Sold by: ParaTools Inc.
Deployed on AWS
Free Trial
AWS Free Tier
This product has charges associated with it for optional seller support and pre-configured stack (ParaTools Pro for E4S™). ParaTools Pro for E4S™ is the hardened Extreme-scale Scientific Software Stack on Ubuntu and Rocky Linux, using AWS ParallelCluster, with over 100 HPC and AI/ML tools, an optional Amazon DCV remote desktop on the cluster head node, and cluster configuration built using the Spack package manager and a proprietary MVAPICH-Plus 4 MPI tuned for AWS Elastic Fabric Adapter (EFA). Develop AI/ML applications using tools such as JAX, Keras, NVIDIA BioNeMo, NVIDIA NeMo™, PyTorch, SGLang, TensorFlow, and vLLM tuned for AWS ParallelCluster, with a complete HPC software stack including numerical libraries (PETSc, SuperLU-dist, Trilinos, WRF), visualization tools (ParaView, VisIt), performance evaluation tools (HPCToolkit, TAU), HPC applications (CP2K, GROMACS, LAMMPS, OpenFOAM, Quantum Espresso, WarpX, Xyce).
Overview
ParaTools Pro for E4S™ - the Extreme-scale Scientific Software Stack, E4S™ hardened for commercial clouds and supported by ParaTools, Inc., provides a platform for developing and deploying HPC and AI/ML applications. It is available in Ubuntu Linux and Rocky Linux variants, both supporting an optional Amazon DCV remote desktop on the cluster head node provisioned via AWS ParallelCluster, with compute nodes interconnected by a low-latency, high-bandwidth network adapter based on AWS Elastic Fabric Adapter (EFA). ParaTools Pro for E4S™ features a suite of over 100 HPC tools built using the Spack package manager and a proprietary MVAPICH-Plus 4 MPI tuned for EFA utilizing SLURM for job management. It features visualization tools (ParaView, VisIt), performance evaluation tools (HPCToolkit, TAU), and ready-to-use HPC applications (CP2K, GROMACS, LAMMPS, OpenFOAM, Quantum Espresso, WarpX, Weather Research and Forecasting Model-WRF, Xyce) as well as AI/ML tools based on Python (JAX, Keras, matplotlib, NVIDIA BioNeMo, NVIDIA NeMo™, OpenCV, PyTorch, SGLang, TensorFlow, vLLM, with JupyterLab and Jupyter Notebook) and the VSCodium IDE. New packages can be easily installed using Spack and pip and are accessible on the cluster compute and login nodes. It may be used for developing the next generation of generative AI applications using a suite of Python tools and interfaces.
E4S™ has built a unified computing environment for deployment of open-source projects. E4S™ was originally developed to provide a common software environment for the exascale leadership computing systems currently being deployed at DOE National Laboratories across the U.S. Support for ParaTools Pro for E4S™ is available through ParaTools, Inc. This product has additional charges associated with it for optional product support and updates.
This material is based upon work supported by the U.S. Department of Energy, Office of Science, Office of Advanced Scientific Computing Research (ASCR), under SBIR Award Number DE-SC0022502 ("E4S: Extreme-Scale Scientific Software Stack for Commercial Clouds").
Note: This product contains repackaged and tuned open source software (e.g., E4S™, Spack and AI/ML tools like NVIDIA NeMo™, JAX, Keras etc.) which is configured and linked against a proprietary MVAPICH-Plus 4 MPI implementation specifically developed and tuned for EFA. An Ubuntu or Rocky Linux version can be selected below.
The full list of E4S applications installed via Spack is as follows:
- adios
- adios2
- alquimia
- aml
- amrex
- arborx
- argobots
- ascent
- axom
- boost
- bricks
- butterflypack
- cabana
- caliper
- chai
- chapel
- charliecloud
- conduit
- cp2k
- cusz
- darshan-runtime
- darshan-util
- datatransferkit
- dyninst
- e4s-alc
- e4s-cl
- exaworks
- faodel
- flit
- flux-core
- fpm
- gasnet
- ginkgo
- globalarrays
- gmp
- gotcha
- gptune
- gromacs
- h5bench
- hdf5
- hdf5-vol-async
- hdf5-vol-cache
- hdf5-vol-log
- heffte
- hpctoolkit
- hpx
- hypre
- kokkos
- kokkos-kernels
- laghos
- lammps
- lbann
- legion
- libcatalyst
- libceed
- libnrm
- libpressio
- libquo
- libunwind
- loki
- magma
- mercury
- metall
- mfem
- mgard
- mpark-variant
- mpifileutils
- nccmp
- nco
- nek5000
- nekbone
- netcdf-fortran
- netlib-scalapack
- nrm
- omega-h
- openfoam
- openmpi
- openpmd-api
- papi
- papyrus
- parallel-netcdf
- parsec
- pdt
- petsc
- phist
- plasma
- plumed
- precice
- pruners-ninja
- pumi
- py-cinemasci
- py-h5py
- py-jupyterhub
- py-libensemble
- py-petsc4py
- qthreads
- quantum-espresso
- raja
- rempi
- scr
- slate
- slepc
- stc
- strumpack
- sundials
- superlu
- superlu-dist
- swig
- sz
- sz3
- tasmanian
- tau
- trilinos
- turbine
- umap
- umpire
- upcxx
- variorum
- veloc
- vtk-m
- wannier90
- warpx
- wps
- wrf
- xyce
- zfp
Highlights
- ParaTools Pro for E4S™ and Machine Learning stacks, including NVIDIA NeMo™, built and optimized for AWS EFA and AWS ParallelCluster
- A proprietary MVAPICH-Plus 4 MPI implementation that offers lower latency and higher throughput than default OpenMPI implementations for pre-installed applications and user installed applications
- HPC software environment managed using the Spack package manager
Details
Sold by
Delivery method
Delivery option
64-bit (x86) Amazon Machine Image (AMI)
Latest version
Operating system
Ubuntu 24.04
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Free trial
Try this product free for 31 days according to the free trial terms set by the vendor. Usage-based pricing is in effect for usage beyond the free trial terms. Your free trial gets automatically converted to a paid subscription when the trial ends, but may be canceled any time before that.
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
If you are an AWS Free Tier customer with a free plan, you are eligible to subscribe to this offer. You can use free credits to cover the cost of eligible AWS infrastructure. See AWS Free Tier for more details. If you created an AWS account before July 15th, 2025, and qualify for the Legacy AWS Free Tier, Amazon EC2 charges for Micro instances are free for up to 750 hours per month. See Legacy AWS Free Tier for more details.
Dimension | Cost/hour |
|---|---|
c5n.9xlarge Recommended | $0.99 |
t3.micro | $0.99 |
c7a.xlarge | $0.99 |
g5.12xlarge | $0.99 |
c6id.12xlarge | $0.99 |
m6in.12xlarge | $0.99 |
r5dn.xlarge | $0.99 |
m7a.8xlarge | $0.99 |
t3.medium | $0.99 |
inf2.48xlarge | $0.99 |
Dimensions summary
You pay by the hour for each EC2 instance type you run this software on. Pricing is usage-based, so your cost depends on which instance you choose and how long it runs. The many dimensions are not tiers or feature levels. Each one maps to a specific EC2 instance size, from small general-purpose machines to large compute, memory, storage, and GPU or accelerator instances. Larger or specialized instances carry higher hourly rates. You select the instance that fits your HPC or AI/ML workload. The software runs on AWS ParallelCluster using x86_64 instances, and billing scales with total instance hours.
Top-of-mind questions for buyers
Each unit is one hour that a chosen EC2 instance runs this software. You are billed for wall-clock hours the instance stays running, per instance. Running several instances in one cluster adds each instance's hours together on the same invoice.
The software rate meters running instance-hours only. A stopped instance does not accrue software charges. Underlying AWS fees, such as storage attached to a stopped instance, may still apply separately from this software charge.
Each running instance is billed at its own hourly rate. Your head node and each compute node accrue software charges independently while running. A small head node instance can manage the cluster, while compute nodes drive most cost. Totals sum across all running instances.
docs.paratoolspro.com
Helpful?
Vendor refund policy
Refund Policy: The standard refund policy outlined here will be followed: https://docs.aws.amazon.com/marketplace/latest/userguide/refunds.html
Any additional refund enquiries can be sent to support@paratools.com and will be considered individually on a case by case basis.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
- AWS ParallelCluster compatibility: pcluster v3.15.1
- E4S release: 26.06
- Default MPI: MVAPICH-Plus 4 (mvapich 4.1 pre-release, module 4.0-plus)
- OS: Ubuntu 24.04
- Toolchain: gcc 13.3.0
CRITICAL:
- Some versions prior to v2024.05.16.1904-pcluster-3.9.1-e4s-24.05-amd64 are exposed to the Log4Shell (CVE-2021-44228) vulnerability.
IMPORTANT:
- To use this product with AWS ParallelCluster, you must use the same version of parallel cluster, v3.15.1
- As of v2025.08.19.1250-pcluster-3.13.2-e4s-25.06-amd64, thanks to the adoption of MVAPICH-Plus 4, EFA enabled nodes are no longer required for multinode support. However, EFA enabled nodes are still recommended to achieve the best performance.
- AWS NeuronX SDK is included on this Ubuntu (x86_64) image for use on Inferentia and Trainium instance families. Two pre-built virtual envs are provided: /opt/aws_neuron_venv_pytorch (torch-neuronx + neuronx_distributed + jax-neuronx) and /opt/aws_neuron_venv_tensorflow (tensorflow-neuronx).
Updates in this version:
- E4S upgraded to 26.06 (from 25.11); AWS ParallelCluster upgraded to v3.15.1 (from v3.15.0)
- Unified Python ML environment at /opt/python/pkgs/python-3.12.12: NVIDIA NeMo, NVIDIA BioNeMo, Megatron, vLLM, and SGLang now share a single environment (the previously separate NeMo venv is gone)
- CUDA 12.9 toolkit (cuda_arch=89; tuned for Ada/Hopper, e.g. L40S/H100/H200), NVIDIA driver 575.57.08
- cuDNN 9.8.0, NCCL 2.30.7 (with libnccl-ofi 1.18.0), NVSHMEM 3.7.0
- NVIDIA Container Toolkit 1.19.1
- PyTorch 2.11.0, TensorFlow 2.21.0, JAX 0.10.1, Keras 3.14.1, vLLM 0.21.0, SGLang 0.5.12, Transformers 5.6.0
- ParaView 6.1.0, VisIt 3.4.2, VSCodium 1.121.03429
- Singularity-CE 4.4.2, Docker 29.6.0, Podman 4.9.3, Ollama 0.30.10
- Julia 1.12.6, Go 1.26.4, NodeJS 24.18.0, Google Cloud SDK 574.0.0
- Updated E4S Spack package versions (see full list below)
ParaTools Pro for E4S (TM) provides a turn-key cloud HPC solution with the E4S Software stack and machine learning tools and SDKs installed and optimized to run on AWS. The key software features and versions installed are:
- Ubuntu 24.04, x86_64
- Optional Amazon DCV remote desktop on cluster head node (Amazon DCV 2025.0)
- VSCodium IDE 1.121.03429
- NVIDIA Container Toolkit 1.19.1
- Singularity-CE 4.4.2, Docker 29.6.0, Podman 4.9.3
- Libfabric 2.4.0 (Amazon EFA installer 1.47.0)
- MVAPICH-Plus 4 (pre-release v4.1)
- CUDA 12.9 (NVIDIA driver 575.57.08), cuDNN 9.8.0, NCCL 2.30.7, NVSHMEM 3.7.0
- Python 3.12.12 at /opt/python/pkgs/python-3.12.12
- Julia 1.12.6
- Go 1.26.4
- NodeJS 24.18.0
- Google Cloud SDK 574.0.0
- Ollama 0.30.10
- Spack 1.1.1 package manager
- E4S 26.06 CPU and CUDA (cuda_arch=89) applications installed
- AWS NeuronX SDK for Inferentia/Trainium (torch-neuronx, neuronx_distributed, jax-neuronx, tensorflow-neuronx)
- Weather Research and Forecasting Model (WRF)
- NVIDIA NeMo (TM) and BioNeMo (unified Python env)
- vLLM 0.21.0, SGLang 0.5.12
- Python/Machine learning tools, SDKs, Frameworks etc.
- PyTorch 2.11.0, TensorFlow 2.21.0, JAX 0.10.1, Keras 3.14.1, OpenCV 4.13.0, scikit-learn 1.8.0, XGBoost 3.3.0, vLLM 0.21.0, SGLang 0.5.12
- numpy 2.3.5, scipy 1.17.1, matplotlib 3.10.9, pandas 2.3.3, polars 1.41.0, plotly 6.7.0, seaborn 0.13.2, geopandas 1.1.3
- JupyterLab 4.5.7, Jupyter Notebook 7.5.6, marimo 0.19.2
- langchain 1.3.1, gradio 6.14.0, Ray 2.55.1, RDKit 2026.3.3, monarch (torchmonarch 0.5.0)
- Google ADK, Google Cloud CLI
- HPC tooling: TAU 2.35.2, HPCToolkit 2026.0.1, PAPI 7.2.0, ParaView 6.1.0, VisIt 3.4.2
The full list of E4S applications installed via Spack is as follows:
-- linux-ubuntu24.04-x86_64_v3 / gcc@13.3.0 --------------
- adios@1.13.1
- adios2@2.12.1
- alquimia@1.1.0
- aml@0.2.1
- amrex@26.05
- arborx@2.1
- argobots@1.2
- ascent@0.9.5
- axom@0.14.0
- boost@1.90.0
- bricks@2023.08.25
- butterflypack@3.2.0
- cabana@0.7.0
- caliper@2.14.0
- chai@2025.12.0
- chapel@2.8.0
- charliecloud@0.44
- conduit@0.9.6
- cp2k@2026.1
- cusz@0.14.0
- darshan-runtime@3.4.7
- darshan-util@3.4.7
- datatransferkit@3.1.1
- dyninst@13.0.1
- e4s-alc@1.0.3
- e4s-cl@1.0.9
- exaworks@0.1.0
- faodel@1.2108.1
- flit@2.1.0
- flux-core@0.81.0
- fpm@0.13.0
- gasnet@2025.8.0
- ginkgo@1.11.0
- globalarrays@5.8.2
- gmp@6.3.0
- gotcha@1.0.8
- gptune@5.0.0
- gromacs@2026.1
- h5bench@1.4
- hdf5@1.14.6
- hdf5-vol-async@1.7
- hdf5-vol-cache@v1.1
- hdf5-vol-log@1.4.0
- heffte@2.4.1
- hpctoolkit@2026.0.1
- hpx@1.11.0
- hypre@3.1.0
- kokkos@5.1.1
- kokkos-kernels@5.1.1
- laghos@3.1
- lammps@20250722.3
- lbann@0.104
- legion@26.03.0
- libcatalyst@2.1.0
- libceed@0.12.0
- libnrm@0.1.0
- libpressio@0.99.4
- libquo@1.4
- libunwind@1.8.3
- loki@0.1.7
- magma@2.10.0
- mercury@2.4.1
- metall@0.30
- mfem@4.9.0
- mgard@1.6.0
- mpark-variant@1.4.0
- mpifileutils@0.12
- nccmp@1.9.1.0
- nco@5.3.4
- nek5000@19.0
- nekbone@17.0
- netcdf-fortran@4.6.2
- netlib-scalapack@2.2.3
- nrm@0.1.0
- omega-h@11.0.0-scorec
- openfoam@2512
- openmpi@5.0.10
- openpmd-api@0.17.0
- papi@7.2.0
- papyrus@1.0.2
- parallel-netcdf@1.14.1
- parsec@4.0.2411
- pdt@3.25.2
- petsc@3.25.1
- phist@1.12.1
- plasma@24.8.7
- plumed@2.10.0
- precice@3.4.0
- pruners-ninja@1.0.2
- pumi@2.2.9
- py-cinemasci@1.7.9
- py-h5py@3.16.0
- py-jupyterhub@1.4.1
- py-libensemble@1.5.0
- py-petsc4py@3.25.1
- qthreads@1.18
- quantum-espresso@7.5
- raja@2025.12.2
- rempi@1.1.0
- scr@3.1.0
- slate@2025.05.28
- slepc@3.25.1
- stc@0.9.0
- strumpack@8.0.0
- sundials@7.7.0
- superlu@7.0.1
- superlu-dist@9.2.1
- swig@4.0.2-fortran
- sz@2.1.12.5
- sz3@3.2.0
- tasmanian@8.1
- tau@2.35.2
- trilinos@16.2.0
- turbine@1.3.0
- umap@2.1.1
- umpire@2025.12.0
- upcxx@2025.10.0
- variorum@0.8.0
- veloc@1.7
- vtk-m@2.3.0
- wannier90@3.1.0
- warpx@26.04
- wps@4.5
- wrf@4.7.1
- xyce@7.10.0
- zfp@1.0.1
Additional details
Usage instructions
The 1-Click Security Group opens port 22 only so that you can access your instance via SSH using login 'ubuntu' (for Ubuntu versions), or 'rocky' (for Rocky Linux versions). You may change this later.
For software development and basic usage:
- Launch the ParaTools Pro for E4S (TM) AMI via 1-Click
- On the 'EC2 Launch an Instance' page pick the key pair you will use to login
- On the 'EC2 Launch an Instance' page optionally edit the network settings by pressing the edit button. Adjust the firewall rules if needed to ensure ssh access and enable Auto-assign public IP if you plan to access the instance remotely from a non-AWS IP address.
- Click 'Launch Instance'
- Find your running instance in the EC2 Instances section of the EC2 dashboard, and connect to the instance via SSH using the key pair you previously selected by picking the instance and pressing the connect button.
For more advanced usage, including launching an ParaTools Pro for E4S (TM) cluster with AWS ParallelCluster, please see:
Resources
Support
Vendor support
For general support questions, please email support@paratools.com
Paid support contracts and custom AMIs and computing environments are available. Please see https://paratoolspro.com/ for additional details.
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
This product has charges associated with it for optional seller support and pre-configured stack (ParaTools Pro for E4S™). ParaTools Pro for E4S™ is the hardened Extreme-scale Scientific Software Stack on Rocky Linux, for use with Adaptive Computing's Heidi AI Cloud Supercomputer. It includes over 100 HPC and AI/ML tools, a VNC-based remote desktop environment, and cluster configuration built using the Spack package manager and a proprietary MVAPICH-Plus 4 MPI tuned for AWS Elastic Fabric Adapter (EFA). Develop AI/ML applications using tools such as JAX, Keras, NVIDIA BioNeMo, NVIDIA NeMo™, PyTorch, TensorFlow, and vLLM tuned for AWS and Heidi, along with Julia. The HPC stack features numerical libraries (PETSc, SuperLU-dist, Trilinos, WRF), visualization tools (ParaView, VisIt), performance evaluation tools (HPCToolkit, TAU), and HPC applications (CP2K, deal.II, GROMACS, LAMMPS, OpenFOAM, Quantum Espresso, WarpX, Xyce). Default SSH user on this image is `rocky`.
This product has charges associated with it for optional seller support and pre-configured stack (ParaTools Pro for E4S™). ParaTools Pro for E4S™ is the hardened Extreme-scale Scientific Software Stack on Ubuntu, using AWS Parallel Computing Service (AWS PCS), with over 100 HPC and AI/ML tools, a remote desktop environment (Amazon DCV), and cluster configuration built using the Spack package manager and a proprietary MVAPICH-Plus 4 MPI tuned for AWS Elastic Fabric Adapter (EFA). Develop AI/ML applications using tools such as JAX, Keras, NVIDIA BioNeMo, NVIDIA NeMo™, PyTorch, TensorFlow, and vLLM tuned for AWS Parallel Computing Service, with a complete HPC software stack including numerical libraries (PETSc, SuperLU-dist, Trilinos, WRF), performance evaluation tools (HPCToolkit, TAU), HPC applications (GROMACS, LAMMPS, OpenFOAM, Quantum Espresso, WarpX, Xyce).
This product has charges associated with it for optional seller support and pre-configured stack (ParaTools Pro for E4S™). ParaTools Pro for E4S™ is the hardened Extreme-scale Scientific Software Stack on Ubuntu, using AWS ParallelCluster, with over 100 HPC and AI/ML tools, an optional Amazon DCV remote desktop on the cluster head node, and cluster configuration built using the Spack package manager and a proprietary MVAPICH-Plus 4 MPI tuned for AWS Elastic Fabric Adapter (EFA). Develop AI/ML applications using tools such as JAX, Keras, NVIDIA BioNeMo, NVIDIA NeMo™, PyTorch, TensorFlow, and vLLM tuned for AWS ParallelCluster, with a complete HPC software stack including numerical libraries (PETSc, SuperLU-dist, Trilinos, WRF), visualization tools (Ascent, VTK-m), performance evaluation tools (HPCToolkit, TAU), HPC applications (GROMACS, LAMMPS, OpenFOAM, Quantum Espresso, WarpX, Xyce).
This product has charges associated with it for optional seller support and pre-configured stack (ParaTools Pro for E4S™). ParaTools Pro for E4S™ is the hardened Extreme-scale Scientific Software Stack on Ubuntu, for use with Adaptive Computing's Heidi AI Cloud Supercomputer. It includes over 100 HPC and AI/ML tools, a web-based remote desktop environment, and cluster configuration built using the Spack package manager and a proprietary MVAPICH-Plus 4 MPI tuned for AWS Elastic Fabric Adapter (EFA). Develop AI/ML applications using tools such as JAX, Keras, NIXL, NVIDIA BioNeMo, NVIDIA NeMo™, PyTorch, SGLang, TensorFlow, and vLLM tuned for AWS and Heidi. The HPC stack features numerical libraries (PETSc, SuperLU-dist, Trilinos, WRF), visualization tools (ParaView, VisIt), performance evaluation tools (HPCToolkit, TAU), GPU communication libraries (NCCL, NVSHMEM), and HPC applications (CP2K, GROMACS, LAMMPS, OpenFOAM, Quantum Espresso, WarpX, Xyce).
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.