gcc/libgfortran/generated/sum_c4.c
Thomas Koenig ccacefc7a6 re PR libfortran/34746 (wrong formats in libgfortran's runtime_error)
2008-01-13  Thomas Koenig  <tkoenig@gcc.gnu.org>

	PR libfortran/34746
	* m4/iforeach.m4 (name`'rtype_qual`_'atype_code):  Use %ld
	in printf format for all bounds checking; cast all
	integer-like arguments to runtime_error() to long int.
	(`m'name`'rtype_qual`_'atype_code):  Likewise.
	(`s'name`'rtype_qual`_'atype_code):  Likewise.
	* m4/ifunction.m4 (name`'rtype_qual`_'atype_code):  Likewise.
	(`m'name`'rtype_qual`_'atype_code):  Likewise.
	(`s'name`'rtype_qual`_'atype_code):  Likewise.
	* generated/all_l16.c: Regenerated.
	* generated/all_l4.c: Regenerated.
	* generated/all_l8.c: Regenerated.
	* generated/any_l16.c: Regenerated.
	* generated/any_l4.c: Regenerated.
	* generated/any_l8.c: Regenerated.
	* generated/count_16_l16.c: Regenerated.
	* generated/count_16_l4.c: Regenerated.
	* generated/count_16_l8.c: Regenerated.
	* generated/count_4_l16.c: Regenerated.
	* generated/count_4_l4.c: Regenerated.
	* generated/count_4_l8.c: Regenerated.
	* generated/count_8_l16.c: Regenerated.
	* generated/count_8_l4.c: Regenerated.
	* generated/count_8_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: r131514
2008-01-13 22:13:52 +00:00

467 lines
12 KiB
C

/* Implementation of the SUM intrinsic
Copyright 2002, 2007 Free Software Foundation, Inc.
Contributed by Paul Brook <paul@nowt.org>
This file is part of the GNU Fortran 95 runtime library (libgfortran).
Libgfortran 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 of the License, 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.)
Libgfortran 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 libgfortran; see the file COPYING. If not,
write to the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
Boston, MA 02110-1301, USA. */
#include "libgfortran.h"
#include <stdlib.h>
#include <assert.h>
#if defined (HAVE_GFC_COMPLEX_4) && defined (HAVE_GFC_COMPLEX_4)
extern void sum_c4 (gfc_array_c4 * const restrict,
gfc_array_c4 * const restrict, const index_type * const restrict);
export_proto(sum_c4);
void
sum_c4 (gfc_array_c4 * const restrict retarray,
gfc_array_c4 * const restrict array,
const index_type * const restrict pdim)
{
index_type count[GFC_MAX_DIMENSIONS];
index_type extent[GFC_MAX_DIMENSIONS];
index_type sstride[GFC_MAX_DIMENSIONS];
index_type dstride[GFC_MAX_DIMENSIONS];
const GFC_COMPLEX_4 * restrict base;
GFC_COMPLEX_4 * restrict dest;
index_type rank;
index_type n;
index_type len;
index_type delta;
index_type dim;
/* Make dim zero based to avoid confusion. */
dim = (*pdim) - 1;
rank = GFC_DESCRIPTOR_RANK (array) - 1;
len = array->dim[dim].ubound + 1 - array->dim[dim].lbound;
delta = array->dim[dim].stride;
for (n = 0; n < dim; n++)
{
sstride[n] = array->dim[n].stride;
extent[n] = array->dim[n].ubound + 1 - array->dim[n].lbound;
if (extent[n] < 0)
extent[n] = 0;
}
for (n = dim; n < rank; n++)
{
sstride[n] = array->dim[n + 1].stride;
extent[n] =
array->dim[n + 1].ubound + 1 - array->dim[n + 1].lbound;
if (extent[n] < 0)
extent[n] = 0;
}
if (retarray->data == NULL)
{
size_t alloc_size;
for (n = 0; n < rank; n++)
{
retarray->dim[n].lbound = 0;
retarray->dim[n].ubound = extent[n]-1;
if (n == 0)
retarray->dim[n].stride = 1;
else
retarray->dim[n].stride = retarray->dim[n-1].stride * extent[n-1];
}
retarray->offset = 0;
retarray->dtype = (array->dtype & ~GFC_DTYPE_RANK_MASK) | rank;
alloc_size = sizeof (GFC_COMPLEX_4) * retarray->dim[rank-1].stride
* extent[rank-1];
if (alloc_size == 0)
{
/* Make sure we have a zero-sized array. */
retarray->dim[0].lbound = 0;
retarray->dim[0].ubound = -1;
return;
}
else
retarray->data = internal_malloc_size (alloc_size);
}
else
{
if (rank != GFC_DESCRIPTOR_RANK (retarray))
runtime_error ("rank of return array incorrect in"
" SUM intrinsic: is %ld, should be %ld",
(long int) (GFC_DESCRIPTOR_RANK (retarray)),
(long int) rank);
if (compile_options.bounds_check)
{
for (n=0; n < rank; n++)
{
index_type ret_extent;
ret_extent = retarray->dim[n].ubound + 1
- retarray->dim[n].lbound;
if (extent[n] != ret_extent)
runtime_error ("Incorrect extent in return value of"
" SUM intrinsic in dimension %ld:"
" is %ld, should be %ld", (long int) n + 1,
(long int) ret_extent, (long int) extent[n]);
}
}
}
for (n = 0; n < rank; n++)
{
count[n] = 0;
dstride[n] = retarray->dim[n].stride;
if (extent[n] <= 0)
len = 0;
}
base = array->data;
dest = retarray->data;
while (base)
{
const GFC_COMPLEX_4 * restrict src;
GFC_COMPLEX_4 result;
src = base;
{
result = 0;
if (len <= 0)
*dest = 0;
else
{
for (n = 0; n < len; n++, src += delta)
{
result += *src;
}
*dest = result;
}
}
/* Advance to the next element. */
count[0]++;
base += sstride[0];
dest += dstride[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 these products, but this is a less
frequently used path so probably not worth it. */
base -= sstride[n] * extent[n];
dest -= dstride[n] * extent[n];
n++;
if (n == rank)
{
/* Break out of the look. */
base = NULL;
break;
}
else
{
count[n]++;
base += sstride[n];
dest += dstride[n];
}
}
}
}
extern void msum_c4 (gfc_array_c4 * const restrict,
gfc_array_c4 * const restrict, const index_type * const restrict,
gfc_array_l1 * const restrict);
export_proto(msum_c4);
void
msum_c4 (gfc_array_c4 * const restrict retarray,
gfc_array_c4 * const restrict array,
const index_type * const restrict pdim,
gfc_array_l1 * const restrict mask)
{
index_type count[GFC_MAX_DIMENSIONS];
index_type extent[GFC_MAX_DIMENSIONS];
index_type sstride[GFC_MAX_DIMENSIONS];
index_type dstride[GFC_MAX_DIMENSIONS];
index_type mstride[GFC_MAX_DIMENSIONS];
GFC_COMPLEX_4 * restrict dest;
const GFC_COMPLEX_4 * restrict base;
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;
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 * mask_kind;
for (n = 0; n < dim; n++)
{
sstride[n] = array->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)
extent[n] = 0;
}
for (n = dim; n < rank; n++)
{
sstride[n] = array->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;
if (extent[n] < 0)
extent[n] = 0;
}
if (retarray->data == NULL)
{
size_t alloc_size;
for (n = 0; n < rank; n++)
{
retarray->dim[n].lbound = 0;
retarray->dim[n].ubound = extent[n]-1;
if (n == 0)
retarray->dim[n].stride = 1;
else
retarray->dim[n].stride = retarray->dim[n-1].stride * extent[n-1];
}
alloc_size = sizeof (GFC_COMPLEX_4) * retarray->dim[rank-1].stride
* extent[rank-1];
retarray->offset = 0;
retarray->dtype = (array->dtype & ~GFC_DTYPE_RANK_MASK) | rank;
if (alloc_size == 0)
{
/* Make sure we have a zero-sized array. */
retarray->dim[0].lbound = 0;
retarray->dim[0].ubound = -1;
return;
}
else
retarray->data = internal_malloc_size (alloc_size);
}
else
{
if (rank != GFC_DESCRIPTOR_RANK (retarray))
runtime_error ("rank of return array incorrect in SUM intrinsic");
if (compile_options.bounds_check)
{
for (n=0; n < rank; n++)
{
index_type ret_extent;
ret_extent = retarray->dim[n].ubound + 1
- retarray->dim[n].lbound;
if (extent[n] != ret_extent)
runtime_error ("Incorrect extent in return value of"
" SUM intrinsic in dimension %ld:"
" is %ld, should be %ld", (long int) n + 1,
(long int) ret_extent, (long int) extent[n]);
}
for (n=0; n<= rank; n++)
{
index_type mask_extent, array_extent;
array_extent = array->dim[n].ubound + 1 - array->dim[n].lbound;
mask_extent = mask->dim[n].ubound + 1 - mask->dim[n].lbound;
if (array_extent != mask_extent)
runtime_error ("Incorrect extent in MASK argument of"
" SUM intrinsic in dimension %ld:"
" is %ld, should be %ld", (long int) n + 1,
(long int) mask_extent, (long int) array_extent);
}
}
}
for (n = 0; n < rank; n++)
{
count[n] = 0;
dstride[n] = retarray->dim[n].stride;
if (extent[n] <= 0)
return;
}
dest = retarray->data;
base = array->data;
while (base)
{
const GFC_COMPLEX_4 * restrict src;
const GFC_LOGICAL_1 * restrict msrc;
GFC_COMPLEX_4 result;
src = base;
msrc = mbase;
{
result = 0;
if (len <= 0)
*dest = 0;
else
{
for (n = 0; n < len; n++, src += delta, msrc += mdelta)
{
if (*msrc)
result += *src;
}
*dest = result;
}
}
/* Advance to the next element. */
count[0]++;
base += sstride[0];
mbase += mstride[0];
dest += dstride[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 these products, but this is a less
frequently used path so probably not worth it. */
base -= sstride[n] * extent[n];
mbase -= mstride[n] * extent[n];
dest -= dstride[n] * extent[n];
n++;
if (n == rank)
{
/* Break out of the look. */
base = NULL;
break;
}
else
{
count[n]++;
base += sstride[n];
mbase += mstride[n];
dest += dstride[n];
}
}
}
}
extern void ssum_c4 (gfc_array_c4 * const restrict,
gfc_array_c4 * const restrict, const index_type * const restrict,
GFC_LOGICAL_4 *);
export_proto(ssum_c4);
void
ssum_c4 (gfc_array_c4 * const restrict retarray,
gfc_array_c4 * const restrict array,
const index_type * const restrict pdim,
GFC_LOGICAL_4 * mask)
{
index_type rank;
index_type n;
index_type dstride;
GFC_COMPLEX_4 *dest;
if (*mask)
{
sum_c4 (retarray, array, pdim);
return;
}
rank = GFC_DESCRIPTOR_RANK (array);
if (rank <= 0)
runtime_error ("Rank of array needs to be > 0");
if (retarray->data == NULL)
{
retarray->dim[0].lbound = 0;
retarray->dim[0].ubound = rank-1;
retarray->dim[0].stride = 1;
retarray->dtype = (retarray->dtype & ~GFC_DTYPE_RANK_MASK) | 1;
retarray->offset = 0;
retarray->data = internal_malloc_size (sizeof (GFC_COMPLEX_4) * rank);
}
else
{
if (compile_options.bounds_check)
{
int ret_rank;
index_type ret_extent;
ret_rank = GFC_DESCRIPTOR_RANK (retarray);
if (ret_rank != 1)
runtime_error ("rank of return array in SUM intrinsic"
" should be 1, is %ld", (long int) ret_rank);
ret_extent = retarray->dim[0].ubound + 1 - retarray->dim[0].lbound;
if (ret_extent != rank)
runtime_error ("dimension of return array incorrect");
}
}
dstride = retarray->dim[0].stride;
dest = retarray->data;
for (n = 0; n < rank; n++)
dest[n * dstride] = 0 ;
}
#endif