Power™ Systems high performance computing solutions configured into highly scalable AIX® and Linux® clusters offer extreme performance for demanding workloads such as computational chemistry, petroleum reservoir modeling, weather forecasting, climate modeling, and financial services.
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-optimized 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 organizations 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 specialized software from IBM, this system is designed to perform and represents the latest Power technology available.
IBM Blue Gene
Blue Gene family of supercomputers deliver ultrascale performance within a standard programming environment while delivering efficiencies in power, cooling and floor-space consumption. Blue Gene's speed and expandability have enabled business and science to address a wide range of complex problems and make more informed decisions. Blue Gene systems have helped map the human genome, investigated medical therapies, safeguarded nuclear arsenals, simulated radioactive decay, replicated brain power, flown airplanes, pinpointed tumors, predicted climate trends, and identified fossil fuels.
IBM Systems Software for high performance computing
General Parallel File System (GPFS)
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. It is designed to optimize the use of storage, to support scale-out applications and to provide a high availability platform for data intensive applications. GPFS provides online storage management, scalable access and tightly integrated information lifecycle tools capable of managing petabytes of data and billions of files. GPFS can help you move beyond simply adding storage to optimizing data management.
Extreme Cloud Administraton Toolkit (xCAT)
An open source scalable distributed computing management and provisioning tool that provides a unified interface for hardware control, discovery, and operating system diskful/diskfree deployment. This robust toolkit can be used for the deployment and administration of AIX or Linux clusters. Its features are based on user requirements, and take advantage of IBM System x and Power Systems hardware.
Cluster Systems Management (CSM)
Designed to minimize 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. CSM is supported for existing clusters, but Extreme Cloud Administration Toolkit (xCAT) is now the recommended solution for administration of new cluster deployments.
Tivoli® Workload Scheduler LoadLeveler®
Used for dynamic workload scheduling, Tivoli Workload Scheduler LoadLeveler is a distributed network-wide job management facility designed to dynamically schedule work to maximize resource utilization and minimize job completion time. Jobs are scheduled based on job priority, job requirements, resource availability and user-defined rules to match processing needs with resources. LoadLeveler provides consolidated accounting and reporting and supports IBM servers including IBM Power Systems and IBM System x environments.
Engineering and Scientific Subroutine Library (ESSL) and Parallel ESSL
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. ESSL and Parallel ESSL are commonly used in the aerospace, automotive, electronics, petroleum, utilities and scientific research industries, and support Fortran, C and C++ applications running under AIX and Linux.
ESSL provides 32-bit integer, 32-bit pointer, 32-bit integer, 64-bit pointer, and 64-bit integer, 64-bit pointer Serial and SMP Libraries, and 32-bit integer, 32-bit pointer Blue Gene Serial and SMP Libraries.
Parallel ESSL supports SPMD parallel processing applications on clusters of processor nodes connected by a high speed switch using the Message Passing Interface (MPI) library provided in Parallel Environment.
Parallel Environment (PE)
A comprehensive development and execution environment for parallel applications (distributed-memory, message-passing applications running across multiple nodes). It is designed to help organizations develop, test, debug, tune and run high-performance parallel applications in C, C++ and Fortran on IBM Power Systems and IBM System x clusters. Parallel Environment runs on AIX and Linux operating systems.
PowerHA SystemMirror for AIX
The PowerHA SystemMirror Standard Edition and Enterprise Edition are designed to provide high availability and disaster recovery for critical business applications and data. The Standard Edition is optimized for the data center; it monitors the status of servers, networks and applications to detect failures or performance degradation and can respond by automatically restarting a troubled application on designated backup hardware, taking care of all network or storage connections in the process. The Enterprise Edition includes all of the capabilities of the Standard Edition plus muti-site HA/DR capability.The PowerHA Enterprise Edition includes support for GLVM and the IBM Storage Server options; Global Mirror, Metro Mirror and also EMC SRDF.
IBM Power 755
IBM Power 775 Supercomputer
1 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
Additional information about Performance (rPerf range)
Contact IBM
- Request a quote
- Email IBM
- Find a Business Partner
Call IBM: 1-866-883-8901
Priority code: 101AR13W
Looking for a deal?
Don't miss these IBM special offers.
Tell us what you think
Your opinion matters and we want to hear from you. Write a review today!
Top Links for IT Professionals
- IBM POWER7 Systems Family Quick Reference Guide (137KB)
- Compare Power Systems
- Power Systems Technical Guide
- POWER7 Performance Benchmarks
- Special Offers
- Get Adobe® Reader®
More hardware information
- IBM i Solution Editions
- AIX Solution Editions
- Vouchers
- POWER7 supports your applications
- Enhanced I/O options for Power Systems
- Systems Performance Report
- Capacity Backup
- Capacity on Demand
- IBM Storage for Power Systems
- IBM Networking solutions
- Product Accessibility
IBM storage system
DCS3700 Storage System for High Performance Computing
Designed for high performance storage in the field of life sciences, real-time analytics, rich media, seismic processing, weather forecasting, telecommunications, and financial markets
UMass Dartmouth
POWER7 proves to be up to 8 times faster than x86 for black hole research codes