IBM Combines POWER5 Processor Based Servers And Storage With DB2 UDB To Set A New World Record In Performance

IBM today announced that IBM POWER5 processor-based servers and IBM TotalStorage systems, running IBM DB2 Universal Database, have combined to set a new record on the three-tier SAP Sales and Distribution (SD) Standard Application Benchmark [1] - a crucial performance test for SAP customers across the globe. The benchmark follows the recent announcement on the integration of DB2 software with SAP software solutions and provides a real-world illustration of the benefits that customers can realize with an Information on Demand solution.

The results highlight the impressive performance capabilities of the two POWER5 systems, and mark the first time that the POWER5 processor-based IBM TotalStorage DS8300 system has been used as a key element of a three-tier SAP SD Standard Application Certified Benchmark. Customers increasingly favor IT infrastructures that provide an integrated solution to manage and store data better, faster and cheaper. This benchmark result provides an example of how IBM is able to leverage its expertise in systems, storage, software and services to provide a unified approach that delivers information on demand - a key differentiator between IBM and its competitors.

The new benchmark result beats the previous record held by HP by 68 percent [2]. In their result, HP used a database server with 64 Itanium 2 processors running Oracle 10g Database Enterprise Edition, while this new IBM result used a 32 processor POWER5 database server running IBM DB2 UDB v8.2.2, all supported by a POWER5 based IBM TotalStorage DS8300 system.

"Today's announcement demonstrates the leading performance and scalability of three of IBM's most advanced products - the p5-595 system, IBM TotalStorage DS8300 system and DB2 database software," said Volker Loehr, General Manager, Global IBM/SAP Alliance. "The POWER5 processor's overwhelming performance against the competition's fastest processors combined with the scalability of a DB2 version that is optimized for SAP applications make this system an unbeatable platform for SAP customers."

The IBM eServer p5 595, IBM TotalStorage DS8300 and DB2 UDB v8.2.2 software achieved 168,300 SAP SD Benchmark users running the three-tier SAP SD Standard Application Benchmark with the SAP R/3® Enterprise Release 4.70 solution. These remarkable results are equivalent in scale to processing 16,896,670 order line items per hour.

The SAP SD Standard Application Benchmark is one of the most demanding benchmarks in the industry today and has become a de-facto standard not just for SAP use but also for other e-business industry comparisons.

Notes:

[1] The 32-way IBM ~ p5 595 (1.90 GHz) achieved the best overall three-tier SAP SD Standard Application Benchmark result as of May 13, 2005: 168,300 SAP SD Benchmark users, 1.95 second average response time, 16,896,670 fully processed line items per hour, 50,690,000 dialog steps/hour running IBM DB2 Universal Database 8.2.2, AIX 5L V5.3, SAP R/3 Enterprise 4.70, certified May 13, 2005, certification number 2005021.

[2]The 64-way HP Integrity Superdome (1.60 GHz) achieved a three-tier SAP SD Standard Application Benchmark result on November 8, 2004: 100,000 SAP SD Benchmark users, 1.75 second average response time, 10,210,330 fully processed line items per hour, 30,631,000 dialog steps/hour running Oracle 10g database, HP-UX 11i, SAP R/3 Enterprise 4.70, certified November 8, 2004, certification number 2004068.

Citation: IBM Combines POWER5 Processor Based Servers And Storage With DB2 UDB To Set A New World Record In Performance (2005, May 20) retrieved 24 April 2024 from https://phys.org/news/2005-05-ibm-combines-power5-processor-based.html
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.

Explore further

Evidence-based policymaking: New study on international perspectives and best-practice models

0 shares

Feedback to editors