alone.
Scientists funded by the Exascale Computing Project (ECP) have developed WarpX, a modern, performance-portable Particle-in-Cell code that describes the relativistic physics of charged plasma particles for accelerator and laser–plasma physics.
Researchers funded by the Exascale Computing Project have delivered a novel method that addresses overloaded communication processes that use MPI-IO by adding a second I/O request aggregation layer.
Scientists working on the VeloC-SZ project have optimized SZ, an error-bounded prediction-based lossy compression model.
Researchers supported by the Exascale Computing Project have developed a Multiscale Modelling Framework (MMF) configuration of E3SM, which involves embedding a limited-area cloud resolving model into each column of the global E3SM model.
Researchers working with the Exascale Computing Project (ECP) have demonstrated a novel moment invariant pattern detection algorithm to drive in situ pattern recognition during simulations running on high-performance computing architectures.
Researchers working under the Exascale Computing Project have shown that JuliaChem, a quantum chemistry software written with the Julia programming language, can deliver effective performance, superior ease of use, and improved scalability of calculations compared to the most commonly used applications.
Researchers working with the Exascale Computing Project’s Center for Efficient Exascale Discretization recently published findings of investigations they conducted into performance trade-offs for compute-intensive kernels in scientific computing applications.
Researchers funded by the Exascale Computing Project have developed a new algorithm that improves kernel ridge regression methods used for supervised learning problems.