Changes

Jump to: navigation, search

GPU621/Analyzing False Sharing

30 bytes added, 14:54, 30 November 2022
Preface
In multicore concurrent programming, if the mutual exclusion is a "performance killer", then false sharing is a worthy "performance assassin". The difference between "killer" and "assassin" is that a "killer" can be easily detected, and we always have many ways to deal with a "killer" when we fight it, such as fighting, running away, detouring, and begging for mercy, but an "assassin" is completely different. Assassins are good at hiding in the shadows and can strike a fatal blow at any time, which makes people defenceless.
In our concurrent development, when we encounter situations that affect concurrency performance, we always have many ways to find and improve the concurrency performance of the program. But false sharing leaves no trace in our code that it is in the "dark" and is seriously slows slowing down concurrency performance, making it hard to find the root cause of the problem, let alone fix itimprove concurrency performance.
= '''What you need to know before understanding false sharing''' =
118
edits

Navigation menu