From:	Christopher Croughton <crough45 AT amc DOT de>
Message-Id:	<97Nov29.183752gmt+0100.17026@internet01.amc.de>
Subject:	Re: Alternate malloc?
To:	dj AT delorie DOT com, djgpp AT delorie DOT com
Date:	Sat, 29 Nov 1997 17:36:07 +0100
Mime-Version:	1.0

DJ Delorie <dj AT delorie DOT com> wrote:

> In light of performance, efficiency, and copyright issues with DJGPP's
> current malloc, I explored other implementations of malloc that we
> might use instead.

Were these other ones (your 'test*') ones which you invented, or other
available ones which you've kept anonymous so we're not prejudiced?  If
they're ones you invented, how do these compare to the other ones people
have talked about on the list/newsgroup?

If I'm reading your charts right, it seems that the DJGPP/BSD one is 
about the fastest but also wastes half the space (although how much 
it really wastes depends on the paging boundaries; that's not easy to
calculate).  It seems to me that 'test6' is a fairly good compromise.

Can someone do them on an ix86 platform?  I don't know what a "R5000 SGI"
is but it doesn't sound like a PC to me <g>.  This could make a difference
both to the memory overhead and to the speed; the latter will also be
influenced by the compiler switches (which could optimise some algorithms
better than others).

Thanks for starting off the discussion...

Chris C

- Raw text -