Re: MMX/3Dnow!/SSE/SSE2 compilers

Marco van de Voort <marcov@toad.stack.nl>
4 May 2002 14:18:21 -0400

          From comp.compilers

Related articles
[3 earlier articles]
Re: MMX/3Dnow!/SSE/SSE2 compilers snowwolf@diku.dk (Allan Sandfeld Jensen) (2002-04-24)
Re: MMX/3Dnow!/SSE/SSE2 compilers dave@icmfp.com (2002-04-29)
Re: MMX/3Dnow!/SSE/SSE2 compilers jgd@cix.co.uk (2002-04-29)
Re: MMX/3Dnow!/SSE/SSE2 compilers jacob@jacob.remcomp.fr (jacob navia) (2002-05-01)
Re: MMX/3Dnow!/SSE/SSE2 compilers a.richards@codeplay.com (Andrew Richards) (2002-05-01)
Re: MMX/3Dnow!/SSE/SSE2 compilers cparpart@surakware.net (Christian Parpart) (2002-05-03)
Re: MMX/3Dnow!/SSE/SSE2 compilers marcov@toad.stack.nl (Marco van de Voort) (2002-05-04)
Re: MMX/3Dnow!/SSE/SSE2 compilers a.richards@codeplay.com (Andrew Richards) (2002-05-08)
Re: MMX/3Dnow!/SSE/SSE2 compilers snowwolf@diku.dk (Allan Sandfeld Jensen) (2002-05-12)
Re: MMX/3Dnow!/SSE/SSE2 compilers jacob@jacob.remcomp.fr (jacob navia) (2002-05-23)
Re: MMX/3Dnow!/SSE/SSE2 compilers jgd@cix.co.uk (2002-05-23)
Re: MMX/3Dnow!/SSE/SSE2 compilers salbin@emse.fr (2002-05-23)
Re: MMX/3Dnow!/SSE/SSE2 compilers jacob@jacob.remcomp.fr (jacob navia) (2002-05-27)
| List of all articles for this month |

From: Marco van de Voort <marcov@toad.stack.nl>
Newsgroups: comp.compilers
Date: 4 May 2002 14:18:21 -0400
Organization: Eindhoven University of Technology, The Netherlands
References: 02-04-126 02-04-161 02-05-004
Keywords: arithmetic, optimize
Posted-Date: 04 May 2002 14:18:21 EDT

jacob navia wrote:


> I implemented all floating point in SSE2 in my compiler system
> (lcc-win32) but failed at the above points. I could not guarantee that
> the results of a+b would be the same and that would have lead to
> incredible problems with floating point code since I set up the FPU to
> use all precision.
>
> Besides if I save some value in an SSE2 register I have to save them all at
> each function call, what means a BIG i/o overhead.


It is unnecessary to save them all always. Simply declare a few regs as
scratch (doesn't have to be saved across calls), and the functions themselves
should save the non-scratch regs if they use them.


If you use SSE2 regs as parameter register for FP values, you must also
consider them scratch inside the procedure.


Post a followup to this message

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