[patch, libfortran] Use functon for counting true values

[Thomas Koenig <tkoenig at netcologne dot de>]

Hello world,

this patch uses the new count_0 function for the pack intrinsic.
Incidentally, it also fixes a bug discovered in count_0 during
regression testing of this patch :-)  No test case, because
no new functionality.

OK for trunk?

	Thomas

2009-08-29  Thomas Koenig  <tkoenig@gcc.gnu.org>

	* m4/pack.m4 (pack_'rtype_code`): Use count_0 for counting true
	values in a logical array.  Mark bounds checking tests as
	unlikely.
	* intrinsics/pack_generic.c (pack_internal): Likewise.
	* runtime/bounds.c (count_0):  Fix off-by-one error in detecting
	empty arrays.
	* generated/pack_c4.c: Regenerated.
	* generated/pack_c8.c: Regenerated.
	* generated/pack_c10.c: Regenerated.
	* generated/pack_c16.c: Regenerated.
	* generated/pack_i1.c: Regenerated.
	* generated/pack_i16.c: Regenerated.
	* generated/pack_i2.c: Regenerated.
	* generated/pack_i4.c: Regenerated.
	* generated/pack_i8.c: Regenerated.
	* generated/pack_r4.c: Regenerated.
	* generated/pack_r8.c: Regenerated.
	* generated/pack_r10.c: Regenerated.
	* generated/pack_r16.c: Regenerated.


Index: intrinsics/pack_generic.c
===================================================================
--- intrinsics/pack_generic.c	(revision 151132)
+++ intrinsics/pack_generic.c	(working copy)
@@ -132,7 +132,7 @@ pack_internal (gfc_array_char *ret, cons
   if (mstride[0] == 0)
     mstride[0] = mask_kind;
 
-  if (ret->data == NULL || compile_options.bounds_check)
+  if (ret->data == NULL || unlikely (compile_options.bounds_check))
     {
       /* Count the elements, either for allocating memory or
 	 for bounds checking.  */
@@ -147,58 +147,7 @@ pack_internal (gfc_array_char *ret, cons
 	{
 	  /* We have to count the true elements in MASK.  */
 
-	  /* TODO: We could speed up pack easily in the case of only
-	     few .TRUE. entries in MASK, by keeping track of where we
-	     would be in the source array during the initial traversal
-	     of MASK, and caching the pointers to those elements. Then,
-	     supposed the number of elements is small enough, we would
-	     only have to traverse the list, and copy those elements
-	     into the result array. In the case of datatypes which fit
-	     in one of the integer types we could also cache the
-	     value instead of a pointer to it.
-	     This approach might be bad from the point of view of
-	     cache behavior in the case where our cache is not big
-	     enough to hold all elements that have to be copied.  */
-
-	  const GFC_LOGICAL_1 *m = mptr;
-
-	  total = 0;
-	  if (zero_sized)
-	    m = NULL;
-
-	  while (m)
-	    {
-	      /* Test this element.  */
-	      if (*m)
-		total++;
-
-	      /* Advance to the next element.  */
-	      m += mstride[0];
-	      count[0]++;
-	      n = 0;
-	      while (count[n] == extent[n])
-		{
-		  /* When we get to the end of a dimension, reset it
-		     and increment the next dimension.  */
-		  count[n] = 0;
-		  /* We could precalculate this product, but this is a
-		     less frequently used path so probably not worth
-		     it.  */
-		  m -= mstride[n] * extent[n];
-		  n++;
-		  if (n >= dim)
-		    {
-		      /* Break out of the loop.  */
-		      m = NULL;
-		      break;
-		    }
-		  else
-		    {
-		      count[n]++;
-		      m += mstride[n];
-		    }
-		}
-	    }
+	  total = count_0 (mask);
 	}
 
       if (ret->data == NULL)
Index: m4/pack.m4
===================================================================
--- m4/pack.m4	(revision 151132)
+++ m4/pack.m4	(working copy)
@@ -139,7 +139,7 @@ pack_'rtype_code` ('rtype` *ret, const '
   else
     sptr = array->data;
 
-  if (ret->data == NULL || compile_options.bounds_check)
+  if (ret->data == NULL || unlikely (compile_options.bounds_check))
     {
       /* Count the elements, either for allocating memory or
 	 for bounds checking.  */
@@ -156,62 +156,10 @@ pack_'rtype_code` ('rtype` *ret, const '
 	    }
 	}
       else
-	{
-	  /* We have to count the true elements in MASK.  */
-
-	  /* TODO: We could speed up pack easily in the case of only
-	     few .TRUE. entries in MASK, by keeping track of where we
-	     would be in the source array during the initial traversal
-	     of MASK, and caching the pointers to those elements. Then,
-	     supposed the number of elements is small enough, we would
-	     only have to traverse the list, and copy those elements
-	     into the result array. In the case of datatypes which fit
-	     in one of the integer types we could also cache the
-	     value instead of a pointer to it.
-	     This approach might be bad from the point of view of
-	     cache behavior in the case where our cache is not big
-	     enough to hold all elements that have to be copied.  */
-
-	  const GFC_LOGICAL_1 *m = mptr;
-
-	  total = 0;
-	  if (zero_sized)
-	    m = NULL;
-
-	  while (m)
-	    {
-	      /* Test this element.  */
-	      if (*m)
-		total++;
-
-	      /* Advance to the next element.  */
-	      m += mstride[0];
-	      count[0]++;
-	      n = 0;
-	      while (count[n] == extent[n])
-		{
-		  /* When we get to the end of a dimension, reset it
-		     and increment the next dimension.  */
-		  count[n] = 0;
-		  /* We could precalculate this product, but this is a
-		     less frequently used path so probably not worth
-		     it.  */
-		  m -= mstride[n] * extent[n];
-		  n++;
-		  if (n >= dim)
-		    {
-		      /* Break out of the loop.  */
-		      m = NULL;
-		      break;
-		    }
-		  else
-		    {
-		      count[n]++;
-		      m += mstride[n];
-		    }
-		}
-	    }
-	}
+        {
+      	  /* We have to count the true elements in MASK.  */
+	  total = count_0 (mask);
+        }
 
       if (ret->data == NULL)
 	{
Index: runtime/bounds.c
===================================================================
--- runtime/bounds.c	(revision 151132)
+++ runtime/bounds.c	(working copy)
@@ -237,7 +237,7 @@ index_type count_0 (const gfc_array_l1 *
       extent[n] = GFC_DESCRIPTOR_EXTENT(array,n);
       count[n] = 0;
 
-      if (extent[n] < 0)
+      if (extent[n] <= 0)
 	return 0;
     }