From: nakata AT ccm DOT cl DOT nec DOT co DOT jp (Toshiyuki Nakata) Subject: Re: Support for malign-double? 22 Aug 1998 08:21:23 -0700 Message-ID: <199808220210.LAA13983.cygnus.gnu-win32@csls3.csl.cl.nec.co.jp> References: <54f67881 DOT 35dd1485 AT aol DOT com> Reply-To: Toshiyuki Nakata To: N8TM AT aol DOT com Cc: nakata AT csl DOT cl DOT nec DOT co DOT jp, gnu-win32 AT cygnus DOT com Hello: Thank you very much for your comments. ; In a message dated 8/20/98 4:13:18 PM Pacific Daylight Time, ; nakata AT csl DOT cl DOT nec DOT co DOT jp writes: ; ; > linux performance is ; > about 20% better for floating point intensive application. ; > ; You'd have to study harder than I'm willing to do to figure out which ; alignments are controlled by -malign-double, which are at the discretion of ; the OS or the math library, and which are controlled by the compiler in which ; version. It appears that linux-gnulibc1 aligns many local variables, ; including register spills, which cygwin32 does not. One of the effects I have ; observed is that -Os may be faster than -O2 on a P-Pro running certain code on ; cygwin32, where the two are about equal on a P2 on cygwin32, and -O2 may be ; faster on linux. My conclusion is that -O2 spills more registers, which are ; stored with unpredictable alignment in cygwin32. I see. ; ; You must be running a P-Pro; data mis-alignment on the P-Pro can slow it down ; by a factor of 2 or 3 when there are L1 data cache misses, while I've never It is a PentiumII.. ; been able to slow the P2 down by more than 50% for data cache misses. But, ; since you mention 20%, that's a typical penalty on the P2 for failing to use ; the p2align feature of current egcs. That, however, is the same on linux or ; cygwin32, if you install the same compiler and gas on each. Both are from (egcs-1.0.2 release)... Best Regards Toshiyuki Nakata - For help on using this list (especially unsubscribing), send a message to "gnu-win32-request AT cygnus DOT com" with one line of text: "help".