Come up with a hypothesis. For example, \(A' = A\). Ask “If \(A' = A\), what is the probability of measuring a speed-up between two programs by chance”. And then examine whether the hypothesis is true for two normal distribution or Student’s t distribution. If the possibility is larger than 5%, then hypothesis \(A' = A\) is true, and the speed-up is insignificance. Otherwise, reject the hypothesis and conclude that the speed-up is significance.
Null Hypothesis Significance Testing
-
Optimisation
The layout of a program could affect its own performance regardless of its own code. This means that the link order (changes of function address) and environment variable size (moves of program stack) could be arbitrary for one architecture which resulted in more or less cache conflict. Therefore, we need to eliminate the layout differences by using a stabiliser, which randomises the memory layout of the program, analyse it using 202205072243# and use causal profiler such as
cozespecially for programs that utilise parallelism#.