re PR libfortran/32972 (performance of pack/unpack)

2007-08-24  Thomas Koenig  <tkoenig@gcc.gnu.org>

	PR fortran/32972
	* iresolve.c:  Don't convert array masks.

2007-08-24  Thomas Koenig  <tkoenig@gcc.gnu.org>

	PR fortran/32972
	* libgfortran.h:  Remove GFOR_POINTER_L8_TO_L4 macro.
	Add GFOR_POINTER_TO_L1 macro.
	* m4/iforeach.m4(`m'name`'rtype_qual`_'atype_code):
	Change argument 'mask' to gfc_array_l1.  Adjust prototype.
	Change mask pointer to GFC_LOGICAL_1.  Multiply strides
	by kind of mask
	* m4/ifunction.m4:  Likewise.
	* intrinsics/pack_generic.c(pack_internal):  Likewise.
	* intrinsics/unpack_generic.c(unpack_internal):  Likewise.
	* m4/matmull.m4:  Switch to GFC_LOGICAL_1.  Multiply strides by
	kind of logical arguments a and b.
	* generated/matmul_l16.c: Regenerated.
	* generated/matmul_l4.c: Regenerated.
	* generated/matmul_l8.c: Regenerated.
	* generated/maxloc0_16_i1.c: Regenerated.
	* generated/maxloc0_16_i16.c: Regenerated.
	* generated/maxloc0_16_i2.c: Regenerated.
	* generated/maxloc0_16_i4.c: Regenerated.
	* generated/maxloc0_16_i8.c: Regenerated.
	* generated/maxloc0_16_r10.c: Regenerated.
	* generated/maxloc0_16_r16.c: Regenerated.
	* generated/maxloc0_16_r4.c: Regenerated.
	* generated/maxloc0_16_r8.c: Regenerated.
	* generated/maxloc0_4_i1.c: Regenerated.
	* generated/maxloc0_4_i16.c: Regenerated.
	* generated/maxloc0_4_i2.c: Regenerated.
	* generated/maxloc0_4_i4.c: Regenerated.
	* generated/maxloc0_4_i8.c: Regenerated.
	* generated/maxloc0_4_r10.c: Regenerated.
	* generated/maxloc0_4_r16.c: Regenerated.
	* generated/maxloc0_4_r4.c: Regenerated.
	* generated/maxloc0_4_r8.c: Regenerated.
	* generated/maxloc0_8_i1.c: Regenerated.
	* generated/maxloc0_8_i16.c: Regenerated.
	* generated/maxloc0_8_i2.c: Regenerated.
	* generated/maxloc0_8_i4.c: Regenerated.
	* generated/maxloc0_8_i8.c: Regenerated.
	* generated/maxloc0_8_r10.c: Regenerated.
	* generated/maxloc0_8_r16.c: Regenerated.
	* generated/maxloc0_8_r4.c: Regenerated.
	* generated/maxloc0_8_r8.c: Regenerated.
	* generated/maxloc1_16_i1.c: Regenerated.
	* generated/maxloc1_16_i16.c: Regenerated.
	* generated/maxloc1_16_i2.c: Regenerated.
	* generated/maxloc1_16_i4.c: Regenerated.
	* generated/maxloc1_16_i8.c: Regenerated.
	* generated/maxloc1_16_r10.c: Regenerated.
	* generated/maxloc1_16_r16.c: Regenerated.
	* generated/maxloc1_16_r4.c: Regenerated.
	* generated/maxloc1_16_r8.c: Regenerated.
	* generated/maxloc1_4_i1.c: Regenerated.
	* generated/maxloc1_4_i16.c: Regenerated.
	* generated/maxloc1_4_i2.c: Regenerated.
	* generated/maxloc1_4_i4.c: Regenerated.
	* generated/maxloc1_4_i8.c: Regenerated.
	* generated/maxloc1_4_r10.c: Regenerated.
	* generated/maxloc1_4_r16.c: Regenerated.
	* generated/maxloc1_4_r4.c: Regenerated.
	* generated/maxloc1_4_r8.c: Regenerated.
	* generated/maxloc1_8_i1.c: Regenerated.
	* generated/maxloc1_8_i16.c: Regenerated.
	* generated/maxloc1_8_i2.c: Regenerated.
	* generated/maxloc1_8_i4.c: Regenerated.
	* generated/maxloc1_8_i8.c: Regenerated.
	* generated/maxloc1_8_r10.c: Regenerated.
	* generated/maxloc1_8_r16.c: Regenerated.
	* generated/maxloc1_8_r4.c: Regenerated.
	* generated/maxloc1_8_r8.c: Regenerated.
	* generated/maxval_i1.c: Regenerated.
	* generated/maxval_i16.c: Regenerated.
	* generated/maxval_i2.c: Regenerated.
	* generated/maxval_i4.c: Regenerated.
	* generated/maxval_i8.c: Regenerated.
	* generated/maxval_r10.c: Regenerated.
	* generated/maxval_r16.c: Regenerated.
	* generated/maxval_r4.c: Regenerated.
	* generated/maxval_r8.c: Regenerated.
	* generated/minloc0_16_i1.c: Regenerated.
	* generated/minloc0_16_i16.c: Regenerated.
	* generated/minloc0_16_i2.c: Regenerated.
	* generated/minloc0_16_i4.c: Regenerated.
	* generated/minloc0_16_i8.c: Regenerated.
	* generated/minloc0_16_r10.c: Regenerated.
	* generated/minloc0_16_r16.c: Regenerated.
	* generated/minloc0_16_r4.c: Regenerated.
	* generated/minloc0_16_r8.c: Regenerated.
	* generated/minloc0_4_i1.c: Regenerated.
	* generated/minloc0_4_i16.c: Regenerated.
	* generated/minloc0_4_i2.c: Regenerated.
	* generated/minloc0_4_i4.c: Regenerated.
	* generated/minloc0_4_i8.c: Regenerated.
	* generated/minloc0_4_r10.c: Regenerated.
	* generated/minloc0_4_r16.c: Regenerated.
	* generated/minloc0_4_r4.c: Regenerated.
	* generated/minloc0_4_r8.c: Regenerated.
	* generated/minloc0_8_i1.c: Regenerated.
	* generated/minloc0_8_i16.c: Regenerated.
	* generated/minloc0_8_i2.c: Regenerated.
	* generated/minloc0_8_i4.c: Regenerated.
	* generated/minloc0_8_i8.c: Regenerated.
	* generated/minloc0_8_r10.c: Regenerated.
	* generated/minloc0_8_r16.c: Regenerated.
	* generated/minloc0_8_r4.c: Regenerated.
	* generated/minloc0_8_r8.c: Regenerated.
	* generated/minloc1_16_i1.c: Regenerated.
	* generated/minloc1_16_i16.c: Regenerated.
	* generated/minloc1_16_i2.c: Regenerated.
	* generated/minloc1_16_i4.c: Regenerated.
	* generated/minloc1_16_i8.c: Regenerated.
	* generated/minloc1_16_r10.c: Regenerated.
	* generated/minloc1_16_r16.c: Regenerated.
	* generated/minloc1_16_r4.c: Regenerated.
	* generated/minloc1_16_r8.c: Regenerated.
	* generated/minloc1_4_i1.c: Regenerated.
	* generated/minloc1_4_i16.c: Regenerated.
	* generated/minloc1_4_i2.c: Regenerated.
	* generated/minloc1_4_i4.c: Regenerated.
	* generated/minloc1_4_i8.c: Regenerated.
	* generated/minloc1_4_r10.c: Regenerated.
	* generated/minloc1_4_r16.c: Regenerated.
	* generated/minloc1_4_r4.c: Regenerated.
	* generated/minloc1_4_r8.c: Regenerated.
	* generated/minloc1_8_i1.c: Regenerated.
	* generated/minloc1_8_i16.c: Regenerated.
	* generated/minloc1_8_i2.c: Regenerated.
	* generated/minloc1_8_i4.c: Regenerated.
	* generated/minloc1_8_i8.c: Regenerated.
	* generated/minloc1_8_r10.c: Regenerated.
	* generated/minloc1_8_r16.c: Regenerated.
	* generated/minloc1_8_r4.c: Regenerated.
	* generated/minloc1_8_r8.c: Regenerated.
	* generated/minval_i1.c: Regenerated.
	* generated/minval_i16.c: Regenerated.
	* generated/minval_i2.c: Regenerated.
	* generated/minval_i4.c: Regenerated.
	* generated/minval_i8.c: Regenerated.
	* generated/minval_r10.c: Regenerated.
	* generated/minval_r16.c: Regenerated.
	* generated/minval_r4.c: Regenerated.
	* generated/minval_r8.c: Regenerated.
	* generated/product_c10.c: Regenerated.
	* generated/product_c16.c: Regenerated.
	* generated/product_c4.c: Regenerated.
	* generated/product_c8.c: Regenerated.
	* generated/product_i1.c: Regenerated.
	* generated/product_i16.c: Regenerated.
	* generated/product_i2.c: Regenerated.
	* generated/product_i4.c: Regenerated.
	* generated/product_i8.c: Regenerated.
	* generated/product_r10.c: Regenerated.
	* generated/product_r16.c: Regenerated.
	* generated/product_r4.c: Regenerated.
	* generated/product_r8.c: Regenerated.
	* generated/sum_c10.c: Regenerated.
	* generated/sum_c16.c: Regenerated.
	* generated/sum_c4.c: Regenerated.
	* generated/sum_c8.c: Regenerated.
	* generated/sum_i1.c: Regenerated.
	* generated/sum_i16.c: Regenerated.
	* generated/sum_i2.c: Regenerated.
	* generated/sum_i4.c: Regenerated.
	* generated/sum_i8.c: Regenerated.
	* generated/sum_r10.c: Regenerated.
	* generated/sum_r16.c: Regenerated.
	* generated/sum_r4.c: Regenerated.
	* generated/sum_r8.c: Regenerated.

From-SVN: r127774

1 files changed, 22 insertions, 18 deletions

diff --git a/libgfortran/generated/maxloc1_4_i8.c b/libgfortran/generated/maxloc1_4_i8.c
index b12a40b9050..f5131140355 100644
--- a/libgfortran/generated/maxloc1_4_i8.c
+++ b/libgfortran/generated/maxloc1_4_i8.c
@@ -191,14 +191,14 @@ maxloc1_4_i8 (gfc_array_i4 * const restrict retarray,
 
 extern void mmaxloc1_4_i8 (gfc_array_i4 * const restrict, 
 	gfc_array_i8 * const restrict, const index_type * const restrict,
-	gfc_array_l4 * const restrict);
+	gfc_array_l1 * const restrict);
 export_proto(mmaxloc1_4_i8);
 
 void
 mmaxloc1_4_i8 (gfc_array_i4 * const restrict retarray, 
 	gfc_array_i8 * const restrict array, 
 	const index_type * const restrict pdim, 
-	gfc_array_l4 * const restrict mask)
+	gfc_array_l1 * const restrict mask)
 {
   index_type count[GFC_MAX_DIMENSIONS];
   index_type extent[GFC_MAX_DIMENSIONS];
@@ -207,13 +207,14 @@ mmaxloc1_4_i8 (gfc_array_i4 * const restrict retarray,
   index_type mstride[GFC_MAX_DIMENSIONS];
   GFC_INTEGER_4 * restrict dest;
   const GFC_INTEGER_8 * restrict base;
-  const GFC_LOGICAL_4 * restrict mbase;
+  const GFC_LOGICAL_1 * restrict mbase;
   int rank;
   int dim;
   index_type n;
   index_type len;
   index_type delta;
   index_type mdelta;
+  int mask_kind;
 
   dim = (*pdim) - 1;
   rank = GFC_DESCRIPTOR_RANK (array) - 1;
@@ -221,13 +222,27 @@ mmaxloc1_4_i8 (gfc_array_i4 * const restrict retarray,
   len = array->dim[dim].ubound + 1 - array->dim[dim].lbound;
   if (len <= 0)
     return;
+
+  mbase = mask->data;
+
+  mask_kind = GFC_DESCRIPTOR_SIZE (mask);
+
+  if (mask_kind == 1 || mask_kind == 2 || mask_kind == 4 || mask_kind == 8
+#ifdef HAVE_GFC_LOGICAL_16
+      || mask_kind == 16
+#endif
+      )
+    mbase = GFOR_POINTER_TO_L1 (mbase, mask_kind);
+  else
+    runtime_error ("Funny sized logical array");
+
   delta = array->dim[dim].stride;
-  mdelta = mask->dim[dim].stride;
+  mdelta = mask->dim[dim].stride * mask_kind;
 
   for (n = 0; n < dim; n++)
     {
       sstride[n] = array->dim[n].stride;
-      mstride[n] = mask->dim[n].stride;
+      mstride[n] = mask->dim[n].stride * mask_kind;
       extent[n] = array->dim[n].ubound + 1 - array->dim[n].lbound;
 
       if (extent[n] < 0)
@@ -237,7 +252,7 @@ mmaxloc1_4_i8 (gfc_array_i4 * const restrict retarray,
   for (n = dim; n < rank; n++)
     {
       sstride[n] = array->dim[n + 1].stride;
-      mstride[n] = mask->dim[n + 1].stride;
+      mstride[n] = mask->dim[n + 1].stride * mask_kind;
       extent[n] =
         array->dim[n + 1].ubound + 1 - array->dim[n + 1].lbound;
 
@@ -292,22 +307,11 @@ mmaxloc1_4_i8 (gfc_array_i4 * const restrict retarray,
 
   dest = retarray->data;
   base = array->data;
-  mbase = mask->data;
-
-  if (GFC_DESCRIPTOR_SIZE (mask) != 4)
-    {
-      /* This allows the same loop to be used for all logical types.  */
-      assert (GFC_DESCRIPTOR_SIZE (mask) == 8);
-      for (n = 0; n < rank; n++)
-        mstride[n] <<= 1;
-      mdelta <<= 1;
-      mbase = (GFOR_POINTER_L8_TO_L4 (mbase));
-    }
 
   while (base)
     {
       const GFC_INTEGER_8 * restrict src;
-      const GFC_LOGICAL_4 * restrict msrc;
+      const GFC_LOGICAL_1 * restrict msrc;
       GFC_INTEGER_4 result;
       src = base;
       msrc = mbase;