The current CASS software portfolio focuses on freely available libraries and tools that support leading-edge computational science and engineering research on high-performance parallel computers. Most of the software has been developed with support from the U.S. Department of Energy Office of Advanced Scientific Computing Research, and the Software Technologies focus area of the Exascale Computing Project. Many products have Spack packages available and are part of the E4S distribution to facilitate installation.

Switch to Alphabetical view

Data and visualization (10)

ADIOS

Provides a simple, flexible way for scientists to describe the data in their code that may need to be written, read, or processed

Data and visualization

Ascent

A featherweight in situ visualization and analysis tool designed to be integrated with applications to reduce I/O overhead

Data and visualization

DIY

A block-parallel library for writing scalable parallel algorithms

Data and visualization

HDF5

A parallel I/O library for high performance access to self-describing HDF5 datasets

Data and visualization

ParaView Catalyst

A tool for in situ data analysis and visualization at scale

Data and visualization

ParaView

A tool for data analysis and visualization at scale

Data and visualization

PnetCDF

An I/O library for high-performance parallel access to self-describing netCDF datasets

Data and visualization

VisIt

An open source, interactive, scalable, visualization, animation and analysis tool.

Data and visualization

VTK-m

A performance-portable visualization library leveraged by production tools such as ParaView and VisIt

Data and visualization

zfp

An open-source library for compressed floating-point and integer arrays that support high-throughput random access read and write

Data and visualization

Back to Top ↑

Development tools (6)

Darshan

A lightweight I/O characterization tool that transparently captures I/O access pattern information from HPC applications

Development tools

Dyninst

A toolkit for binary analysis, instrumentation, and code modification across a variety of CPU and GPU architectures

Development tools

Empirical Roofline Tool

Automates generation of roofline model for architecture-specific performance analysis and optimization

Development tools

HPCToolkit

A toolkit that supports measurement, analysis, attribution, and inspection of application performance on CPU and GPU-accelerated architectures

Development tools

PAPI

A universal interface for hardware counters to monitor software performance

Development tools

TAU

A performance evaluation tool that supports GPUs from multiple vendors for HPC and AI applications

Development tools

Back to Top ↑

Mathematical libraries (14)

AMReX

Software framework for block structured AMR

Mathematical libraries

Ginkgo

High-performance linear algebra library for manycore systems, with a focus on sparse solution of linear systems

Mathematical libraries

hypre

High-performance linear solvers library

Mathematical libraries

Kokkos Kernels

Performance portable math kernels of the Kokkos Ecosystem.

Mathematical libraries

libCEED

Fast algebra for element-based discretizations

Mathematical libraries

libEnsemble

A Python toolkit for coordinating asynchronous and dynamic ensembles of calculations

Mathematical libraries

MAGMA

A library for BLAS and LAPACK on GPUs

Mathematical libraries

MFEM

High-performance finite element library

Mathematical libraries

PETSc/TAO

The Portable, Extensible Toolkit for Scientific Computation

Mathematical libraries

STRUMPACK

Low-rank STRUctured Matrix PACKage for both dense and sparse matrices.

Mathematical libraries

SUNDIALS

A library of time integrators and nonlinear solvers for ordinary differential equations (ODEs), differential-algebraic equations (DAEs), and nonlinear algebr...

Mathematical libraries

SuperLU

Sparse direct solver and preconditioner based on supernodal sparse LU factorization

Mathematical libraries

Trilinos

Collection of reusable scientific software libraries

Mathematical libraries

xSDK

The Extreme-scale Scientific Software Development Kit

Mathematical libraries

Back to Top ↑

Programming models and runtimes (11)

Caffeine

The CoArray Fortran Framework of Efficient Interfaces to Network Environments

Programming models and runtimes

chipStar

A tool for compiling and running HIP/CUDA on SPIR-V via OpenCL or Level Zero APIs

Programming models and runtimes

GASNet

A network-independent, high-performance communications middleware

Programming models and runtimes

Kokkos

Performance portability programming model

Programming models and runtimes

Legion

A task-based programming model and runtime

Programming models and runtimes

LLVM Flang

A Fortran compiler

Programming models and runtimes

MPICH

A high performance open-source implementation of the Message Passing Interface (MPI) standard

Programming models and runtimes

Open MPI

A high performance open-source implementation of the Message Passing Interface (MPI) standard

Programming models and runtimes

UPC++

A C++ library that supports Partitioned Global Address Space (PGAS) programming

Programming models and runtimes

Back to Top ↑

Software ecosystem and delivery (2)

E4S

The Extreme-Scale Scientific Software Stack

Software ecosystem and delivery

Spack

A flexible package manager that supports multiple versions, configurations, platforms, and compilers

Software ecosystem and delivery

Back to Top ↑