Hello!
This patch splits SSE specific part of set_fast_math to its own
function, decorated with "fxsr,sse" target attribute. This way, we can
avoid compiling the whole file with -msse that implies generation of
possibly unsupported CMOVE insns.
Additionally, we can now use generic t-crtfm makefile fragment.
2015-05-22 Uros Bizjak <ubiz...@gmail.com>
* config.host (i[34567]-*-*, x86_64-*-*): Add t-crtfm instead of
i386/t-crtfm to tmake_file.
* config/i386/crtfastmath.c (set_fast_math_sse): New function.
(set_fast_math): Use set_fast_math_sse for SSE targets.
* config/i386/t-crtfm: Remove.
Bootstrapped, regression tested on x86_64-linux-gnu {,-m32} and
committed to mainline SVN.
Uros.
Index: config.host
===================================================================
--- config.host (revision 223519)
+++ config.host (working copy)
@@ -553,12 +553,12 @@ hppa*-*-openbsd*)
tmake_file="$tmake_file pa/t-openbsd"
;;
i[34567]86-*-darwin*)
- tmake_file="$tmake_file i386/t-crtpc i386/t-crtfm"
+ tmake_file="$tmake_file i386/t-crtpc t-crtfm"
tm_file="$tm_file i386/darwin-lib.h"
extra_parts="$extra_parts crtprec32.o crtprec64.o crtprec80.o
crtfastmath.o"
;;
x86_64-*-darwin*)
- tmake_file="$tmake_file i386/t-crtpc i386/t-crtfm"
+ tmake_file="$tmake_file i386/t-crtpc t-crtfm"
tm_file="$tm_file i386/darwin-lib.h"
extra_parts="$extra_parts crtprec32.o crtprec64.o crtprec80.o
crtfastmath.o"
;;
@@ -595,24 +595,24 @@ x86_64-*-openbsd*)
;;
i[34567]86-*-linux*)
extra_parts="$extra_parts crtprec32.o crtprec64.o crtprec80.o
crtfastmath.o"
- tmake_file="${tmake_file} i386/t-crtpc i386/t-crtfm i386/t-crtstuff
t-dfprules"
+ tmake_file="${tmake_file} i386/t-crtpc t-crtfm i386/t-crtstuff
t-dfprules"
tm_file="${tm_file} i386/elf-lib.h"
md_unwind_header=i386/linux-unwind.h
;;
i[34567]86-*-kfreebsd*-gnu | i[34567]86-*-knetbsd*-gnu | i[34567]86-*-gnu* |
i[34567]86-*-kopensolaris*-gnu)
extra_parts="$extra_parts crtprec32.o crtprec64.o crtprec80.o
crtfastmath.o"
- tmake_file="${tmake_file} i386/t-crtpc i386/t-crtfm i386/t-crtstuff
t-dfprules"
+ tmake_file="${tmake_file} i386/t-crtpc t-crtfm i386/t-crtstuff
t-dfprules"
tm_file="${tm_file} i386/elf-lib.h"
;;
x86_64-*-linux*)
extra_parts="$extra_parts crtprec32.o crtprec64.o crtprec80.o
crtfastmath.o"
- tmake_file="${tmake_file} i386/t-crtpc i386/t-crtfm i386/t-crtstuff
t-dfprules"
+ tmake_file="${tmake_file} i386/t-crtpc t-crtfm i386/t-crtstuff
t-dfprules"
tm_file="${tm_file} i386/elf-lib.h"
md_unwind_header=i386/linux-unwind.h
;;
x86_64-*-kfreebsd*-gnu | x86_64-*-knetbsd*-gnu)
extra_parts="$extra_parts crtprec32.o crtprec64.o crtprec80.o
crtfastmath.o"
- tmake_file="${tmake_file} i386/t-crtpc i386/t-crtfm i386/t-crtstuff
t-dfprules"
+ tmake_file="${tmake_file} i386/t-crtpc t-crtfm i386/t-crtstuff
t-dfprules"
tm_file="${tm_file} i386/elf-lib.h"
;;
i[34567]86-pc-msdosdjgpp*)
@@ -628,7 +628,7 @@ i[34567]86-*-rtems*)
extra_parts="$extra_parts crti.o crtn.o"
;;
i[34567]86-*-solaris2* | x86_64-*-solaris2.1[0-9]*)
- tmake_file="$tmake_file i386/t-crtpc i386/t-crtfm"
+ tmake_file="$tmake_file i386/t-crtpc t-crtfm"
extra_parts="$extra_parts crtprec32.o crtprec64.o crtprec80.o
crtfastmath.o"
tm_file="${tm_file} i386/elf-lib.h"
md_unwind_header=i386/sol2-unwind.h
@@ -652,7 +652,7 @@ i[34567]86-*-cygwin*)
else
tmake_dlldir_file="i386/t-dlldir-x"
fi
- tmake_file="${tmake_file} ${tmake_eh_file} ${tmake_dlldir_file}
i386/t-slibgcc-cygming i386/t-cygming i386/t-cygwin i386/t-crtfm i386/t-chkstk
t-dfprules"
+ tmake_file="${tmake_file} ${tmake_eh_file} ${tmake_dlldir_file}
i386/t-slibgcc-cygming i386/t-cygming i386/t-cygwin t-crtfm i386/t-chkstk
t-dfprules"
;;
x86_64-*-cygwin*)
extra_parts="crtbegin.o crtbeginS.o crtend.o crtfastmath.o"
@@ -672,7 +672,7 @@ x86_64-*-cygwin*)
tmake_dlldir_file="i386/t-dlldir-x"
fi
# FIXME - dj - t-chkstk used to be in here, need a 64-bit version of
that
- tmake_file="${tmake_file} ${tmake_eh_file} ${tmake_dlldir_file}
i386/t-slibgcc-cygming i386/t-cygming i386/t-cygwin i386/t-crtfm t-dfprules
i386/t-chkstk"
+ tmake_file="${tmake_file} ${tmake_eh_file} ${tmake_dlldir_file}
i386/t-slibgcc-cygming i386/t-cygming i386/t-cygwin t-crtfm t-dfprules
i386/t-chkstk"
;;
i[34567]86-*-mingw*)
extra_parts="crtbegin.o crtend.o crtfastmath.o"
@@ -700,7 +700,7 @@ i[34567]86-*-mingw*)
else
tmake_dlldir_file="i386/t-dlldir-x"
fi
- tmake_file="${tmake_file} ${tmake_eh_file} ${tmake_dlldir_file}
i386/t-slibgcc-cygming i386/t-cygming i386/t-mingw32 i386/t-crtfm i386/t-chkstk
t-dfprules"
+ tmake_file="${tmake_file} ${tmake_eh_file} ${tmake_dlldir_file}
i386/t-slibgcc-cygming i386/t-cygming i386/t-mingw32 t-crtfm i386/t-chkstk
t-dfprules"
;;
x86_64-*-mingw*)
case ${target_thread_file} in
@@ -723,7 +723,7 @@ x86_64-*-mingw*)
else
tmake_dlldir_file="i386/t-dlldir-x"
fi
- tmake_file="${tmake_file} ${tmake_eh_file} ${tmake_dlldir_file}
i386/t-slibgcc-cygming i386/t-cygming i386/t-mingw32 t-dfprules i386/t-crtfm
i386/t-chkstk"
+ tmake_file="${tmake_file} ${tmake_eh_file} ${tmake_dlldir_file}
i386/t-slibgcc-cygming i386/t-cygming i386/t-mingw32 t-dfprules t-crtfm
i386/t-chkstk"
extra_parts="$extra_parts crtbegin.o crtend.o crtfastmath.o"
if test x$enable_vtable_verify = xyes; then
extra_parts="$extra_parts vtv_start.o vtv_end.o
vtv_start_preinit.o vtv_end_preinit.o"
Index: config/i386/t-crtfm
===================================================================
--- config/i386/t-crtfm (revision 223519)
+++ config/i386/t-crtfm (working copy)
@@ -1,4 +0,0 @@
-# This is an endfile, Use -minline-all-stringops to ensure
-# that __builtin_memset doesn't refer to the lib function memset().
-crtfastmath.o: $(srcdir)/config/i386/crtfastmath.c
- $(gcc_compile) -mfxsr -msse -c $<
Index: config/i386/crtfastmath.c
===================================================================
--- config/i386/crtfastmath.c (revision 223519)
+++ config/i386/crtfastmath.c (working copy)
@@ -29,15 +29,57 @@
/* All 64-bit targets have SSE and DAZ;
only check them explicitly for 32-bit ones. */
#include "cpuid.h"
-#endif
-static void __attribute__((constructor))
-#ifndef __x86_64__
+__attribute__ ((target("fxsr,sse")))
+static void
/* The i386 ABI only requires 4-byte stack alignment, so this is necessary
to make sure the fxsave struct gets correct alignment.
See PR27537 and PR28621. */
__attribute__ ((force_align_arg_pointer))
+set_fast_math_sse (unsigned int edx)
+{
+ unsigned int mxcsr;
+
+ if (edx & bit_FXSAVE)
+ {
+ /* Check if DAZ is available. */
+ struct
+ {
+ unsigned short cwd;
+ unsigned short swd;
+ unsigned short twd;
+ unsigned short fop;
+ unsigned int fip;
+ unsigned int fcs;
+ unsigned int foo;
+ unsigned int fos;
+ unsigned int mxcsr;
+ unsigned int mxcsr_mask;
+ unsigned int st_space[32];
+ unsigned int xmm_space[32];
+ unsigned int padding[56];
+ } __attribute__ ((aligned (16))) fxsave;
+
+ /* This is necessary since some implementations of FXSAVE
+ do not modify reserved areas within the image. */
+ fxsave.mxcsr_mask = 0;
+
+ __builtin_ia32_fxsave (&fxsave);
+
+ mxcsr = fxsave.mxcsr;
+
+ if (fxsave.mxcsr_mask & MXCSR_DAZ)
+ mxcsr |= MXCSR_DAZ;
+ }
+ else
+ mxcsr = __builtin_ia32_stmxcsr ();
+
+ mxcsr |= MXCSR_FTZ;
+ __builtin_ia32_ldmxcsr (mxcsr);
+}
#endif
+
+static void __attribute__((constructor))
set_fast_math (void)
{
#ifndef __x86_64__
@@ -47,46 +89,7 @@ set_fast_math (void)
return;
if (edx & bit_SSE)
- {
- unsigned int mxcsr;
-
- if (edx & bit_FXSAVE)
- {
- /* Check if DAZ is available. */
- struct
- {
- unsigned short cwd;
- unsigned short swd;
- unsigned short twd;
- unsigned short fop;
- unsigned int fip;
- unsigned int fcs;
- unsigned int foo;
- unsigned int fos;
- unsigned int mxcsr;
- unsigned int mxcsr_mask;
- unsigned int st_space[32];
- unsigned int xmm_space[32];
- unsigned int padding[56];
- } __attribute__ ((aligned (16))) fxsave;
-
- /* This is necessary since some implementations of FXSAVE
- do not modify reserved areas within the image. */
- fxsave.mxcsr_mask = 0;
-
- __builtin_ia32_fxsave (&fxsave);
-
- mxcsr = fxsave.mxcsr;
-
- if (fxsave.mxcsr_mask & MXCSR_DAZ)
- mxcsr |= MXCSR_DAZ;
- }
- else
- mxcsr = __builtin_ia32_stmxcsr ();
-
- mxcsr |= MXCSR_FTZ;
- __builtin_ia32_ldmxcsr (mxcsr);
- }
+ set_fast_math_sse (edx);
#else
unsigned int mxcsr = __builtin_ia32_stmxcsr ();
mxcsr |= MXCSR_DAZ | MXCSR_FTZ;
