Quote from JR Shin, senior IT manager, Samsung SDS Europe:
"The amount of equipment we use is increasing. We have to adopt the latest technology and meet the critical support levels of our business, and we expect excellent performance from our servers. We decided to stay with HP because of its futuristic approach.”
TPC-C is an online transaction processing benchmark. The current version is 5.0. It continues to be a popular yardstick for comparing OLTP performance on various hardware and software configurations.
TPC-H is an ad-hoc, decision support benchmark. The current version is 1.4.0. The TPC-H (ad-hoc, decision support) benchmark represents decision support environments where users don't know which queries will be executed against a database system; hence, the "ad-hoc" label. Pre-knowledge of the queries may not be used to optimize the DBMS system. The TPC believes that comparisons of TPC-H results measured against different database sizes are misleading and discourages such comparisons. Therefore results are grouped by database size.
The SAP Business Information Warehouse (SAP BW) Standard Application Benchmark consists of two phases that run consecutively: The load phase which consists of the reading of master data from an external flat file structure and the query phase which simulates multiple-user queries.
The SAP ATO benchmark uses more SAP components and stresses more parts of SAP than any other SAP benchmark. It imitates a Supply Chain Management application through a series of automatically generated dialog steps. It uses a predefined client database, where each client is an organizational unit with its own master tables and its own set of tables. Tests were performed either using a simple 2-tier or a 3-tier SAP configuration.
SAP APO Production Planning and Detailed Scheduling (PP/DS) benchmark
This benchmark creates customer demands in each production plant and uses the Production Planning Run to fulfill this demands. The benchmark covers two layers:
For the Demand Planning Benchmark it is assumed that each of two thousand customers buys five hundred products resulting in one million characteristic combinations (2,000 customers times 500 products). As demand planning considers the last two years to plan for the next two years, the total number of time buckets (weeks) is two hundred and eight (4 times 52). Therefore the total number of considered data records is two hundred and eight million. The number of automatically aggregated characteristic combinations (combinations of products and distribution centers) is one hundred thousand (in each distribution center, all products are available). The results of the benchmark are demand figures that result in actual demand.
Printable version
