benchmark

benchmark

A performance test of hardware and/or software. There are various programs that very accurately test the raw power of a single machine, the interaction in a single client/server system (one server/multiple clients) and the transactions per second in a transaction processing system. However, it is next to impossible to benchmark the performance of an entire enterprise network with a great degree of accuracy.

Benchmarks may change their rating scale with new releases of the software. Thus, the same version of the test must often be run to compare results. See PC Magazine benchmarks, BAPCo, ECperf, Linpack, Dhrystone, Whetstone, Khornerstone, SPEC, GPC and RAMP-C.

---

benchmark [′bench‚märk]

(engineering)

A relatively permanent natural or artificial object bearing a marked point whose elevation above or below an adopted datum—for example, sea level—is known. Abbreviated BM.

(industrial engineering)

A standard of measurement possessing sufficient identifiable characteristics common to the individual units of a population to facilitate economical and efficient comparison of attributes for units selected from a sample.

(science and technology)

A reference value against which a measurement or a series of measurements may be compared.

---

(benchmark)

benchmark - A standard program or set of programs which can be run on different computers to give an inaccurate measure of their performance. "In the computer industry, there are three kinds of lies: lies, damn lies, and benchmarks." A benchmark may attempt to indicate the overall power of a system by including a "typical" mixture of programs or it may attempt to measure more specific aspects of performance, like graphics, I/O or computation (integer or floating-point). Others measure specific tasks like rendering polygons, reading and writing files or performing operations on matrices. The most useful kind of benchmark is one which is tailored to a user's own typical tasks. While no one benchmark can fully characterise overall system performance, the results of a variety of realistic benchmarks can give valuable insight into expected real performance. Benchmarks should be carefully interpreted, you should know exactly which benchmark was run (name, version); exactly what configuration was it run on (CPU, memory, compiler options, single user/multi-user, peripherals, network); how does the benchmark relate to your workload? Well-known benchmarks include Whetstone, Dhrystone, Rhealstone (see h), the Gabriel benchmarks for Lisp, the SPECmark suite, and LINPACK. See also machoflops, MIPS, smoke and mirrors. Usenet newsgroup: news:comp.benchmarks. Tennessee BenchWeb.