IBM Power™ Systems high performance computing solutions lead the Top10 list of supercomputers in not only performance but also energy efficiency. When configured into highly scalable AIX® and Linux® clusters Power Systems offer extreme performance for demanding workloads such as computational chemistry, petroleum reservoir modeling, weather forecasting, climate modeling, and analytics.
IBM Blue Gene (US)
IBM Blue Gene/Q delivers ultrascale performance within a standard programming environment while delivering efficiencies in power, cooling and floor-space consumption. Consistently recognised as the fastest “big data”, data intensive computing system,1 Blue Gene enables business and science to address a wide range of complex problems such as helping map the human genome, investigating medical therapies, flying airplanes, pinpointing tumors, predicting climate trends, and safeguarding nuclear arsenals. Today, with BlueGene/Q Express, a half rack configuration, this leading technology is available to a broader set of users requiring big data management that keeps them ahead of the competition.
Power servers for high performance computing
| Sockets | 4 |
|---|---|
| Processor cores | 8-core POWER7 with AltiVec™ SIMD acceleration |
| Clock rates (Min/Max) | 3.6 GHz |
| System memory (Min/Max) | 128 GB / 256 GB |
| Internal storage (Min/Max) | 73.4 GB / 2.4 TB |
| Performance (rPerf range)* | 45.13 / 91.96 |
Read more
The Power® 755 is a 4-socket, 32-core server with outstanding performance in a dense 4U rack-optimised package. Using 12X InfiniBand adapters up to 641 Power 755 nodes, each with 32 cores, can be clustered together providing up to 2,048 POWER7 cores.
The IBM Power 775 supercomputing server is designed for organisations that require a highly scalable system with extreme parallel processing performance and dense, modular packaging. Use it in clustered configurations of as few as 256 processor cores or in world-class supercomputer configurations of hundreds of thousands of processors. Combined with specialised software from IBM, this system is designed to perform and represents the latest Power technology available.
IBM Systems Software for high performance computing
General Parallel File System (GPFS) (US)
GPFS™ is a high-performance cluster file management infrastructure for AIX, Linux, Windows® and mixed clusters that provides world-class performance, scalability and availability for your file data.
Extreme Cloud Administraton Toolkit (xCAT) (US)
An open source scalable distributed computing management and provisioning tool that provides a unified interface for hardware control, discovery, and operating system deployment.
Cluster Systems Management (CSM) (US)
Designed to minimise the cost and complexity of administering IBM Cluster Systems built on IBM System x and IBM Power Systems by enabling comprehensive management and monitoring of the entire environment from a single point of control.
Tivoli® Workload Scheduler LoadLeveler® (US)
Used for dynamic workload scheduling, Tivoli® Workload Scheduler LoadLeveler® is a distributed network-wide job management facility designed to dynamically schedule work to maximise resource utilisation and minimise job completion time.
Engineering and Scientific Subroutine Library (ESSL) and Parallel ESSL (US)
Collections of state-of-the-art mathematical subroutines specifically designed to improve the performance of serial, SMP and SPMD applications on the IBM POWER™ processor-based servers.
Parallel Environment (PE) (US)
A comprehensive development and execution environment for parallel applications (distributed-memory, message-passing applications running across multiple nodes).
PowerHA SystemMirror for AIX (US)
The PowerHA SystemMirror Standard Edition and Enterprise Edition are designed to provide high availability and disaster recovery for critical business applications and data.
IBM Power 755
IBM Power 775 Supercomputer
1 Graph500.org
2 Capability to create a cluster of up to 64 nodes is planned to be available in March, 2010. Clusters larger than 64 nodes will be considered for support on a case-by-case basis.
* The benchmarks and values shown herein were derived using particular, well configured, development-level computer systems. Actual system performance may vary and is dependent upon many factors including system hardware configuration and software design and configuration.
Additional information about benchmarks and associated trademarks (US)
Additional information about Performance (rPerf range) (US)
We're here to help
- Easy ways to get the answers you
need.
- E-mail us
Or call us at: 1800 557 343
Mon - Fri,
8:30 a.m. - 5:00 p.m. AEST
Web code: AU1BB01W