gnash-commit
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Gnash-commit] [SCM] Gnash branch, master, updated.


From: Rob Savoye
Subject: Re: [Gnash-commit] [SCM] Gnash branch, master, updated.
Date: Tue, 29 Mar 2011 16:40:13 -0600
User-agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.2.15) Gecko/20110307 Fedora/3.1.9-0.38.b3pre.fc13 Lightning/1.0b2 Thunderbird/3.1.9

On 03/29/11 12:04, Bastiaan Jacques wrote:

> The key word in the comment is "extensive." (Obviously Firefox allocates
> memory in several threads.) There is apparently a point where the
> amount of allocations in separate threads makes it worthwhile to use
> multiple arenas. The question then is where Gnash is in that spectrum.

  I don't think in the Gnash case allocating from multiple threads
concurrently would buy much, as Gnash is not heavily threaded. The main
thing Gnash takes advantage of with jemalloc is separate memory pools
for each core of the CPU, which does make a difference. Along with that,
jemalloc also works better for all little allocations both C++ and
ActionScript use, than the system malloc.

        - rob -



reply via email to

[Prev in Thread] Current Thread [Next in Thread]