2013-11-27 Kugan Vivekanandarajah <kuganv@linaro.org>

	gcc/
	* doc/tm.texi.in (TARGET_HAS_NO_HW_DIVIDE): Define.
	* doc/tm.texi (TARGET_HAS_NO_HW_DIVIDE): Regenerate.

	libgcc/
	* libgcc2.c (__udivmoddi4): Define new implementation when
	TARGET_HAS_NO_HW_DIVIDE is defined, for processors without any
	divide instructions.



git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@205444 138bc75d-0d04-0410-961f-82ee72b054a4

5 files changed, 96 insertions, 0 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 31e9670fa89..15ce5e698f2 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,8 @@
+2013-11-27  Kugan Vivekanandarajah  <kuganv@linaro.org>
+
+	* doc/tm.texi.in (TARGET_HAS_NO_HW_DIVIDE): Define.
+	* doc/tm.texi (TARGET_HAS_NO_HW_DIVIDE): Regenerate.
+
 2013-11-27  Marek Polacek  <polacek@redhat.com>
 
 	PR sanitizer/59306
diff --git a/gcc/doc/tm.texi b/gcc/doc/tm.texi
index 966576fe721..68b59b9975b 100644
--- a/gcc/doc/tm.texi
+++ b/gcc/doc/tm.texi
@@ -5365,6 +5365,14 @@ If this macro evaluates to @code{false} the comparison functions return
 in @file{libgcc.a}, you do not need to define this macro.
 @end defmac
 
+@defmac TARGET_HAS_NO_HW_DIVIDE
+This macro should be defined if the target has no hardware divide
+instructions.  If this macro is defined, GCC will use an algorithm which
+make use of simple logical and arithmetic operations for 64-bit
+division.  If the macro is not defined, GCC will use an algorithm which
+make use of a 64-bit by 32-bit divide primitive.
+@end defmac
+
 @cindex @code{EDOM}, implicit usage
 @findex matherr
 @defmac TARGET_EDOM
diff --git a/gcc/doc/tm.texi.in b/gcc/doc/tm.texi.in
index 63f4edb3a43..1bb3806c5df 100644
--- a/gcc/doc/tm.texi.in
+++ b/gcc/doc/tm.texi.in
@@ -4205,6 +4205,14 @@ If this macro evaluates to @code{false} the comparison functions return
 in @file{libgcc.a}, you do not need to define this macro.
 @end defmac
 
+@defmac TARGET_HAS_NO_HW_DIVIDE
+This macro should be defined if the target has no hardware divide
+instructions.  If this macro is defined, GCC will use an algorithm which
+make use of simple logical and arithmetic operations for 64-bit
+division.  If the macro is not defined, GCC will use an algorithm which
+make use of a 64-bit by 32-bit divide primitive.
+@end defmac
+
 @cindex @code{EDOM}, implicit usage
 @findex matherr
 @defmac TARGET_EDOM
diff --git a/libgcc/ChangeLog b/libgcc/ChangeLog
index a1f84555826..7e7aa4a40d1 100644
--- a/libgcc/ChangeLog
+++ b/libgcc/ChangeLog
@@ -1,3 +1,9 @@
+2013-11-27  Kugan Vivekanandarajah  <kuganv@linaro.org>
+
+	* libgcc2.c (__udivmoddi4): Define new implementation when
+	TARGET_HAS_NO_HW_DIVIDE is defined, for processors without any
+	divide instructions.
+
 2013-11-25  Oleg Endo  <olegendo@gcc.gnu.org>
 
 	* config/sh/crt1.S (start): Don't do VBR_SETUP for SH2E.
diff --git a/libgcc/libgcc2.c b/libgcc/libgcc2.c
index bec411be0b5..8c4cc6a316c 100644
--- a/libgcc/libgcc2.c
+++ b/libgcc/libgcc2.c
@@ -934,6 +934,74 @@ __parityDI2 (UDWtype x)
 #endif
 
 #ifdef L_udivmoddi4
+#ifdef TARGET_HAS_NO_HW_DIVIDE
+
+#if (defined (L_udivdi3) || defined (L_divdi3) || \
+     defined (L_umoddi3) || defined (L_moddi3))
+static inline __attribute__ ((__always_inline__))
+#endif
+UDWtype
+__udivmoddi4 (UDWtype n, UDWtype d, UDWtype *rp)
+{
+  UDWtype q = 0, r = n, y = d;
+  UWtype lz1, lz2, i, k;
+
+  /* Implements align divisor shift dividend method. This algorithm
+     aligns the divisor under the dividend and then perform number of
+     test-subtract iterations which shift the dividend left. Number of
+     iterations is k + 1 where k is the number of bit positions the
+     divisor must be shifted left  to align it under the dividend.
+     quotient bits can be saved in the rightmost positions of the dividend
+     as it shifts left on each test-subtract iteration. */
+
+  if (y <= r)
+    {
+      lz1 = __builtin_clzll (d);
+      lz2 = __builtin_clzll (n);
+
+      k = lz1 - lz2;
+      y = (y << k);
+
+      /* Dividend can exceed 2 ^ (width − 1) − 1 but still be less than the
+	 aligned divisor. Normal iteration can drops the high order bit
+	 of the dividend. Therefore, first test-subtract iteration is a
+	 special case, saving its quotient bit in a separate location and
+	 not shifting the dividend. */
+      if (r >= y)
+	{
+	  r = r - y;
+	  q =  (1ULL << k);
+	}
+
+      if (k > 0)
+	{
+	  y = y >> 1;
+
+	  /* k additional iterations where k regular test subtract shift
+	    dividend iterations are done.  */
+	  i = k;
+	  do
+	    {
+	      if (r >= y)
+		r = ((r - y) << 1) + 1;
+	      else
+		r =  (r << 1);
+	      i = i - 1;
+	    } while (i != 0);
+
+	  /* First quotient bit is combined with the quotient bits resulting
+	     from the k regular iterations.  */
+	  q = q + r;
+	  r = r >> k;
+	  q = q - (r << k);
+	}
+    }
+
+  if (rp)
+    *rp = r;
+  return q;
+}
+#else
 
 #if (defined (L_udivdi3) || defined (L_divdi3) || \
      defined (L_umoddi3) || defined (L_moddi3))
@@ -1152,6 +1220,7 @@ __udivmoddi4 (UDWtype n, UDWtype d, UDWtype *rp)
   return ww.ll;
 }
 #endif
+#endif
 
 #ifdef L_divdi3
 DWtype