thread-affinity-openmp
Differences
This shows you the differences between two versions of the page.
| thread-affinity-openmp [June 11, 2026 at 09:20] – created - external edit 127.0.0.1 | thread-affinity-openmp [June 11, 2026 at 11:10] (current) – Ivan Janevski | ||
|---|---|---|---|
| Line 1: | Line 1: | ||
| # Thread affinity (OpenMP) | # Thread affinity (OpenMP) | ||
| - | On a laptop or single-socket desktop, every core reaches the same RAM at the same speed. On a multi-socket server, each socket has its own bank of RAM (NUMA, non-uniform memory access): accessing local memory is fast, but crossing the inter-socket interconnect to reach the other socket' | + | On a laptop or single-socket desktop, every core reaches the same RAM at the same speed. On a multi-socket server, each socket has its own bank of RAM (NUMA, non-uniform memory access): accessing local memory is fast, but crossing the inter-socket interconnect to reach the other socket' |
| + | |||
| + | **Thread affinity** pins threads to specific hardware locations to prevent migration and keep threads close to their data. | ||
| ```c | ```c | ||
thread-affinity-openmp.txt · Last modified: by Ivan Janevski
