Accelerating HEP Science: Inference and Machine Learning at Extreme Scales

Developing and applying new methods and algorithms in extreme-scale inference and machine learning

Mathematics and Computer Science

Access Grid

Ensemble of resources supports human interaction across the grid

Mathematics and Computer Science

ADLB: Asynchronous Dynamic Load Balancer

Software library to rapidly build scalable parallel programs

Mathematics and Computer Science

Advancing Integrated Development Environments for Quantum Computing through Fundamental Research (AIDE-QC)

Advancing the computer science stack for quantum computing

Mathematics and Computer Science

AMASE: Architecture and Management for Autonomic Science

Exploring the architecture, methods, and algorithms needed to support future scientific computing systems

Mathematics and Computer Science

Argo: Low-Level Resource Management for the OS and Runtime

Argo will improve or augment existing OS/R components for use in HPC

Mathematics and Computer Science

Array of Things

First at-scale research infrastructure deployment enabling researchers to study an urban environment

Mathematics and Computer Science

Autotuning Compiler Technology for Cross-Architecture Transformation and Code Generation

Developing an approach that separates a high-level C/C++/FORTRAN implementation from architecture-specific implementation, optimization, and tuning

Mathematics and Computer Science

AWE: Argonne Workflow Engine

Workload management system for bioinformatic workflow applications

Mathematics and Computer Science

Block-Structured Adaptive Mesh Refinement Co-Design Center

Creating a new framework to support development of block-structured adaptive mesh refinement algorithms

Mathematics and Computer Science

Butterfly: View Protein Features in 3D Structure

Analyzing protein features

Mathematics and Computer Science

Can Exascale Computers Handle Extreme-Scale Real-Time Science Workflows?

Will exascale computers run anticipated experimental science workloads effectively?

Mathematics and Computer Science

CDIGS: Community-Driven Improvement of Globus Software

Evolving and enhancing Globus functionality

Mathematics and Computer Science

Center for Efficient Exascale Discretizations

The CEED co-design center is a focused team effort to develop the next-generation discretization software and algorithms that will enable a wide range of finite element applications to run efficiently on future hardware.

Mathematics and Computer Science

CFD: Computational Fluid Dynamics

Developing tools to enable accurate simulation of fluid flows in three-dimensional geometries

Mathematics and Computer Science

Cloud-resolving Climate Modeling of the Earth’s Water Cycle

Developing a cloud-resolving Earth system model for multi-decade, high-resolution climate simulations

Mathematics and Computer Science

Co-design Center for Online Data Analysis and Reduction at the Exascale

Co-design Center for Online Data Analysis and Reduction at the Exascale (CODAR) will address a growing disparity between simulation speeds and I/O rates rendering it infeasible for HPC and data analytic applications to perform offline analysis.

Mathematics and Computer Science

COBALT: Component-Based Lightweight Toolkit

Component-based system software for system and resource management

Mathematics and Computer Science

Collaborative Visualization and the Analysis Pipeline

Allowing remote participants to interact with their visualizations

Mathematics and Computer Science

Community Project for Accelerator Science and Simulation 4 (COMPASS-4)

Developing and deploying state-of-the-art accelerator modeling tools for particle accelerators

Mathematics and Computer Science

Computational Differentiation

Developing technologies for generating efficient derivative code for models implemented as computer programs

Mathematics and Computer Science

Concerted Flows: Infrastructure for Terabits Data Networks

Developing concepts, methods, and software to efficiently express and implement parallelism

Mathematics and Computer Science

Coupled Monte Carlo Neutronics and Fluid Flow Simulation of Small Modular Reactors

Providing benchmarks for multicycle operational design parameters for small modular reactors by 2025

Mathematics and Computer Science

Coupling Approaches for Next-Generation Architectures (CANGA)

Developing new high-performance coupling approaches for coupled Earth system models on next-generation computing architectures

Mathematics and Computer Science

DAMSEL: Data Model Storage Library for Exascale Science

Enabling exascale computational science applications to interact conveniently and efficiently with storage

Mathematics and Computer Science

Darshan: HPC I/O Characterization Tool

Characterization tool provides snapshot of application I/O behavior

Mathematics and Computer Science

Data Libraries and Services Enabling Exascale Science

A widening gap between computational and I/O performance, deeper memory and storage hierarchies with complex organization, and massive levels of parallelism (e.g., billions of cores) are but a few of the challenges to data management at the exascale.

Mathematics and Computer Science

Data Model Storage Library for Exascale Science

The goal of this project is to enable exascale computational science applications to interact conveniently and efficiently with storage through abstractions that match their data models.

Mathematics and Computer Science

Data-Driven Optimization under Uncertainty, Parallel Algorithms and Solver

Integrating data into optimization for statistically robust solutions

Mathematics and Computer Science

Decaf: High-Performance Decoupling of Tightly Coupled Flows

Exploring a hybrid approach to decoupling tightly coupled applications to enhance usability

Mathematics and Computer Science

Derivative-Free Optimization of Complex Systems

Developing, analyzing, and implementing algorithms in software

Mathematics and Computer Science

Designing Resilient Infrastructure

Computational tools to assess impact of natural and manmade disasters on national infrastructure

Mathematics and Computer Science

Development of an Ocean Model Adjoint for Decadal Prediction

Developing an adjoint of the Parallel Ocean Program using automatic differentiation

Mathematics and Computer Science

DIY: Do-it-Yourself Analysis

Open-source package of scalable building blocks for data movement

Mathematics and Computer Science

Dragonfly: Web-Based Multiple-Sequence Partial-Order Alignment Viewer

Visualizing and analyzing alignments of protein sequences

Mathematics and Computer Science

ECP Co-Design Center for Particle-Based Methods: From Quantum to Classical, Molecular to Cosmological

Creating co-designed numerical ​“recipes” for particle-based methods

Mathematics and Computer Science

EMP: Earth Microbiome Project

Analyzing microbial communities across the globe

Mathematics and Computer Science

Enabling Co-Design of Multilayer Exascale Storage Architectures

The goal of the CODES project is use highly parallel simulation to explore the design of exascale storage architectures and distributed data-intensive science facilities.

Mathematics and Computer Science

Enabling Exascale Science through Node Local Storage Systems

The goal of the NoLoSS project is to conduct a detailed assessment of the potential roles and benefits of in-system storage in extreme-scale computational science.

Mathematics and Computer Science

Energy Exascale Earth System Model

Developing a computationally advanced coupled climate-energy model to investigate the challenges posed by the interactions of weather-climate scale variability with energy and related sectors

Mathematics and Computer Science

Enhancing and Hardening the Legion Programming System for the Exascale Computing Project

Developing and integrating new and modified features into Legion to achieve high performance at the exascale

Mathematics and Computer Science

ESG: Earth System Grid

Integrating supercomputers with large-scale data and analysis servers to create a powerful environment for next-generation climate research

Mathematics and Computer Science

Exascale Computing in the MCS Division

Accelerating delivery of an exascale computing ecosystem to provide breakthrough modeling and simulation to address the nation’s most critical challenges

Mathematics and Computer Science

Exascale MPI

This project seeks to enable the ongoing MPI-related research and development work at Argonne, with the overall goal of enabling MPICH and its derivatives to run effectively at exascale.

Mathematics and Computer Science

ExM: System Support for Extreme-Scale, Many-Task Applications

Novel stack of system services to enable broad range of applications on extreme-scale platforms

Mathematics and Computer Science

Exploring Efficient Data Movement Strategies for Exascale Systems with Deep Memory Hierarchies

This project explores efficient techniques for data movement on heterogeneous memory architectures, where applications can move data from any memory segment to any other memory segment.

Mathematics and Computer Science

EXPRESS: Toward an Architecture for Online Data Analysis

Defining an architecture for an online data analysis facility, evaluating promising technologies, and developing a 10-year technology roadmap

Mathematics and Computer Science

Extreme-Scale Distribution-Based Data Analysis

Optimizing in situ processing and analysis of extreme-scale scientific data

Mathematics and Computer Science

Extreme-scale Scientific Software Development Kit for the Exascale Computing Project

The xSDK4ECP project is working to enable the seamless combined use of diverse, independently developed software packages as needed by ECP applications.

Mathematics and Computer Science

EZ: Fast, effective, parallel error-bounded exascale lossy compression for scientific data

EZ is a lossy compressor for scientific datasets respecting user-set error controls.

Mathematics and Computer Science

FASTMath: Frameworks, Algorithms and Scalable Technologies for Mathematics

Introducing leading-edge computational math technologies and high-performance software for DOE supercomputers

Mathematics and Computer Science

Flash Center Visualization

Astrophysics comes to life

Mathematics and Computer Science

Fundamental Algorithmic Research for Quantum Computing (FAR-QC)

Advancing quantum computing capabilities through performance analysis and algorithm development

Mathematics and Computer Science

Globus Online: Robust File Transfer of Big Data

A software-as-a-service for secure, reliable, data management

Mathematics and Computer Science

Globus Toolkit: Grid Computing Middleware

Open-source grid software

Mathematics and Computer Science

GVR: Global View Resilience

Exploiting a global view data model and adding reliability to globally visible distributed arrays

Mathematics and Computer Science

HEIGHTS: High Energy Interaction with General Heterogeneous Target Systems

Comprehensive software package that runs on a range of computers

Mathematics and Computer Science

HEP Data Analytics on HPC

Developing and deploying new tools and algorithms to enable HPC facilities to meet new data analysis demands

Mathematics and Computer Science

High-Fidelity Whole Device Modeling of Magnetically Confined Fusion Plasmas

Developing a high-fidelity whole device model of magnetically confined fusion plasmas

Mathematics and Computer Science

HPC Framework for Event Generation at Colliders

New Monte Carlo techniques for addressing integration and scaling calculations on high-performance computing resources

Mathematics and Computer Science

IDEAS-ECP: Advancing Software Productivity for Exascale Applications

Improving ECP developer productivity and software sustainability

Mathematics and Computer Science

IDEAS: Interoperable Design of Extreme-scale Application Software

Qualitatively changing the culture of extreme-scale computational science

Mathematics and Computer Science

Improving Data Movement on Large HPC Systems

Identifying strategies and architectures (network and I/O) for improving commication on large-scale supercomputers, focusing on climate science and artificial intelligence workloads.

Mathematics and Computer Science

Indexed Parallel Programming

Post-MPI parallel programming in which the runtime system manages the simulation data

Mathematics and Computer Science

Integrating Simulation and Observation: Discovery Engines for Big Data

Aiming for revolutionary advances in cosmology and materials science

Mathematics and Computer Science

IOFSL: I/O Forwarding Scalability Layer

A scalable, unified high-end computing I/O forwarding software layer

Mathematics and Computer Science

Joint Laboratory for System Evaluation

Collaboration to evaluate future high-performance computing platforms

Mathematics and Computer Science

Jumpshot: Performance Visualization Tool

Visualization tool for performance analysis

Mathematics and Computer Science

Kronos: Hybrid Discrete Event Simulations

Kronos: enabling long timescale parallel discrete event simulations (PDES) via multi-resolution methods. Surrogate models are coupled with high-fidelity PDES models of supercomputing architectures to accelerate large-scale simulations.

Mathematics and Computer Science

libEnsemble

Software for coordinating the concurrent evaluation of dynamic ensembles of calculations.

Mathematics and Computer Science

M2ACS: Multifaceted Mathematics for Complex Energy Systems Project

Developing predictive models for complex energy systems

Mathematics and Computer Science

Machine Learning

Exploring machine learning projects, ranging from algorithm and software development to applications in science and the environment, to facilitate discovery of new scientific insights

Mathematics and Computer Science

MACSER: Multifaceted Mathematics for Rare, High-Impact Events in Complex Energy and Environment Systems

Quantifying the occurrence and features of rare, high-impact events and designing energy systems to withstand them

Mathematics and Computer Science

MAUI: Modeling, Analysis, and Ultrafast Imaging

Integrating ultrafast time-resolved imaging with large-scale molecular dynamics modeling and in situ data analysis and visualization

Mathematics and Computer Science

Mercury

C library for implementing RPC, optimized for high-performance computing systems

Mathematics and Computer Science

MG-RAST: Metagenomics RAST Server

SEED-based environment that allows users to upload metagenomes for automated analyses

Mathematics and Computer Science

MINOTAUR: Toolkit for Mixed Integer Nonlinear Optimization Problems

Toolkit for solving mixed integer nonlinear optimization problems

Mathematics and Computer Science

MPICH: A High-Performance, Portable Implementation of MPI

Vehicle for MPI implementation research and improved parallel programming environments

Mathematics and Computer Science

MPITypes: A Library for Processing MPI Datatypes Outside MPI

An open-source, portable library

Mathematics and Computer Science

Multiscale Coupled Urban Systems

Integrated modeling framework that will equip city officials to develop solutions to issues that affect cities

Mathematics and Computer Science

Nek5000: Computational Fluid Dynamics Code

Computational fluid dynamics code that simulates fluid flow with thermal and passive scalar transport

Mathematics and Computer Science

NekCEM: Nekton for Computational Electromagnetics

Featuring geometric flexibility, spectrally accurate numerical convergence, and an efficient parallel implementation

Mathematics and Computer Science

Nested Task-Parallel Workflows for Scientific Applications

Developing a task-parallel in situ workflow system that will expose a task-parallel user interface

Mathematics and Computer Science

Next-Generation Optimization under Uncertainty: Structure-Oriented Algorithms

Developing scalable algorithms and supporting convergence theory to address national infrastructure operations

Mathematics and Computer Science

Nimbus: Cloud Computing for Science

Open-source toolkit converting computer clusters into Infrastructure-as-a-Service cloud to provide computing for science communities

Mathematics and Computer Science

NoLoSS: Enabling Exascale Science through Node Local Storage Systems

Detailed assessment of potential benefits of in-system storage in extreme-scale computational science

Mathematics and Computer Science

Nucelar Computational Low-Energy Initiative (NUCLEI)

SciDAC project advancing large-scale computations of atomic nuclei

Mathematics and Computer Science

OpenAD/F: Automatic Differentiation of Fortran Codes

Developing a modular, open-source tool to auto-generate code

Mathematics and Computer Science

OpenMC

Enabling coupled Monte Carlo neutron transport – computational fluid dynamics at exascale to study reactor designs

Mathematics and Computer Science

OpenPA: Open Portable Atomics

Open-source library providing a consistent C API for atomic operations

Mathematics and Computer Science

Optimizing Stochastic Grid Dynamics at Exascale

The unprecedented power grid evolution poses a monumental challenge in optimizing grid planning.

Mathematics and Computer Science

Orio: Automatic Performance Tuning

Tuning system to improve software performance and productivity

Mathematics and Computer Science

OSCon: Optimizing superconductor transport properties through large-scale simulation

Developing novel methods to optimize superconductors for energy applications

Mathematics and Computer Science

OSG: Open Science Grid

Consortium-built, production-scale, shared cyber infrastructure

Mathematics and Computer Science

PARIS

Exploring fundamental properties of numerical science to improve resilience of extreme-scale executions

Mathematics and Computer Science

Parsl: A Parallel Scripting Library for Python

A Python library for programming and executing data-oriented workflows in parallel

Mathematics and Computer Science

Performance Engineering for the Next Generation CCSM

Enabling more efficient use of next-generation massively parallel systems

Mathematics and Computer Science

Petrel

High-performance research data storage system that enables dynamic data mirroring

Mathematics and Computer Science

PETSc: Portable, Extensible Toolkit for Scientific Computation

Suite of data structures and routines for the scalable solution of scientific applications

Mathematics and Computer Science

Pilot for Evaluation, Development, and Application of Genotype Imputation Algorithms and Pipelines at Scale

Scaling and benchmarking study for analysis of hundreds of thousands of experimental genotype samples

Mathematics and Computer Science

Plasma Surface Interactions: Predicting the Performance and Impact of Dynamic PFC Surfaces

Enabling discovery of phenomena controlling critical PFC performance issues

Mathematics and Computer Science

Preparing PETSc/TAO for Exascale

Developing and extending PETSc/TAO for simulations at the exascale

Mathematics and Computer Science

PRIME: Facility for Particle/Radiation Interaction with Matter Experiments

Studying interaction of intense particle/radiation and matter

Mathematics and Computer Science

ProVESA: Program Verification for Extreme-Scale Applications

Facilitating migration of scientific software from simple homogeneous architectures to complex heterogeneous architectures

Mathematics and Computer Science

PVFS: Parallel Virtual File System

Platform for I/O research and production file system for cluster computing

Mathematics and Computer Science

QMCPACK: Framework for Predictive and Systematically Improvable Quantum-Mechanics Based Simulations of Materials

High-performance quantum Monte Carlo code helps researchers better understand electronic structure of extremely small-scale molecular systems

Mathematics and Computer Science

Quantifying Global Structural Errors in Predictive Scientific Simulations

Developing novel numerical strategies to identify model errors in complex predictive simulations

Mathematics and Computer Science

Quantum Algorithms, Mathematics and Compilation Tools for Chemical Sciences

Designing and delivering novel algorithms, compiling techniques, scheduling tools, and linear algebra approaches for chemical sciences

Mathematics and Computer Science

Quantum Computing

Developing quantum technologies to revolutionize computing and communication

Mathematics and Computer Science

RAMSES: Robust Analytical Models for Science at Extreme Scales

Transforming our understanding of science workflows in extreme-scale science environments

Mathematics and Computer Science

RAPIDS: A SciDAC Institute for Computer Science and Data

Institute to overcome challenges in using DOE supercomputing resources to achieve breakthrough science

Mathematics and Computer Science

Rapsodia: Automatic Differentiation Code

A joint French-American project to combine operator overloading with code generation

Mathematics and Computer Science

RAST: Rapid Annotation using Subsystem Technology

Providing high-quality genome annotations for prokaryotes across the whole phylogenetic tree

Mathematics and Computer Science

RDCEP: Center for Robust Decision Making on Climate and Energy Policy

Partnership to improve computational models for climate and energy policies

Mathematics and Computer Science

ROMIO: High-Performance, Portable MPI-IO Implementation

High-performance, portable implementation of MPI-IO

Mathematics and Computer Science

ROMPR: Robust Optimization and Modeling for Phase Retrieval

Developing nonlinearly constrained robust, stochastic, and global optimization models

Mathematics and Computer Science

SAGE: A Software-Defined Sensor Network

SAGE will build a national research infrastructure of new sensors that support programmable edge computers and machine learning within an interconnected cyberinfrastructure, spanning multiple major science instruments

Mathematics and Computer Science

Scalable Analysis Methods and In Situ Infrastructure for Extreme Scale Knowledge Discovery

Enabling scientific discovery using in situ processing at extreme scales

Mathematics and Computer Science

Scaling OpenMP via LLVM for Exascale Performance and Portability

Delivering a high-quality, robust implementation of OpenMP

Mathematics and Computer Science

SciDAC-4 Institutes

MCS plays key role in SciDAC RAPIDS and FASTMath projects

Mathematics and Computer Science

SciDAC: Scientific Discovery through Advanced Computing

Applying advanced software and algorithms to complex science and engineering problems

Mathematics and Computer Science

SDAV: Scientific Data Management, Analysis, and Visualization Institute

Comprehensive expertise in scientific data management, analysis, and visualization

Mathematics and Computer Science

SEANO: Structure-Exploiting Algorithms for Nonlinear Optimization

Unified approach for addressing a diverse set of nonlinear optimization problems

Mathematics and Computer Science

SHOCK

Object store/active store designed for streaming data analysis

Mathematics and Computer Science

Simulation of Fission Gas in Uranium Oxide Nuclear Fuel

Studying the behavior of the diffusion mechanisms

Mathematics and Computer Science

SPRUCE: Special PRiority and Urgent Computing Environment

Supporting urgent or event-driven computing on both traditional supercomputers and distributed grids

Mathematics and Computer Science

SUPER: Institute for Sustained Performance, Energy and Resilience

Successfully exploiting emerging generation of high-performance computing systems

Mathematics and Computer Science

Swift: Fast Parallel Scripting Language

Providing rapid and reliable management of large-scale science and engineering workflows

Mathematics and Computer Science

System for Identification and Characterization of Evolutionary Enzyme Variations

Automated identification, analysis, and characterization of evolutionary enzyme variations

Mathematics and Computer Science

TAO: Toolkit for Advanced Optimization

Flexible toolkit for solving large-scale optimization problems

Mathematics and Computer Science

Target Database

Bioinformatics support and selection of protein targets of biomedical importance

Mathematics and Computer Science

Tokamak Disruption Simulation

Simulating the nonlinear physical phenomena in plasma disruptions

Mathematics and Computer Science

TOKIO: Total Knowledge of I/O

Collects and correlates I/O workload data from production HPC resources at multiple system levels

Mathematics and Computer Science

Toward Exascale Astrophysics of Mergers and Supernovae (TEAMS)

Developing improved simulations of supernovae explosions and neutron-star mergers

Mathematics and Computer Science

Triton

Novel, highly resilient, self-repairing distributed storage system

Mathematics and Computer Science

UrbanCCD: Urban Sciences Center for Computation and Data

Applying advanced computational techniques to the design of smarter cities

Mathematics and Computer Science

VeloC: Very Low Overhead transparent multilevel Checkpoint/restart

Providing a framework for a simple checkpoint/restart interface and multilevel checkpointing for exascale applications

Mathematics and Computer Science

Visual Analytics for Large-Scale Scientific Ensemble Datasets

Building a comprehensive visual analytic framework for analyzing large-scale scientific ensemble data

Mathematics and Computer Science

vl3: Scalable and Interactive Parallel Volume Rendering

Novel parallel volume rendering framework for visualizing large datasets

Mathematics and Computer Science

Waggle: An open platform for intelligent attentive sensors

Novel wireless sensor system enabling a new breed of smart city research and sensor-driven environmental science

Mathematics and Computer Science

XTUNE: Autotuning for Exascale

Developing the first unified autotuning framework that seamlessly integrates programmer-directed and compiler-directed autotuning

Mathematics and Computer Science

ZeptoOS: Operating Systems for Petascale

Studying operating systems for petascale architectures (10,000 to 1 million CPUs)

Mathematics and Computer Science