Imported Upstream version 4.2-build2006upstream/4.2-build2006upstream

7 files changed, 3515 insertions, 0 deletions

diff --git a/setup/Linux/arm/Makefile.osscore.arm b/setup/Linux/arm/Makefile.osscore.arm
new file mode 100644
index 0000000..ffe2d3f
--- /dev/null
+++ b/setup/Linux/arm/Makefile.osscore.arm
@@ -0,0 +1,17 @@
+
+ifneq ($(KERNELRELEASE),)
+
+	obj-m := osscore.o
+
+else
+
+	PWD := $(shell pwd)
+endif
+
+default:
+	@echo "static const char __oss_compile_vermagic[];" > ubuntu_version_hack.inc
+	$(MAKE) -C $(KERNELDIR) M=$(PWD) modules
+
+clean:
+	rm -f *.o *.ko *.mod.c *.mod.o .*.cmd core core.* x y z
+	rm -rf .tmp_versions
diff --git a/setup/Linux/arm/Makefile.tmpl.arm b/setup/Linux/arm/Makefile.tmpl.arm
new file mode 100644
index 0000000..a8f0df2
--- /dev/null
+++ b/setup/Linux/arm/Makefile.tmpl.arm
@@ -0,0 +1,21 @@
+include /etc/oss.conf
+
+EXTRA_CFLAGS += -I${OSSLIBDIR}/include/internals -I${OSSLIBDIR}/include/sys
+
+ifneq ($(KERNELRELEASE),)
+
+	obj-m := MODNAME.o
+
+else
+
+	#KERNELDIR ?= /lib/modules/$(shell uname -r)/build
+	PWD := $(shell pwd)
+
+default:
+	$(MAKE) -C $(KERNELDIR) M=$(PWD) modules
+
+endif
+
+clean:
+	@rm -f *.o *.ko *.mod.c *.mod.o .*.cmd core core.* x y z
+	@rm -rf .tmp_versions
diff --git a/setup/Linux/arm/bpabi.S b/setup/Linux/arm/bpabi.S
new file mode 100644
index 0000000..1f08346
--- /dev/null
+++ b/setup/Linux/arm/bpabi.S
@@ -0,0 +1,119 @@
+/* Miscellaneous BPABI functions.
+
+   Copyright (C) 2003, 2004, 2007  Free Software Foundation, Inc.
+   Contributed by CodeSourcery, LLC.
+
+   This file is free software; you can redistribute it and/or modify it
+   under the terms of the GNU General Public License as published by the
+   Free Software Foundation; either version 2, or (at your option) any
+   later version.
+
+   In addition to the permissions in the GNU General Public License, the
+   Free Software Foundation gives you unlimited permission to link the
+   compiled version of this file into combinations with other programs,
+   and to distribute those combinations without any restriction coming
+   from the use of this file.  (The General Public License restrictions
+   do apply in other respects; for example, they cover modification of
+   the file, and distribution when not linked into a combine
+   executable.)
+
+   This file is distributed in the hope that it will be useful, but
+   WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+   General Public License for more details.
+
+   You should have received a copy of the GNU General Public License
+   along with this program; see the file COPYING.  If not, write to
+   the Free Software Foundation, 51 Franklin Street, Fifth Floor,
+   Boston, MA 02110-1301, USA.  */
+
+#ifdef __ARMEB__
+#define xxh r0
+#define xxl r1
+#define yyh r2
+#define yyl r3
+#else
+#define xxh r1
+#define xxl r0
+#define yyh r3
+#define yyl r2
+#endif	
+	
+#ifdef L_aeabi_lcmp
+
+ARM_FUNC_START aeabi_lcmp
+	cmp	xxh, yyh
+	do_it	lt
+	movlt	r0, #-1
+	do_it	gt
+	movgt	r0, #1
+	do_it	ne
+	RETc(ne)
+	subs	r0, xxl, yyl
+	do_it	lo
+	movlo	r0, #-1
+	do_it	hi
+	movhi	r0, #1
+	RET
+	FUNC_END aeabi_lcmp
+
+#endif /* L_aeabi_lcmp */
+	
+#ifdef L_aeabi_ulcmp
+
+ARM_FUNC_START aeabi_ulcmp
+	cmp	xxh, yyh
+	do_it	lo
+	movlo	r0, #-1
+	do_it	hi
+	movhi	r0, #1
+	do_it	ne
+	RETc(ne)
+	cmp	xxl, yyl
+	do_it	lo
+	movlo	r0, #-1
+	do_it	hi
+	movhi	r0, #1
+	do_it	eq
+	moveq	r0, #0
+	RET
+	FUNC_END aeabi_ulcmp
+
+#endif /* L_aeabi_ulcmp */
+
+#ifdef L_aeabi_ldivmod
+
+ARM_FUNC_START aeabi_ldivmod
+	sub sp, sp, #8
+#if defined(__thumb2__)
+	mov ip, sp
+	push {ip, lr}
+#else
+	do_push {sp, lr}
+#endif
+	bl SYM(__gnu_ldivmod_helper) __PLT__
+	ldr lr, [sp, #4]
+	add sp, sp, #8
+	do_pop {r2, r3}
+	RET
+	
+#endif /* L_aeabi_ldivmod */
+
+#ifdef L_aeabi_uldivmod
+
+ARM_FUNC_START aeabi_uldivmod
+	sub sp, sp, #8
+#if defined(__thumb2__)
+	mov ip, sp
+	push {ip, lr}
+#else
+	do_push {sp, lr}
+#endif
+	bl SYM(__gnu_uldivmod_helper) __PLT__
+	ldr lr, [sp, #4]
+	add sp, sp, #8
+	do_pop {r2, r3}
+	RET
+	
+#endif /* L_aeabi_divmod */
+	
diff --git a/setup/Linux/arm/bpabi.c b/setup/Linux/arm/bpabi.c
new file mode 100644
index 0000000..7ff8e2a
--- /dev/null
+++ b/setup/Linux/arm/bpabi.c
@@ -0,0 +1,375 @@
+/* Miscellaneous BPABI functions.
+
+   Copyright (C) 2003, 2004  Free Software Foundation, Inc.
+   Contributed by CodeSourcery, LLC.
+
+   This file is free software; you can redistribute it and/or modify it
+   under the terms of the GNU General Public License as published by the
+   Free Software Foundation; either version 2, or (at your option) any
+   later version.
+
+   In addition to the permissions in the GNU General Public License, the
+   Free Software Foundation gives you unlimited permission to link the
+   compiled version of this file into combinations with other programs,
+   and to distribute those combinations without any restriction coming
+   from the use of this file.  (The General Public License restrictions
+   do apply in other respects; for example, they cover modification of
+   the file, and distribution when not linked into a combine
+   executable.)
+
+   This file is distributed in the hope that it will be useful, but
+   WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+   General Public License for more details.
+
+   You should have received a copy of the GNU General Public License
+   along with this program; see the file COPYING.  If not, write to
+   the Free Software Foundation, 51 Franklin Street, Fifth Floor,
+   Boston, MA 02110-1301, USA.  */
+
+extern long long __divdi3 (long long, long long);
+extern unsigned long long __udivdi3 (unsigned long long, 
+				     unsigned long long);
+extern long long __gnu_ldivmod_helper (long long, long long, long long *);
+extern unsigned long long __gnu_uldivmod_helper (unsigned long long, 
+						 unsigned long long, 
+						 unsigned long long *);
+#define UQItype unsigned char
+#define DWtype long long
+#define UDItype unsigned long long
+#define Wtype int
+#define USItype		unsigned int
+
+#include "longlong.h"
+
+const UQItype __clz_tab[256] =
+{
+  0,1,2,2,3,3,3,3,4,4,4,4,4,4,4,4,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,
+  6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,
+  7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,
+  7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,
+  8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,
+  8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,
+  8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,
+  8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8
+};
+
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+  __asm__ ("adds	%1, %4, %5\n\tadc	%0, %2, %3"		\
+	   : "=r" ((USItype) (sh)),					\
+	     "=&r" ((USItype) (sl))					\
+	   : "%r" ((USItype) (ah)),					\
+	     "rI" ((USItype) (bh)),					\
+	     "%r" ((USItype) (al)),					\
+	     "rI" ((USItype) (bl)) __CLOBBER_CC)
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+  __asm__ ("subs	%1, %4, %5\n\tsbc	%0, %2, %3"		\
+	   : "=r" ((USItype) (sh)),					\
+	     "=&r" ((USItype) (sl))					\
+	   : "r" ((USItype) (ah)),					\
+	     "rI" ((USItype) (bh)),					\
+	     "r" ((USItype) (al)),					\
+	     "rI" ((USItype) (bl)) __CLOBBER_CC)
+#define umul_ppmm(xh, xl, a, b) \
+{register USItype __t0, __t1, __t2;					\
+  __asm__ ("%@ Inlined umul_ppmm\n"					\
+	   "	mov	%2, %5, lsr #16\n"				\
+	   "	mov	%0, %6, lsr #16\n"				\
+	   "	bic	%3, %5, %2, lsl #16\n"				\
+	   "	bic	%4, %6, %0, lsl #16\n"				\
+	   "	mul	%1, %3, %4\n"					\
+	   "	mul	%4, %2, %4\n"					\
+	   "	mul	%3, %0, %3\n"					\
+	   "	mul	%0, %2, %0\n"					\
+	   "	adds	%3, %4, %3\n"					\
+	   "	addcs	%0, %0, #65536\n"				\
+	   "	adds	%1, %1, %3, lsl #16\n"				\
+	   "	adc	%0, %0, %3, lsr #16"				\
+	   : "=&r" ((USItype) (xh)),					\
+	     "=r" ((USItype) (xl)),					\
+	     "=&r" (__t0), "=&r" (__t1), "=r" (__t2)			\
+	   : "r" ((USItype) (a)),					\
+	     "r" ((USItype) (b)) __CLOBBER_CC );}
+#define UMUL_TIME 20
+#define UDIV_TIME 100
+
+#if 1 	/* Big endian */
+  struct DWstruct {Wtype high, low;};
+#else
+  struct DWstruct {Wtype low, high;};
+#endif
+
+/* We need this union to unpack/pack DImode values, since we don't have
+   any arithmetic yet.  Incoming DImode parameters are stored into the
+   `ll' field, and the unpacked result is read from the struct `s'.  */
+
+typedef union
+{
+  struct DWstruct s;
+  DWtype ll;
+} DWunion;
+
+UDWtype
+__udivmoddi4 (UDWtype n, UDWtype d, UDWtype *rp)
+{
+  const DWunion nn = {.ll = n};
+  const DWunion dd = {.ll = d};
+  DWunion rr;
+  UWtype d0, d1, n0, n1, n2;
+  UWtype q0, q1;
+  UWtype b, bm;
+
+  d0 = dd.s.low;
+  d1 = dd.s.high;
+  n0 = nn.s.low;
+  n1 = nn.s.high;
+
+#if !UDIV_NEEDS_NORMALIZATION
+  if (d1 == 0)
+    {
+      if (d0 > n1)
+	{
+	  /* 0q = nn / 0D */
+
+	  udiv_qrnnd (q0, n0, n1, n0, d0);
+	  q1 = 0;
+
+	  /* Remainder in n0.  */
+	}
+      else
+	{
+	  /* qq = NN / 0d */
+
+	  if (d0 == 0)
+	    d0 = 1 / d0;	/* Divide intentionally by zero.  */
+
+	  udiv_qrnnd (q1, n1, 0, n1, d0);
+	  udiv_qrnnd (q0, n0, n1, n0, d0);
+
+	  /* Remainder in n0.  */
+	}
+
+      if (rp != 0)
+	{
+	  rr.s.low = n0;
+	  rr.s.high = 0;
+	  *rp = rr.ll;
+	}
+    }
+
+#else /* UDIV_NEEDS_NORMALIZATION */
+
+  if (d1 == 0)
+    {
+      if (d0 > n1)
+	{
+	  /* 0q = nn / 0D */
+
+	  count_leading_zeros (bm, d0);
+
+	  if (bm != 0)
+	    {
+	      /* Normalize, i.e. make the most significant bit of the
+		 denominator set.  */
+
+	      d0 = d0 << bm;
+	      n1 = (n1 << bm) | (n0 >> (W_TYPE_SIZE - bm));
+	      n0 = n0 << bm;
+	    }
+
+	  udiv_qrnnd (q0, n0, n1, n0, d0);
+	  q1 = 0;
+
+	  /* Remainder in n0 >> bm.  */
+	}
+      else
+	{
+	  /* qq = NN / 0d */
+
+	  if (d0 == 0)
+	    d0 = 1 / d0;	/* Divide intentionally by zero.  */
+
+	  count_leading_zeros (bm, d0);
+
+	  if (bm == 0)
+	    {
+	      /* From (n1 >= d0) /\ (the most significant bit of d0 is set),
+		 conclude (the most significant bit of n1 is set) /\ (the
+		 leading quotient digit q1 = 1).
+
+		 This special case is necessary, not an optimization.
+		 (Shifts counts of W_TYPE_SIZE are undefined.)  */
+
+	      n1 -= d0;
+	      q1 = 1;
+	    }
+	  else
+	    {
+	      /* Normalize.  */
+
+	      b = W_TYPE_SIZE - bm;
+
+	      d0 = d0 << bm;
+	      n2 = n1 >> b;
+	      n1 = (n1 << bm) | (n0 >> b);
+	      n0 = n0 << bm;
+
+	      udiv_qrnnd (q1, n1, n2, n1, d0);
+	    }
+
+	  /* n1 != d0...  */
+
+	  udiv_qrnnd (q0, n0, n1, n0, d0);
+
+	  /* Remainder in n0 >> bm.  */
+	}
+
+      if (rp != 0)
+	{
+	  rr.s.low = n0 >> bm;
+	  rr.s.high = 0;
+	  *rp = rr.ll;
+	}
+    }
+#endif /* UDIV_NEEDS_NORMALIZATION */
+
+  else
+    {
+      if (d1 > n1)
+	{
+	  /* 00 = nn / DD */
+
+	  q0 = 0;
+	  q1 = 0;
+
+	  /* Remainder in n1n0.  */
+	  if (rp != 0)
+	    {
+	      rr.s.low = n0;
+	      rr.s.high = n1;
+	      *rp = rr.ll;
+	    }
+	}
+      else
+	{
+	  /* 0q = NN / dd */
+
+	  count_leading_zeros (bm, d1);
+	  if (bm == 0)
+	    {
+	      /* From (n1 >= d1) /\ (the most significant bit of d1 is set),
+		 conclude (the most significant bit of n1 is set) /\ (the
+		 quotient digit q0 = 0 or 1).
+
+		 This special case is necessary, not an optimization.  */
+
+	      /* The condition on the next line takes advantage of that
+		 n1 >= d1 (true due to program flow).  */
+	      if (n1 > d1 || n0 >= d0)
+		{
+		  q0 = 1;
+		  sub_ddmmss (n1, n0, n1, n0, d1, d0);
+		}
+	      else
+		q0 = 0;
+
+	      q1 = 0;
+
+	      if (rp != 0)
+		{
+		  rr.s.low = n0;
+		  rr.s.high = n1;
+		  *rp = rr.ll;
+		}
+	    }
+	  else
+	    {
+	      UWtype m1, m0;
+	      /* Normalize.  */
+
+	      b = W_TYPE_SIZE - bm;
+
+	      d1 = (d1 << bm) | (d0 >> b);
+	      d0 = d0 << bm;
+	      n2 = n1 >> b;
+	      n1 = (n1 << bm) | (n0 >> b);
+	      n0 = n0 << bm;
+
+	      udiv_qrnnd (q0, n1, n2, n1, d1);
+	      umul_ppmm (m1, m0, q0, d0);
+
+	      if (m1 > n1 || (m1 == n1 && m0 > n0))
+		{
+		  q0--;
+		  sub_ddmmss (m1, m0, m1, m0, d1, d0);
+		}
+
+	      q1 = 0;
+
+	      /* Remainder in (n1n0 - m1m0) >> bm.  */
+	      if (rp != 0)
+		{
+		  sub_ddmmss (n1, n0, n1, n0, m1, m0);
+		  rr.s.low = (n1 << b) | (n0 >> bm);
+		  rr.s.high = n1 >> bm;
+		  *rp = rr.ll;
+		}
+	    }
+	}
+    }
+
+  const DWunion ww = {{.low = q0, .high = q1}};
+  return ww.ll;
+}
+
+UDWtype
+__udivdi3 (UDWtype n, UDWtype d)
+{
+  return __udivmoddi4 (n, d, (UDWtype *) 0);
+}
+
+long long
+__divdi3 (DWtype u, DWtype v)
+{
+  Wtype c = 0;
+  DWunion uu = {.ll = u};
+  DWunion vv = {.ll = v};
+  DWtype w;
+
+  if (uu.s.high < 0)
+    c = ~c,
+    uu.ll = -uu.ll;
+  if (vv.s.high < 0)
+    c = ~c,
+    vv.ll = -vv.ll;
+
+  w = __udivmoddi4 (uu.ll, vv.ll, (UDWtype *) 0);
+  if (c)
+    w = -w;
+
+  return w;
+}
+
+long long
+__gnu_ldivmod_helper (long long a, 
+		      long long b, 
+		      long long *remainder)
+{
+  long long quotient;
+
+  quotient = __divdi3 (a, b);
+  *remainder = a - b * quotient;
+  return quotient;
+}
+
+unsigned long long
+__gnu_uldivmod_helper (unsigned long long a, 
+		       unsigned long long b,
+		       unsigned long long *remainder)
+{
+  unsigned long long quotient;
+
+  quotient = __udivdi3 (a, b);
+  *remainder = a - b * quotient;
+  return quotient;
+}
diff --git a/setup/Linux/arm/bpabi.h b/setup/Linux/arm/bpabi.h
new file mode 100644
index 0000000..a67f649
--- /dev/null
+++ b/setup/Linux/arm/bpabi.h
@@ -0,0 +1,125 @@
+/* Configuration file for ARM BPABI targets.
+   Copyright (C) 2004, 2005, 2007
+   Free Software Foundation, Inc.
+   Contributed by CodeSourcery, LLC   
+
+   This file is part of GCC.
+
+   GCC is free software; you can redistribute it and/or modify it
+   under the terms of the GNU General Public License as published
+   by the Free Software Foundation; either version 3, or (at your
+   option) any later version.
+
+   GCC is distributed in the hope that it will be useful, but WITHOUT
+   ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+   or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public
+   License for more details.
+
+   You should have received a copy of the GNU General Public License
+   along with GCC; see the file COPYING3.  If not see
+   <http://www.gnu.org/licenses/>.  */
+
+/* Use the AAPCS ABI by default.  */
+#define ARM_DEFAULT_ABI ARM_ABI_AAPCS
+
+/* Assume that AAPCS ABIs should adhere to the full BPABI.  */ 
+#define TARGET_BPABI (TARGET_AAPCS_BASED)
+
+/* BPABI targets use EABI frame unwinding tables.  */
+#define TARGET_UNWIND_INFO 1
+
+/* Section 4.1 of the AAPCS requires the use of VFP format.  */
+#undef  FPUTYPE_DEFAULT
+#define FPUTYPE_DEFAULT FPUTYPE_VFP
+
+/* TARGET_BIG_ENDIAN_DEFAULT is set in
+   config.gcc for big endian configurations.  */
+#if TARGET_BIG_ENDIAN_DEFAULT
+#define TARGET_ENDIAN_DEFAULT MASK_BIG_END
+#else
+#define TARGET_ENDIAN_DEFAULT 0
+#endif
+
+/* EABI targets should enable interworking by default.  */
+#undef  TARGET_DEFAULT
+#define TARGET_DEFAULT (MASK_INTERWORK | TARGET_ENDIAN_DEFAULT)
+
+/* The ARM BPABI functions return a boolean; they use no special
+   calling convention.  */
+#define FLOAT_LIB_COMPARE_RETURNS_BOOL(MODE, COMPARISON) TARGET_BPABI
+
+/* The BPABI integer comparison routines return { -1, 0, 1 }.  */
+#define TARGET_LIB_INT_CMP_BIASED !TARGET_BPABI
+
+/* Tell the assembler to build BPABI binaries.  */
+#undef  SUBTARGET_EXTRA_ASM_SPEC
+#define SUBTARGET_EXTRA_ASM_SPEC "%{mabi=apcs-gnu|mabi=atpcs:-meabi=gnu;:-meabi=4}"
+
+/* The generic link spec in elf.h does not support shared libraries.  */
+#undef  LINK_SPEC
+#define LINK_SPEC "%{mbig-endian:-EB} %{mlittle-endian:-EL} "		\
+  "%{static:-Bstatic} %{shared:-shared} %{symbolic:-Bsymbolic} "	\
+  "-X"
+
+#if defined (__thumb__)
+#define RENAME_LIBRARY_SET ".thumb_set"
+#else
+#define RENAME_LIBRARY_SET ".set"
+#endif
+
+/* Make __aeabi_AEABI_NAME an alias for __GCC_NAME.  */
+#define RENAME_LIBRARY(GCC_NAME, AEABI_NAME)		\
+  __asm__ (".globl\t__aeabi_" #AEABI_NAME "\n"		\
+	   RENAME_LIBRARY_SET "\t__aeabi_" #AEABI_NAME 	\
+	     ", __" #GCC_NAME "\n");
+
+/* Give some libgcc functions an additional __aeabi name.  */
+#ifdef L_muldi3
+#define DECLARE_LIBRARY_RENAMES RENAME_LIBRARY (muldi3, lmul)
+#endif
+#ifdef L_muldi3
+#define DECLARE_LIBRARY_RENAMES RENAME_LIBRARY (muldi3, lmul)
+#endif
+#ifdef L_fixdfdi
+#define DECLARE_LIBRARY_RENAMES RENAME_LIBRARY (fixdfdi, d2lz)
+#endif
+#ifdef L_fixunsdfdi
+#define DECLARE_LIBRARY_RENAMES RENAME_LIBRARY (fixunsdfdi, d2ulz)
+#endif
+#ifdef L_fixsfdi
+#define DECLARE_LIBRARY_RENAMES RENAME_LIBRARY (fixsfdi, f2lz)
+#endif
+#ifdef L_fixunssfdi
+#define DECLARE_LIBRARY_RENAMES RENAME_LIBRARY (fixunssfdi, f2ulz)
+#endif
+#ifdef L_floatdidf
+#define DECLARE_LIBRARY_RENAMES RENAME_LIBRARY (floatdidf, l2d)
+#endif
+#ifdef L_floatdisf
+#define DECLARE_LIBRARY_RENAMES RENAME_LIBRARY (floatdisf, l2f)
+#endif
+
+/* The BPABI requires that we always use an out-of-line implementation
+   of RTTI comparison, even if the target supports weak symbols,
+   because the same object file might be used on a target that does
+   not support merging symbols across DLL boundaries.  This macro is
+   broken out separately so that it can be used within
+   TARGET_OS_CPP_BUILTINS in configuration files for systems based on
+   the BPABI.  */
+#define TARGET_BPABI_CPP_BUILTINS()			\
+  do							\
+    {							\
+      builtin_define ("__GXX_TYPEINFO_EQUALITY_INLINE=0");	\
+    }							\
+  while (false)
+
+#undef TARGET_OS_CPP_BUILTINS
+#define TARGET_OS_CPP_BUILTINS() \
+  TARGET_BPABI_CPP_BUILTINS()
+
+/* The BPABI specifies the use of .{init,fini}_array.  Therefore, we
+   do not want GCC to put anything into the .{init,fini} sections.  */
+#undef INIT_SECTION_ASM_OP
+#undef FINI_SECTION_ASM_OP
+#define INIT_ARRAY_SECTION_ASM_OP ARM_EABI_CTORS_SECTION_OP
+#define FINI_ARRAY_SECTION_ASM_OP ARM_EABI_DTORS_SECTION_OP
diff --git a/setup/Linux/arm/lib1funcs.asm b/setup/Linux/arm/lib1funcs.asm
new file mode 100644
index 0000000..e2c2201
--- /dev/null
+++ b/setup/Linux/arm/lib1funcs.asm
@@ -0,0 +1,1393 @@
+@ libgcc routines for ARM cpu.
+@ Division routines, written by Richard Earnshaw, (rearnsha@armltd.co.uk)
+
+/* Copyright 1995, 1996, 1998, 1999, 2000, 2003, 2004, 2005, 2007
+   Free Software Foundation, Inc.
+
+This file is free software; you can redistribute it and/or modify it
+under the terms of the GNU General Public License as published by the
+Free Software Foundation; either version 2, or (at your option) any
+later version.
+
+In addition to the permissions in the GNU General Public License, the
+Free Software Foundation gives you unlimited permission to link the
+compiled version of this file into combinations with other programs,
+and to distribute those combinations without any restriction coming
+from the use of this file.  (The General Public License restrictions
+do apply in other respects; for example, they cover modification of
+the file, and distribution when not linked into a combine
+executable.)
+
+This file is distributed in the hope that it will be useful, but
+WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program; see the file COPYING.  If not, write to
+the Free Software Foundation, 51 Franklin Street, Fifth Floor,
+Boston, MA 02110-1301, USA.  */
+
+/* An executable stack is *not* required for these functions.  */
+#if defined(__ELF__) && defined(__linux__)
+.section .note.GNU-stack,"",%progbits
+.previous
+#endif
+
+/* ------------------------------------------------------------------------ */
+
+/* We need to know what prefix to add to function names.  */
+
+#ifndef __USER_LABEL_PREFIX__
+#error  __USER_LABEL_PREFIX__ not defined
+#endif
+
+/* ANSI concatenation macros.  */
+
+#define CONCAT1(a, b) CONCAT2(a, b)
+#define CONCAT2(a, b) a ## b
+
+/* Use the right prefix for global labels.  */
+
+#define SYM(x) CONCAT1 (__USER_LABEL_PREFIX__, x)
+
+#ifdef __ELF__
+#ifdef __thumb__
+#define __PLT__  /* Not supported in Thumb assembler (for now).  */
+#elif defined __vxworks && !defined __PIC__
+#define __PLT__ /* Not supported by the kernel loader.  */
+#else
+#define __PLT__ (PLT)
+#endif
+#define TYPE(x) .type SYM(x),function
+#define SIZE(x) .size SYM(x), . - SYM(x)
+#define LSYM(x) .x
+#else
+#define __PLT__
+#define TYPE(x)
+#define SIZE(x)
+#define LSYM(x) x
+#endif
+
+/* Function end macros.  Variants for interworking.  */
+
+#if defined(__ARM_ARCH_2__)
+# define __ARM_ARCH__ 2
+#endif
+
+#if defined(__ARM_ARCH_3__)
+# define __ARM_ARCH__ 3
+#endif
+
+#if defined(__ARM_ARCH_3M__) || defined(__ARM_ARCH_4__) \
+	|| defined(__ARM_ARCH_4T__)
+/* We use __ARM_ARCH__ set to 4 here, but in reality it's any processor with
+   long multiply instructions.  That includes v3M.  */
+# define __ARM_ARCH__ 4
+#endif
+	
+#if defined(__ARM_ARCH_5__) || defined(__ARM_ARCH_5T__) \
+	|| defined(__ARM_ARCH_5E__) || defined(__ARM_ARCH_5TE__) \
+	|| defined(__ARM_ARCH_5TEJ__)
+# define __ARM_ARCH__ 5
+#endif
+
+#if defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) \
+	|| defined(__ARM_ARCH_6K__) || defined(__ARM_ARCH_6Z__) \
+	|| defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_6T2__)
+# define __ARM_ARCH__ 6
+#endif
+
+#if defined(__ARM_ARCH_7__) || defined(__ARM_ARCH_7A__) \
+	|| defined(__ARM_ARCH_7R__) || defined(__ARM_ARCH_7M__)
+# define __ARM_ARCH__ 7
+#endif
+
+#ifndef __ARM_ARCH__
+#error Unable to determine architecture.
+#endif
+
+/* How to return from a function call depends on the architecture variant.  */
+
+#if (__ARM_ARCH__ > 4) || defined(__ARM_ARCH_4T__)
+
+# define RET		bx	lr
+# define RETc(x)	bx##x	lr
+
+/* Special precautions for interworking on armv4t.  */
+# if (__ARM_ARCH__ == 4)
+
+/* Always use bx, not ldr pc.  */
+#  if (defined(__thumb__) || defined(__THUMB_INTERWORK__))
+#    define __INTERWORKING__
+#   endif /* __THUMB__ || __THUMB_INTERWORK__ */
+
+/* Include thumb stub before arm mode code.  */
+#  if defined(__thumb__) && !defined(__THUMB_INTERWORK__)
+#   define __INTERWORKING_STUBS__
+#  endif /* __thumb__ && !__THUMB_INTERWORK__ */
+
+#endif /* __ARM_ARCH == 4 */
+
+#else
+
+# define RET		mov	pc, lr
+# define RETc(x)	mov##x	pc, lr
+
+#endif
+
+.macro	cfi_pop		advance, reg, cfa_offset
+#ifdef __ELF__
+	.pushsection	.debug_frame
+	.byte	0x4		/* DW_CFA_advance_loc4 */
+	.4byte	\advance
+	.byte	(0xc0 | \reg)	/* DW_CFA_restore */
+	.byte	0xe		/* DW_CFA_def_cfa_offset */
+	.uleb128 \cfa_offset
+	.popsection
+#endif
+.endm
+.macro	cfi_push	advance, reg, offset, cfa_offset
+#ifdef __ELF__
+	.pushsection	.debug_frame
+	.byte	0x4		/* DW_CFA_advance_loc4 */
+	.4byte	\advance
+	.byte	(0x80 | \reg)	/* DW_CFA_offset */
+	.uleb128 (\offset / -4)
+	.byte	0xe		/* DW_CFA_def_cfa_offset */
+	.uleb128 \cfa_offset
+	.popsection
+#endif
+.endm
+.macro cfi_start	start_label, end_label
+#ifdef __ELF__
+	.pushsection	.debug_frame
+LSYM(Lstart_frame):
+	.4byte	LSYM(Lend_cie) - LSYM(Lstart_cie) @ Length of CIE
+LSYM(Lstart_cie):
+        .4byte	0xffffffff	@ CIE Identifier Tag
+        .byte	0x1	@ CIE Version
+        .ascii	"\0"	@ CIE Augmentation
+        .uleb128 0x1	@ CIE Code Alignment Factor
+        .sleb128 -4	@ CIE Data Alignment Factor
+        .byte	0xe	@ CIE RA Column
+        .byte	0xc	@ DW_CFA_def_cfa
+        .uleb128 0xd
+        .uleb128 0x0
+
+	.align 2
+LSYM(Lend_cie):
+	.4byte	LSYM(Lend_fde)-LSYM(Lstart_fde)	@ FDE Length
+LSYM(Lstart_fde):
+	.4byte	LSYM(Lstart_frame)	@ FDE CIE offset
+	.4byte	\start_label	@ FDE initial location
+	.4byte	\end_label-\start_label	@ FDE address range
+	.popsection
+#endif
+.endm
+.macro cfi_end	end_label
+#ifdef __ELF__
+	.pushsection	.debug_frame
+	.align	2
+LSYM(Lend_fde):
+	.popsection
+\end_label:
+#endif
+.endm
+
+/* Don't pass dirn, it's there just to get token pasting right.  */
+
+.macro	RETLDM	regs=, cond=, unwind=, dirn=ia
+#if defined (__INTERWORKING__)
+	.ifc "\regs",""
+	ldr\cond	lr, [sp], #8
+	.else
+# if defined(__thumb2__)
+	pop\cond	{\regs, lr}
+# else
+	ldm\cond\dirn	sp!, {\regs, lr}
+# endif
+	.endif
+	.ifnc "\unwind", ""
+	/* Mark LR as restored.  */
+97:	cfi_pop 97b - \unwind, 0xe, 0x0
+	.endif
+	bx\cond	lr
+#else
+	/* Caller is responsible for providing IT instruction.  */
+	.ifc "\regs",""
+	ldr\cond	pc, [sp], #8
+	.else
+# if defined(__thumb2__)
+	pop\cond	{\regs, pc}
+# else
+	ldm\cond\dirn	sp!, {\regs, pc}
+# endif
+	.endif
+#endif
+.endm
+
+/* The Unified assembly syntax allows the same code to be assembled for both
+   ARM and Thumb-2.  However this is only supported by recent gas, so define
+   a set of macros to allow ARM code on older assemblers.  */
+#if defined(__thumb2__)
+.macro do_it cond, suffix=""
+	it\suffix	\cond
+.endm
+.macro shift1 op, arg0, arg1, arg2
+	\op	\arg0, \arg1, \arg2
+.endm
+#define do_push	push
+#define do_pop	pop
+#define COND(op1, op2, cond) op1 ## op2 ## cond
+/* Perform an arithmetic operation with a variable shift operand.  This
+   requires two instructions and a scratch register on Thumb-2.  */
+.macro shiftop name, dest, src1, src2, shiftop, shiftreg, tmp
+	\shiftop \tmp, \src2, \shiftreg
+	\name \dest, \src1, \tmp
+.endm
+#else
+.macro do_it cond, suffix=""
+.endm
+.macro shift1 op, arg0, arg1, arg2
+	mov	\arg0, \arg1, \op \arg2
+.endm
+#define do_push	stmfd sp!,
+#define do_pop	ldmfd sp!,
+#define COND(op1, op2, cond) op1 ## cond ## op2
+.macro shiftop name, dest, src1, src2, shiftop, shiftreg, tmp
+	\name \dest, \src1, \src2, \shiftop \shiftreg
+.endm
+#endif
+
+.macro ARM_LDIV0 name
+	str	lr, [sp, #-8]!
+98:	cfi_push 98b - __\name, 0xe, -0x8, 0x8
+	bl	SYM (__div0) __PLT__
+	mov	r0, #0			@ About as wrong as it could be.
+	RETLDM	unwind=98b
+.endm
+
+
+.macro THUMB_LDIV0 name
+	push	{ r1, lr }
+98:	cfi_push 98b - __\name, 0xe, -0x4, 0x8
+	bl	SYM (__div0)
+	mov	r0, #0			@ About as wrong as it could be.
+#if defined (__INTERWORKING__)
+	pop	{ r1, r2 }
+	bx	r2
+#else
+	pop	{ r1, pc }
+#endif
+.endm
+
+.macro FUNC_END name
+	SIZE (__\name)
+.endm
+
+.macro DIV_FUNC_END name
+	cfi_start	__\name, LSYM(Lend_div0)
+LSYM(Ldiv0):
+#ifdef __thumb__
+	THUMB_LDIV0 \name
+#else
+	ARM_LDIV0 \name
+#endif
+	cfi_end	LSYM(Lend_div0)
+	FUNC_END \name
+.endm
+
+.macro THUMB_FUNC_START name
+	.globl	SYM (\name)
+	TYPE	(\name)
+	.thumb_func
+SYM (\name):
+.endm
+
+/* Function start macros.  Variants for ARM and Thumb.  */
+
+#ifdef __thumb__
+#define THUMB_FUNC .thumb_func
+#define THUMB_CODE .force_thumb
+# if defined(__thumb2__)
+#define THUMB_SYNTAX .syntax divided
+# else
+#define THUMB_SYNTAX
+# endif
+#else
+#define THUMB_FUNC
+#define THUMB_CODE
+#define THUMB_SYNTAX
+#endif
+
+.macro FUNC_START name
+	.text
+	.globl SYM (__\name)
+	TYPE (__\name)
+	.align 0
+	THUMB_CODE
+	THUMB_FUNC
+	THUMB_SYNTAX
+SYM (__\name):
+.endm
+
+/* Special function that will always be coded in ARM assembly, even if
+   in Thumb-only compilation.  */
+
+#if defined(__thumb2__)
+
+/* For Thumb-2 we build everything in thumb mode.  */
+.macro ARM_FUNC_START name
+       FUNC_START \name
+       .syntax unified
+.endm
+#define EQUIV .thumb_set
+.macro  ARM_CALL name
+	bl	__\name
+.endm
+
+#elif defined(__INTERWORKING_STUBS__)
+
+.macro	ARM_FUNC_START name
+	FUNC_START \name
+	bx	pc
+	nop
+	.arm
+/* A hook to tell gdb that we've switched to ARM mode.  Also used to call
+   directly from other local arm routines.  */
+_L__\name:		
+.endm
+#define EQUIV .thumb_set
+/* Branch directly to a function declared with ARM_FUNC_START.
+   Must be called in arm mode.  */
+.macro  ARM_CALL name
+	bl	_L__\name
+.endm
+
+#else /* !(__INTERWORKING_STUBS__ || __thumb2__) */
+
+.macro	ARM_FUNC_START name
+	.text
+	.globl SYM (__\name)
+	TYPE (__\name)
+	.align 0
+	.arm
+SYM (__\name):
+.endm
+#define EQUIV .set
+.macro  ARM_CALL name
+	bl	__\name
+.endm
+
+#endif
+
+.macro	FUNC_ALIAS new old
+	.globl	SYM (__\new)
+#if defined (__thumb__)
+	.thumb_set	SYM (__\new), SYM (__\old)
+#else
+	.set	SYM (__\new), SYM (__\old)
+#endif
+.endm
+
+.macro	ARM_FUNC_ALIAS new old
+	.globl	SYM (__\new)
+	EQUIV	SYM (__\new), SYM (__\old)
+#if defined(__INTERWORKING_STUBS__)
+	.set	SYM (_L__\new), SYM (_L__\old)
+#endif
+.endm
+
+#ifdef __thumb__
+/* Register aliases.  */
+
+work		.req	r4	@ XXXX is this safe ?
+dividend	.req	r0
+divisor		.req	r1
+overdone	.req	r2
+result		.req	r2
+curbit		.req	r3
+#endif
+#if 0
+ip		.req	r12
+sp		.req	r13
+lr		.req	r14
+pc		.req	r15
+#endif
+
+/* ------------------------------------------------------------------------ */
+/*		Bodies of the division and modulo routines.		    */
+/* ------------------------------------------------------------------------ */	
+.macro ARM_DIV_BODY dividend, divisor, result, curbit
+
+#if __ARM_ARCH__ >= 5 && ! defined (__OPTIMIZE_SIZE__)
+
+	clz	\curbit, \dividend
+	clz	\result, \divisor
+	sub	\curbit, \result, \curbit
+	rsbs	\curbit, \curbit, #31
+	addne	\curbit, \curbit, \curbit, lsl #1
+	mov	\result, #0
+	addne	pc, pc, \curbit, lsl #2
+	nop
+	.set	shift, 32
+	.rept	32
+	.set	shift, shift - 1
+	cmp	\dividend, \divisor, lsl #shift
+	adc	\result, \result, \result
+	subcs	\dividend, \dividend, \divisor, lsl #shift
+	.endr
+
+#else /* __ARM_ARCH__ < 5 || defined (__OPTIMIZE_SIZE__) */
+#if __ARM_ARCH__ >= 5
+
+	clz	\curbit, \divisor
+	clz	\result, \dividend
+	sub	\result, \curbit, \result
+	mov	\curbit, #1
+	mov	\divisor, \divisor, lsl \result
+	mov	\curbit, \curbit, lsl \result
+	mov	\result, #0
+	
+#else /* __ARM_ARCH__ < 5 */
+
+	@ Initially shift the divisor left 3 bits if possible,
+	@ set curbit accordingly.  This allows for curbit to be located
+	@ at the left end of each 4-bit nibbles in the division loop
+	@ to save one loop in most cases.
+	tst	\divisor, #0xe0000000
+	moveq	\divisor, \divisor, lsl #3
+	moveq	\curbit, #8
+	movne	\curbit, #1
+
+	@ Unless the divisor is very big, shift it up in multiples of
+	@ four bits, since this is the amount of unwinding in the main
+	@ division loop.  Continue shifting until the divisor is 
+	@ larger than the dividend.
+1:	cmp	\divisor, #0x10000000
+	cmplo	\divisor, \dividend
+	movlo	\divisor, \divisor, lsl #4
+	movlo	\curbit, \curbit, lsl #4
+	blo	1b
+
+	@ For very big divisors, we must shift it a bit at a time, or
+	@ we will be in danger of overflowing.
+1:	cmp	\divisor, #0x80000000
+	cmplo	\divisor, \dividend
+	movlo	\divisor, \divisor, lsl #1
+	movlo	\curbit, \curbit, lsl #1
+	blo	1b
+
+	mov	\result, #0
+
+#endif /* __ARM_ARCH__ < 5 */
+
+	@ Division loop
+1:	cmp	\dividend, \divisor
+	subhs	\dividend, \dividend, \divisor
+	orrhs	\result,   \result,   \curbit
+	cmp	\dividend, \divisor,  lsr #1
+	subhs	\dividend, \dividend, \divisor, lsr #1
+	orrhs	\result,   \result,   \curbit,  lsr #1
+	cmp	\dividend, \divisor,  lsr #2
+	subhs	\dividend, \dividend, \divisor, lsr #2
+	orrhs	\result,   \result,   \curbit,  lsr #2
+	cmp	\dividend, \divisor,  lsr #3
+	subhs	\dividend, \dividend, \divisor, lsr #3
+	orrhs	\result,   \result,   \curbit,  lsr #3
+	cmp	\dividend, #0			@ Early termination?
+	movnes	\curbit,   \curbit,  lsr #4	@ No, any more bits to do?
+	movne	\divisor,  \divisor, lsr #4
+	bne	1b
+
+#endif /* __ARM_ARCH__ < 5 || defined (__OPTIMIZE_SIZE__) */
+
+.endm
+/* ------------------------------------------------------------------------ */	
+.macro ARM_DIV2_ORDER divisor, order
+
+#if __ARM_ARCH__ >= 5
+
+	clz	\order, \divisor
+	rsb	\order, \order, #31
+
+#else
+
+	cmp	\divisor, #(1 << 16)
+	movhs	\divisor, \divisor, lsr #16
+	movhs	\order, #16
+	movlo	\order, #0
+
+	cmp	\divisor, #(1 << 8)
+	movhs	\divisor, \divisor, lsr #8
+	addhs	\order, \order, #8
+
+	cmp	\divisor, #(1 << 4)
+	movhs	\divisor, \divisor, lsr #4
+	addhs	\order, \order, #4
+
+	cmp	\divisor, #(1 << 2)
+	addhi	\order, \order, #3
+	addls	\order, \order, \divisor, lsr #1
+
+#endif
+
+.endm
+/* ------------------------------------------------------------------------ */
+.macro ARM_MOD_BODY dividend, divisor, order, spare
+
+#if __ARM_ARCH__ >= 5 && ! defined (__OPTIMIZE_SIZE__)
+
+	clz	\order, \divisor
+	clz	\spare, \dividend
+	sub	\order, \order, \spare
+	rsbs	\order, \order, #31
+	addne	pc, pc, \order, lsl #3
+	nop
+	.set	shift, 32
+	.rept	32
+	.set	shift, shift - 1
+	cmp	\dividend, \divisor, lsl #shift
+	subcs	\dividend, \dividend, \divisor, lsl #shift
+	.endr
+
+#else /* __ARM_ARCH__ < 5 || defined (__OPTIMIZE_SIZE__) */
+#if __ARM_ARCH__ >= 5
+
+	clz	\order, \divisor
+	clz	\spare, \dividend
+	sub	\order, \order, \spare
+	mov	\divisor, \divisor, lsl \order
+	
+#else /* __ARM_ARCH__ < 5 */
+
+	mov	\order, #0
+
+	@ Unless the divisor is very big, shift it up in multiples of
+	@ four bits, since this is the amount of unwinding in the main
+	@ division loop.  Continue shifting until the divisor is 
+	@ larger than the dividend.
+1:	cmp	\divisor, #0x10000000
+	cmplo	\divisor, \dividend
+	movlo	\divisor, \divisor, lsl #4
+	addlo	\order, \order, #4
+	blo	1b
+
+	@ For very big divisors, we must shift it a bit at a time, or
+	@ we will be in danger of overflowing.
+1:	cmp	\divisor, #0x80000000
+	cmplo	\divisor, \dividend
+	movlo	\divisor, \divisor, lsl #1
+	addlo	\order, \order, #1
+	blo	1b
+
+#endif /* __ARM_ARCH__ < 5 */
+
+	@ Perform all needed substractions to keep only the reminder.
+	@ Do comparisons in batch of 4 first.
+	subs	\order, \order, #3		@ yes, 3 is intended here
+	blt	2f
+
+1:	cmp	\dividend, \divisor
+	subhs	\dividend, \dividend, \divisor
+	cmp	\dividend, \divisor,  lsr #1
+	subhs	\dividend, \dividend, \divisor, lsr #1
+	cmp	\dividend, \divisor,  lsr #2
+	subhs	\dividend, \dividend, \divisor, lsr #2
+	cmp	\dividend, \divisor,  lsr #3
+	subhs	\dividend, \dividend, \divisor, lsr #3
+	cmp	\dividend, #1
+	mov	\divisor, \divisor, lsr #4
+	subges	\order, \order, #4
+	bge	1b
+
+	tst	\order, #3
+	teqne	\dividend, #0
+	beq	5f
+
+	@ Either 1, 2 or 3 comparison/substractions are left.
+2:	cmn	\order, #2
+	blt	4f
+	beq	3f
+	cmp	\dividend, \divisor
+	subhs	\dividend, \dividend, \divisor
+	mov	\divisor,  \divisor,  lsr #1
+3:	cmp	\dividend, \divisor
+	subhs	\dividend, \dividend, \divisor
+	mov	\divisor,  \divisor,  lsr #1
+4:	cmp	\dividend, \divisor
+	subhs	\dividend, \dividend, \divisor
+5:
+
+#endif /* __ARM_ARCH__ < 5 || defined (__OPTIMIZE_SIZE__) */
+
+.endm
+/* ------------------------------------------------------------------------ */
+.macro THUMB_DIV_MOD_BODY modulo
+	@ Load the constant 0x10000000 into our work register.
+	mov	work, #1
+	lsl	work, #28
+LSYM(Loop1):
+	@ Unless the divisor is very big, shift it up in multiples of
+	@ four bits, since this is the amount of unwinding in the main
+	@ division loop.  Continue shifting until the divisor is 
+	@ larger than the dividend.
+	cmp	divisor, work
+	bhs	LSYM(Lbignum)
+	cmp	divisor, dividend
+	bhs	LSYM(Lbignum)
+	lsl	divisor, #4
+	lsl	curbit,  #4
+	b	LSYM(Loop1)
+LSYM(Lbignum):
+	@ Set work to 0x80000000
+	lsl	work, #3
+LSYM(Loop2):
+	@ For very big divisors, we must shift it a bit at a time, or
+	@ we will be in danger of overflowing.
+	cmp	divisor, work
+	bhs	LSYM(Loop3)
+	cmp	divisor, dividend
+	bhs	LSYM(Loop3)
+	lsl	divisor, #1
+	lsl	curbit,  #1
+	b	LSYM(Loop2)
+LSYM(Loop3):
+	@ Test for possible subtractions ...
+  .if \modulo
+	@ ... On the final pass, this may subtract too much from the dividend, 
+	@ so keep track of which subtractions are done, we can fix them up 
+	@ afterwards.
+	mov	overdone, #0
+	cmp	dividend, divisor
+	blo	LSYM(Lover1)
+	sub	dividend, dividend, divisor
+LSYM(Lover1):
+	lsr	work, divisor, #1
+	cmp	dividend, work
+	blo	LSYM(Lover2)
+	sub	dividend, dividend, work
+	mov	ip, curbit
+	mov	work, #1
+	ror	curbit, work
+	orr	overdone, curbit
+	mov	curbit, ip
+LSYM(Lover2):
+	lsr	work, divisor, #2
+	cmp	dividend, work
+	blo	LSYM(Lover3)
+	sub	dividend, dividend, work
+	mov	ip, curbit
+	mov	work, #2
+	ror	curbit, work
+	orr	overdone, curbit
+	mov	curbit, ip
+LSYM(Lover3):
+	lsr	work, divisor, #3
+	cmp	dividend, work
+	blo	LSYM(Lover4)
+	sub	dividend, dividend, work
+	mov	ip, curbit
+	mov	work, #3
+	ror	curbit, work
+	orr	overdone, curbit
+	mov	curbit, ip
+LSYM(Lover4):
+	mov	ip, curbit
+  .else
+	@ ... and note which bits are done in the result.  On the final pass,
+	@ this may subtract too much from the dividend, but the result will be ok,
+	@ since the "bit" will have been shifted out at the bottom.
+	cmp	dividend, divisor
+	blo	LSYM(Lover1)
+	sub	dividend, dividend, divisor
+	orr	result, result, curbit
+LSYM(Lover1):
+	lsr	work, divisor, #1
+	cmp	dividend, work
+	blo	LSYM(Lover2)
+	sub	dividend, dividend, work
+	lsr	work, curbit, #1
+	orr	result, work
+LSYM(Lover2):
+	lsr	work, divisor, #2
+	cmp	dividend, work
+	blo	LSYM(Lover3)
+	sub	dividend, dividend, work
+	lsr	work, curbit, #2
+	orr	result, work
+LSYM(Lover3):
+	lsr	work, divisor, #3
+	cmp	dividend, work
+	blo	LSYM(Lover4)
+	sub	dividend, dividend, work
+	lsr	work, curbit, #3
+	orr	result, work
+LSYM(Lover4):
+  .endif
+	
+	cmp	dividend, #0			@ Early termination?
+	beq	LSYM(Lover5)
+	lsr	curbit,  #4			@ No, any more bits to do?
+	beq	LSYM(Lover5)
+	lsr	divisor, #4
+	b	LSYM(Loop3)
+LSYM(Lover5):
+  .if \modulo
+	@ Any subtractions that we should not have done will be recorded in
+	@ the top three bits of "overdone".  Exactly which were not needed
+	@ are governed by the position of the bit, stored in ip.
+	mov	work, #0xe
+	lsl	work, #28
+	and	overdone, work
+	beq	LSYM(Lgot_result)
+	
+	@ If we terminated early, because dividend became zero, then the 
+	@ bit in ip will not be in the bottom nibble, and we should not
+	@ perform the additions below.  We must test for this though
+	@ (rather relying upon the TSTs to prevent the additions) since
+	@ the bit in ip could be in the top two bits which might then match
+	@ with one of the smaller RORs.
+	mov	curbit, ip
+	mov	work, #0x7
+	tst	curbit, work
+	beq	LSYM(Lgot_result)
+	
+	mov	curbit, ip
+	mov	work, #3
+	ror	curbit, work
+	tst	overdone, curbit
+	beq	LSYM(Lover6)
+	lsr	work, divisor, #3
+	add	dividend, work
+LSYM(Lover6):
+	mov	curbit, ip
+	mov	work, #2
+	ror	curbit, work
+	tst	overdone, curbit
+	beq	LSYM(Lover7)
+	lsr	work, divisor, #2
+	add	dividend, work
+LSYM(Lover7):
+	mov	curbit, ip
+	mov	work, #1
+	ror	curbit, work
+	tst	overdone, curbit
+	beq	LSYM(Lgot_result)
+	lsr	work, divisor, #1
+	add	dividend, work
+  .endif
+LSYM(Lgot_result):
+.endm	
+/* ------------------------------------------------------------------------ */
+/*		Start of the Real Functions				    */
+/* ------------------------------------------------------------------------ */
+#ifdef L_udivsi3
+
+	FUNC_START udivsi3
+	FUNC_ALIAS aeabi_uidiv udivsi3
+
+#ifdef __thumb__
+
+	cmp	divisor, #0
+	beq	LSYM(Ldiv0)
+	mov	curbit, #1
+	mov	result, #0
+	
+	push	{ work }
+	cmp	dividend, divisor
+	blo	LSYM(Lgot_result)
+
+	THUMB_DIV_MOD_BODY 0
+	
+	mov	r0, result
+	pop	{ work }
+	RET
+
+#else /* ARM version.  */
+
+	subs	r2, r1, #1
+	RETc(eq)
+	bcc	LSYM(Ldiv0)
+	cmp	r0, r1
+	bls	11f
+	tst	r1, r2
+	beq	12f
+	
+	ARM_DIV_BODY r0, r1, r2, r3
+	
+	mov	r0, r2
+	RET	
+
+11:	moveq	r0, #1
+	movne	r0, #0
+	RET
+
+12:	ARM_DIV2_ORDER r1, r2
+
+	mov	r0, r0, lsr r2
+	RET
+
+#endif /* ARM version */
+
+	DIV_FUNC_END udivsi3
+
+FUNC_START aeabi_uidivmod
+#ifdef __thumb__
+	push	{r0, r1, lr}
+	bl	SYM(__udivsi3)
+	POP	{r1, r2, r3}
+	mul	r2, r0
+	sub	r1, r1, r2
+	bx	r3
+#else
+	stmfd	sp!, { r0, r1, lr }
+	bl	SYM(__udivsi3)
+	ldmfd	sp!, { r1, r2, lr }
+	mul	r3, r2, r0
+	sub	r1, r1, r3
+	RET
+#endif
+	FUNC_END aeabi_uidivmod
+	
+#endif /* L_udivsi3 */
+/* ------------------------------------------------------------------------ */
+#ifdef L_umodsi3
+
+	FUNC_START umodsi3
+
+#ifdef __thumb__
+
+	cmp	divisor, #0
+	beq	LSYM(Ldiv0)
+	mov	curbit, #1
+	cmp	dividend, divisor
+	bhs	LSYM(Lover10)
+	RET	
+
+LSYM(Lover10):
+	push	{ work }
+
+	THUMB_DIV_MOD_BODY 1
+	
+	pop	{ work }
+	RET
+	
+#else  /* ARM version.  */
+	
+	subs	r2, r1, #1			@ compare divisor with 1
+	bcc	LSYM(Ldiv0)
+	cmpne	r0, r1				@ compare dividend with divisor
+	moveq   r0, #0
+	tsthi	r1, r2				@ see if divisor is power of 2
+	andeq	r0, r0, r2
+	RETc(ls)
+
+	ARM_MOD_BODY r0, r1, r2, r3
+	
+	RET	
+
+#endif /* ARM version.  */
+	
+	DIV_FUNC_END umodsi3
+
+#endif /* L_umodsi3 */
+/* ------------------------------------------------------------------------ */
+#ifdef L_divsi3
+
+	FUNC_START divsi3	
+	FUNC_ALIAS aeabi_idiv divsi3
+
+#ifdef __thumb__
+	cmp	divisor, #0
+	beq	LSYM(Ldiv0)
+	
+	push	{ work }
+	mov	work, dividend
+	eor	work, divisor		@ Save the sign of the result.
+	mov	ip, work
+	mov	curbit, #1
+	mov	result, #0
+	cmp	divisor, #0
+	bpl	LSYM(Lover10)
+	neg	divisor, divisor	@ Loops below use unsigned.
+LSYM(Lover10):
+	cmp	dividend, #0
+	bpl	LSYM(Lover11)
+	neg	dividend, dividend
+LSYM(Lover11):
+	cmp	dividend, divisor
+	blo	LSYM(Lgot_result)
+
+	THUMB_DIV_MOD_BODY 0
+	
+	mov	r0, result
+	mov	work, ip
+	cmp	work, #0
+	bpl	LSYM(Lover12)
+	neg	r0, r0
+LSYM(Lover12):
+	pop	{ work }
+	RET
+
+#else /* ARM version.  */
+	
+	cmp	r1, #0
+	eor	ip, r0, r1			@ save the sign of the result.
+	beq	LSYM(Ldiv0)
+	rsbmi	r1, r1, #0			@ loops below use unsigned.
+	subs	r2, r1, #1			@ division by 1 or -1 ?
+	beq	10f
+	movs	r3, r0
+	rsbmi	r3, r0, #0			@ positive dividend value
+	cmp	r3, r1
+	bls	11f
+	tst	r1, r2				@ divisor is power of 2 ?
+	beq	12f
+
+	ARM_DIV_BODY r3, r1, r0, r2
+	
+	cmp	ip, #0
+	rsbmi	r0, r0, #0
+	RET	
+
+10:	teq	ip, r0				@ same sign ?
+	rsbmi	r0, r0, #0
+	RET	
+
+11:	movlo	r0, #0
+	moveq	r0, ip, asr #31
+	orreq	r0, r0, #1
+	RET
+
+12:	ARM_DIV2_ORDER r1, r2
+
+	cmp	ip, #0
+	mov	r0, r3, lsr r2
+	rsbmi	r0, r0, #0
+	RET
+
+#endif /* ARM version */
+	
+	DIV_FUNC_END divsi3
+
+FUNC_START aeabi_idivmod
+#ifdef __thumb__
+	push	{r0, r1, lr}
+	bl	SYM(__divsi3)
+	POP	{r1, r2, r3}
+	mul	r2, r0
+	sub	r1, r1, r2
+	bx	r3
+#else
+	stmfd	sp!, { r0, r1, lr }
+	bl	SYM(__divsi3)
+	ldmfd	sp!, { r1, r2, lr }
+	mul	r3, r2, r0
+	sub	r1, r1, r3
+	RET
+#endif
+	FUNC_END aeabi_idivmod
+	
+#endif /* L_divsi3 */
+/* ------------------------------------------------------------------------ */
+#ifdef L_modsi3
+
+	FUNC_START modsi3
+
+#ifdef __thumb__
+
+	mov	curbit, #1
+	cmp	divisor, #0
+	beq	LSYM(Ldiv0)
+	bpl	LSYM(Lover10)
+	neg	divisor, divisor		@ Loops below use unsigned.
+LSYM(Lover10):
+	push	{ work }
+	@ Need to save the sign of the dividend, unfortunately, we need
+	@ work later on.  Must do this after saving the original value of
+	@ the work register, because we will pop this value off first.
+	push	{ dividend }
+	cmp	dividend, #0
+	bpl	LSYM(Lover11)
+	neg	dividend, dividend
+LSYM(Lover11):
+	cmp	dividend, divisor
+	blo	LSYM(Lgot_result)
+
+	THUMB_DIV_MOD_BODY 1
+		
+	pop	{ work }
+	cmp	work, #0
+	bpl	LSYM(Lover12)
+	neg	dividend, dividend
+LSYM(Lover12):
+	pop	{ work }
+	RET	
+
+#else /* ARM version.  */
+	
+	cmp	r1, #0
+	beq	LSYM(Ldiv0)
+	rsbmi	r1, r1, #0			@ loops below use unsigned.
+	movs	ip, r0				@ preserve sign of dividend
+	rsbmi	r0, r0, #0			@ if negative make positive
+	subs	r2, r1, #1			@ compare divisor with 1
+	cmpne	r0, r1				@ compare dividend with divisor
+	moveq	r0, #0
+	tsthi	r1, r2				@ see if divisor is power of 2
+	andeq	r0, r0, r2
+	bls	10f
+
+	ARM_MOD_BODY r0, r1, r2, r3
+
+10:	cmp	ip, #0
+	rsbmi	r0, r0, #0
+	RET	
+
+#endif /* ARM version */
+	
+	DIV_FUNC_END modsi3
+
+#endif /* L_modsi3 */
+/* ------------------------------------------------------------------------ */
+#ifdef L_dvmd_tls
+
+	FUNC_START div0
+	FUNC_ALIAS aeabi_idiv0 div0
+	FUNC_ALIAS aeabi_ldiv0 div0
+
+	RET
+
+	FUNC_END aeabi_ldiv0
+	FUNC_END aeabi_idiv0
+	FUNC_END div0
+	
+#endif /* L_divmodsi_tools */
+/* ------------------------------------------------------------------------ */
+#ifdef L_dvmd_lnx
+@ GNU/Linux division-by zero handler.  Used in place of L_dvmd_tls
+
+/* Constant taken from <asm/signal.h>.  */
+#define SIGFPE	8
+
+	ARM_FUNC_START div0
+
+	do_push	{r1, lr}
+	mov	r0, #SIGFPE
+	bl	SYM(raise) __PLT__
+	RETLDM	r1
+
+	FUNC_END div0
+	
+#endif /* L_dvmd_lnx */
+/* ------------------------------------------------------------------------ */
+/* Dword shift operations.  */
+/* All the following Dword shift variants rely on the fact that
+	shft xxx, Reg
+   is in fact done as
+	shft xxx, (Reg & 255)
+   so for Reg value in (32...63) and (-1...-31) we will get zero (in the
+   case of logical shifts) or the sign (for asr).  */
+
+#ifdef __ARMEB__
+#define al	r1
+#define ah	r0
+#else
+#define al	r0
+#define ah	r1
+#endif
+
+/* Prevent __aeabi double-word shifts from being produced on SymbianOS.  */
+#ifndef __symbian__
+
+#ifdef L_lshrdi3
+
+	FUNC_START lshrdi3
+	FUNC_ALIAS aeabi_llsr lshrdi3
+	
+#ifdef __thumb__
+	lsr	al, r2
+	mov	r3, ah
+	lsr	ah, r2
+	mov	ip, r3
+	sub	r2, #32
+	lsr	r3, r2
+	orr	al, r3
+	neg	r2, r2
+	mov	r3, ip
+	lsl	r3, r2
+	orr	al, r3
+	RET
+#else
+	subs	r3, r2, #32
+	rsb	ip, r2, #32
+	movmi	al, al, lsr r2
+	movpl	al, ah, lsr r3
+	orrmi	al, al, ah, lsl ip
+	mov	ah, ah, lsr r2
+	RET
+#endif
+	FUNC_END aeabi_llsr
+	FUNC_END lshrdi3
+
+#endif
+	
+#ifdef L_ashrdi3
+	
+	FUNC_START ashrdi3
+	FUNC_ALIAS aeabi_lasr ashrdi3
+	
+#ifdef __thumb__
+	lsr	al, r2
+	mov	r3, ah
+	asr	ah, r2
+	sub	r2, #32
+	@ If r2 is negative at this point the following step would OR
+	@ the sign bit into all of AL.  That's not what we want...
+	bmi	1f
+	mov	ip, r3
+	asr	r3, r2
+	orr	al, r3
+	mov	r3, ip
+1:
+	neg	r2, r2
+	lsl	r3, r2
+	orr	al, r3
+	RET
+#else
+	subs	r3, r2, #32
+	rsb	ip, r2, #32
+	movmi	al, al, lsr r2
+	movpl	al, ah, asr r3
+	orrmi	al, al, ah, lsl ip
+	mov	ah, ah, asr r2
+	RET
+#endif
+
+	FUNC_END aeabi_lasr
+	FUNC_END ashrdi3
+
+#endif
+
+#ifdef L_ashldi3
+
+	FUNC_START ashldi3
+	FUNC_ALIAS aeabi_llsl ashldi3
+	
+#ifdef __thumb__
+	lsl	ah, r2
+	mov	r3, al
+	lsl	al, r2
+	mov	ip, r3
+	sub	r2, #32
+	lsl	r3, r2
+	orr	ah, r3
+	neg	r2, r2
+	mov	r3, ip
+	lsr	r3, r2
+	orr	ah, r3
+	RET
+#else
+	subs	r3, r2, #32
+	rsb	ip, r2, #32
+	movmi	ah, ah, lsl r2
+	movpl	ah, al, lsl r3
+	orrmi	ah, ah, al, lsr ip
+	mov	al, al, lsl r2
+	RET
+#endif
+	FUNC_END aeabi_llsl
+	FUNC_END ashldi3
+
+#endif
+
+#endif /* __symbian__ */
+
+/* ------------------------------------------------------------------------ */
+/* These next two sections are here despite the fact that they contain Thumb 
+   assembler because their presence allows interworked code to be linked even
+   when the GCC library is this one.  */
+		
+/* Do not build the interworking functions when the target architecture does 
+   not support Thumb instructions.  (This can be a multilib option).  */
+#if defined __ARM_ARCH_4T__ || defined __ARM_ARCH_5T__\
+      || defined __ARM_ARCH_5TE__ || defined __ARM_ARCH_5TEJ__ \
+      || __ARM_ARCH__ >= 6
+
+#if defined L_call_via_rX
+
+/* These labels & instructions are used by the Arm/Thumb interworking code. 
+   The address of function to be called is loaded into a register and then 
+   one of these labels is called via a BL instruction.  This puts the 
+   return address into the link register with the bottom bit set, and the 
+   code here switches to the correct mode before executing the function.  */
+	
+	.text
+	.align 0
+        .force_thumb
+
+.macro call_via register
+	THUMB_FUNC_START _call_via_\register
+
+	bx	\register
+	nop
+
+	SIZE	(_call_via_\register)
+.endm
+
+	call_via r0
+	call_via r1
+	call_via r2
+	call_via r3
+	call_via r4
+	call_via r5
+	call_via r6
+	call_via r7
+	call_via r8
+	call_via r9
+	call_via sl
+	call_via fp
+	call_via ip
+	call_via sp
+	call_via lr
+
+#endif /* L_call_via_rX */
+
+/* Don't bother with the old interworking routines for Thumb-2.  */
+/* ??? Maybe only omit these on v7m.  */
+#ifndef __thumb2__
+
+#if defined L_interwork_call_via_rX
+
+/* These labels & instructions are used by the Arm/Thumb interworking code,
+   when the target address is in an unknown instruction set.  The address 
+   of function to be called is loaded into a register and then one of these
+   labels is called via a BL instruction.  This puts the return address 
+   into the link register with the bottom bit set, and the code here 
+   switches to the correct mode before executing the function.  Unfortunately
+   the target code cannot be relied upon to return via a BX instruction, so
+   instead we have to store the resturn address on the stack and allow the
+   called function to return here instead.  Upon return we recover the real
+   return address and use a BX to get back to Thumb mode.
+
+   There are three variations of this code.  The first,
+   _interwork_call_via_rN(), will push the return address onto the
+   stack and pop it in _arm_return().  It should only be used if all
+   arguments are passed in registers.
+
+   The second, _interwork_r7_call_via_rN(), instead stores the return
+   address at [r7, #-4].  It is the caller's responsibility to ensure
+   that this address is valid and contains no useful data.
+
+   The third, _interwork_r11_call_via_rN(), works in the same way but
+   uses r11 instead of r7.  It is useful if the caller does not really
+   need a frame pointer.  */
+	
+	.text
+	.align 0
+
+	.code   32
+	.globl _arm_return
+LSYM(Lstart_arm_return):
+	cfi_start	LSYM(Lstart_arm_return) LSYM(Lend_arm_return)
+	cfi_push	0, 0xe, -0x8, 0x8
+	nop	@ This nop is for the benefit of debuggers, so that
+		@ backtraces will use the correct unwind information.
+_arm_return:
+	RETLDM	unwind=LSYM(Lstart_arm_return)
+	cfi_end	LSYM(Lend_arm_return)
+
+	.globl _arm_return_r7
+_arm_return_r7:
+	ldr	lr, [r7, #-4]
+	bx	lr
+
+	.globl _arm_return_r11
+_arm_return_r11:
+	ldr	lr, [r11, #-4]
+	bx	lr
+
+.macro interwork_with_frame frame, register, name, return
+	.code	16
+
+	THUMB_FUNC_START \name
+
+	bx	pc
+	nop
+
+	.code	32
+	tst	\register, #1
+	streq	lr, [\frame, #-4]
+	adreq	lr, _arm_return_\frame
+	bx	\register
+
+	SIZE	(\name)
+.endm
+
+.macro interwork register
+	.code	16
+
+	THUMB_FUNC_START _interwork_call_via_\register
+
+	bx	pc
+	nop
+
+	.code	32
+	.globl LSYM(Lchange_\register)
+LSYM(Lchange_\register):
+	tst	\register, #1
+	streq	lr, [sp, #-8]!
+	adreq	lr, _arm_return
+	bx	\register
+
+	SIZE	(_interwork_call_via_\register)
+
+	interwork_with_frame r7,\register,_interwork_r7_call_via_\register
+	interwork_with_frame r11,\register,_interwork_r11_call_via_\register
+.endm
+	
+	interwork r0
+	interwork r1
+	interwork r2
+	interwork r3
+	interwork r4
+	interwork r5
+	interwork r6
+	interwork r7
+	interwork r8
+	interwork r9
+	interwork sl
+	interwork fp
+	interwork ip
+	interwork sp
+	
+	/* The LR case has to be handled a little differently...  */
+	.code 16
+
+	THUMB_FUNC_START _interwork_call_via_lr
+
+	bx 	pc
+	nop
+	
+	.code 32
+	.globl .Lchange_lr
+.Lchange_lr:
+	tst	lr, #1
+	stmeqdb	r13!, {lr, pc}
+	mov	ip, lr
+	adreq	lr, _arm_return
+	bx	ip
+	
+	SIZE	(_interwork_call_via_lr)
+	
+#endif /* L_interwork_call_via_rX */
+#endif /* !__thumb2__ */
+#endif /* Arch supports thumb.  */
+
+#ifndef __symbian__
+//#include "ieee754-df.S"
+//#include "ieee754-sf.S"
+#include "bpabi.S"
+#endif /* __symbian__ */
diff --git a/setup/Linux/arm/longlong.h b/setup/Linux/arm/longlong.h
new file mode 100644
index 0000000..a2f4e56
--- /dev/null
+++ b/setup/Linux/arm/longlong.h
@@ -0,0 +1,1465 @@
+/* longlong.h -- definitions for mixed size 32/64 bit arithmetic.
+   Copyright (C) 1991, 1992, 1994, 1995, 1996, 1997, 1998, 1999, 2000,
+   2001, 2002, 2003, 2004, 2005, 2006, 2007, 2009
+   Free Software Foundation, Inc.
+
+   This file is part of the GNU C Library.
+
+   The GNU C Library is free software; you can redistribute it and/or
+   modify it under the terms of the GNU Lesser General Public
+   License as published by the Free Software Foundation; either
+   version 2.1 of the License, or (at your option) any later version.
+
+   In addition to the permissions in the GNU Lesser General Public
+   License, the Free Software Foundation gives you unlimited
+   permission to link the compiled version of this file into
+   combinations with other programs, and to distribute those
+   combinations without any restriction coming from the use of this
+   file.  (The Lesser General Public License restrictions do apply in
+   other respects; for example, they cover modification of the file,
+   and distribution when not linked into a combine executable.)
+
+   The GNU C Library is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+   Lesser General Public License for more details.
+
+   You should have received a copy of the GNU Lesser General Public
+   License along with the GNU C Library; if not, write to the Free
+   Software Foundation, 51 Franklin Street, Fifth Floor, Boston,
+   MA 02110-1301, USA.  */
+
+/* You have to define the following before including this file:
+
+   UWtype -- An unsigned type, default type for operations (typically a "word")
+   UHWtype -- An unsigned type, at least half the size of UWtype.
+   UDWtype -- An unsigned type, at least twice as large a UWtype
+   W_TYPE_SIZE -- size in bits of UWtype
+
+   UQItype -- Unsigned 8 bit type.
+   SItype, USItype -- Signed and unsigned 32 bit types.
+   DItype, UDItype -- Signed and unsigned 64 bit types.
+
+   On a 32 bit machine UWtype should typically be USItype;
+   on a 64 bit machine, UWtype should typically be UDItype.  */
+
+#define __BITS4 (W_TYPE_SIZE / 4)
+#define __ll_B ((UWtype) 1 << (W_TYPE_SIZE / 2))
+#define __ll_lowpart(t) ((UWtype) (t) & (__ll_B - 1))
+#define __ll_highpart(t) ((UWtype) (t) >> (W_TYPE_SIZE / 2))
+
+#ifndef W_TYPE_SIZE
+#define W_TYPE_SIZE	32
+#define UWtype		USItype
+#define UHWtype		USItype
+#define UDWtype		UDItype
+#endif
+
+extern const UQItype __clz_tab[256];
+
+/* Define auxiliary asm macros.
+
+   1) umul_ppmm(high_prod, low_prod, multiplier, multiplicand) multiplies two
+   UWtype integers MULTIPLIER and MULTIPLICAND, and generates a two UWtype
+   word product in HIGH_PROD and LOW_PROD.
+
+   2) __umulsidi3(a,b) multiplies two UWtype integers A and B, and returns a
+   UDWtype product.  This is just a variant of umul_ppmm.
+
+   3) udiv_qrnnd(quotient, remainder, high_numerator, low_numerator,
+   denominator) divides a UDWtype, composed by the UWtype integers
+   HIGH_NUMERATOR and LOW_NUMERATOR, by DENOMINATOR and places the quotient
+   in QUOTIENT and the remainder in REMAINDER.  HIGH_NUMERATOR must be less
+   than DENOMINATOR for correct operation.  If, in addition, the most
+   significant bit of DENOMINATOR must be 1, then the pre-processor symbol
+   UDIV_NEEDS_NORMALIZATION is defined to 1.
+
+   4) sdiv_qrnnd(quotient, remainder, high_numerator, low_numerator,
+   denominator).  Like udiv_qrnnd but the numbers are signed.  The quotient
+   is rounded towards 0.
+
+   5) count_leading_zeros(count, x) counts the number of zero-bits from the
+   msb to the first nonzero bit in the UWtype X.  This is the number of
+   steps X needs to be shifted left to set the msb.  Undefined for X == 0,
+   unless the symbol COUNT_LEADING_ZEROS_0 is defined to some value.
+
+   6) count_trailing_zeros(count, x) like count_leading_zeros, but counts
+   from the least significant end.
+
+   7) add_ssaaaa(high_sum, low_sum, high_addend_1, low_addend_1,
+   high_addend_2, low_addend_2) adds two UWtype integers, composed by
+   HIGH_ADDEND_1 and LOW_ADDEND_1, and HIGH_ADDEND_2 and LOW_ADDEND_2
+   respectively.  The result is placed in HIGH_SUM and LOW_SUM.  Overflow
+   (i.e. carry out) is not stored anywhere, and is lost.
+
+   8) sub_ddmmss(high_difference, low_difference, high_minuend, low_minuend,
+   high_subtrahend, low_subtrahend) subtracts two two-word UWtype integers,
+   composed by HIGH_MINUEND_1 and LOW_MINUEND_1, and HIGH_SUBTRAHEND_2 and
+   LOW_SUBTRAHEND_2 respectively.  The result is placed in HIGH_DIFFERENCE
+   and LOW_DIFFERENCE.  Overflow (i.e. carry out) is not stored anywhere,
+   and is lost.
+
+   If any of these macros are left undefined for a particular CPU,
+   C macros are used.  */
+
+/* The CPUs come in alphabetical order below.
+
+   Please add support for more CPUs here, or improve the current support
+   for the CPUs below!
+   (E.g. WE32100, IBM360.)  */
+
+#if defined (__GNUC__) && !defined (NO_ASM)
+
+/* We sometimes need to clobber "cc" with gcc2, but that would not be
+   understood by gcc1.  Use cpp to avoid major code duplication.  */
+#if __GNUC__ < 2
+#define __CLOBBER_CC
+#define __AND_CLOBBER_CC
+#else /* __GNUC__ >= 2 */
+#define __CLOBBER_CC : "cc"
+#define __AND_CLOBBER_CC , "cc"
+#endif /* __GNUC__ < 2 */
+
+#if defined (__alpha) && W_TYPE_SIZE == 64
+#define umul_ppmm(ph, pl, m0, m1) \
+  do {									\
+    UDItype __m0 = (m0), __m1 = (m1);					\
+    (ph) = __builtin_alpha_umulh (__m0, __m1);				\
+    (pl) = __m0 * __m1;							\
+  } while (0)
+#define UMUL_TIME 46
+#ifndef LONGLONG_STANDALONE
+#define udiv_qrnnd(q, r, n1, n0, d) \
+  do { UDItype __r;							\
+    (q) = __udiv_qrnnd (&__r, (n1), (n0), (d));				\
+    (r) = __r;								\
+  } while (0)
+extern UDItype __udiv_qrnnd (UDItype *, UDItype, UDItype, UDItype);
+#define UDIV_TIME 220
+#endif /* LONGLONG_STANDALONE */
+#ifdef __alpha_cix__
+#define count_leading_zeros(COUNT,X)	((COUNT) = __builtin_clzl (X))
+#define count_trailing_zeros(COUNT,X)	((COUNT) = __builtin_ctzl (X))
+#define COUNT_LEADING_ZEROS_0 64
+#else
+#define count_leading_zeros(COUNT,X) \
+  do {									\
+    UDItype __xr = (X), __t, __a;					\
+    __t = __builtin_alpha_cmpbge (0, __xr);				\
+    __a = __clz_tab[__t ^ 0xff] - 1;					\
+    __t = __builtin_alpha_extbl (__xr, __a);				\
+    (COUNT) = 64 - (__clz_tab[__t] + __a*8);				\
+  } while (0)
+#define count_trailing_zeros(COUNT,X) \
+  do {									\
+    UDItype __xr = (X), __t, __a;					\
+    __t = __builtin_alpha_cmpbge (0, __xr);				\
+    __t = ~__t & -~__t;							\
+    __a = ((__t & 0xCC) != 0) * 2;					\
+    __a += ((__t & 0xF0) != 0) * 4;					\
+    __a += ((__t & 0xAA) != 0);						\
+    __t = __builtin_alpha_extbl (__xr, __a);				\
+    __a <<= 3;								\
+    __t &= -__t;							\
+    __a += ((__t & 0xCC) != 0) * 2;					\
+    __a += ((__t & 0xF0) != 0) * 4;					\
+    __a += ((__t & 0xAA) != 0);						\
+    (COUNT) = __a;							\
+  } while (0)
+#endif /* __alpha_cix__ */
+#endif /* __alpha */
+
+#if defined (__arc__) && W_TYPE_SIZE == 32
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+  __asm__ ("add.f	%1, %4, %5\n\tadc	%0, %2, %3"		\
+	   : "=r" ((USItype) (sh)),					\
+	     "=&r" ((USItype) (sl))					\
+	   : "%r" ((USItype) (ah)),					\
+	     "rIJ" ((USItype) (bh)),					\
+	     "%r" ((USItype) (al)),					\
+	     "rIJ" ((USItype) (bl)))
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+  __asm__ ("sub.f	%1, %4, %5\n\tsbc	%0, %2, %3"		\
+	   : "=r" ((USItype) (sh)),					\
+	     "=&r" ((USItype) (sl))					\
+	   : "r" ((USItype) (ah)),					\
+	     "rIJ" ((USItype) (bh)),					\
+	     "r" ((USItype) (al)),					\
+	     "rIJ" ((USItype) (bl)))
+/* Call libgcc routine.  */
+#define umul_ppmm(w1, w0, u, v) \
+do {									\
+  DWunion __w;								\
+  __w.ll = __umulsidi3 (u, v);						\
+  w1 = __w.s.high;							\
+  w0 = __w.s.low;							\
+} while (0)
+#define __umulsidi3 __umulsidi3
+UDItype __umulsidi3 (USItype, USItype);
+#endif
+
+#if defined (__arm__) && !defined (__thumb__) && W_TYPE_SIZE == 32
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+  __asm__ ("adds	%1, %4, %5\n\tadc	%0, %2, %3"		\
+	   : "=r" ((USItype) (sh)),					\
+	     "=&r" ((USItype) (sl))					\
+	   : "%r" ((USItype) (ah)),					\
+	     "rI" ((USItype) (bh)),					\
+	     "%r" ((USItype) (al)),					\
+	     "rI" ((USItype) (bl)) __CLOBBER_CC)
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+  __asm__ ("subs	%1, %4, %5\n\tsbc	%0, %2, %3"		\
+	   : "=r" ((USItype) (sh)),					\
+	     "=&r" ((USItype) (sl))					\
+	   : "r" ((USItype) (ah)),					\
+	     "rI" ((USItype) (bh)),					\
+	     "r" ((USItype) (al)),					\
+	     "rI" ((USItype) (bl)) __CLOBBER_CC)
+#define umul_ppmm(xh, xl, a, b) \
+{register USItype __t0, __t1, __t2;					\
+  __asm__ ("%@ Inlined umul_ppmm\n"					\
+	   "	mov	%2, %5, lsr #16\n"				\
+	   "	mov	%0, %6, lsr #16\n"				\
+	   "	bic	%3, %5, %2, lsl #16\n"				\
+	   "	bic	%4, %6, %0, lsl #16\n"				\
+	   "	mul	%1, %3, %4\n"					\
+	   "	mul	%4, %2, %4\n"					\
+	   "	mul	%3, %0, %3\n"					\
+	   "	mul	%0, %2, %0\n"					\
+	   "	adds	%3, %4, %3\n"					\
+	   "	addcs	%0, %0, #65536\n"				\
+	   "	adds	%1, %1, %3, lsl #16\n"				\
+	   "	adc	%0, %0, %3, lsr #16"				\
+	   : "=&r" ((USItype) (xh)),					\
+	     "=r" ((USItype) (xl)),					\
+	     "=&r" (__t0), "=&r" (__t1), "=r" (__t2)			\
+	   : "r" ((USItype) (a)),					\
+	     "r" ((USItype) (b)) __CLOBBER_CC );}
+#define UMUL_TIME 20
+#define UDIV_TIME 100
+#endif /* __arm__ */
+
+#if defined (__CRIS__) && __CRIS_arch_version >= 3
+#define count_leading_zeros(COUNT, X) ((COUNT) = __builtin_clz (X))
+#if __CRIS_arch_version >= 8
+#define count_trailing_zeros(COUNT, X) ((COUNT) = __builtin_ctz (X))
+#endif
+#endif /* __CRIS__ */
+
+#if defined (__hppa) && W_TYPE_SIZE == 32
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+  __asm__ ("add %4,%5,%1\n\taddc %2,%3,%0"				\
+	   : "=r" ((USItype) (sh)),					\
+	     "=&r" ((USItype) (sl))					\
+	   : "%rM" ((USItype) (ah)),					\
+	     "rM" ((USItype) (bh)),					\
+	     "%rM" ((USItype) (al)),					\
+	     "rM" ((USItype) (bl)))
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+  __asm__ ("sub %4,%5,%1\n\tsubb %2,%3,%0"				\
+	   : "=r" ((USItype) (sh)),					\
+	     "=&r" ((USItype) (sl))					\
+	   : "rM" ((USItype) (ah)),					\
+	     "rM" ((USItype) (bh)),					\
+	     "rM" ((USItype) (al)),					\
+	     "rM" ((USItype) (bl)))
+#if defined (_PA_RISC1_1)
+#define umul_ppmm(w1, w0, u, v) \
+  do {									\
+    union								\
+      {									\
+	UDItype __f;							\
+	struct {USItype __w1, __w0;} __w1w0;				\
+      } __t;								\
+    __asm__ ("xmpyu %1,%2,%0"						\
+	     : "=x" (__t.__f)						\
+	     : "x" ((USItype) (u)),					\
+	       "x" ((USItype) (v)));					\
+    (w1) = __t.__w1w0.__w1;						\
+    (w0) = __t.__w1w0.__w0;						\
+     } while (0)
+#define UMUL_TIME 8
+#else
+#define UMUL_TIME 30
+#endif
+#define UDIV_TIME 40
+#define count_leading_zeros(count, x) \
+  do {									\
+    USItype __tmp;							\
+    __asm__ (								\
+       "ldi		1,%0\n"						\
+"	extru,=		%1,15,16,%%r0		; Bits 31..16 zero?\n"	\
+"	extru,tr	%1,15,16,%1		; No.  Shift down, skip add.\n"\
+"	ldo		16(%0),%0		; Yes.  Perform add.\n"	\
+"	extru,=		%1,23,8,%%r0		; Bits 15..8 zero?\n"	\
+"	extru,tr	%1,23,8,%1		; No.  Shift down, skip add.\n"\
+"	ldo		8(%0),%0		; Yes.  Perform add.\n"	\
+"	extru,=		%1,27,4,%%r0		; Bits 7..4 zero?\n"	\
+"	extru,tr	%1,27,4,%1		; No.  Shift down, skip add.\n"\
+"	ldo		4(%0),%0		; Yes.  Perform add.\n"	\
+"	extru,=		%1,29,2,%%r0		; Bits 3..2 zero?\n"	\
+"	extru,tr	%1,29,2,%1		; No.  Shift down, skip add.\n"\
+"	ldo		2(%0),%0		; Yes.  Perform add.\n"	\
+"	extru		%1,30,1,%1		; Extract bit 1.\n"	\
+"	sub		%0,%1,%0		; Subtract it.\n"	\
+	: "=r" (count), "=r" (__tmp) : "1" (x));			\
+  } while (0)
+#endif
+
+#if (defined (__i370__) || defined (__s390__) || defined (__mvs__)) && W_TYPE_SIZE == 32
+#define smul_ppmm(xh, xl, m0, m1) \
+  do {									\
+    union {DItype __ll;							\
+	   struct {USItype __h, __l;} __i;				\
+	  } __x;							\
+    __asm__ ("lr %N0,%1\n\tmr %0,%2"					\
+	     : "=&r" (__x.__ll)						\
+	     : "r" (m0), "r" (m1));					\
+    (xh) = __x.__i.__h; (xl) = __x.__i.__l;				\
+  } while (0)
+#define sdiv_qrnnd(q, r, n1, n0, d) \
+  do {									\
+    union {DItype __ll;							\
+	   struct {USItype __h, __l;} __i;				\
+	  } __x;							\
+    __x.__i.__h = n1; __x.__i.__l = n0;					\
+    __asm__ ("dr %0,%2"							\
+	     : "=r" (__x.__ll)						\
+	     : "0" (__x.__ll), "r" (d));				\
+    (q) = __x.__i.__l; (r) = __x.__i.__h;				\
+  } while (0)
+#endif
+
+#if (defined (__i386__) || defined (__i486__)) && W_TYPE_SIZE == 32
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+  __asm__ ("add{l} {%5,%1|%1,%5}\n\tadc{l} {%3,%0|%0,%3}"		\
+	   : "=r" ((USItype) (sh)),					\
+	     "=&r" ((USItype) (sl))					\
+	   : "%0" ((USItype) (ah)),					\
+	     "g" ((USItype) (bh)),					\
+	     "%1" ((USItype) (al)),					\
+	     "g" ((USItype) (bl)))
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+  __asm__ ("sub{l} {%5,%1|%1,%5}\n\tsbb{l} {%3,%0|%0,%3}"		\
+	   : "=r" ((USItype) (sh)),					\
+	     "=&r" ((USItype) (sl))					\
+	   : "0" ((USItype) (ah)),					\
+	     "g" ((USItype) (bh)),					\
+	     "1" ((USItype) (al)),					\
+	     "g" ((USItype) (bl)))
+#define umul_ppmm(w1, w0, u, v) \
+  __asm__ ("mul{l} %3"							\
+	   : "=a" ((USItype) (w0)),					\
+	     "=d" ((USItype) (w1))					\
+	   : "%0" ((USItype) (u)),					\
+	     "rm" ((USItype) (v)))
+#define udiv_qrnnd(q, r, n1, n0, dv) \
+  __asm__ ("div{l} %4"							\
+	   : "=a" ((USItype) (q)),					\
+	     "=d" ((USItype) (r))					\
+	   : "0" ((USItype) (n0)),					\
+	     "1" ((USItype) (n1)),					\
+	     "rm" ((USItype) (dv)))
+#define count_leading_zeros(count, x)	((count) = __builtin_clz (x))
+#define count_trailing_zeros(count, x)	((count) = __builtin_ctz (x))
+#define UMUL_TIME 40
+#define UDIV_TIME 40
+#endif /* 80x86 */
+
+#if (defined (__x86_64__) || defined (__i386__)) && W_TYPE_SIZE == 64
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+  __asm__ ("add{q} {%5,%1|%1,%5}\n\tadc{q} {%3,%0|%0,%3}"		\
+	   : "=r" ((UDItype) (sh)),					\
+	     "=&r" ((UDItype) (sl))					\
+	   : "%0" ((UDItype) (ah)),					\
+	     "rme" ((UDItype) (bh)),					\
+	     "%1" ((UDItype) (al)),					\
+	     "rme" ((UDItype) (bl)))
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+  __asm__ ("sub{q} {%5,%1|%1,%5}\n\tsbb{q} {%3,%0|%0,%3}"		\
+	   : "=r" ((UDItype) (sh)),					\
+	     "=&r" ((UDItype) (sl))					\
+	   : "0" ((UDItype) (ah)),					\
+	     "rme" ((UDItype) (bh)),					\
+	     "1" ((UDItype) (al)),					\
+	     "rme" ((UDItype) (bl)))
+#define umul_ppmm(w1, w0, u, v) \
+  __asm__ ("mul{q} %3"							\
+	   : "=a" ((UDItype) (w0)),					\
+	     "=d" ((UDItype) (w1))					\
+	   : "%0" ((UDItype) (u)),					\
+	     "rm" ((UDItype) (v)))
+#define udiv_qrnnd(q, r, n1, n0, dv) \
+  __asm__ ("div{q} %4"							\
+	   : "=a" ((UDItype) (q)),					\
+	     "=d" ((UDItype) (r))					\
+	   : "0" ((UDItype) (n0)),					\
+	     "1" ((UDItype) (n1)),					\
+	     "rm" ((UDItype) (dv)))
+#define count_leading_zeros(count, x)	((count) = __builtin_clzl (x))
+#define count_trailing_zeros(count, x)	((count) = __builtin_ctzl (x))
+#define UMUL_TIME 40
+#define UDIV_TIME 40
+#endif /* x86_64 */
+
+#if defined (__i960__) && W_TYPE_SIZE == 32
+#define umul_ppmm(w1, w0, u, v) \
+  ({union {UDItype __ll;						\
+	   struct {USItype __l, __h;} __i;				\
+	  } __xx;							\
+  __asm__ ("emul	%2,%1,%0"					\
+	   : "=d" (__xx.__ll)						\
+	   : "%dI" ((USItype) (u)),					\
+	     "dI" ((USItype) (v)));					\
+  (w1) = __xx.__i.__h; (w0) = __xx.__i.__l;})
+#define __umulsidi3(u, v) \
+  ({UDItype __w;							\
+    __asm__ ("emul	%2,%1,%0"					\
+	     : "=d" (__w)						\
+	     : "%dI" ((USItype) (u)),					\
+	       "dI" ((USItype) (v)));					\
+    __w; })
+#endif /* __i960__ */
+
+#if defined (__M32R__) && W_TYPE_SIZE == 32
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+  /* The cmp clears the condition bit.  */ \
+  __asm__ ("cmp %0,%0\n\taddx %1,%5\n\taddx %0,%3"			\
+	   : "=r" ((USItype) (sh)),					\
+	     "=&r" ((USItype) (sl))					\
+	   : "0" ((USItype) (ah)),					\
+	     "r" ((USItype) (bh)),					\
+	     "1" ((USItype) (al)),					\
+	     "r" ((USItype) (bl))					\
+	   : "cbit")
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+  /* The cmp clears the condition bit.  */ \
+  __asm__ ("cmp %0,%0\n\tsubx %1,%5\n\tsubx %0,%3"			\
+	   : "=r" ((USItype) (sh)),					\
+	     "=&r" ((USItype) (sl))					\
+	   : "0" ((USItype) (ah)),					\
+	     "r" ((USItype) (bh)),					\
+	     "1" ((USItype) (al)),					\
+	     "r" ((USItype) (bl))					\
+	   : "cbit")
+#endif /* __M32R__ */
+
+#if defined (__mc68000__) && W_TYPE_SIZE == 32
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+  __asm__ ("add%.l %5,%1\n\taddx%.l %3,%0"				\
+	   : "=d" ((USItype) (sh)),					\
+	     "=&d" ((USItype) (sl))					\
+	   : "%0" ((USItype) (ah)),					\
+	     "d" ((USItype) (bh)),					\
+	     "%1" ((USItype) (al)),					\
+	     "g" ((USItype) (bl)))
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+  __asm__ ("sub%.l %5,%1\n\tsubx%.l %3,%0"				\
+	   : "=d" ((USItype) (sh)),					\
+	     "=&d" ((USItype) (sl))					\
+	   : "0" ((USItype) (ah)),					\
+	     "d" ((USItype) (bh)),					\
+	     "1" ((USItype) (al)),					\
+	     "g" ((USItype) (bl)))
+
+/* The '020, '030, '040, '060 and CPU32 have 32x32->64 and 64/32->32q-32r.  */
+#if (defined (__mc68020__) && !defined (__mc68060__))
+#define umul_ppmm(w1, w0, u, v) \
+  __asm__ ("mulu%.l %3,%1:%0"						\
+	   : "=d" ((USItype) (w0)),					\
+	     "=d" ((USItype) (w1))					\
+	   : "%0" ((USItype) (u)),					\
+	     "dmi" ((USItype) (v)))
+#define UMUL_TIME 45
+#define udiv_qrnnd(q, r, n1, n0, d) \
+  __asm__ ("divu%.l %4,%1:%0"						\
+	   : "=d" ((USItype) (q)),					\
+	     "=d" ((USItype) (r))					\
+	   : "0" ((USItype) (n0)),					\
+	     "1" ((USItype) (n1)),					\
+	     "dmi" ((USItype) (d)))
+#define UDIV_TIME 90
+#define sdiv_qrnnd(q, r, n1, n0, d) \
+  __asm__ ("divs%.l %4,%1:%0"						\
+	   : "=d" ((USItype) (q)),					\
+	     "=d" ((USItype) (r))					\
+	   : "0" ((USItype) (n0)),					\
+	     "1" ((USItype) (n1)),					\
+	     "dmi" ((USItype) (d)))
+
+#elif defined (__mcoldfire__) /* not mc68020 */
+
+#define umul_ppmm(xh, xl, a, b) \
+  __asm__ ("| Inlined umul_ppmm\n"					\
+	   "	move%.l	%2,%/d0\n"					\
+	   "	move%.l	%3,%/d1\n"					\
+	   "	move%.l	%/d0,%/d2\n"					\
+	   "	swap	%/d0\n"						\
+	   "	move%.l	%/d1,%/d3\n"					\
+	   "	swap	%/d1\n"						\
+	   "	move%.w	%/d2,%/d4\n"					\
+	   "	mulu	%/d3,%/d4\n"					\
+	   "	mulu	%/d1,%/d2\n"					\
+	   "	mulu	%/d0,%/d3\n"					\
+	   "	mulu	%/d0,%/d1\n"					\
+	   "	move%.l	%/d4,%/d0\n"					\
+	   "	clr%.w	%/d0\n"						\
+	   "	swap	%/d0\n"						\
+	   "	add%.l	%/d0,%/d2\n"					\
+	   "	add%.l	%/d3,%/d2\n"					\
+	   "	jcc	1f\n"						\
+	   "	add%.l	%#65536,%/d1\n"					\
+	   "1:	swap	%/d2\n"						\
+	   "	moveq	%#0,%/d0\n"					\
+	   "	move%.w	%/d2,%/d0\n"					\
+	   "	move%.w	%/d4,%/d2\n"					\
+	   "	move%.l	%/d2,%1\n"					\
+	   "	add%.l	%/d1,%/d0\n"					\
+	   "	move%.l	%/d0,%0"					\
+	   : "=g" ((USItype) (xh)),					\
+	     "=g" ((USItype) (xl))					\
+	   : "g" ((USItype) (a)),					\
+	     "g" ((USItype) (b))					\
+	   : "d0", "d1", "d2", "d3", "d4")
+#define UMUL_TIME 100
+#define UDIV_TIME 400
+#else /* not ColdFire */
+/* %/ inserts REGISTER_PREFIX, %# inserts IMMEDIATE_PREFIX.  */
+#define umul_ppmm(xh, xl, a, b) \
+  __asm__ ("| Inlined umul_ppmm\n"					\
+	   "	move%.l	%2,%/d0\n"					\
+	   "	move%.l	%3,%/d1\n"					\
+	   "	move%.l	%/d0,%/d2\n"					\
+	   "	swap	%/d0\n"						\
+	   "	move%.l	%/d1,%/d3\n"					\
+	   "	swap	%/d1\n"						\
+	   "	move%.w	%/d2,%/d4\n"					\
+	   "	mulu	%/d3,%/d4\n"					\
+	   "	mulu	%/d1,%/d2\n"					\
+	   "	mulu	%/d0,%/d3\n"					\
+	   "	mulu	%/d0,%/d1\n"					\
+	   "	move%.l	%/d4,%/d0\n"					\
+	   "	eor%.w	%/d0,%/d0\n"					\
+	   "	swap	%/d0\n"						\
+	   "	add%.l	%/d0,%/d2\n"					\
+	   "	add%.l	%/d3,%/d2\n"					\
+	   "	jcc	1f\n"						\
+	   "	add%.l	%#65536,%/d1\n"					\
+	   "1:	swap	%/d2\n"						\
+	   "	moveq	%#0,%/d0\n"					\
+	   "	move%.w	%/d2,%/d0\n"					\
+	   "	move%.w	%/d4,%/d2\n"					\
+	   "	move%.l	%/d2,%1\n"					\
+	   "	add%.l	%/d1,%/d0\n"					\
+	   "	move%.l	%/d0,%0"					\
+	   : "=g" ((USItype) (xh)),					\
+	     "=g" ((USItype) (xl))					\
+	   : "g" ((USItype) (a)),					\
+	     "g" ((USItype) (b))					\
+	   : "d0", "d1", "d2", "d3", "d4")
+#define UMUL_TIME 100
+#define UDIV_TIME 400
+
+#endif /* not mc68020 */
+
+/* The '020, '030, '040 and '060 have bitfield insns.
+   cpu32 disguises as a 68020, but lacks them.  */
+#if defined (__mc68020__) && !defined (__mcpu32__)
+#define count_leading_zeros(count, x) \
+  __asm__ ("bfffo %1{%b2:%b2},%0"					\
+	   : "=d" ((USItype) (count))					\
+	   : "od" ((USItype) (x)), "n" (0))
+/* Some ColdFire architectures have a ff1 instruction supported via
+   __builtin_clz. */
+#elif defined (__mcfisaaplus__) || defined (__mcfisac__)
+#define count_leading_zeros(count,x) ((count) = __builtin_clz (x))
+#define COUNT_LEADING_ZEROS_0 32
+#endif
+#endif /* mc68000 */
+
+#if defined (__m88000__) && W_TYPE_SIZE == 32
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+  __asm__ ("addu.co %1,%r4,%r5\n\taddu.ci %0,%r2,%r3"			\
+	   : "=r" ((USItype) (sh)),					\
+	     "=&r" ((USItype) (sl))					\
+	   : "%rJ" ((USItype) (ah)),					\
+	     "rJ" ((USItype) (bh)),					\
+	     "%rJ" ((USItype) (al)),					\
+	     "rJ" ((USItype) (bl)))
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+  __asm__ ("subu.co %1,%r4,%r5\n\tsubu.ci %0,%r2,%r3"			\
+	   : "=r" ((USItype) (sh)),					\
+	     "=&r" ((USItype) (sl))					\
+	   : "rJ" ((USItype) (ah)),					\
+	     "rJ" ((USItype) (bh)),					\
+	     "rJ" ((USItype) (al)),					\
+	     "rJ" ((USItype) (bl)))
+#define count_leading_zeros(count, x) \
+  do {									\
+    USItype __cbtmp;							\
+    __asm__ ("ff1 %0,%1"						\
+	     : "=r" (__cbtmp)						\
+	     : "r" ((USItype) (x)));					\
+    (count) = __cbtmp ^ 31;						\
+  } while (0)
+#define COUNT_LEADING_ZEROS_0 63 /* sic */
+#if defined (__mc88110__)
+#define umul_ppmm(wh, wl, u, v) \
+  do {									\
+    union {UDItype __ll;						\
+	   struct {USItype __h, __l;} __i;				\
+	  } __xx;							\
+    __asm__ ("mulu.d	%0,%1,%2"					\
+	     : "=r" (__xx.__ll)						\
+	     : "r" ((USItype) (u)),					\
+	       "r" ((USItype) (v)));					\
+    (wh) = __xx.__i.__h;						\
+    (wl) = __xx.__i.__l;						\
+  } while (0)
+#define udiv_qrnnd(q, r, n1, n0, d) \
+  ({union {UDItype __ll;						\
+	   struct {USItype __h, __l;} __i;				\
+	  } __xx;							\
+  USItype __q;								\
+  __xx.__i.__h = (n1); __xx.__i.__l = (n0);				\
+  __asm__ ("divu.d %0,%1,%2"						\
+	   : "=r" (__q)							\
+	   : "r" (__xx.__ll),						\
+	     "r" ((USItype) (d)));					\
+  (r) = (n0) - __q * (d); (q) = __q; })
+#define UMUL_TIME 5
+#define UDIV_TIME 25
+#else
+#define UMUL_TIME 17
+#define UDIV_TIME 150
+#endif /* __mc88110__ */
+#endif /* __m88000__ */
+
+#if defined (__mips__) && W_TYPE_SIZE == 32
+#define umul_ppmm(w1, w0, u, v) \
+  __asm__ ("multu %2,%3"						\
+	   : "=l" ((USItype) (w0)),					\
+	     "=h" ((USItype) (w1))					\
+	   : "d" ((USItype) (u)),					\
+	     "d" ((USItype) (v)))
+#define UMUL_TIME 10
+#define UDIV_TIME 100
+
+#if (__mips == 32 || __mips == 64) && ! __mips16
+#define count_leading_zeros(COUNT,X)	((COUNT) = __builtin_clz (X))
+#define COUNT_LEADING_ZEROS_0 32
+#endif
+#endif /* __mips__ */
+
+#if defined (__ns32000__) && W_TYPE_SIZE == 32
+#define umul_ppmm(w1, w0, u, v) \
+  ({union {UDItype __ll;						\
+	   struct {USItype __l, __h;} __i;				\
+	  } __xx;							\
+  __asm__ ("meid %2,%0"							\
+	   : "=g" (__xx.__ll)						\
+	   : "%0" ((USItype) (u)),					\
+	     "g" ((USItype) (v)));					\
+  (w1) = __xx.__i.__h; (w0) = __xx.__i.__l;})
+#define __umulsidi3(u, v) \
+  ({UDItype __w;							\
+    __asm__ ("meid %2,%0"						\
+	     : "=g" (__w)						\
+	     : "%0" ((USItype) (u)),					\
+	       "g" ((USItype) (v)));					\
+    __w; })
+#define udiv_qrnnd(q, r, n1, n0, d) \
+  ({union {UDItype __ll;						\
+	   struct {USItype __l, __h;} __i;				\
+	  } __xx;							\
+  __xx.__i.__h = (n1); __xx.__i.__l = (n0);				\
+  __asm__ ("deid %2,%0"							\
+	   : "=g" (__xx.__ll)						\
+	   : "0" (__xx.__ll),						\
+	     "g" ((USItype) (d)));					\
+  (r) = __xx.__i.__l; (q) = __xx.__i.__h; })
+#define count_trailing_zeros(count,x) \
+  do {									\
+    __asm__ ("ffsd     %2,%0"						\
+            : "=r" ((USItype) (count))					\
+            : "0" ((USItype) 0),					\
+              "r" ((USItype) (x)));					\
+  } while (0)
+#endif /* __ns32000__ */
+
+/* FIXME: We should test _IBMR2 here when we add assembly support for the
+   system vendor compilers.
+   FIXME: What's needed for gcc PowerPC VxWorks?  __vxworks__ is not good
+   enough, since that hits ARM and m68k too.  */
+#if (defined (_ARCH_PPC)	/* AIX */				\
+     || defined (_ARCH_PWR)	/* AIX */				\
+     || defined (_ARCH_COM)	/* AIX */				\
+     || defined (__powerpc__)	/* gcc */				\
+     || defined (__POWERPC__)	/* BEOS */				\
+     || defined (__ppc__)	/* Darwin */				\
+     || (defined (PPC) && ! defined (CPU_FAMILY)) /* gcc 2.7.x GNU&SysV */    \
+     || (defined (PPC) && defined (CPU_FAMILY)    /* VxWorks */               \
+         && CPU_FAMILY == PPC)                                                \
+     ) && W_TYPE_SIZE == 32
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+  do {									\
+    if (__builtin_constant_p (bh) && (bh) == 0)				\
+      __asm__ ("{a%I4|add%I4c} %1,%3,%4\n\t{aze|addze} %0,%2"		\
+	     : "=r" (sh), "=&r" (sl) : "r" (ah), "%r" (al), "rI" (bl));\
+    else if (__builtin_constant_p (bh) && (bh) == ~(USItype) 0)		\
+      __asm__ ("{a%I4|add%I4c} %1,%3,%4\n\t{ame|addme} %0,%2"		\
+	     : "=r" (sh), "=&r" (sl) : "r" (ah), "%r" (al), "rI" (bl));\
+    else								\
+      __asm__ ("{a%I5|add%I5c} %1,%4,%5\n\t{ae|adde} %0,%2,%3"		\
+	     : "=r" (sh), "=&r" (sl)					\
+	     : "%r" (ah), "r" (bh), "%r" (al), "rI" (bl));		\
+  } while (0)
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+  do {									\
+    if (__builtin_constant_p (ah) && (ah) == 0)				\
+      __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{sfze|subfze} %0,%2"	\
+	       : "=r" (sh), "=&r" (sl) : "r" (bh), "rI" (al), "r" (bl));\
+    else if (__builtin_constant_p (ah) && (ah) == ~(USItype) 0)		\
+      __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{sfme|subfme} %0,%2"	\
+	       : "=r" (sh), "=&r" (sl) : "r" (bh), "rI" (al), "r" (bl));\
+    else if (__builtin_constant_p (bh) && (bh) == 0)			\
+      __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{ame|addme} %0,%2"		\
+	       : "=r" (sh), "=&r" (sl) : "r" (ah), "rI" (al), "r" (bl));\
+    else if (__builtin_constant_p (bh) && (bh) == ~(USItype) 0)		\
+      __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{aze|addze} %0,%2"		\
+	       : "=r" (sh), "=&r" (sl) : "r" (ah), "rI" (al), "r" (bl));\
+    else								\
+      __asm__ ("{sf%I4|subf%I4c} %1,%5,%4\n\t{sfe|subfe} %0,%3,%2"	\
+	       : "=r" (sh), "=&r" (sl)					\
+	       : "r" (ah), "r" (bh), "rI" (al), "r" (bl));		\
+  } while (0)
+#define count_leading_zeros(count, x) \
+  __asm__ ("{cntlz|cntlzw} %0,%1" : "=r" (count) : "r" (x))
+#define COUNT_LEADING_ZEROS_0 32
+#if defined (_ARCH_PPC) || defined (__powerpc__) || defined (__POWERPC__) \
+  || defined (__ppc__)                                                    \
+  || (defined (PPC) && ! defined (CPU_FAMILY)) /* gcc 2.7.x GNU&SysV */       \
+  || (defined (PPC) && defined (CPU_FAMILY)    /* VxWorks */                  \
+         && CPU_FAMILY == PPC)
+#define umul_ppmm(ph, pl, m0, m1) \
+  do {									\
+    USItype __m0 = (m0), __m1 = (m1);					\
+    __asm__ ("mulhwu %0,%1,%2" : "=r" (ph) : "%r" (m0), "r" (m1));	\
+    (pl) = __m0 * __m1;							\
+  } while (0)
+#define UMUL_TIME 15
+#define smul_ppmm(ph, pl, m0, m1) \
+  do {									\
+    SItype __m0 = (m0), __m1 = (m1);					\
+    __asm__ ("mulhw %0,%1,%2" : "=r" (ph) : "%r" (m0), "r" (m1));	\
+    (pl) = __m0 * __m1;							\
+  } while (0)
+#define SMUL_TIME 14
+#define UDIV_TIME 120
+#elif defined (_ARCH_PWR)
+#define UMUL_TIME 8
+#define smul_ppmm(xh, xl, m0, m1) \
+  __asm__ ("mul %0,%2,%3" : "=r" (xh), "=q" (xl) : "r" (m0), "r" (m1))
+#define SMUL_TIME 4
+#define sdiv_qrnnd(q, r, nh, nl, d) \
+  __asm__ ("div %0,%2,%4" : "=r" (q), "=q" (r) : "r" (nh), "1" (nl), "r" (d))
+#define UDIV_TIME 100
+#endif
+#endif /* 32-bit POWER architecture variants.  */
+
+/* We should test _IBMR2 here when we add assembly support for the system
+   vendor compilers.  */
+#if (defined (_ARCH_PPC64) || defined (__powerpc64__)) && W_TYPE_SIZE == 64
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+  do {									\
+    if (__builtin_constant_p (bh) && (bh) == 0)				\
+      __asm__ ("{a%I4|add%I4c} %1,%3,%4\n\t{aze|addze} %0,%2"		\
+	     : "=r" (sh), "=&r" (sl) : "r" (ah), "%r" (al), "rI" (bl));\
+    else if (__builtin_constant_p (bh) && (bh) == ~(UDItype) 0)		\
+      __asm__ ("{a%I4|add%I4c} %1,%3,%4\n\t{ame|addme} %0,%2"		\
+	     : "=r" (sh), "=&r" (sl) : "r" (ah), "%r" (al), "rI" (bl));\
+    else								\
+      __asm__ ("{a%I5|add%I5c} %1,%4,%5\n\t{ae|adde} %0,%2,%3"		\
+	     : "=r" (sh), "=&r" (sl)					\
+	     : "%r" (ah), "r" (bh), "%r" (al), "rI" (bl));		\
+  } while (0)
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+  do {									\
+    if (__builtin_constant_p (ah) && (ah) == 0)				\
+      __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{sfze|subfze} %0,%2"	\
+	       : "=r" (sh), "=&r" (sl) : "r" (bh), "rI" (al), "r" (bl));\
+    else if (__builtin_constant_p (ah) && (ah) == ~(UDItype) 0)		\
+      __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{sfme|subfme} %0,%2"	\
+	       : "=r" (sh), "=&r" (sl) : "r" (bh), "rI" (al), "r" (bl));\
+    else if (__builtin_constant_p (bh) && (bh) == 0)			\
+      __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{ame|addme} %0,%2"		\
+	       : "=r" (sh), "=&r" (sl) : "r" (ah), "rI" (al), "r" (bl));\
+    else if (__builtin_constant_p (bh) && (bh) == ~(UDItype) 0)		\
+      __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{aze|addze} %0,%2"		\
+	       : "=r" (sh), "=&r" (sl) : "r" (ah), "rI" (al), "r" (bl));\
+    else								\
+      __asm__ ("{sf%I4|subf%I4c} %1,%5,%4\n\t{sfe|subfe} %0,%3,%2"	\
+	       : "=r" (sh), "=&r" (sl)					\
+	       : "r" (ah), "r" (bh), "rI" (al), "r" (bl));		\
+  } while (0)
+#define count_leading_zeros(count, x) \
+  __asm__ ("cntlzd %0,%1" : "=r" (count) : "r" (x))
+#define COUNT_LEADING_ZEROS_0 64
+#define umul_ppmm(ph, pl, m0, m1) \
+  do {									\
+    UDItype __m0 = (m0), __m1 = (m1);					\
+    __asm__ ("mulhdu %0,%1,%2" : "=r" (ph) : "%r" (m0), "r" (m1));	\
+    (pl) = __m0 * __m1;							\
+  } while (0)
+#define UMUL_TIME 15
+#define smul_ppmm(ph, pl, m0, m1) \
+  do {									\
+    DItype __m0 = (m0), __m1 = (m1);					\
+    __asm__ ("mulhd %0,%1,%2" : "=r" (ph) : "%r" (m0), "r" (m1));	\
+    (pl) = __m0 * __m1;							\
+  } while (0)
+#define SMUL_TIME 14  /* ??? */
+#define UDIV_TIME 120 /* ??? */
+#endif /* 64-bit PowerPC.  */
+
+#if defined (__ibm032__) /* RT/ROMP */ && W_TYPE_SIZE == 32
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+  __asm__ ("a %1,%5\n\tae %0,%3"					\
+	   : "=r" ((USItype) (sh)),					\
+	     "=&r" ((USItype) (sl))					\
+	   : "%0" ((USItype) (ah)),					\
+	     "r" ((USItype) (bh)),					\
+	     "%1" ((USItype) (al)),					\
+	     "r" ((USItype) (bl)))
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+  __asm__ ("s %1,%5\n\tse %0,%3"					\
+	   : "=r" ((USItype) (sh)),					\
+	     "=&r" ((USItype) (sl))					\
+	   : "0" ((USItype) (ah)),					\
+	     "r" ((USItype) (bh)),					\
+	     "1" ((USItype) (al)),					\
+	     "r" ((USItype) (bl)))
+#define umul_ppmm(ph, pl, m0, m1) \
+  do {									\
+    USItype __m0 = (m0), __m1 = (m1);					\
+    __asm__ (								\
+       "s	r2,r2\n"						\
+"	mts	r10,%2\n"						\
+"	m	r2,%3\n"						\
+"	m	r2,%3\n"						\
+"	m	r2,%3\n"						\
+"	m	r2,%3\n"						\
+"	m	r2,%3\n"						\
+"	m	r2,%3\n"						\
+"	m	r2,%3\n"						\
+"	m	r2,%3\n"						\
+"	m	r2,%3\n"						\
+"	m	r2,%3\n"						\
+"	m	r2,%3\n"						\
+"	m	r2,%3\n"						\
+"	m	r2,%3\n"						\
+"	m	r2,%3\n"						\
+"	m	r2,%3\n"						\
+"	m	r2,%3\n"						\
+"	cas	%0,r2,r0\n"						\
+"	mfs	r10,%1"							\
+	     : "=r" ((USItype) (ph)),					\
+	       "=r" ((USItype) (pl))					\
+	     : "%r" (__m0),						\
+		"r" (__m1)						\
+	     : "r2");							\
+    (ph) += ((((SItype) __m0 >> 31) & __m1)				\
+	     + (((SItype) __m1 >> 31) & __m0));				\
+  } while (0)
+#define UMUL_TIME 20
+#define UDIV_TIME 200
+#define count_leading_zeros(count, x) \
+  do {									\
+    if ((x) >= 0x10000)							\
+      __asm__ ("clz	%0,%1"						\
+	       : "=r" ((USItype) (count))				\
+	       : "r" ((USItype) (x) >> 16));				\
+    else								\
+      {									\
+	__asm__ ("clz	%0,%1"						\
+		 : "=r" ((USItype) (count))				\
+		 : "r" ((USItype) (x)));					\
+	(count) += 16;							\
+      }									\
+  } while (0)
+#endif
+
+#if defined(__sh__) && !__SHMEDIA__ && W_TYPE_SIZE == 32
+#ifndef __sh1__
+#define umul_ppmm(w1, w0, u, v) \
+  __asm__ (								\
+       "dmulu.l	%2,%3\n\tsts%M1	macl,%1\n\tsts%M0	mach,%0"	\
+	   : "=r<" ((USItype)(w1)),					\
+	     "=r<" ((USItype)(w0))					\
+	   : "r" ((USItype)(u)),					\
+	     "r" ((USItype)(v))						\
+	   : "macl", "mach")
+#define UMUL_TIME 5
+#endif
+
+/* This is the same algorithm as __udiv_qrnnd_c.  */
+#define UDIV_NEEDS_NORMALIZATION 1
+
+#define udiv_qrnnd(q, r, n1, n0, d) \
+  do {									\
+    extern UWtype __udiv_qrnnd_16 (UWtype, UWtype)			\
+                        __attribute__ ((visibility ("hidden")));	\
+    /* r0: rn r1: qn */ /* r0: n1 r4: n0 r5: d r6: d1 */ /* r2: __m */	\
+    __asm__ (								\
+	"mov%M4 %4,r5\n"						\
+"	swap.w %3,r4\n"							\
+"	swap.w r5,r6\n"							\
+"	jsr @%5\n"							\
+"	shll16 r6\n"							\
+"	swap.w r4,r4\n"							\
+"	jsr @%5\n"							\
+"	swap.w r1,%0\n"							\
+"	or r1,%0"							\
+	: "=r" (q), "=&z" (r)						\
+	: "1" (n1), "r" (n0), "rm" (d), "r" (&__udiv_qrnnd_16)		\
+	: "r1", "r2", "r4", "r5", "r6", "pr");				\
+  } while (0)
+
+#define UDIV_TIME 80
+
+#define sub_ddmmss(sh, sl, ah, al, bh, bl)				\
+  __asm__ ("clrt;subc %5,%1; subc %4,%0"				\
+	   : "=r" (sh), "=r" (sl)					\
+	   : "0" (ah), "1" (al), "r" (bh), "r" (bl))
+
+#endif /* __sh__ */
+
+#if defined (__SH5__) && __SHMEDIA__ && W_TYPE_SIZE == 32
+#define __umulsidi3(u,v) ((UDItype)(USItype)u*(USItype)v)
+#define count_leading_zeros(count, x) \
+  do									\
+    {									\
+      UDItype x_ = (USItype)(x);					\
+      SItype c_;							\
+									\
+      __asm__ ("nsb %1, %0" : "=r" (c_) : "r" (x_));			\
+      (count) = c_ - 31;						\
+    }									\
+  while (0)
+#define COUNT_LEADING_ZEROS_0 32
+#endif
+
+#if defined (__sparc__) && !defined (__arch64__) && !defined (__sparcv9) \
+    && W_TYPE_SIZE == 32
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+  __asm__ ("addcc %r4,%5,%1\n\taddx %r2,%3,%0"				\
+	   : "=r" ((USItype) (sh)),					\
+	     "=&r" ((USItype) (sl))					\
+	   : "%rJ" ((USItype) (ah)),					\
+	     "rI" ((USItype) (bh)),					\
+	     "%rJ" ((USItype) (al)),					\
+	     "rI" ((USItype) (bl))					\
+	   __CLOBBER_CC)
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+  __asm__ ("subcc %r4,%5,%1\n\tsubx %r2,%3,%0"				\
+	   : "=r" ((USItype) (sh)),					\
+	     "=&r" ((USItype) (sl))					\
+	   : "rJ" ((USItype) (ah)),					\
+	     "rI" ((USItype) (bh)),					\
+	     "rJ" ((USItype) (al)),					\
+	     "rI" ((USItype) (bl))					\
+	   __CLOBBER_CC)
+#if defined (__sparc_v8__)
+#define umul_ppmm(w1, w0, u, v) \
+  __asm__ ("umul %2,%3,%1;rd %%y,%0"					\
+	   : "=r" ((USItype) (w1)),					\
+	     "=r" ((USItype) (w0))					\
+	   : "r" ((USItype) (u)),					\
+	     "r" ((USItype) (v)))
+#define udiv_qrnnd(__q, __r, __n1, __n0, __d) \
+  __asm__ ("mov %2,%%y;nop;nop;nop;udiv %3,%4,%0;umul %0,%4,%1;sub %3,%1,%1"\
+	   : "=&r" ((USItype) (__q)),					\
+	     "=&r" ((USItype) (__r))					\
+	   : "r" ((USItype) (__n1)),					\
+	     "r" ((USItype) (__n0)),					\
+	     "r" ((USItype) (__d)))
+#else
+#if defined (__sparclite__)
+/* This has hardware multiply but not divide.  It also has two additional
+   instructions scan (ffs from high bit) and divscc.  */
+#define umul_ppmm(w1, w0, u, v) \
+  __asm__ ("umul %2,%3,%1;rd %%y,%0"					\
+	   : "=r" ((USItype) (w1)),					\
+	     "=r" ((USItype) (w0))					\
+	   : "r" ((USItype) (u)),					\
+	     "r" ((USItype) (v)))
+#define udiv_qrnnd(q, r, n1, n0, d) \
+  __asm__ ("! Inlined udiv_qrnnd\n"					\
+"	wr	%%g0,%2,%%y	! Not a delayed write for sparclite\n"	\
+"	tst	%%g0\n"							\
+"	divscc	%3,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%%g1\n"						\
+"	divscc	%%g1,%4,%0\n"						\
+"	rd	%%y,%1\n"						\
+"	bl,a 1f\n"							\
+"	add	%1,%4,%1\n"						\
+"1:	! End of inline udiv_qrnnd"					\
+	   : "=r" ((USItype) (q)),					\
+	     "=r" ((USItype) (r))					\
+	   : "r" ((USItype) (n1)),					\
+	     "r" ((USItype) (n0)),					\
+	     "rI" ((USItype) (d))					\
+	   : "g1" __AND_CLOBBER_CC)
+#define UDIV_TIME 37
+#define count_leading_zeros(count, x) \
+  do {                                                                  \
+  __asm__ ("scan %1,1,%0"                                               \
+           : "=r" ((USItype) (count))                                   \
+           : "r" ((USItype) (x)));					\
+  } while (0)
+/* Early sparclites return 63 for an argument of 0, but they warn that future
+   implementations might change this.  Therefore, leave COUNT_LEADING_ZEROS_0
+   undefined.  */
+#else
+/* SPARC without integer multiplication and divide instructions.
+   (i.e. at least Sun4/20,40,60,65,75,110,260,280,330,360,380,470,490) */
+#define umul_ppmm(w1, w0, u, v) \
+  __asm__ ("! Inlined umul_ppmm\n"					\
+"	wr	%%g0,%2,%%y	! SPARC has 0-3 delay insn after a wr\n"\
+"	sra	%3,31,%%o5	! Don't move this insn\n"		\
+"	and	%2,%%o5,%%o5	! Don't move this insn\n"		\
+"	andcc	%%g0,0,%%g1	! Don't move this insn\n"		\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,%3,%%g1\n"						\
+"	mulscc	%%g1,0,%%g1\n"						\
+"	add	%%g1,%%o5,%0\n"						\
+"	rd	%%y,%1"							\
+	   : "=r" ((USItype) (w1)),					\
+	     "=r" ((USItype) (w0))					\
+	   : "%rI" ((USItype) (u)),					\
+	     "r" ((USItype) (v))						\
+	   : "g1", "o5" __AND_CLOBBER_CC)
+#define UMUL_TIME 39		/* 39 instructions */
+/* It's quite necessary to add this much assembler for the sparc.
+   The default udiv_qrnnd (in C) is more than 10 times slower!  */
+#define udiv_qrnnd(__q, __r, __n1, __n0, __d) \
+  __asm__ ("! Inlined udiv_qrnnd\n"					\
+"	mov	32,%%g1\n"						\
+"	subcc	%1,%2,%%g0\n"						\
+"1:	bcs	5f\n"							\
+"	 addxcc %0,%0,%0	! shift n1n0 and a q-bit in lsb\n"	\
+"	sub	%1,%2,%1	! this kills msb of n\n"		\
+"	addx	%1,%1,%1	! so this can't give carry\n"		\
+"	subcc	%%g1,1,%%g1\n"						\
+"2:	bne	1b\n"							\
+"	 subcc	%1,%2,%%g0\n"						\
+"	bcs	3f\n"							\
+"	 addxcc %0,%0,%0	! shift n1n0 and a q-bit in lsb\n"	\
+"	b	3f\n"							\
+"	 sub	%1,%2,%1	! this kills msb of n\n"		\
+"4:	sub	%1,%2,%1\n"						\
+"5:	addxcc	%1,%1,%1\n"						\
+"	bcc	2b\n"							\
+"	 subcc	%%g1,1,%%g1\n"						\
+"! Got carry from n.  Subtract next step to cancel this carry.\n"	\
+"	bne	4b\n"							\
+"	 addcc	%0,%0,%0	! shift n1n0 and a 0-bit in lsb\n"	\
+"	sub	%1,%2,%1\n"						\
+"3:	xnor	%0,0,%0\n"						\
+"	! End of inline udiv_qrnnd"					\
+	   : "=&r" ((USItype) (__q)),					\
+	     "=&r" ((USItype) (__r))					\
+	   : "r" ((USItype) (__d)),					\
+	     "1" ((USItype) (__n1)),					\
+	     "0" ((USItype) (__n0)) : "g1" __AND_CLOBBER_CC)
+#define UDIV_TIME (3+7*32)	/* 7 instructions/iteration. 32 iterations.  */
+#endif /* __sparclite__ */
+#endif /* __sparc_v8__ */
+#endif /* sparc32 */
+
+#if ((defined (__sparc__) && defined (__arch64__)) || defined (__sparcv9)) \
+    && W_TYPE_SIZE == 64
+#define add_ssaaaa(sh, sl, ah, al, bh, bl)				\
+  __asm__ ("addcc %r4,%5,%1\n\t"					\
+   	   "add %r2,%3,%0\n\t"						\
+   	   "bcs,a,pn %%xcc, 1f\n\t"					\
+   	   "add %0, 1, %0\n"						\
+	   "1:"								\
+	   : "=r" ((UDItype)(sh)),				      	\
+	     "=&r" ((UDItype)(sl))				      	\
+	   : "%rJ" ((UDItype)(ah)),				     	\
+	     "rI" ((UDItype)(bh)),				      	\
+	     "%rJ" ((UDItype)(al)),				     	\
+	     "rI" ((UDItype)(bl))				       	\
+	   __CLOBBER_CC)
+
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) 				\
+  __asm__ ("subcc %r4,%5,%1\n\t"					\
+   	   "sub %r2,%3,%0\n\t"						\
+   	   "bcs,a,pn %%xcc, 1f\n\t"					\
+   	   "sub %0, 1, %0\n\t"						\
+	   "1:"								\
+	   : "=r" ((UDItype)(sh)),				      	\
+	     "=&r" ((UDItype)(sl))				      	\
+	   : "rJ" ((UDItype)(ah)),				     	\
+	     "rI" ((UDItype)(bh)),				      	\
+	     "rJ" ((UDItype)(al)),				     	\
+	     "rI" ((UDItype)(bl))				       	\
+	   __CLOBBER_CC)
+
+#define umul_ppmm(wh, wl, u, v)						\
+  do {									\
+	  UDItype tmp1, tmp2, tmp3, tmp4;				\
+	  __asm__ __volatile__ (					\
+		   "srl %7,0,%3\n\t"					\
+		   "mulx %3,%6,%1\n\t"					\
+		   "srlx %6,32,%2\n\t"					\
+		   "mulx %2,%3,%4\n\t"					\
+		   "sllx %4,32,%5\n\t"					\
+		   "srl %6,0,%3\n\t"					\
+		   "sub %1,%5,%5\n\t"					\
+		   "srlx %5,32,%5\n\t"					\
+		   "addcc %4,%5,%4\n\t"					\
+		   "srlx %7,32,%5\n\t"					\
+		   "mulx %3,%5,%3\n\t"					\
+		   "mulx %2,%5,%5\n\t"					\
+		   "sethi %%hi(0x80000000),%2\n\t"			\
+		   "addcc %4,%3,%4\n\t"					\
+		   "srlx %4,32,%4\n\t"					\
+		   "add %2,%2,%2\n\t"					\
+		   "movcc %%xcc,%%g0,%2\n\t"				\
+		   "addcc %5,%4,%5\n\t"					\
+		   "sllx %3,32,%3\n\t"					\
+		   "add %1,%3,%1\n\t"					\
+		   "add %5,%2,%0"					\
+	   : "=r" ((UDItype)(wh)),					\
+	     "=&r" ((UDItype)(wl)),					\
+	     "=&r" (tmp1), "=&r" (tmp2), "=&r" (tmp3), "=&r" (tmp4)	\
+	   : "r" ((UDItype)(u)),					\
+	     "r" ((UDItype)(v))						\
+	   __CLOBBER_CC);						\
+  } while (0)
+#define UMUL_TIME 96
+#define UDIV_TIME 230
+#endif /* sparc64 */
+
+#if defined (__vax__) && W_TYPE_SIZE == 32
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+  __asm__ ("addl2 %5,%1\n\tadwc %3,%0"					\
+	   : "=g" ((USItype) (sh)),					\
+	     "=&g" ((USItype) (sl))					\
+	   : "%0" ((USItype) (ah)),					\
+	     "g" ((USItype) (bh)),					\
+	     "%1" ((USItype) (al)),					\
+	     "g" ((USItype) (bl)))
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+  __asm__ ("subl2 %5,%1\n\tsbwc %3,%0"					\
+	   : "=g" ((USItype) (sh)),					\
+	     "=&g" ((USItype) (sl))					\
+	   : "0" ((USItype) (ah)),					\
+	     "g" ((USItype) (bh)),					\
+	     "1" ((USItype) (al)),					\
+	     "g" ((USItype) (bl)))
+#define umul_ppmm(xh, xl, m0, m1) \
+  do {									\
+    union {								\
+	UDItype __ll;							\
+	struct {USItype __l, __h;} __i;					\
+      } __xx;								\
+    USItype __m0 = (m0), __m1 = (m1);					\
+    __asm__ ("emul %1,%2,$0,%0"						\
+	     : "=r" (__xx.__ll)						\
+	     : "g" (__m0),						\
+	       "g" (__m1));						\
+    (xh) = __xx.__i.__h;						\
+    (xl) = __xx.__i.__l;						\
+    (xh) += ((((SItype) __m0 >> 31) & __m1)				\
+	     + (((SItype) __m1 >> 31) & __m0));				\
+  } while (0)
+#define sdiv_qrnnd(q, r, n1, n0, d) \
+  do {									\
+    union {DItype __ll;							\
+	   struct {SItype __l, __h;} __i;				\
+	  } __xx;							\
+    __xx.__i.__h = n1; __xx.__i.__l = n0;				\
+    __asm__ ("ediv %3,%2,%0,%1"						\
+	     : "=g" (q), "=g" (r)					\
+	     : "g" (__xx.__ll), "g" (d));				\
+  } while (0)
+#endif /* __vax__ */
+
+#if defined (__xtensa__) && W_TYPE_SIZE == 32
+/* This code is not Xtensa-configuration-specific, so rely on the compiler
+   to expand builtin functions depending on what configuration features
+   are available.  This avoids library calls when the operation can be
+   performed in-line.  */
+#define umul_ppmm(w1, w0, u, v)						\
+  do {									\
+    DWunion __w;							\
+    __w.ll = __builtin_umulsidi3 (u, v);				\
+    w1 = __w.s.high;							\
+    w0 = __w.s.low;							\
+  } while (0)
+#define __umulsidi3(u, v)		__builtin_umulsidi3 (u, v)
+#define count_leading_zeros(COUNT, X)	((COUNT) = __builtin_clz (X))
+#define count_trailing_zeros(COUNT, X)	((COUNT) = __builtin_ctz (X))
+#endif /* __xtensa__ */
+
+#if defined (__z8000__) && W_TYPE_SIZE == 16
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+  __asm__ ("add	%H1,%H5\n\tadc	%H0,%H3"				\
+	   : "=r" ((unsigned int)(sh)),					\
+	     "=&r" ((unsigned int)(sl))					\
+	   : "%0" ((unsigned int)(ah)),					\
+	     "r" ((unsigned int)(bh)),					\
+	     "%1" ((unsigned int)(al)),					\
+	     "rQR" ((unsigned int)(bl)))
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+  __asm__ ("sub	%H1,%H5\n\tsbc	%H0,%H3"				\
+	   : "=r" ((unsigned int)(sh)),					\
+	     "=&r" ((unsigned int)(sl))					\
+	   : "0" ((unsigned int)(ah)),					\
+	     "r" ((unsigned int)(bh)),					\
+	     "1" ((unsigned int)(al)),					\
+	     "rQR" ((unsigned int)(bl)))
+#define umul_ppmm(xh, xl, m0, m1) \
+  do {									\
+    union {long int __ll;						\
+	   struct {unsigned int __h, __l;} __i;				\
+	  } __xx;							\
+    unsigned int __m0 = (m0), __m1 = (m1);				\
+    __asm__ ("mult	%S0,%H3"					\
+	     : "=r" (__xx.__i.__h),					\
+	       "=r" (__xx.__i.__l)					\
+	     : "%1" (__m0),						\
+	       "rQR" (__m1));						\
+    (xh) = __xx.__i.__h; (xl) = __xx.__i.__l;				\
+    (xh) += ((((signed int) __m0 >> 15) & __m1)				\
+	     + (((signed int) __m1 >> 15) & __m0));			\
+  } while (0)
+#endif /* __z8000__ */
+
+#endif /* __GNUC__ */
+
+/* If this machine has no inline assembler, use C macros.  */
+
+#if !defined (add_ssaaaa)
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+  do {									\
+    UWtype __x;								\
+    __x = (al) + (bl);							\
+    (sh) = (ah) + (bh) + (__x < (al));					\
+    (sl) = __x;								\
+  } while (0)
+#endif
+
+#if !defined (sub_ddmmss)
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+  do {									\
+    UWtype __x;								\
+    __x = (al) - (bl);							\
+    (sh) = (ah) - (bh) - (__x > (al));					\
+    (sl) = __x;								\
+  } while (0)
+#endif
+
+/* If we lack umul_ppmm but have smul_ppmm, define umul_ppmm in terms of
+   smul_ppmm.  */
+#if !defined (umul_ppmm) && defined (smul_ppmm)
+#define umul_ppmm(w1, w0, u, v)						\
+  do {									\
+    UWtype __w1;							\
+    UWtype __xm0 = (u), __xm1 = (v);					\
+    smul_ppmm (__w1, w0, __xm0, __xm1);					\
+    (w1) = __w1 + (-(__xm0 >> (W_TYPE_SIZE - 1)) & __xm1)		\
+		+ (-(__xm1 >> (W_TYPE_SIZE - 1)) & __xm0);		\
+  } while (0)
+#endif
+
+/* If we still don't have umul_ppmm, define it using plain C.  */
+#if !defined (umul_ppmm)
+#define umul_ppmm(w1, w0, u, v)						\
+  do {									\
+    UWtype __x0, __x1, __x2, __x3;					\
+    UHWtype __ul, __vl, __uh, __vh;					\
+									\
+    __ul = __ll_lowpart (u);						\
+    __uh = __ll_highpart (u);						\
+    __vl = __ll_lowpart (v);						\
+    __vh = __ll_highpart (v);						\
+									\
+    __x0 = (UWtype) __ul * __vl;					\
+    __x1 = (UWtype) __ul * __vh;					\
+    __x2 = (UWtype) __uh * __vl;					\
+    __x3 = (UWtype) __uh * __vh;					\
+									\
+    __x1 += __ll_highpart (__x0);/* this can't give carry */		\
+    __x1 += __x2;		/* but this indeed can */		\
+    if (__x1 < __x2)		/* did we get it? */			\
+      __x3 += __ll_B;		/* yes, add it in the proper pos.  */	\
+									\
+    (w1) = __x3 + __ll_highpart (__x1);					\
+    (w0) = __ll_lowpart (__x1) * __ll_B + __ll_lowpart (__x0);		\
+  } while (0)
+#endif
+
+#if !defined (__umulsidi3)
+#define __umulsidi3(u, v) \
+  ({DWunion __w;							\
+    umul_ppmm (__w.s.high, __w.s.low, u, v);				\
+    __w.ll; })
+#endif
+
+/* Define this unconditionally, so it can be used for debugging.  */
+#define __udiv_qrnnd_c(q, r, n1, n0, d) \
+  do {									\
+    UWtype __d1, __d0, __q1, __q0;					\
+    UWtype __r1, __r0, __m;						\
+    __d1 = __ll_highpart (d);						\
+    __d0 = __ll_lowpart (d);						\
+									\
+    __r1 = (n1) % __d1;							\
+    __q1 = (n1) / __d1;							\
+    __m = (UWtype) __q1 * __d0;						\
+    __r1 = __r1 * __ll_B | __ll_highpart (n0);				\
+    if (__r1 < __m)							\
+      {									\
+	__q1--, __r1 += (d);						\
+	if (__r1 >= (d)) /* i.e. we didn't get carry when adding to __r1 */\
+	  if (__r1 < __m)						\
+	    __q1--, __r1 += (d);					\
+      }									\
+    __r1 -= __m;							\
+									\
+    __r0 = __r1 % __d1;							\
+    __q0 = __r1 / __d1;							\
+    __m = (UWtype) __q0 * __d0;						\
+    __r0 = __r0 * __ll_B | __ll_lowpart (n0);				\
+    if (__r0 < __m)							\
+      {									\
+	__q0--, __r0 += (d);						\
+	if (__r0 >= (d))						\
+	  if (__r0 < __m)						\
+	    __q0--, __r0 += (d);					\
+      }									\
+    __r0 -= __m;							\
+									\
+    (q) = (UWtype) __q1 * __ll_B | __q0;				\
+    (r) = __r0;								\
+  } while (0)
+
+/* If the processor has no udiv_qrnnd but sdiv_qrnnd, go through
+   __udiv_w_sdiv (defined in libgcc or elsewhere).  */
+#if !defined (udiv_qrnnd) && defined (sdiv_qrnnd)
+#define udiv_qrnnd(q, r, nh, nl, d) \
+  do {									\
+    USItype __r;							\
+    (q) = __udiv_w_sdiv (&__r, nh, nl, d);				\
+    (r) = __r;								\
+  } while (0)
+#endif
+
+/* If udiv_qrnnd was not defined for this processor, use __udiv_qrnnd_c.  */
+#if !defined (udiv_qrnnd)
+#define UDIV_NEEDS_NORMALIZATION 1
+#define udiv_qrnnd __udiv_qrnnd_c
+#endif
+
+#if !defined (count_leading_zeros)
+#define count_leading_zeros(count, x) \
+  do {									\
+    UWtype __xr = (x);							\
+    UWtype __a;								\
+									\
+    if (W_TYPE_SIZE <= 32)						\
+      {									\
+	__a = __xr < ((UWtype)1<<2*__BITS4)				\
+	  ? (__xr < ((UWtype)1<<__BITS4) ? 0 : __BITS4)			\
+	  : (__xr < ((UWtype)1<<3*__BITS4) ?  2*__BITS4 : 3*__BITS4);	\
+      }									\
+    else								\
+      {									\
+	for (__a = W_TYPE_SIZE - 8; __a > 0; __a -= 8)			\
+	  if (((__xr >> __a) & 0xff) != 0)				\
+	    break;							\
+      }									\
+									\
+    (count) = W_TYPE_SIZE - (__clz_tab[__xr >> __a] + __a);		\
+  } while (0)
+#define COUNT_LEADING_ZEROS_0 W_TYPE_SIZE
+#endif
+
+#if !defined (count_trailing_zeros)
+/* Define count_trailing_zeros using count_leading_zeros.  The latter might be
+   defined in asm, but if it is not, the C version above is good enough.  */
+#define count_trailing_zeros(count, x) \
+  do {									\
+    UWtype __ctz_x = (x);						\
+    UWtype __ctz_c;							\
+    count_leading_zeros (__ctz_c, __ctz_x & -__ctz_x);			\
+    (count) = W_TYPE_SIZE - 1 - __ctz_c;				\
+  } while (0)
+#endif
+
+#ifndef UDIV_NEEDS_NORMALIZATION
+#define UDIV_NEEDS_NORMALIZATION 0
+#endif