SAP Benchmark Glossary

  • A

    Active Idle

    In the context of the SAP power benchmarks, active idle means the SAP system is up and running and service/dialog requests are processed with a response time of an average of 1 second. For details refer to the SAP Power benchmark specification.

    APO-DP Benchmark

    The Demand Planning benchmark is one of three benchmarks in the SAP Advanced Planner & Optimizer benchmark suite. See benchmark description for details.

    APO-PP/DS Benchmark

    The Production Planning and Detailed Scheduling benchmark is one of three benchmarks in the SAP Advanced Planner & Optimizer benchmark suite. See benchmark description for details.

    APO-SNP Benchmark

    The Supply Network Planning benchmark is one of three benchmarks in the SAP Advanced Planner & Optimizer benchmark suite. See benchmark description for details.

    Average Response Time

    Simplified, the average amount of time between the sending of a request to the SAP system and its return to the requestor upon completion. For dialog benchmarks the average response time must be below one (1) seconds (previously two (2) seconds). (Technically the response time is calculated from the throughput as shown by the enqueue monitor.)

  • B

    Batch Benchmark

    Benchmark which runs in the background. The work is done by background processing. Examples are the HR benchmark and the ISU/CCS benchmark.

    Benchmark Rules

    The benchmark rules define what constitutes a valid benchmark execution. Usually these define allowed configurations, parameter settings, experimental limitations, and any operating constraints.

    BI-D Benchmark

    Business Intelligence data mart benchmark. See benchmark description for details.

    BI-MXL Benchmark

    Business Intelligence mixed load benchmark. See benchmark description for details.

    Benchmark User

    A simulated user that runs the specific dialog benchmark scenario in a loop, repeating the actions with a think time of 10 seconds between each user interaction.

    BW Benchmark

    SAP Business Information Warehouse benchmark. See benchmark description for details.

  • C

    CATS Benchmark

    Cross Application Time Sheet benchmark. See benchmark description for details.

    Central Server

    A server that is running the database and all application instances, commonly referred to as two-tier setup.

    Certification

    A confirmation by SAP on behalf of the SAP Benchmark Council that the benchmark run complies with the benchmark rules. All certified benchmarks are publicly available on this Web site.

    Characteristics Combinations Per Hour

    Throughput value of the APO-DP benchmark. In a Demand Planning master planning object structure you define the characteristics to be used for planning. Before you can start planning you must define possible values for these characteristics. You enter the values in combinations and not individually. This means that you only create planning objects for those combinations that are actually used. You must enter a value for each characteristic in the combination.

    Comparison

    To compare benchmark results means to place results side by side in order to show differences and similarities. The purpose of comparing results is to show relative values or excellences by bringing out characteristic qualities, either similar or divergent. (Details and restrictions are available in the SAP Benchmark Publication Policy.)

    Configuration Defaults

    Over the years, specific sets of configurations have become the de facto standard, independent of the hardware vendor, operating system, or database version. To simplify certification, these configuration examples are used as a default. Any deviation from this default needs to be stated explicitly. See configuration defaults for details.

    Core

    "Execution unit that is capable of running one or more processor threads. If a hardware unit can run more than one concurrent processor thread without requiring the processor threads to share execution resources, it is more than one core. It may rely on other "assist" units, such as cache, hardware accelerators, and the like - some or all of which may be shared by multiple cores. The reported number of cores must be the number of cores that are enabled for the benchmark.Execution Unit. The electronic circuits necessary to implement the semantics of all possible instructions in a computer architecture." Source: TPC (Transaction Processing Performance Council) http://www.tpc.org/reports/status/BS-2005-08.asp. (August 2005)
    For SAP benchmarks the reported number of cores must be the number of cores that are available in the server.

    Council

    See SAP Benchmark Council

    CPU Utilization

    CPU utilization on SAP standard application benchmark certificates shows the average use of the CPU resources available to the system during the high load phase of the benchmark, as reported by the operating system. High CPU utilization suggests that the benchmark has been tuned to achieve maximum throughput.
    Exercise caution in extrapolating system performance based on low CPU utilization (e.g. CPU utilization significantly lower than 100%). For example, a benchmark result achieved at 80% CPU utilization may mean that some other system component, such as memory, disk, or network, has become a bottleneck. This is why you cannot expect to achieve better performance. Also, due to modern processor architectures, the percentage of CPU utilization reported by the operating system does not necessarily reflect the percentage of the achievable throughput. For an interpretation of the CPU utilization in a benchmark certificate please contact the respective hardware partner.

  • D

    Database Server

    A server running at least one database instance. There may also be application instances running on that server.

    Dialog Benchmark

    A benchmark that simulates user interaction steps, for example, SD benchmark, ATO benchmark.

    Dialog Step

    User action that provokes a change of a user's state by requesting a new screen.

  • E

    Enqueue Monitor

    A tool that monitors the lock table (also called enqueue table) of the SAP system. The information in the lock table is used to calculate the throughput and the average response time of a benchmark.

    EP-ESS Benchmark (ESS Portal benchmark)

    Employee Self-Service is one of two benchmarks of the SAP NetWeaver Portal benchmark suite. See benchmark description for details.

    EP-PCC benchmark (PCC Portal benchmark)

    People-centric CRM is one of two benchmarks of the SAP NetWeaver Portal benchmark suite. See benchmark description for details.

    E-Selling Benchmark

    See benchmark description for details.

  • F

    Fence Claim

    A statement that proclaimes a "number one result" (leadership) in a certain class. Unlike a comparison, a fence claim compares a result to all other existing results in the same class and the other results do not have to be explicitly listed. (Details and restrictions are available in the SAP Benchmark Publication Policy.)

    FI Benchmark

    Financial Accounting benchmark. See benchmark description for details.

  • H

    High Load Phase

    A period of time when the system load is at its maximum. For example: all benchmark users are logged in and are running the benchmark scenario concurrently when the actual measurement is taken.

    HR Benchmark

    Human Resources - Payroll benchmark. See benchmark description for details.

  • I

    IC Benchmark

    Interaction Center benchmark. See benchmark description for details.

    ISU/CCS Benchmark

    The Customer Care and Service benchmark simulates typical processes in a utilities company. See benchmark description for details.

  • L

    Leadership Statement

    Statement to claim a "number one result" (see fence claim).

  • M

    Minimum Data

    The dataset that has to be completely listed whenever a benchmark result is published. (Details are available in the SAP Benchmark Publication Policy.)

    MM Benchmark

    Materials Management benchmark. See benchmark description for details.

  • N

    Network

    In the context of the SAP power benchmarks, network is defined as all infrastructure components required to run the SAP system except for storage and servers. For details refer to the SAP power benchmark specification.

    n-way SMP

    A Symmetric Multi Processor system with n CPUs (Central Processing Units), where the general meaning of CPU is not defined. Every hardware vendor defines the exact meaning for himself. Because of this the terms processors/cores/threads were introduced in all benchmark certifications starting in August 2005.

  • O

    Order Line Items per Hour

    Throughput value of the SD benchmark. A line item is the part of a document containing information of a single item. It always includes an amount, an account number, the assignment to debits or credits and further specifications that depend on the business transactions to be posted. For the SD benchmark each sales order document contains 5 line items. See also SAPS.

    Orders per Hour (APO)

    Throughput value of the APO-PP/DS benchmark and the APO-SNP benchmark. In the SAP Advanced Planner and Optimizer, sales orders, planned independent requirements, stocks, planned orders and purchase orders are modeled as orders. An order can consist of receipt elements, requirements elements and activities.

  • P

    Payroll Periods per Hour

    Throughput value of the HR benchmark, based on one payroll period per employee. The period for which regular payroll is run. A payroll period is identified by a period number and payroll year.

    POS Inbound Benchmark

    Point-of-sale inbound benchmark based on SAP for Retail. See benchmark description for details.

    Power Efficiency Indicator

    In the context of the SAP power benchmarks, the power efficiency indicator is the unweighted average power consumption over all load levels divided by the unweighted average throughput over all load levels. In the SAP server power benchmark this is expressed in watts/kSAPS. For details refer to the SAP power benchmark specification.

    PP Benchmark

    Production Planning benchmark. See benchmark description for details.

    Processor

    "A component that contains one or more cores. The number of processors claimed by the test sponsor must be consistent with the way the product is represented in the test sponsor's marketing collateral, including that which is not related to TPC benchmark results. The reported number of processors must be the number of processors that are enabled for the benchmark."
    Source: TPC (Transaction Processing Performance Council) http://www.tpc.org/reports/status/BS-2005-08.asp. (August 2005)
    For SAP benchmarks the technology partner who submits the benchmark data is the equivalent to the "test sponsor". In the case of SAP benchmarks the reported number of processors must be the number of processors that are available in the server, not only the ones used in the benchmark.

    Processors/Cores/Threads

    Replacement of the n-way SMP specification in benchmark certifications to provide detailed technical information. This change went into effect in August 2005. See processor, core, thread for details.

    PS Benchmark

    Project System benchmark. See benchmark description for details.

    Publication Policy

    See SAP Benchmark Publication Policy.

    Publication Violation

    Publications that are not in line with the publication policies are considered to be a violation if the issue cannot be solved. In this case the SAP Benchmark Publication Workgroup makes the decision on the violation.

    Publication Workgroup

    See SAP Benchmark Publication Workgroup.

  • Q

    Query Navigation Steps per Hour

    Throughput value of the BW benchmark. A query is a combination of characteristics and key figures (InfoObjects) for the analysis of the data of an InfoProvider. The query data can be displayed in different views. A view change through a user interaction is considered to be a navigation step.

  • R

    Retail Benchmark

    Benchmarks based on SAP for Retail: See POS Inbound benchmark and Store Replenishment benchmark for details.

  • S

    Sales Data Line Items per Hour (POS Inbound)

    Throughput value of the POS Inbound benchmark.

    SAP Benchmark Council

    Established in 1995, the SAP Benchmark Council monitors all benchmarking activities and provides standards for publishing benchmark results in the SAP environment. Representatives of SAP and technology partners, such as hardware and database vendors involved in benchmarking, make up the SAP Benchmark Council.

    SAP Benchmark Publication Policy

    The SAP Benchmark Publication Policy is a set of fair practices for the publication of competitive information related to SAP Standard Application Benchmarks.

    SAP Benchmark Publication Workgroup

    The SAP Benchmark Publication Workgroup establishes and maintains the SAP Benchmark Publication Policy and makes sure that those policies are respected.

    SAP Benchmark Suite

    Different benchmarks which are based on the same SAP solution and which cover the most typical business scenarios of this solution. Each of the benchmarks can be certified individually.

    SAP Release

    Release or version of the SAP business software.

    SAPS

    The SAP Application Performance Standard (SAPS) is a hardware-independent unit that describes the performance of a system configuration in the SAP environment. It is derived from the Sales and Distribution (SD) Benchmark, where 100 SAPS is defined as 2,000 fully business processed order line items per hour. In technical terms, this throughput is achieved by processing 6,000 dialog steps (screen changes), 2,000 postings per hour in the SD benchmark, or 2,400 SAP transactions. In the SD benchmark, fully business processed means the full business process of an order line item: creating the order, creating a delivery note for the order, displaying the order, changing the delivery, posting a goods issue, listing orders, and creating an invoice.

    SAP Server Power Benchmark (SEP)

    One of two power efficiency benchmarks in the SAP power benchmark suite. It shows the power consumed by the server(s) in an SAP system environment. This encompasses CPU, memory and, in the case of a three-tier setup, the power consumed by the network connections between the servers, excluding the storage. For details refer to the SAP Power Benchmark description.

    SAP System Power Benchmark (SYP)

    One of two power efficiency benchmarks in the SAP power benchmark suite. It shows the power consumption of an entire SAP system, i.e. the power consumption of the server(s), the storage and the network to connect them. For details refer to the SAP Power Benchmark description.

    SAP Standard Application Benchmark

    Benchmarks are standardized load tests that measure and record performance key figures for quantitative comparison of hardware and software. SAP Standard Application Benchmarks reflect typical business scenarios of SAP Solutions. There are several different benchmarks available, e.g. SD, BW, ... If benchmarks are based on the same SAP solution they belong to the same Benchmark Suite. The most common benchmark is SD. The throughput value SAPS is defined by the SD-benchmark.

    Server

    For a definition of "server" in the context of the SAP power benchmarks refer to section 4.1.1.2 of the SAP Power Benchmark Specification.

    SD Benchmark

    Sales & Distribution benchmark. See benchmark description for details. The SD benchmark is the basis for the calculation of SAPS and thus the basis for sizing forecasts.

    SD Parallel Benchmark

    Benchmark running the business transactions of the SD benchmark on more than one active database server. To create maximum load and contention for the database and the application servers, the data is distributed round robin to all SAP application servers. See benchmark description for details.

    Segmentation

    In the benchmark certificates, "segmentation" refers to any kind of partitioning, virtualization, or other technology that can be used to run more than one operating system image on a physical server.

    Storage

    For a definition of "storage" in the context of the SAP power benchmarks refer to section 4.1.1.4 of the SAP power benchmark specification.

    Stores Per Hour

    Throughput value of the Store Replenishment benchmark.

    Store Replenishment Benchmark

    Benchmark based on SAP for Retail. It comprises a pre-step for point-of-sale (POS) upload that provides the sales data for the replenishment process. See benchmark description for details.

  • T

    Think Time

    Time before the user sends the next request to the SAP system. For dialog benchmarks the think time is equal to 10 seconds.

    Thread

    "Processor Thread. The hardware necessary to maintain the state of a Software Thread. The reported number of processor threads must be the number of concurrent processor threads that are enabled for the benchmark. Software Thread. An instruction sequence that performs operations within an address space and is scheduled by software." Source: the Processor Thread definition of TPC (Transaction Processing Performance Council) http://www.tpc.org/reports/status/BS-2005-08.asp. (August 2005)
    For SAP benchmarks the reported number of threads must be the number of threads that are available in the server.

    Three-Tier (3-tier)

    Every configuration that does not fall into the class of a 2-tier configuration is called 3-tier.

    Throughput

    The amount of work that can be performed by an SAP system in a given period of time.

    Throughput Level

    In the context of the SAP power benchmark, throughput level means the relative throughput achieved based on a specific load level. For details refer to the SAP power benchmark specification.

    Transport & Production Orders per Hour

    Throughput value of the APO-PP/DS and APO-SNP benchmarks. Production orders used for discrete manufacturing. Production orders can only be processed and backflushed in the linked R/3 or ERP system. Planned orders that were created in APO are converted into production orders in the linked system.

    TRBK Benchmark

    Transaction Banking benchmark. See benchmark description for details. This benchmark replaced the Bank Customer Accounts (BCA) benchmark.

    Two-Tier (2-tier)

    An SAP Standard Application Benchmark can be termed two-tier if it is: Executed on one server – What constitutes one server is defined by the individual hardware vendor. The minimum condition is that it must be sold and supported as one server.
    Running the SAP application and the database on one operating system image – A running operating system is one operating system image if, during the benchmark run, all processes used by the SAP application and the database theoretically are able to communicate with each other via shared memory and semaphore.
    Examples are available in the SAP Benchmark Publication Policy.

  • U

    URCs per Hour

    Throughput value of the ISU/CCS benchmark. A Utility Reference Customer (URC) is the specific representation of a typical customer of a utility company in the ISU/CCS data model. In terms of this data model, a URC consists of one business partner with one contract account and two contracts.

  • W

    WM Benchmark

    Warehouse Management benchmark. See benchmark description for details.

    Workgroup

    Representatives of SAP and technology partners who work out certain issues on behalf of the SAP Benchmark Council.