IBM Power Systems performance benchmarks

Three-tier SAP® Sales and Distribution (SD) Standard Application Benchmark

Evaluates the performance of multiple application servers and a database for a Sales and Distribution (SD) environment using the standard application benchmark provided by SAP AG.

• The 4-core IBM Power 550 (4.2 GHz) achieved the best 4-core three tier SAP SD Standard Application benchmark result (32,000 benchmark users, 2 processors/8 threads, average dialog response time: 1.89 seconds , Fully Processed Order Line items/hour: 3,230,330, Dialog steps/hour: 9,691,000) running AIX 5L V5.3 , DB2 9.5 , ECC Release: 6.0. SAP Certification number 2008001.
• The 32-core IBM eServer p5 595 (1.9 GHz) achieved the best 32-core three-tier SAP SD Standard Application Benchmark result (168,300 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 v8.2.2, AIX 5L™ V5.3, SAP R/3® Enterprise Release 4.70 solution. SAP Certification number 2005021.
• The 64-core IBM Power 780 (3.72 GHz) achieved the best three-tier SAP SD Standard Application Benchmark result (266,000 SAP SD benchmark users; 8 processors / 64 cores / 256 threads, POWER7+; AIX 7.1, DB2 10.5; dialog resp.: 0.84s, line items/hour: 29,433,670, dialog steps/hour: 88,301,000, SAPS: 1,471,680, SAP enhancement package 5 for SAP ERP 6.0) SAP Certification number 2013010.

Source: http://www.sap.com/benchmark (link resides outside of ibm.com)

Two-tier SAP Sales and Distribution (SD) Standard Application Benchmark

Evaluates the performance of a single server running both the application servers and the database server for a Sales and Distribution (SD) environment using the standard application benchmark provided by SAP AG.

• The 2-core IBM System p5 505 (2.1 GHz) achieved the best 2-core two-tier SAP SD Standard Application Benchmark pre-Unicode result (680 benchmark users, 1.98 second average response time, 68,000 fully processed line items per hour, 204,000 dialog steps/hour, 3,400 SAPS, 0.020 sec / 0.016 sec Average DB request time (dia/upd), 98% CPU utilization of central server) running IBM DB2 9, AIX 5L V5.3, SAP ECC Release 5.0. (2 processors/2 cores/4 threads). SAP Certification number 2006047.
• The 4-core IBM Power 570 (4.7 GHz) achieved the best 4-core two-tier SAP SD Standard Application Benchmark pre-Unicode result (2,035 benchmark users, 1.99 second average response time, 203,670 fully processed line items per hour, 611,000 dialog steps/hour, 10,180 SAPS, 0.011 sec / 0.015 sec Average DB request time (dia/upd), 99% CPU utilization) running Oracle 10g, AIX 5L V5.3, SAP ECC Release 6.0. (2 processor chips/4 cores/8 threads). SAP Certification number 2007037.
• The 4-core IBM System p5 550 (1.9 GHz) achieved the best 4-core Linux two-tier SAP SD Standard Application Benchmark pre-Unicode result (1,000 benchmark users, 1.9 second average response time, running IBM DB2 Universal Database v8.2.2, Linux SLES9, SAP R/3 Enterprise Release 5.0 solution. SAP Certification number 2005040.
• The 16-core IBM PowerLinux 7R2 (4.22 GHz) achieved the best 16-core two-tier SAP SD Standard Application Benchmark result (SAP enhancement package 5 for SAP ERP 6.0: 2 processors / 16 cores / 64 threads, POWER7+, 8,256 SAP SD benchmark users, Red Hat Enterprise Linux 6.4, DB2 10. Certification #: 2013006).
• The 16-core IBM Power 570 (4.7 GHz) achieved the best 16-core two-tier SAP SD Standard Application Benchmark pre-Unicode result (8,000 benchmark users, 1.98 second average response time, 801,330 fully processed line items per hour, 2,404,000 dialog steps/hour, 40,070 SAPS, 0.021 sec / 0.013 sec Average DB request time (dia/upd), 99% CPU utilization of central server) running IBM DB2 9, AIX 5L V5.3, SAP ECC Release 6.0. (8 processor chips/16 cores/32 threads). SAP Certification number 2007039.
• The 32-core IBM Power 750 (3.55 GHz) achieved the best 32-core two-tier SAP SD Standard Application Benchmark result (17,312 SD users, dialog resp.: 0.96s, line items/hour: 1,894,670, Dialog steps/hour: 5,684,000, SAPS: 94,730, DB time (dialog/ update):0.012s / 0.022s, CPU utilization: 99%), OS: AIX 7.1, DB2 9.7 (4 processor chips / 32 cores / 128 threads, 256 GB memory), SAP EHP 4 for SAP ERP 6.0 (Unicode). SAP Certification number 2011043.
• The 48-core IBM Power 760 (3.41 GHz) achieved the best 48-core two-tier SAP SD standard application benchmark result running SAP enhancement package 5 for the SAP ERP 6.0 application; 8 processors / 48 cores / 192 threads, POWER7+, 1024 GB memory, 25,488 SD benchmark users, running AIX® 7.1 and DB2® 10, dialog resp.: 0.99s, line items/hour: 2,784,330, Dialog steps/hour: 8,353,000 SAPS: 139,220, DB time (dialog/ update): .009s/.015s, CPU utilization: 99%, Certification number 2013004.
• The 64-core IBM Power 595 (5 GHz) achieved the best non-Unicode 64-core two-tier SAP SD Standard Application Benchmark result (35,400 benchmark users, 1.94 second average response time, 3,559,000 fully processed line items per hour, 10.677,000 dialog steps/hour, 177.950 SAPS, 0.013 sec / 0.017 sec Average DB request time (dia/upd), 99% CPU utilization of central server) running IBM DB2 Enterprise 9.5 database software, AIX 6.1, SAP ECC Release 6.0. (32 processors/64 cores/128 threads). SAP certification number 2008019.
• The 64-core IBM Power 780 (3.86 GHz) achieved the best 64-core two-tier SAP SD Standard Application Benchmark result (SAP enhancement package 4 for SAP ERP 6.0 (Unicode): 8 processors / 64 cores / 256 threads, POWER7, 1024 GB memory, 37,000 SAP SD benchmark users, OS: AIX 6.1, DB2 9.7. Certification #: 2010013).
• The 96-core IBM Power 780 (3.72 GHz) achieved the best 96-core two-tier SAP SD Standard Application Benchmark result (SAP enhancement package 5 for the SAP ERP 6.0 application: 12 processors / 96 cores / 384 threads, POWER7+, 1536 GB memory, 57,024 SD benchmark users, running AIX® 7.1 and DB2® 10, dialog resp.: 0.98s, line items/hour: 6,234,330, Dialog steps/hour: 18,703,000, SAPS: 311,720, DB time (dialog/ update): 0.009s / 0.014s, CPU utilization: 99%, Certification #2012033.
• The 128-core IBM Power 795 (4.00 GHz) achieved the best 128-core two-tier SAP SD Standard Application Benchmark result (SAP enhancement package 4 for SAP ERP 6.0 (Unicode): 16 processors / 128 cores / 512 threads, POWER7, 2048 GB memory, 70,032 SAP SD benchmark users, dialog resp.: 0.93s, line items/hour: 7,686.670 Dialog steps/hour: 23,060,000, SAPS: 384,330, DB resp. time (dialog/ update):0.015s / 0.028s, CPU utilization: 99%, OS: AIX 7.1, DB2 9.7; Certification #2010042).
• The 256-core IBM Power 795 (4.00 GHz) achieved the best overall two-tier SAP SD Standard Application Benchmark result (SAP enhancement package 4 for SAP ERP 6.0 (Unicode): 32 processors / 256 cores / 1024 threads, POWER7, 4096 GB memory, 126,063 SAP SD benchmark users, OS: AIX 7.1, DB2 9.7. Certification #: 2010046).

Source: http://www.sap.com/benchmark (link resides outside of ibm.com)

SAP BI Mixed Load (BI-MXL) Benchmark

The mixed load scenario is one use of the Business Intelligence capabilities of SAP NetWeaver. In this scenario, query activity and load/update activity are executed in parallel. Multiple users run queries on data in 10 SD InfoCubes. The key figure of this benchmark is the number of query navigation steps/hour.

• The 2-core IBM Power 520 (4.7 GHz) achieved the best 2-core SAP BI-MXL Benchmark result (41,090 query navigation steps/hour) (1 processor/2 cores/4 threads). SAP Certification number 2009002.
• The 4-core IBM Power 740 (3.30 GHz) achieved the best 4-core SAP BI-MXL Benchmark result (151,426 query navigation steps/hour) (1 processor/4 cores/16 threads). SAP Certification Number 2010035.
• The 8-core IBM Power 750 Express (3.30 GHz) achieved the best 8-core SAP BI-MXL Benchmark result (278,462 query navigation steps/hour) (1 processor/8 cores/32 threads). SAP Certification number 2010014.
• The 16-core IBM Power 780 (4.10 GHz) achieved the best overall SAP BI-MXL Benchmark result (625,646 query navigation steps/hour) (4 processors/16 cores/64 threads). SAP Certification number 2010047.

Source: http://www.sap.com/benchmark (link resides outside of ibm.com)

SAP BI Data Mart Benchmark

The data mart scenario is one use of the Business Intelligence capabilities of SAP NetWeaver. The data mart contains a static snapshot of operational data. Multiple users run queries on this data in 10 InfoCubes which contain 2,500,000,000 records. The key figure is the number of query navigation steps/hour.

• The 2-core IBM Power 520 (4.2 GHz) achieved the best two-tier 2-core SAP BI Data Mart Benchmark result (40,445 query navigation steps/hour) (1 processors/2 cores/4 threads). SAP Certification number 2008020.
• The 4-core IBM Power 570 (4.7 GHz) achieved the best two-tier 4-core SAP BI Data Mart Benchmark result (92,716 query navigation steps/hour) (2 processors/4 cores/8 threads). SAP Certification number 2007047.

Source: http://www.sap.com/benchmark (link resides outside of ibm.com)

Oracle Applications Standard Online Benchmark v11.5.9

An ERP application that represents a mixed workload intended to model the most common transactions operating on the seven most widely used enterprise application modules (AP, AR, GL, FA, SCM, PO, OE, and Inventory). The 11.5.9 benchmark introduces "self-service" transactions in Expense, Procurement, HR and Time.

• An 8-core IBM eServer p5 570 (1.9 GHz) achieved the best overall result (15,004 users, .533 second average response time).

Source: http://www.oracle.com/us/solutions/performance-scalability/index.html (link resides outside of ibm.com)

Oracle Applications Standard Online Benchmark v11.5.10

An ERP application that represents a mixed workload intended to model the most common transactions operating on the seven most widely used enterprise application modules (AP, AR, GL, FA, SCM, PO, OE, and Inventory). The modules used by the E-Business 11.5.10 benchmark are: Oracle Financials: Accounts Payable, Accounts Receivable, Fixed Assets, General Ledger; Human Resource Management System; Sales and Marketing; Customer Support: Service; Supply Chain Management (SCM): Logistics, Order Management, Purchasing, Shipping; Self-Service Applications: Employee Self-Service, iExpenses, iProcurement, Oracle Time & Labor.

• An 8-core IBM Power 570 (4.7 GHz) achieved the best 8-core medium kit single results of 3000 users at .764 response time, 94,757 lines/hr, 74,257 checks/hr; 2700 users at .702 response time, 97,784 lines/hr, 84,270 checks/hr; 2100 users at .625 response time, 106,838 lines/hr, 91,047 checks/hr.

Source: http://www.oracle.com/us/solutions/performance-scalability/index.html (link resides outside of ibm.com)

Oracle Applications Standard Batch Benchmark v11.5.9

The Release 11i Order Management HVOP benchmark represents a core component of the order to cash business flow demonstrating the overall order processing throughput focused exclusively on meeting the high order volumes originating from the new electronic channels, such as consumer and business web sites, B2B exchanges, and EDI.

• An 8-core IBM eServer p5 570 (1.9 GHz) achieved the best overall result (2,744,000 throughput in lines per 62 minutes).

Source: http://www.oracle.com/us/solutions/performance-scalability/index.html (link resides outside of ibm.com)

Oracle R12 E-Business Standard Benchmark

The Oracle R12 E-Business Standard Benchmark follows the E-Business 11i (11.5.10) benchmark model by combining Online transaction execution by simulated users with concurrent Batch processing to model a "Day-in-the-Life" scenario for a global enterprise.

• A 6-core IBM Power 750 Express (3.30 GHz) achieved the best 6-core medium two-tier Payroll batch result (257,143 checks per hour).
• A 6-core IBM Power 710 (3.72 GHz) achieved the best medium two-tier Order-to-Cash batch result (213,523 lines per hour).
• An 8-core IBM Flex System p260 (4.0 GHz, POWER7+) achieved the best 8-core large/extra-large two-tier Payroll batch result (626,741 employees per hour).
• A 12-core IBM Power 730 (3.72 GHz) achieved the best 12-core large/extra-large two-tier Payroll batch result (702,576 checks per hour).

Source: http://www.oracle.com/us/solutions/performance-scalability/index.html (link resides outside of ibm.com)

Back to top