The HPC platform, software and support you need to get your job done.
Our flagship science, engineering and research computing platform comes in multiple editions sized to fit your budget and suit your support requirements.
As for Flight Compute Solo plus:
As for Flight Compute Advanced plus:
Price on request
|Alces Gridware software library|
|Interactive GUI sessions|
|Secure VPN access|
|Choice of HPC job scheduler|
|Selectible software packs|
|Dedicated support channel|
|Multiple compute queues|
|Enhanced management capabilities|
|Managed support option|
|On-premises hosted option|
Your favourite applications, at your fingertips and ready to go.
Alces Gridware is a collection of scientific applications and libraries ready to install on your Alces Flight Compute cluster, ensuring you've got absolutely everything you need and allowing your analysis to start as quickly as possible.
Covering many fields of scientific research, from fluid dynamics to molecular dynamics, bioinformatics to statistics, machine learning to electron microscopy, Alces Gridware puts an entire research toolkit at your fingertips.
Alces Flight Compute allows you to install from a selection of preconfigured software depots providing quick batch deployment of groups of popular applications, or the freedom to install your own selection of key applications – with all dependencies satisfied and appearing automatically alongside your selections.
From the installation of multiple versions of the same application to building your own architecture- and environment-optimized software, Alces Gridware has got you covered. And for those who want to get started quickly you can install many applications from one of our prebuilt binary repositories.
The de facto market leader in open source computational fluid dynamics, CFD Direct's OpenFOAM ("Open source Field Operation And Manipulation") is a C++ toolbox for the development of customized numerical solvers and pre-/post- processing utilities for the solution of continuum mechanics problems. Provides a friendly syntax for partial differential equations and supports a wide range of ready-to-use applications and models.
Developed at Électricité de France R&D, Code_Saturne is a general-purpose, open source CFD package based on a co-located finite-volume approach. Code_Saturne solves the Navier-Stokes equations for 2D, 2d-axisymmetric and 3-d flows, steady or unsteady, laminar or turbulent, incompressible or weakly dilateable, isothermal or not, with scalar transport if required.
ParaView is an open source data analysis and visualization application providing means to build visualizations and to perform data analysis using qualitative and quantitative techniques. As well as providing batch processing capabilities, ParaView can be used to display interactive visualizations generated using level-of-detail (LOD) models that maintain interactive frame rates for large datasets and client-server architecture to facilitate the visualization of remote datasets.
Developed by the Google Brain team for internal Google use, TensorFlow is an open-source software library for machine learning across a wide range of tasks. Providing tools to build and train neural networks represented as stateful dataflow graphs to detect and decipher patterns and correlations, TensorFlow can run across single devices, multiple CPUs and GPGPUs with optional CUDA extensions.
Largely written in the user-friendly Python language and designed to interoperate with the well established Python numerical and scientific libraries NumPy and SCIPy, Scikit-learn is a free software machine learning library featuring various classification, regression and clustering algorithms, including support vector machines, random forests, gradient boosting, k-means and DBSCAN.
Originally developed at UC Berkeley, Caffe is a deep learning framework that values expression, speed, and modularity. Caffe is used both in academic research and industrial applications in vision, speech and multimedia and is written in C++ with a Python interface.
Choose the level of engagement that suits you.
If you have a question, encounter a bug or have an enhancement request to make why not visit our community support portal. The Alces Flight Crew may be available to respond to your request, or you may find that somebody else in the community has had a similar problem and can help you out.
Staff members actively engage in the community and will frequently be available to offer help and advice regarding your problem. However please note that there is no guaranteed response time to customer requests. Should you require immediate assistance then the Advanced or Enterprise editions may be a better choice.
If you're seeking enhanced features, access to further configuration options or looking to build a multi-user platform, our pay-as-you-go Advanced or bespoke Enterprise editions of Alces Flight may better suit your needs.
As an Advanced or Enterprise edition customer, you'll have access to a dedicated area on the community support site where you can raise issues which will be responded to by staff members in accordance with your SLA.
Already a subscriber? Login now to engage the Alces Flight Crew directly.
If you need to create a more complex HPC environment, Flight Compute Advanced will help keep you airborne.
For users or groups with more complicated cluster requirements, Flight Compute Advanced provides a rock solid foundation for building a multiple-user and multiple-queue HPC environment.
Configured with an always-on master node combined with your choice of autoscaling compute queues, Flight Compute Advanced gives you the best of both worlds – the configurability and longevity of a traditional cluster at a fraction of the cost. By offering a pay-as-you-go model, these HPC clusters are put to work as and when you need them and operate entirely within your budgetary constraints, driving up efficiency and slashing your costs.
Choose from a selection of deployment options that allow you to fine-tune the capabilities of the your HPC platform:
Register your interest in using Flight Compute Advanced now and we'll get in touch with more details.
Alces Flight Compute can satisfy your software requirements with our Flight Connections programme.
As part of our Flight Connections programme we work together with software vendors to prepare their software so it's ready to launch on the Alces Flight Compute platform.
Developed by the Fraunhofer Institute for Industrial Mathematics, BeeGFS is a parallel file system developed and optimized for high-performance computing. BeeGFS uses a distributed metadata architecture for scalability and flexibility and has excellent data throughput characteristics.
Experts in I/O profiling, Ellexus provide tools for application monitoring and profiling that can be run on a live compute cluster. Ellexus Mistral is a ground-breaking tool allowing application developers to monitor application I/O and I/O performance across the cluster to identify rogue jobs and hotspots.
With over 17 years in the HPC industry, NICE deliver the industry-leading NICE EnginFrame HPC applications portal, a user-friendly interface to batch and interactive applications accessed across the internet or intranet using a standard web browser, and Desktop Cloud Visualization (DCV), a remote access solution that optimizes the usage of graphical applications over standard networks.
Alces Flight Compute also has support for:
The successor to CD-adapco's STAR-CD, STAR-CCM+ is a computational fluid dynamics package employing a client-server architecture allowing engineers to offload the heavy lifting to a remote HPC cluster.
ANSYS have been advancing technology in the field of engineering simulation for more than 45 years. Their market-leading solutions include ANSYS Fluent, computational fluid dynamics software tools that empower engineers to simulate fluid flows in a virtual environment.
MATLAB is a multi-paradigm numerical computing environment consisting of a programming language that can be used to create standalone numerical applications and a graphical interface for plotting functions and advanced data visualizations.
The Genome Analysis Toolkit (GATK), developed in the Data Sciences Platform at the Broad Institute, offers a spectum of tools focussed on variant discovery and genotyping.
The parallel computing platform and application programming interface model created by Nvidia to support general-purpose computing on CUDA-enabled GPUs providing direct access to the virtual instruction set and parallel computational elements of the GPU.
Adaptive Computing's world-leading workload and resource orchestration software platform, Moab, that intelligently integrates scheduling, managing. monitoring and reporting of cluster workloads.
Intel's software development product provides C, C++ and Fortran compilers optimized to work with Intel processors, as well as the Intel MPI (Message Passing interface) and MKL (Math Kernel Library) libraries.
Compilers developed by the Portland Group targeting both Intel and AMD processors incorporating global optimization, vectorization, software pipelining and shared-memory parallelization capabilties. Fortran, C and C++ compilers included.