The benefits of cloud computing are well-known—efficiency, flexibility, high utilisation—but have been difficult to achieve in technical and high-performance computing (HPC) environments. IBM® Platform Computing™ solutions for HPC Cloud are designed to deliver high-performance cloud resources that provide the performance you need along with the advantages of the cloud model.
The extraordinary performance demands that engineering, scientific, financial and research workloads place upon technical and HPC infrastructure have historically meant that these workloads were not suitable for cloud deployments, especially those that use virtualisation technology. However, cloud management software and non-virtualised, bare-metal cloud-based infrastructure is now available, and HPC users can benefit from the flexibility, cost efficiencies and improved resource sharing that cloud provides.
Faster answers, fewer new costs
Cloud technologies, when carefully and flexibly applied, maximise the advantages and minimise the disadvantages for HPC. Platform Computing cloud solutions for HPC are designed to transform static computing resources into flexible high-performance private, hybrid and public clouds that can be shared, remotely managed and easily provisioned to support the demands of compute- and data-intensive workloads and changing user requirements. This means your organisation can deploy an efficient, consolidated infrastructure that meets time-variant business and research demands—and also offers the performance that your users demand.
Based on proven cluster, grid and HPC cloud technology, the Platform Computing solutions for private cloud have intuitive and versatile user interfaces, automated workload-based virtual and physical machine provisioning, robust “resource-aware” job scheduling and migration, and powerful self-service deployment capabilities to help ensure departmental, enterprise or community resources are optimally distributed and easy to manage. The tools are designed so you can align resources with project priorities and realise improved operational and cost efficiencies while achieving business goals unattainable with other management systems.
For hybrid and public cloud deployments, IBM Platform Computing Cloud Service running on SoftLayer® infrastructure delivers a versatile, application-ready solution. The service includes market-leading IBM Platform™ LSF® or IBM Platform Symphony workload management software and codename Elastic Storage data management software delivered as a service. The entire cluster is fully supported by IBM’s technical computing experts and can be deployed in your data centre of choice.
Organisations that are looking to burst their workload from local infrastructure out to SoftLayer as part of a hybrid cloud deployment can add capacity on demand with Platform Symphony and Platform LSF clusters provisioned on the SoftLayer cloud and connected to an on-premises cluster. For companies experiencing new or emerging resource demands, a stand-alone cluster running on the SoftLayer cloud provides compute and storage resources as needed, accessible on a temporary basis with drastically reduced wait times.
By applying cloud technologies and standards to established technical computing and HPC infrastructures, your organisation benefits from:
- Improved time-to-results with on-demand access to ready-to-run clusters in the cloud.
- Enhanced productivity and collaboration with an easy-to-use, web-based portal and visualisation tools.
- Improved data access, resource availability and security while boosting performance.
- Increased automation and decreased manual effort for improved administrator productivity.
- High-performance data storage with unsurpassed end-to-end data availability, reliability and scalability.
- Reduced operating costs and total cost of ownership with a consolidated HPC infrastructure.
A comprehensive set of cloud capabilities designed to work together to address your HPC cloud needs.
Application-ready clusters in the cloud
- IBM Platform Computing Cloud Service is available in two solution models: a hybrid cluster (cloud bursting) and a stand-alone cluster in the SoftLayer cloud (public cloud). It includes SoftLayer infrastructure with dedicated bare metal servers, InfiniBand interconnect and the latest processor technology to help ensure optimal application performance and security.
- Elastic Storage on Cloud, based on IBM General Parallel File System (GPFS™) technology, provides a scalable, high-performance data and file management storage solution that is optimised for HPC and can be installed as part of a complete hybrid or public cloud implementation.
- IBM Platform LSF is a powerful workload management platform for demanding, distributed HPC environments. It provides a comprehensive set of intelligent, policy-driven scheduling features that enable you to utilise all of your compute infrastructure resources and ensure optimal application performance.
- IBM Platform HPC is a complete HPC management solution in a single product. It includes a range of out-of the-box features designed to help reduce the complexity of your HPC environment and improve your time-to-solution.
- IBM Platform Symphony software delivers powerful enterprise-class management for running compute- and data-intensive distributed applications on a scalable, shared grid. It accelerates dozens of parallel applications for faster results and better utilisation of all available resources.
Automated private cloud provisioning and workload migration
- IBM Platform Dynamic Cluster (US) turns static Platform LSF clusters into dynamic cloud infrastructure. By automatically changing the composition of clusters to meet ever-changing workload demands, service levels are improved and organisations can do more work with less infrastructure.
Shared private cloud infrastructure, self-serve cluster creation
- IBM Platform Cluster Manager - Advanced Edition enables self-service creation and management of multiple flexible clusters from a shared pool of resources to deliver the resources required by the compute- and data-intensive workloads in multitenant private cloud environments. Platform Cluster Manager consolidates disparate infrastructure and provides one centralised interface to simplify infrastructure management.
Graphical job submission and process flow management
- IBM Platform Application Centre (US) provides a flexible, easy-to-use interface for cluster users and administrators. Available as an add-on module to Platform LSF and integrated into the Platform Computing Cloud Service, Platform Application Centre enables users to interact with intuitive, self-documenting standardised interfaces.
- IBM Platform Process Manager (US) enables users to design computational processes, capturing and protecting repeatable best practices. Platform LSF or Platform Symphony workflow steps and dependencies are documented using an intuitive graphical interface, enabling users to automate lengthy, repetitive tasks that are prone to human error.