Re: Lockfree algorithms are good for small number of cores

From	"Chris M. Thomasson" <no@spam.invalid>
Newsgroups	comp.programming.threads, comp.programming
Subject	Re: Lockfree algorithms are good for small number of cores
Date	2013-06-20 22:11 -0700
Organization	Aioe.org NNTP Server
Message-ID	<kq0n9k$7ts$1@speranza.aioe.org> (permalink)
References	<kq09he$vbk$2@dont-email.me>

Cross-posted to 2 groups.

Show all headers | View raw

> "aminer"  wrote in message news:kq09he$vbk$2@dont-email.me... 

>Lockfree algorithms are good for small number of cores
>up to 16 cores , but they are not good for more cores
>than that, cause they higher the contention.

You are focusing on wrong areas. For instance,  have you ever thought 
of distributed lock/wait-free algorithms? For instance, even a distributed
rwlock based on atomic RMW cannot really even think about beating 
a RCU like system.

Calm down a little bit and ponder the thought Aminer...

Back to comp.programming | Previous | Next | Find similar | Unroll thread

Thread

Re: Lockfree algorithms are good for small number of cores "Chris M. Thomasson" <no@spam.invalid> - 2013-06-20 22:11 -0700

csiph-web