Add ARM assembly optimizations

This was my first time writing ARM assembly, so it may not be the
best; but they're still significantly faster than the optimized
C versions[1] of the functions replace.

An knowledgable ARM coder should be able to make better
optimizations, but nobody has done so for FLAC yet (at least not
publicly, to my knowledge), so I decided to take a stab at it.

Also tweaked configure.in a bit to better support
cross-compilation.  no longer enable 3dnow, sse, or altivec
optimizations unless our CPU supports them.  (note: sse and
3dnow are supported by 64-bit chips, but the code is currently
only optimized for 32-bit sse and 3dnow).

FLAC__fixed_restore_signal_asm_arm and
FLAC__lpc_restore_signal_asm_arm are pretty well-tested from
tracks in my music collection.  I do not think I have any music
that can exersises FLAC__lpc_restore_signal_asm_arm_wide
(especially the 64-bit ASR macro).

These optimizations changes result in an approximately 20%
reduction in decoding time on my 3rd generation ipod (running
ipodlinux).

[1] - I still have them at hand, but they're not probably not
worth it for the non-ASM optimized architectures.

1 files changed, 13 insertions, 6 deletions

diff --git a/configure.in b/configure.in
index 7dce4e77..bf48c4d7 100644
--- a/configure.in
+++ b/configure.in
@@ -61,6 +61,11 @@ case "$host_cpu" in
                 AC_DEFINE(FLAC__CPU_PPC)
                 AH_TEMPLATE(FLAC__CPU_PPC, [define if building for PowerPC])
                 ;;
+        arm)
+                cpu_arm=true
+                AC_DEFINE(FLAC__CPU_ARM)
+                AH_TEMPLATE(FLAC__CPU_ARM, [define if building for ARM])
+                ;;
         sparc)
                 cpu_sparc=true
                 AC_DEFINE(FLAC__CPU_SPARC)
@@ -69,6 +74,7 @@ case "$host_cpu" in
 esac
 AM_CONDITIONAL(FLaC__CPU_IA32, test "x$cpu_ia32" = xtrue)
 AM_CONDITIONAL(FLaC__CPU_PPC, test "x$cpu_ppc" = xtrue)
+AM_CONDITIONAL(FLaC__CPU_ARM, test "x$cpu_arm" = xtrue)
 AM_CONDITIONAL(FLaC__CPU_SPARC, test "x$cpu_sparc" = xtrue)
 case "$host" in
         i386-*-openbsd3.[[0-3]]) OBJ_FORMAT=aoutb ;;
@@ -119,8 +125,8 @@ AC_HELP_STRING([--enable-sse], [Enable SSE support by asserting that the OS supp
         no)  sse_os=false ;;
         *) AC_MSG_ERROR(bad value ${enableval} for --enable-sse) ;;
 esac],[sse_os=false])
-AM_CONDITIONAL(FLaC__SSE_OS, test "x$sse_os" = xtrue)
-if test "x$sse_os" = xtrue ; then
+AM_CONDITIONAL(FLaC__SSE_OS, test "x$sse_os" = xtrue && test "x$cpu_ia32" = xtrue)
+if test "x$sse_os" = xtrue && test "x$cpu_ia32" = xtrue; then
 AC_DEFINE(FLAC__SSE_OS)
 AH_TEMPLATE(FLAC__SSE_OS, [define if your operating system supports SSE instructions])
 fi
@@ -132,8 +138,8 @@ AC_HELP_STRING([--disable-3dnow], [Disable 3DNOW! optimizations]),
         no)  use_3dnow=false ;;
         *) AC_MSG_ERROR(bad value ${enableval} for --enable-3dnow) ;;
 esac],[use_3dnow=true])
-AM_CONDITIONAL(FLaC__USE_3DNOW, test "x$use_3dnow" = xtrue)
-if test "x$use_3dnow" = xtrue ; then
+AM_CONDITIONAL(FLaC__USE_3DNOW, test "x$use_3dnow" = xtrue && test "x$cpu_ia32" = xtrue)
+if test "x$use_3dnow" = xtrue && test "x$cpu_ia32" = xtrue; then
 AC_DEFINE(FLAC__USE_3DNOW)
 AH_TEMPLATE(FLAC__USE_3DNOW, [define to enable use of 3Dnow! instructions])
 fi
@@ -145,8 +151,8 @@ AC_HELP_STRING([--disable-altivec], [Disable Altivec optimizations]),
         no)  use_altivec=false ;;
         *) AC_MSG_ERROR(bad value ${enableval} for --enable-altivec) ;;
 esac],[use_altivec=true])
-AM_CONDITIONAL(FLaC__USE_ALTIVEC, test "x$use_altivec" = xtrue)
-if test "x$use_altivec" = xtrue ; then
+AM_CONDITIONAL(FLaC__USE_ALTIVEC, test "x$use_altivec" = xtrue && test "x$cpu_ppc" = xtrue)
+if test "x$use_altivec" = xtrue && test "x$cpu_ppc" = xtrue; then
 AC_DEFINE(FLAC__USE_ALTIVEC)
 AH_TEMPLATE(FLAC__USE_ALTIVEC, [define to enable use of Altivec instructions])
 fi
@@ -281,6 +287,7 @@ AC_CONFIG_FILES([ \
         Makefile \
         src/Makefile \
         src/libFLAC/Makefile \
+        src/libFLAC/arm/Makefile \
         src/libFLAC/ia32/Makefile \
         src/libFLAC/ppc/Makefile \
         src/libFLAC/ppc/as/Makefile \