Subj : Re: STL Containers w/ Virtually Zero-Overhead Lock-Free Reads...
To   : (Usenet)
From : Markus Elfring
Date : Thu Sep 22 2005 05:55 am

> Not even in the allocators?  In the end, all of the allocator
> implementations I know finish sooner or later in malloc, and the
> malloc implementations I know use a lock.

Would you like to consider lock-free memory allocators?
Is the approach that is described in the paper "Scalable Lock-Free Dynamic Memory
Allocation" by
Maged M. Michael appropriate for the discussed use cases?
http://www.research.ibm.com/people/m/michael/pldi-2004.pdf

How do you think about alternative ways to improve the situation for multi-threaded
programming?
http://en.wikipedia.org/wiki/Hoard_memory_allocator

Regards,
Markus



      [ See http://www.gotw.ca/resources/clcm.htm for info about ]
      [ comp.lang.c++.moderated.    First time posters: Do this! ]

.