An approach to 95th Percentile with SIMD
11/05/2023
Introduction
In a previous post I looked into using Single instruction, multiple data, SIMD to Sum
an array of integer elements and to find the Median
value of sample.
When working with statistical data, we often need to find the 95th percentile element of a sample. Calculating the Sum
is useful for finding the mean value but finding the 95th percentile element requires a different approach. However, the P95 algorithm is similar to the way the Median
element is found.
The 95th percentile is a statistical term that means the value below which 95% of the data in a given set is found. For example, if you have a set of test scores, the 95th percentile score is the one that is higher than 95% of the other scores. You can calculate the 95th percentile using this formula: n = (P/100) x N, where P = percentile, N = number of values in the data set, and n = ordinal rank of the given set. The 95th percentile is often used to measure service response times, as it allows for burstable usage patterns.