This is the mail archive of the gcc-help@gcc.gnu.org mailing list for the GCC project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

Re: Re: Misalignment of local SSE variables in thread function



-----Original Message-----
From: Jonathan Kinsey <jon_kinsey@hotmail.com>
To: Tim Prince <tprince@myrealbox.com>
Date: Thu, 18 Jan 2007 15:37:48 +0000
Subject: Re: Misalignment of local SSE variables in thread function

Tim Prince wrote:
> This is my original point, even though your gcc function receives a
> mis-aligned stack, with normal options, and correctly built binutils, it
> should pass an aligned stack to its callee.

This isn't the case here, the only stack alignment is done in main().
I'm using binutils 2.16 if that helps.

___________________________________________
I suppose it helps a little, because broken binutils I have seen had older versions than that.  Somewhere along the line, if you said what environment you were using, I missed it.  It looks like others have figured out you were using mingw32, with which I have relatively little experience.  I haven't looked to see whether mingw binutils is generally built with only 4-byte alignment support, as cygwin used to be.  Not only did that break SSE, it made doubles slow.
Tim Prince


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]