|
Boost : |
From: Chris Thomasson (cristom_at_[hidden])
Date: 2006-10-27 19:24:18
"Peter Dimov" <pdimov_at_[hidden]> wrote in message
news:00d101c6f9d7$8a44b000$6607a8c0_at_pdimov2...
> Peter Dimov wrote:
>> Anthony Williams wrote:
>>> "Peter Dimov" <pdimov_at_[hidden]> writes:
>>>> Peter Dimov wrote:
>>>>> Howard Hinnant wrote:
[...]
> Your last algorithm also suffers from it, not as much, though:
[...]
> This is probably very much OS/kernel/CPU/workload specific, though. Your
> algorithm definitely holds its own in all realistic scenarios.
I just remembered that Joe Seigh posted a couple of 'ad-hoc' rw-mutex
implementations over on c.p.t; back when I was SenderX... Joe was using them
for something to compare his atomic_ptr proxy collector... Here is the link:
http://groups.google.com/group/comp.programming.threads/browse_frm/thread/b586dbbbf273764d
It might be worth taking a look, and possibly including it your test
application(s)...
Boost list run by bdawes at acm.org, gregod at cs.rpi.edu, cpdaniel at pacbell.net, john at johnmaddock.co.uk