SAP Standard Application Benchmarks

SAP Standard Application Benchmarks help customers and partners find the appropriate hardware configuration for their IT solutions. Working in concert, SAP and our hardware partners developed the SAP Standard Application Benchmarks to test the hardware and database performance of SAP applications and components.

Procedure

Benefits

Measuring in SAPS

Sizing

Performance

ERP

Assemble to Order
Cross Application Time Sheet (CATS)
Financial Accounting (FI)
Human Resources - Payroll (HR)
Material Management (MM)
Production Planning (PP)
Sales & Distribution (SD & SD-Parallel)

Assemble to Order

The Assemble-to-Order (ATO) Benchmark integrates process chains across SAP Business Suite components.

The ATO scenario is characterized by high volume sales, short production times (from hours to one day), and individual assembly for such products as PCs, pumps, and cars. In general, each benchmark user has its own master data, such as material, vendor, or customer master data to avoid data locking situations. However, the ATO Benchmark has been designed to handle and overcome data locking situations – the ATO benchmark users access common master data, such as material, vendor, or customer master data.

Technical Components

Financials CO-OM, CO-PC, FI-GL
Logistics MM-IM, LE-WM, LO-VC, CS, SD-BIL, SD-SHP, SD-SLS, PP-BD, PP-ATO
Basis BC-BMT, BC-SRV
Human resources PD-OM
Cross application CA-CL

Published results of the ATO Benchmark contain throughput numbers; for example 2,500 assembly orders per hour. An assembly order is a request to assemble pre-manufactured parts and assemblies to finished products based to an existing sales order.

Dialog Steps

0. Logon

1. Main screen

2. Call /nVA01 (create customer order)

3. Enter order and organizational data

4. Enter customer and material

5. First level characteristic value assignment

6. Second level characteristic value assignment

7. Second level characteristic value assignment

8. Choose Back (Control of resulting price)

9. Choose Save (Create assembly order)

10. Call /nMFBF (Repetitive Manufacturing backflush)

11. Enter sales order data

12. Choose Save

13. Call /nVL01N (Create outbound delivery)

14. Select sales order

15. Choose Save

16. Call /nLT03 (create transfer order)

17. Save transfer order

18. Call /nLT12 (confirm transfer order)

19. Confirm transfer

20. Call /nSO01 (SAP office - inbox)

21. Select workflow-item

22. Start goods issue via workflow

23. Call /nVF01 (create invoice)

24. Choose Save invoice

25. Call /nend

26. Confirm log off

User interaction steps 2 - 24 are repeated n times (23 user interaction steps --> min. 230 sec. duration).

Business aspect:
One run corresponds to the full assemble-to-order scenario for one item.

SAP ATO Standard Application Benchmark Results, Two-Tier Internet Configuration, R/3 Releases 4.0 - 4.6

Date of Certification (mm/dd/yyyy)	Technology Partner	Fully Processed Assembly Orders Per Hour	Operating System Release	RDBMS Release	R/3 Release	Central Server	Central server memory (MB)	Certification Number
09/02/2011	Oracle	206360	Solaris 10	Oracle 11g	SAP enhancement package 4 for SAP ERP 6.0	SPARC Enterprise Server M9000, 64 processors / 256 cores / 512 threads, SPARC64 VII+, 3.00 GHz, 64 KB (D) + 64 KB (I) L1 cache per core, 12 MB L2 cache per processor,	2097152	2011033
09/02/2011	Fujitsu	206360	Solaris 10	Oracle 11g	SAP enhancement package 4 for SAP ERP 6.0	SPARC Enterprise Server M9000, 64 processors / 256 cores / 512 threads, SPARC64 VII+, 3.00 GHz, 64 KB (D) + 64 KB (I) L1 cache per core, 12 MB L2 cache per processor,	2097152	2011033
03/11/2003	Fujitsu Siemens Computers	12170	Solaris 8	Oracle 9i	4.6C	Fujitsu Siemens Computers PRIMEPOWER 900, 16-way SMP, SPARC64TM V, 1.35 GHz, 256 KB L1 cache, 2 MB L2 cache	65536	2003012
03/11/2003	Fujitsu Siemens Computers	6220	Solaris 8	Oracle 9i	4.6C	Fujitsu Siemens Computers PRIMEPOWER 900, 8-way SMP, SPARC64TM V, 1.35 GHz, 256 KB L1 cache, 2 MB L2 cache	32768	2003011
12/13/2002	HP	3090	HP-UX 11i	Oracle 9i	4.6C	hp rx5670, 4-way SMP, Itanium II, 1 GHz, 3 MB L3 cache	24576	2002069
03/22/2002	HP	3740	HP-UX 11i	Oracle 9i	4.6C	HP Server Model RP7410, 8-processors SMP, PA-RISC 8700 750 MHz, 2.25 MB L1 cache	16384	2002016
09/17/2001	HP	7000	HP-UX 11i	Oracle 8.1.7	4.6C	HP RP8400, 16-way PA-RISC 8700 750 MHz, 2.25 MB cache	32768	2001034
05/29/2001	Fujitsu Siemens	34260	Solaris 8	Oracle 8.1.7	4.6B	Fujitsu Siemens Primepower 2000, 128-processors SMP, Sparc64 560 MHz, 8 MB L2 cache	131072	2001018
04/12/2001	HP	18870	HP-UX 11.11	Oracle 8.1.6	4.6B	HP9000 Superdome Enterprise Server, 64-way SMP, PA-RISC 8600, 552 MHz	131072	2001014
02/05/2001	HP	1610	Windows 2000	SQL Server 2000	4.6B	HP NetServer LXr8500, 8-way SMP, Pentium III Xeon 700 MHz, 2 MB L2 cache	8192	2001003
12/11/2000	HP	16480	HP-UX 11.11	Oracle 8.1.6	4.6B	HP9000 Superdome Enterprise Server, 64-way SMP, PA-RISC 8600, 552 MHz	131072	2000030
11/10/2000	Bull	8570	AIX 4.3.3	DB2 UDB 7.1	4.6B	Bull Escala Model EPC 2450, 24-way SMP, RS64-IV 600 MHz, 16 MB L2 cache	32768	2000027
11/10/2000	Bull	6300	AIX 4.3.3	DB2 UDB 7.1	4.6B	Bull Escala Model EPC 2400, 24-way SMP, RS64-III 450 MHz, 8 MB L2 cache	32768	2000026
10/13/2000	IBM	8570	AIX 4.3.3	DB2 UDB 7.1	4.6B	IBM eServer pSeries 680, 24-way SMP, RS64-IV 600 MHz, 16 MB L2 cache	32768	2000025
10/13/2000	IBM	6300	AIX 4.3.3	DB2 UDB 7.1	4.6B	IBM RS/6000 Enterprise Server S80, 24-way SMP, RS64-III 450 MHz, 8 MB L2 cache	32768	2000024
03/31/2000	IBM	7700	AIX 4.3.3	DB2 UDB 6.1	4.0B	IBM RS/6000 Enterprise Server S80, 24-way SMP, RS64-III 450 MHz, 8 MB L2 cache	32768	2000008
09/13/1999	Compaq	2610	Tru64 Unix 4.0 F	Oracle 8.0.4	4.0B	AlphaServer GS 140, 8 way SMP, Alpha 21264A EV67 700 MHz, 8 MB L2 cache	16384	1999028
09/10/1999	HP	2260	HP-UX 11.0	Informix 7.30 FC7	4.0B	HP9000 N4000, 8-way SMP, PA-8500 440 MHz, 1.5 MB L1 cache	16384	1999026
06/14/1999	IBM	2390	QS/400 V4R4	DB2 UDB for AS/400 V4R4	4.0B	IBM AS/400e Model S40-2208 12-way SMP, Power PC 262 MHz, 8 MB L2 cache	6144	1999013
03/12/1999	Sun	2020	Sun Solaris 2.6	Informix 7.30 UC7	4.0B	Sun 6000, Model E 6000, 24 way SMP, UltraSparc II 250 MHz, 1MB L2 cache	16384	1999006
12/18/1998	Compaq	780	Digital Unix 4.0 D	Oracle 8.0.4	4.0B	Compaq Alpha Server 4100 5/600, 4 way SMP, 600 MHz, 4MB L2 cache	8192	1998040

Enlarge

View table

SAP ATO Standard Application Benchmark Results, Three-Tier Internet Configuration, R/3 Releases 4.0 - 4.6

Date of Certifcation (mm/dd/yyyy)	Technology Partner	Fully Processed Assembly Orders Per Hour	Operating System Release	RDBMS Release	R/3 Release	Database Server	Database server memory (MB)	Number & Type of Application Servers	Certification Number
01/17/2002	HP	144090	HP-UX 11i	Oracle 9i	4.6C	HP 9000 Superdome Enterprise Server, 64-way PA-RISC 8700, 750 MHz, 2.25 MB L1 cache	131072	(total 79), 78 x HP RP7400, 8-way PA-RISC 8600, 550 MHz, 1.5 MB L1 cache	2002003
12/04/2001	HP	130570	HP-UX 11i	Oracle 9i	4.6C	HP 9000 Superdome Enterprise Server, 64-way PA-RISC 8700 750 MHz, 2.25 MB L1 cache	131072	(total 71), 70 x HP RP7400, 8-way PA-RISC 8600, 550 MHz, 1.5 MB L1 cache	2001047
09/01/2000	Bull	54170	AIX 4.3.3	DB2 V7.1	4.6B	Bull Escala Model EPC2400, 24-way RS64-III 450 MHz, 8 MB L2 cache	32768	(total 11), 10 x Escala Model EPC2400, 24-way RS64-III, 450 MHz	2000020
08/23/2000	IBM	54220	AIX 4.3.3	DB2 V7.1	4.6B	IBM RS/6000 Enterprise Server Model S80, 24-way RS64-III 450 MHz, 8 MB L2 cache	32768	(total 11), 10 x IBM RS/6000 Enterprise Server Model S80, 24-way RS64-III, 450 MHz	2000019
06/13/2000	HP	22610	HP-UX 11.0	Oracle 8i Rel. 2	4.6B	HP 9000 V2600, 16-way PA-RISC 8600 550 MHz, 1 MB L2 cache	8192	(total 18), 17 x HP9000 N4000, 8-way PA-RISC 8500 440 MHz	2000013
04/26/1999	HP	9130	Windows NT 4.0	Oracle 8.0.5	4.0B	HP Netserver LXr 8000, 4-way Pentium III Xeon 500 MHz, 2 MB L2 cache	2048	13 x Netserver LXr 8000, 4-way Pent III Xeon 500 MHz	1999011

Enlarge

View table

Cross Application Time Sheet (CATS)

The Cross Application Time Sheet (CATS) can be used by employees or personal administrators to track employee working times. Time data is recorded with information referring to orders and cost centers, for example, and can be transferred to corresponding applications and components of the SAP Business Suite.

Dialog Steps

0. Logon

1. Call transaction CAC2

2. Sort employees

3. Choose four employees (scroll down once)

4. Choose Create time data

5. Enter time data and choose Return

6. Choose Save

7. Choose Sort

8. Select another employee

9. Call help requests for cost center

10. Select cost center

11. Call help request for internal order

12. Select internal order

13. Enter new time data and choose Return

14. Choose Save

15. Choose Sort

16. Select five employees

17. Change data

18. Choose Last page

19. Select last line

20. Select all

21. Choose Delete

22. Choose Save

23. Log off

Business aspect:
One run corresponds to the processing of 80 activity reports for 5 employees

Financial Accounting (FI)

The following table provides an overview of the business process the Financial Accounting (FI) Benchmark simulates.

In this scenario, four financial documents with three line items are posted, with the line items in the fourth posting displayed. Following that, 44 open items of one debtor, including the previously posted documents, are displayed, and four are balanced. At the end of each run there are exactly 40 open items for each debtor, which serve as the basis for a new run.

Dialog Steps

0. Logon

1. Main screen

2. Call Post Document

3. Create customer item

4. Create general ledger account item

5. Choose Post

6. Call Display document

7. Enter previous posted document

8. Double-click first line

9. Call Customer line item display

10. Enter data and choose Execute

11. Select first line

12. Call Post incoming payments

13. Enter header data

14. Choose Process open items

15. Select item 5 of the list

16. Scroll down to the end

17. Select last item

18. Deactivate all selected items

19. Choose Post

20. Call /nend

21. Confirm log off

Human Resources - Payroll (HR)

In contrast to online benchmarks, the Human Resources - Payroll (HR) Benchmark is a report with variants that is run as a batch job on the basis of events. The report, called RPCALCD0, exercises the German payroll program.

Procedure

While the procedure for this report is complex, the following features can provide insight into its underlying business processes. Starting with the personal number and the payroll period, the report runs through these transactions in the German payroll program:

Basic data

Last payroll results

Capital formation

Company pension plan

Net payments/deductions and transfers

Final processing

The benchmark run has the following procedure:

. Two users log on to the system.

. The first user resets the data.

. When the high-load phase of the run has come to an end (when the first batch process has come to an end), the first user logs off.

. The second user waits until all processes have finished and then triggers the evaluation before logging off.

Material Management (MM)

The Materials Management (MM) Benchmark takes you through a series of steps to create a purchase requisition for five materials (transaction ME51N), a purchase order for the five materials (ME21N), a goods receipt (MIGO), and an invoice (MIRO) for the purchase order.

Dialog Steps

0. Logon

1. Main screen

2. Call /nME51N (Create purchase requisition)

3. Enter data

4. Choose Post

5. Call /nME21N (Create purchase order)

6. Enter data

7. Choose Post

8. Call /nMIGO (Goods receipt purchase order)

9. Enter data

10. Choose Execute

11. Choose Post

12. Call /nMIRO (Create invoice), enter company code

13. Enter basic data

14. Choose Payment

15. Enter data

16. Choose Post

17. Call /nend

18. Confirm log off

SAP MM Standard Application Benchmark Results, Two-Tier Internet Configuration, R/3 Release 2.2

Date of Certification (mm/yyyy)	Technology Partner	Number of Benchmark Users	Benchmark Type	Average Dialog Response Time (sec)	Operating System - Release	RDBMS Release	R/3 Release	Central Server	Central Server Memory (MB)
03/1995	Digital	360	MM	0.65	OSF/1 3.2	Oracle 7.1.4	2.2 C	DEC 8400 TurboLaser, 8-way SMP	8,192

Enlarge

View table

Production Planning (PP)

The Production Planning (PP) Benchmark consists of the following transactions:

Create a production order. (CO01)
Change the amount on the production order, release order for production, and print order. (CO02)
Create two completion confirmations for the production order (milestone confirmation with back flush and final confirmation). (CO11N)
Post goods receipt for the order. (MB31)
Settle the production order. (CO02)

Dialog Steps

0. Logon

1. Main screen

2. Call Create production order

3. Enter general data

4. Enter data

5. Choose Save

6. Call Change production order

7. Enter order number, choose Return

8. Change data

9. Select order

10. Choose Functions

11. Choose Release

12. Choose Order

13. Choose Print

14. Choose OK

15. Choose Save

16. Call Create completion confirmation

17. Enter data

18. Choose Save

19. Call Create completion confirmation

20. Enter data

21. Choose Save

22. Call Create goods receipt

23. Enter data

24. Copy data

25. Choose Save

26. Call Change production order

27. Choose Environment

28. Choose Individual processing

29. Enter data and choose execute

30. Call /nend

31. Confirm log off

SAP PP Standard Application Benchmark Results, Two-Tier Internet Configuration, R/3 Release 2.2

Date of Certification (mm/yyyy)	Technology Partner	Number of Benchmark Users	Benchmark Type	Average Dialog Response Time (sec)	Operating System - Release	RDBMS Release	R/3 Release	Central Server	Central Server Memory (MB)
03/1995	Digital	180	PP	2.00	OSF/1 3.2	Oracle 7.1.4	2.2 C	DEC 8400 TurboLaser, 8-way SMP	8,192

Enlarge

View table

Sales & Distribution (SD & SD-Parallel)

The Sales and Distribution (SD) Benchmark covers a sell-from-stock scenario, which includes the creation of a customer order with five line items and the corresponding delivery with subsequent goods movement and invoicing.

It consists of the following transactions:

Create an order with five line items. (VA01)

Create a delivery for this order. (VL01N)

Display the customer order. (VA03)

Change the delivery (VL02N) and post goods issue.

List 40 orders for one sold-to party. (VA05)

Create an invoice. (VF01)

Each benchmark user has his or her own master data, such as material, vendor, or customer master data to avoid data-locking situations.

Important note: On January 1, 2009, the SAP SD Benchmark was updated. Alongside the upgrade to SAP Business Suite 7 and the SAP enhancement package 4 for SAP ERP 6.0, a number of additional, necessary updates were implemented. Business changes constantly, for example, Unicode and the use of the new general ledger are now common practice for SAP customers across all industries, and the SAP standard application benchmarks need to reflect this change. The updates are transparent; that is, the steps of the benchmark scenario remain unchanged. Please be aware that these changes make the SD benchmark more resource-intensive, which has a direct impact on the benchmark results.

SD Versus SD-Parallel

The SD-Parallel Benchmark consists of the same transactions and user interaction steps as the SD Benchmark. This means that the SD-Parallel Benchmark runs the same business processes as the SD Benchmark. The difference between the benchmarks is the technical data distribution.

An Additional Rule for Parallel and Distributed Databases

It is generally accepted that data distribution can significantly influence the benchmark result in a parallel environment. Therefore, in May 1996, the SAP Benchmark Council redefined data distribution to establish a means to reproduce and compare results within parallel benchmarks. The additional rule is: Equally distribute the benchmark users across all database nodes for the used benchmark clients (round-robin-method).

How to Appraise the Benchmark Results

Parallel benchmarks depend on the additional parameter "data distribution," which, by definition, does not exist in single database benchmarks. All tests show that the scalability of parallel databases significantly depends on the data distribution. When you compare SD Benchmark with SD-Parallel Benchmark results, you have to remember this difference.

Dialog Steps

0. Logon

1. Main screen

2. Call /nVA01 (Create customer order)

3. First screen

4. Second screen (with five items)

5. Choose Save

6. Call /nVL01N (Create a delivery)

7. First screen

8. Choose Save

9. Call /nVA03 (Display customer order)

10. Choose Enter

11. Call /nVL02n (Change delivery)

12. Choose [F20] (Posts goods issue)

13. Call /nVA05 (List orders)

14. Choose Enter

15. Call /nVF01 (Create invoice)

16. Choose Save

17. Call /nend

18. Confirm log off

User interaction steps 2 - 16 are repeated n times (15 user interaction steps --> min. 150 sec. duration).

Business aspect:
One run (user interaction steps 2 - 16) corresponds to the selling of five items.

SD-Parallel Benchmarks Results

ERP

Assemble to Order

Cross Application Time Sheet (CATS)

Financial Accounting (FI)

Human Resources - Payroll (HR)

Material Management (MM)

Production Planning (PP)

Sales & Distribution (SD & SD-Parallel)

SD Versus SD-Parallel

An Additional Rule for Parallel and Distributed Databases

How to Appraise the Benchmark Results

Call me now