Deploy analytics, technical computing and Hadoop workloads on high-performance clusters in the cloud with IBM High Performance Services
IBM High Performance Services deliver versatile, application-ready clusters in the cloud for organizations that need to quickly and economically add computing capacity for high performance application workloads. The services include market-leading IBM Platform LSF® and IBM Platform Symphony workload management software, IBM Spectrum Scale software defined storage, IBM High Performance Services for Hadoop and the new IBM High Performance Services for EDA. The software is integrated, provisioned and deployed as part of complete, integrated services which includes bare-metal IBM SoftLayer® infrastructure, optional InfinfiBand interconnects and support from an experienced and dedicated cloud operations team. A global presence with the choice of data center location helps ensure that data regulations are met.
Meet New and Peak Demand Challenges
IBM High Performance Services are designed for:
- Organizations seeking to meet variable workload demands inherent in their business
- Companies that can benefit from clustered resources but do not have the budget or the in-house skills to deploy and manage a high performance infrastructure
- Organizations who need a fully supported, ready-to-run Hadoop environment for production use or as a development and test environment
- Electronics design companies who want more affordable access to EDA tools in an on-demand, high-performance and secure environment.
- Application providers that want to make applications available on a pay-per-use basis but don’t have the infrastructure or the time to create a service
Add High Performance Computing Capacity as Needed
IBM High Performance Services enables speedy deployment of technical computing, analytics or Hadoop workloads in the cloud. Organizations using the service can easily meet additional resource demands without the cost of purchasing or managing in-house infrastructure, minimizing their administrative burden and quickly addressing evolving business needs.
To burst workloads from local infrastructure out to the cloud, organizations can add capacity on demand with application-ready clusters provisioned on the SoftLayer cloud and connected to an on-premise 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.
IBM High Performance Services provide:
- A single source for end-to-end cluster support, with access to high performance computing experts to eliminate the skills barrier for using clustered resources
- Dedicated bare-metal servers and InfiniBand interconnects for applications that require the raw horsepower of a non-virtualized, parallel computing environment
- Control of data center locality, enabling organizations to choose the location where their workloads run to meet data regulations
- Non-shared physical machines and a dedicated network for workloads requiring maximum security
- Remote 2-D and 3-D visualization to improve the productivity, collaboration and security of the design process
Achieve Faster Business Results
Organizations using IBM High Performance Services benefit from:
- The ability to add high performance computing resources just when they need them
- Improved time to results and faster time to market with access to ready-to-run, high performance clusters on demand
- Reduced costs with pay-as-you-go access to the resources needed for fueling business growth
- Enhanced user productivity with workload management software that delivers the same user experience for cloud resources as it does for local resources
- High-performance software defined storage with unsurpassed end-to-end data availability, reliability and scalability
Leverage IBM Software with SoftLayer Infrastructure and Support
In addition to offering fully integrated workload management spanning on-premises and on-cloud resources, the IBM High Performance Services provides a security-rich cloud environment for demanding technical computing, analytics and Hadoop applications. The SoftLayer infrastructure includes dedicated physical machines, InfiniBand interconnect, Aspera for high speed data transfer and the latest processor technology to ensure optimal application performance and fastest time to results. SoftLayer public, private and out-of-band management networks are fully integrated, spanning data centers and network points-of-presence in multiple locations around the world.
Architected to meet your organization’s needs
IBM High Performance Services eliminate the complexity of architecting, integrating, provisioning and managing a high performance cluster. Organizations have a choice of five cloud service options:
- IBM High Performance Services for HPC: Ready-to-run, high-performance computing (HPC) cluster in the cloud which can be integrated with an on-premise LSF cluster as a hybrid cloud complete with cloud bursting, data-aware scheduling and remote 2-D/3-D visualization.
- IBM High Performance Services for Analytics: Complete, integrated service optimized for the most demanding Hadoop and analytics public and hybrid cloud environments.
- IBM High Performance Services for Data: Data and file storage management solution based on IBM General Parallel File System (GPFS™) technology for adding high-performance storage capacity and sharing data across the cloud.
- High Performance Services for Hadoop: On-demand access to fully supported, ready-to-run Hadoop clusters on the SoftLayer cloud
- IBM High Performance Services for EDA: On-demand access to the IBM Electronic Design Automation (EDA) tools that have been used to bring over 100 state-of-the-art projects to market including IBM mainframe and Power microprocessors. Made available on an IBM Platform LSF cluster built on the IBM SoftLayer cloud. This first phase delivers three key tools, IBM Library Characterization, to create electrical and timing models for chip design tools and methodologies; IBM Logic Verification, to simulate electronic systems using VHDL and Verilog, and IBM Spice, an electronic circuit simulator used to check design integrity and predict circuit behavior. This service is deployed in VMs on dedicated (non-shared) hypervisors with isolated networks in the datacenter of your choice.
Figure 1. A hybrid cloud model enables businesses to meet peak demands with near- zero wait times.
Figure 2. A stand- alone cluster helps companies meet new, emerging needs
Back to products