Re: When/why did function calls get cheap?

Andreas Klimas <klimas@klimas-consulting.com>
9 Mar 2003 17:47:09 -0500

          From comp.compilers

Related articles
[10 earlier articles]
Re: When/why did function calls get cheap? {spamtrap}@qeng-ho.org (Arthur Chance) (2003-02-24)
Re: When/why did function calls get cheap? gah@ugcs.caltech.edu (Glen Herrmannsfeldt) (2003-02-24)
Re: When/why did function calls get cheap? alexc@std.com (Alex Colvin) (2003-02-24)
Re: When/why did function calls get cheap? vbdis@aol.com (2003-02-24)
Re: When/why did function calls get cheap? firefly@diku.dk (Peter Finderup Lund) (2003-03-09)
Re: When/why did function calls get cheap? joachim_d@gmx.de (Joachim Durchholz) (2003-03-09)
Re: When/why did function calls get cheap? klimas@klimas-consulting.com (Andreas Klimas) (2003-03-09)
Re: When/why did function calls get cheap? bonzini@gnu.org (2003-03-14)
Re: When/why did function calls get cheap? jcrens@earthlink.net (Jack Crenshaw) (2003-03-14)
Re: When/why did function calls get cheap? david.thompson1@worldnet.att.net (David Thompson) (2003-03-22)
Re: When/why did function calls get cheap? alex_mcd@btopenworld.com (Alex McDonald) (2003-03-22)
Re: When/why did function calls get cheap? tenger@idirect.com (Terrence Enger) (2003-03-23)
Re: When/why did function calls get cheap? gah@ugcs.caltech.edu (Glen Herrmannsfeldt) (2003-03-24)
| List of all articles for this month |

From: Andreas Klimas <klimas@klimas-consulting.com>
Newsgroups: comp.compilers
Date: 9 Mar 2003 17:47:09 -0500
Organization: Compilers Central
References: 03-02-098 03-02-144
Keywords: performance, architecture
Posted-Date: 09 Mar 2003 17:47:09 EST

VBDis wrote:
>
> Joachim Durchholz <joachim_d@gmx.de> schreibt:
> >I then
> >inlined the system code, making the CPU wait 80% of the time...
>
> The Atari ST perhaps is not a good example, due to the bad compiler used for
> the kernel ROMs. A simple recompile of the system, using an better compiler,
> could have similar effects. Do you remember KAOS, the manually optimized ST
> kernel?


I think this answer is beside the point. Joachim's example is pretty
good in showing that inlining in fact has been a positive influence.
Processors are mostly designed to do a good job as long as code is in
linear sequence. Another point is that the return address has to be
saved anywhere which would be avoided by inlinig. Concrete
measurements probably will proof the benefit of inlinig. todays
compilers will support inlining anyway - as far as I can tell.


--
Andreas Klimas


Post a followup to this message

Return to the comp.compilers page.
Search the comp.compilers archives again.