i386.c (ix86_fpmath, [...]): New.

Fri Dec 14 12:05:14 CET 2001  Jan Hubicka  <jh@suse.cz>

	* i386.c (ix86_fpmath, ix86_fpmath_string): New.
	(override_option): Set ix86_fpmath.
	* i386.h (MASK_MIX_SSE_I387): Remove.
	(TARGET_SSE_MATH): New.
	(TARGET_MIX_SSE_I387): Use ix86_fpmath.
	(TARGET_SWITCHES): Remove "mix-sse-i387".
	(fpmath_unit): New enum.
	(ix86_fpmath, ix86_fpmath_string): Declare.
	* i386.md (swapsf): Fix condition.
	(add?f, sub?f, mul?f, div?f, sqrt?f, min?f): Use TARGET_SSE_MATH.
	(fp_?f_*_nosse): New.
	(fp_*): Use TARGET_SSE_MATH.
	* invoke.texi (-mfpmath): Document.
	(-msse2): Add.

From-SVN: r47999

1 files changed, 46 insertions, 2 deletions

diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 91fe9bc..03def55 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -473,12 +473,12 @@ in the following sections.
 
 @emph{i386 and x86-64 Options}
 @gccoptlist{
--mcpu=@var{cpu-type}  -march=@var{cpu-type} @gol
+-mcpu=@var{cpu-type}  -march=@var{cpu-type} -mfpmath=@var{unit} @gol
 -mintel-syntax -mieee-fp  -mno-fancy-math-387 @gol
 -mno-fp-ret-in-387  -msoft-float  -msvr3-shlib @gol
 -mno-wide-multiply  -mrtd  -malign-double @gol
 -mpreferred-stack-boundary=@var{num} @gol
--mmmx  -msse  -m3dnow @gol
+-mmmx  -msse -msse2 -msse-math -m3dnow @gol
 -mthreads  -mno-align-stringops  -minline-all-stringops @gol
 -mpush-args  -maccumulate-outgoing-args  -m128bit-long-double @gol
 -m96bit-long-double  -mregparm=@var{num}  -momit-leaf-frame-pointer @gol
@@ -7513,6 +7513,48 @@ These options are synonyms for @option{-mcpu=i386}, @option{-mcpu=i486},
 @option{-mcpu=pentium}, and @option{-mcpu=pentiumpro} respectively.
 These synonyms are deprecated.
 
+@item -mfpmath=@var{unit}
+@opindex march
+generate floating point arithmetics for selected unit @var{unit}.  the choices
+for @var{unit} are:
+
+@table @samp
+@item 387
+Use the standard 387 floating point coprocessor present majority of chips and
+emulated otherwise.  Code compiled with this option will run almost everywhere.
+The temporary results are computed in 80bit precesion instead of precision
+specified by the type resulting in slightly different results compared to most
+of other chips. See @option{-ffloat-store} for more detailed description.
+
+This is the default choice for i386 compiler.
+
+@item sse
+Use scalar floating point instructions present in the SSE instruction set.
+This instruction set is supported by Pentium3 and newer chips, in the AMD line
+by Athlon-4, Athlon-xp and Athlon-mp chips.  The earlier version of SSE
+instruction set supports only single precision arithmetics, thus the double and
+extended precision arithmetics is still done using 387.  Later version, present
+only in Pentium4 and the future AMD x86-64 chips supports double precision
+arithmetics too.
+
+For i387 you need to use @option{-march=@var{cpu-type}}, @option{-msse} or
+@option{-msse2} switches to enable SSE extensions and make this option
+effective.  For x86-64 compiler, these extensions are enabled by default.
+
+The resulting code should be considerably faster in majority of cases and avoid
+the numerical instability problems of 387 code, but may break some existing
+code that expects temporaries to be 80bit.
+
+This is the default choice for x86-64 compiler.
+
+@item sse,387
+Attempt to utilize both instruction sets at once.  This effectivly double the
+amount of available registers and on chips with separate execution units for
+387 and SSE the execution resources too.  Use this option with care, as it is
+still experimental, because gcc register allocator does not model separate
+functional units well resulting in instable performance.
+@end table
+
 @item -mintel-syntax
 @opindex mintel-syntax
 Emit assembly using Intel syntax opcodes instead of AT&T syntax.
@@ -7663,6 +7705,8 @@ preferred alignment to @option{-mpreferred-stack-boundary=2}.
 @itemx -mno-mmx
 @item -msse
 @itemx -mno-sse
+@item -msse2
+@itemx -mno-sse2
 @item -m3dnow
 @itemx -mno-3dnow
 @opindex mmmx