This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
Re: [i386] Document -mmmx, -msse, and -msse2.
- To: gcc-patches at gcc dot gnu dot org
- Subject: Re: [i386] Document -mmmx, -msse, and -msse2.
- From: Kelley Cook <Kelley dot Cook at home dot com>
- Date: Mon, 30 Apr 2001 12:41:00 -0400 (EDT)
- References: <200104301551.f3UFp9E20209@ahmlir1.mail.eds.com>
Sorry, I dropped a hunk in the previous patch. Full patch reincluded.
Passed "make info"
Kelley Cook <no check-in privileges>
2001-04-30 16:34:33 2001 Kelley Cook <2elley.cook@home.com>
* invoke.texi: Document -mmx, -msse, msse2
--- invoke.texi.orig Mon Apr 30 11:29:30 2001
+++ invoke.texi Mon Apr 30 12:34:33 2001
@@ -460,7 +460,7 @@
@gccoptlist{
-mcpu=@var{cpu type} -march=@var{cpu type} @gol
-mintel-syntax -mieee-fp -mno-fancy-math-387 @gol
--mno-fp-ret-in-387 -msoft-float -msvr3-shlib @gol
+-mno-fp-ret-in-387 -mmmx -msse -msse2 -msoft-float -msvr3-shlib @gol
-mno-wide-multiply -mrtd -malign-double @gol
-malign-jumps=@var{num} -malign-loops=@var{num} @gol
-malign-functions=@var{num} -mpreferred-stack-boundary=@var{num} @gol
@@ -6712,6 +6712,23 @@
generating those instructions. This option is the default on FreeBSD.
As of revision 2.6.1, these instructions are not generated unless you
also use the @samp{-funsafe-math-optimizations} switch.
+
+@item -mmmx
+@itemx -mno-mmx
+Allow the compiler to use MMX opcodes and registers. These vectorized
+integer instructions were originally introduced with the Pentium II.
+
+@item -msse
+@itemx -mno-sse
+Allow the compiler to use SSE opcodes and registers. These vectorized
+integer and single precision floating point opcodes were originally
+introduced with the Pentium III. This option implies @samp{-mmmx}.
+
+@item -msse2
+@itemx -mno-sse2
+Allow the compiler to use SSE2 opcodes and registers. These vectorized
+double precision opcodes were originally introduced with the Pentium 4.
+This option implies @samp{-mmmx} and @samp{-msse}.
@item -malign-double
@itemx -mno-align-double