RTEMS | draft: microbenchmark to compare the before and after optimization of posix priority message insertion (!1151)

[Chandan U (@Chandanuvm)]

Chandan U created a merge request: https://gitlab.rtems.org/rtems/rtos/rtems/-/merge_requests/1151

Project:Branches: Chandanuvm/rtems:chandan/posixmsgqinsert-bench to rtems/rtos/rtems:main
Author:   Chandan U



[## Summary

draft mr that contains a microbenchmark file to test the current POSIX linear priority message insertion and the same 
benchmark will be used to test the optimized priority bucket+bitmap algorithm.

For a constant queue depth , message with same priority is added completely to fill the queue, a receiver is called to remove exactly one message from the queue, and then sender is called to send a message with same priority.

Since the current existing algorithm is linear it traverses all the existing messages and then adds the new message at the end , making O(n) complexity.

Later after optimization same benchmark will be tested on the new implemented algorithm and will be compared with before and after results.

Other regression tests are already present in the psxmsgq01 - psxmsgq04

- SPARC/erc32 sis simulator is used
[result.txt](/uploads/d881f74ce3c881a8f7d07ea5ad250ce4/result.txt)

-- 
View it on GitLab: https://gitlab.rtems.org/rtems/rtos/rtems/-/merge_requests/1151
You're receiving this email because of your account on gitlab.rtems.org.


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.rtems.org/pipermail/bugs/attachments/20260320/1f77ebc2/attachment.htm>