A simple example of pure synthetic benchmarks is my own app AsmAttic, which uses tight loops of (mostly) assembly code which don’t even access memory, and run entirely on the core and its registers. As processors have advanced, these have become more complex. Historically important examples include Whetstone and Dhrystone benchmarks, which for many years were popular benchmarks for floating-point and integer performance of CPUs, respectively. Synthetic benchmarks are specially constructed to test individual aspects of overall performance. These form the two main types of benchmark: synthetic, and application. There are two basic ways to tackle the assessment of performance: test each individual step, such as GPU and disk performance, one at a time, and test them altogether by performing the whole task. Good engineering aims to remove each of those bottlenecks, but there’s always the next. In each system and every action there’s a bottleneck or rate-limiting step which determines how long different tasks take. Let me explain how they could work.Įverything we do on and with our Macs is limited somewhere by performance. Taking my tongue slightly out of my cheek, we’re only too well aware of how misleading benchmarks can be, and how popular arguing about them becomes. Then, when the comparison doesn’t go the way you wanted, pick a different test, and so on, until you satisfy your confirmation bias. The basic concept is simple: select a test, time how long it takes to perform, and compare that result with those on other systems. There’s nothing as controversial in computing as benchmarking.
0 Comments
Leave a Reply. |