• Benchmarking is the activity to measure performance reliably and to assess the obtained performance.
• A benchmark is the act of running a computer program, a set of programs, or other operations, in order to assess the relative performance of an object, normally by running a number of standard tests and trials against it.

Such a controlled experiment is named a benchmark, but the term is also used – apparent from the context – for the program that is, or set of programs that are used for benchmarking.

For HPC users measuring the performance behavior of the parallel program(s) they use is of primary importance in order to make optimal use of HPC hardware.

• Provide a basic understanding of benchmarking or performance measurement, so one can quantify successes and failures and use that information to improve the application performance.
• Prepare a method of comparing the performance of various subsystems across different chip/system architectures.
• To assess speedups and efficiencies as the key measures for benchmarks of a parallel program.
• To differentiate between strong and weak scaling
• To assess the performance impact of certain features of current CPU architectures (temperature and dynamic CPU frequencies)

• Consider not only the speed of computational performance, but also the qualities of service, the total cost of ownership and facilities burden (space, power, and cooling).
• Differentiate types of benchmarks.
• Assess speedups and efficiencies as the key measures for benchmarks of a parallel program
• Benchmark the runtime behaviour of parallel programs, performing controlled experiments by providing varying HPC resources (e.g. 1, 2, 4, 8, … cores on shared memory systems or 1, 2, 4, 8, … nodes on distributed systems for the benchmarks)

• K2.1-B Performance Frontiers