64b1806b2d
2018-01-15 Thomas Koenig <tkoenig@gcc.gnu.org> PR fortran/54613 * gfortran.h (gfc_check_f): Rename f4ml to f5ml. (gfc_logical_4_kind): New macro * intrinsic.h (gfc_simplify_minloc): Add a gfc_expr *argument. (gfc_simplify_maxloc): Likewise. (gfc_resolve_maxloc): Likewise. (gfc_resolve_minloc): Likewise. * check.c (gfc_check_minloc_maxloc): Add checking for "back" argument; also raise error if it is used (for now). Add it if it isn't present. * intrinsic.c (add_sym_4ml): Rename to (add_sym_5ml), adjust for extra argument. (add_functions): Add "back" constant. Adjust maxloc and minloc for back argument. * iresolve.c (gfc_resolve_maxloc): Add back argument. If back is not of gfc_logical_4_kind, convert. (gfc_resolve_minloc): Likewise. * simplify.c (gfc_simplify_minloc): Add back argument. (gfc_simplify_maxloc): Likewise. * trans-intinsic.c (gfc_conv_intrinsic_minmaxloc): Rename last argument to %VAL to ensure passing by value. (gfc_conv_intrinsic_function): Call gfc_conv_intrinsic_minmaxloc also for library calls. 2018-01-15 Thomas Koenig <tkoenig@gcc.gnu.org> PR fortran/54613 * m4/iparm.m4: Add back_arg macro if in minloc or maxloc. * m4/iforeach-s.m4: Add optional argument back with back_arg macro. Improve m4 quoting. If HAVE_BACK_ARG is defined, assert that back is non-true. * m4/iforeach.m4: Likewise. * m4/ifunction-s.m4: Likewise. * m4/ifunction.m4: Likewise. * m4/maxloc0.m4: Include assert.h * m4/minloc0.m4: Likewise. * m4/maxloc0s.m4: #define HAVE_BACK_ARG. * m4/minloc0s.m4: Likewise. * m4/maxloc1s.m4: Likewise. * m4/minloc1s.m4: Likewise. * m4/maxloc1.m4: Include assert.h, #define HAVE_BACK_ARG. * m4/minloc1.m4: Likewise. * m4/maxloc2s.m4: Add assert.h, add back_arg, assert that back is non-true. * m4/minloc2s.m4: Likewise. * generated/iall_i1.c: Regenerated. * generated/iall_i16.c: Regenerated. * generated/iall_i2.c: Regenerated. * generated/iall_i4.c: Regenerated. * generated/iall_i8.c: Regenerated. * generated/iany_i1.c: Regenerated. * generated/iany_i16.c: Regenerated. * generated/iany_i2.c: Regenerated. * generated/iany_i4.c: Regenerated. * generated/iany_i8.c: Regenerated. * generated/iparity_i1.c: Regenerated. * generated/iparity_i16.c: Regenerated. * generated/iparity_i2.c: Regenerated. * generated/iparity_i4.c: Regenerated. * generated/iparity_i8.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_16_s1.c: Regenerated. * generated/maxloc0_16_s4.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_4_s1.c: Regenerated. * generated/maxloc0_4_s4.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/maxloc0_8_s1.c: Regenerated. * generated/maxloc0_8_s4.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_16_s1.c: Regenerated. * generated/maxloc1_16_s4.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_4_s1.c: Regenerated. * generated/maxloc1_4_s4.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/maxloc1_8_s1.c: Regenerated. * generated/maxloc1_8_s4.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_16_s1.c: Regenerated. * generated/minloc0_16_s4.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_4_s1.c: Regenerated. * generated/minloc0_4_s4.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/minloc0_8_s1.c: Regenerated. * generated/minloc0_8_s4.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_16_s1.c: Regenerated. * generated/minloc1_16_s4.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_4_s1.c: Regenerated. * generated/minloc1_4_s4.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/minloc1_8_s1.c: Regenerated. * generated/minloc1_8_s4.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/norm2_r10.c: Regenerated. * generated/norm2_r16.c: Regenerated. * generated/norm2_r4.c: Regenerated. * generated/norm2_r8.c: Regenerated. * generated/parity_l1.c: Regenerated. * generated/parity_l16.c: Regenerated. * generated/parity_l2.c: Regenerated. * generated/parity_l4.c: Regenerated. * generated/parity_l8.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. 2018-01-15 Thomas Koenig <tkoenig@gcc.gnu.org> PR fortran/54613 * gfortran.dg/minmaxloc_9.f90: New test. * gfortran.dg/minmaxloc_10.f90: New test. * gfortran.dg/minmaxloc_11.f90: New test. From-SVN: r256705
532 lines
12 KiB
C
532 lines
12 KiB
C
/* Implementation of the SUM intrinsic
|
|
Copyright (C) 2002-2018 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 3 of the License, or (at your option) any later version.
|
|
|
|
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.
|
|
|
|
Under Section 7 of GPL version 3, you are granted additional
|
|
permissions described in the GCC Runtime Library Exception, version
|
|
3.1, as published by the Free Software Foundation.
|
|
|
|
You should have received a copy of the GNU General Public License and
|
|
a copy of the GCC Runtime Library Exception along with this program;
|
|
see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
|
|
<http://www.gnu.org/licenses/>. */
|
|
|
|
#include "libgfortran.h"
|
|
|
|
|
|
#if defined (HAVE_GFC_COMPLEX_10) && defined (HAVE_GFC_COMPLEX_10)
|
|
|
|
|
|
extern void sum_c10 (gfc_array_c10 * const restrict,
|
|
gfc_array_c10 * const restrict, const index_type * const restrict);
|
|
export_proto(sum_c10);
|
|
|
|
void
|
|
sum_c10 (gfc_array_c10 * const restrict retarray,
|
|
gfc_array_c10 * 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_10 * restrict base;
|
|
GFC_COMPLEX_10 * restrict dest;
|
|
index_type rank;
|
|
index_type n;
|
|
index_type len;
|
|
index_type delta;
|
|
index_type dim;
|
|
int continue_loop;
|
|
|
|
#ifdef HAVE_BACK_ARG
|
|
assert(back == 0);
|
|
#endif
|
|
|
|
/* Make dim zero based to avoid confusion. */
|
|
rank = GFC_DESCRIPTOR_RANK (array) - 1;
|
|
dim = (*pdim) - 1;
|
|
|
|
if (unlikely (dim < 0 || dim > rank))
|
|
{
|
|
runtime_error ("Dim argument incorrect in SUM intrinsic: "
|
|
"is %ld, should be between 1 and %ld",
|
|
(long int) dim + 1, (long int) rank + 1);
|
|
}
|
|
|
|
len = GFC_DESCRIPTOR_EXTENT(array,dim);
|
|
if (len < 0)
|
|
len = 0;
|
|
delta = GFC_DESCRIPTOR_STRIDE(array,dim);
|
|
|
|
for (n = 0; n < dim; n++)
|
|
{
|
|
sstride[n] = GFC_DESCRIPTOR_STRIDE(array,n);
|
|
extent[n] = GFC_DESCRIPTOR_EXTENT(array,n);
|
|
|
|
if (extent[n] < 0)
|
|
extent[n] = 0;
|
|
}
|
|
for (n = dim; n < rank; n++)
|
|
{
|
|
sstride[n] = GFC_DESCRIPTOR_STRIDE(array, n + 1);
|
|
extent[n] = GFC_DESCRIPTOR_EXTENT(array, n + 1);
|
|
|
|
if (extent[n] < 0)
|
|
extent[n] = 0;
|
|
}
|
|
|
|
if (retarray->base_addr == NULL)
|
|
{
|
|
size_t alloc_size, str;
|
|
|
|
for (n = 0; n < rank; n++)
|
|
{
|
|
if (n == 0)
|
|
str = 1;
|
|
else
|
|
str = GFC_DESCRIPTOR_STRIDE(retarray,n-1) * extent[n-1];
|
|
|
|
GFC_DIMENSION_SET(retarray->dim[n], 0, extent[n] - 1, str);
|
|
|
|
}
|
|
|
|
retarray->offset = 0;
|
|
GFC_DTYPE_COPY_SETRANK(retarray,array,rank);
|
|
|
|
alloc_size = GFC_DESCRIPTOR_STRIDE(retarray,rank-1) * extent[rank-1];
|
|
|
|
retarray->base_addr = xmallocarray (alloc_size, sizeof (GFC_COMPLEX_10));
|
|
if (alloc_size == 0)
|
|
{
|
|
/* Make sure we have a zero-sized array. */
|
|
GFC_DIMENSION_SET(retarray->dim[0], 0, -1, 1);
|
|
return;
|
|
|
|
}
|
|
}
|
|
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 (unlikely (compile_options.bounds_check))
|
|
bounds_ifunction_return ((array_t *) retarray, extent,
|
|
"return value", "SUM");
|
|
}
|
|
|
|
for (n = 0; n < rank; n++)
|
|
{
|
|
count[n] = 0;
|
|
dstride[n] = GFC_DESCRIPTOR_STRIDE(retarray,n);
|
|
if (extent[n] <= 0)
|
|
return;
|
|
}
|
|
|
|
base = array->base_addr;
|
|
dest = retarray->base_addr;
|
|
|
|
continue_loop = 1;
|
|
while (continue_loop)
|
|
{
|
|
const GFC_COMPLEX_10 * restrict src;
|
|
GFC_COMPLEX_10 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 loop. */
|
|
continue_loop = 0;
|
|
break;
|
|
}
|
|
else
|
|
{
|
|
count[n]++;
|
|
base += sstride[n];
|
|
dest += dstride[n];
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
|
|
extern void msum_c10 (gfc_array_c10 * const restrict,
|
|
gfc_array_c10 * const restrict, const index_type * const restrict,
|
|
gfc_array_l1 * const restrict);
|
|
export_proto(msum_c10);
|
|
|
|
void
|
|
msum_c10 (gfc_array_c10 * const restrict retarray,
|
|
gfc_array_c10 * 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_10 * restrict dest;
|
|
const GFC_COMPLEX_10 * restrict base;
|
|
const GFC_LOGICAL_1 * restrict mbase;
|
|
index_type rank;
|
|
index_type dim;
|
|
index_type n;
|
|
index_type len;
|
|
index_type delta;
|
|
index_type mdelta;
|
|
int mask_kind;
|
|
|
|
#ifdef HAVE_BACK_ARG
|
|
assert (back == 0);
|
|
#endif
|
|
dim = (*pdim) - 1;
|
|
rank = GFC_DESCRIPTOR_RANK (array) - 1;
|
|
|
|
|
|
if (unlikely (dim < 0 || dim > rank))
|
|
{
|
|
runtime_error ("Dim argument incorrect in SUM intrinsic: "
|
|
"is %ld, should be between 1 and %ld",
|
|
(long int) dim + 1, (long int) rank + 1);
|
|
}
|
|
|
|
len = GFC_DESCRIPTOR_EXTENT(array,dim);
|
|
if (len <= 0)
|
|
return;
|
|
|
|
mbase = mask->base_addr;
|
|
|
|
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 = GFC_DESCRIPTOR_STRIDE(array,dim);
|
|
mdelta = GFC_DESCRIPTOR_STRIDE_BYTES(mask,dim);
|
|
|
|
for (n = 0; n < dim; n++)
|
|
{
|
|
sstride[n] = GFC_DESCRIPTOR_STRIDE(array,n);
|
|
mstride[n] = GFC_DESCRIPTOR_STRIDE_BYTES(mask,n);
|
|
extent[n] = GFC_DESCRIPTOR_EXTENT(array,n);
|
|
|
|
if (extent[n] < 0)
|
|
extent[n] = 0;
|
|
|
|
}
|
|
for (n = dim; n < rank; n++)
|
|
{
|
|
sstride[n] = GFC_DESCRIPTOR_STRIDE(array,n + 1);
|
|
mstride[n] = GFC_DESCRIPTOR_STRIDE_BYTES(mask, n + 1);
|
|
extent[n] = GFC_DESCRIPTOR_EXTENT(array, n + 1);
|
|
|
|
if (extent[n] < 0)
|
|
extent[n] = 0;
|
|
}
|
|
|
|
if (retarray->base_addr == NULL)
|
|
{
|
|
size_t alloc_size, str;
|
|
|
|
for (n = 0; n < rank; n++)
|
|
{
|
|
if (n == 0)
|
|
str = 1;
|
|
else
|
|
str= GFC_DESCRIPTOR_STRIDE(retarray,n-1) * extent[n-1];
|
|
|
|
GFC_DIMENSION_SET(retarray->dim[n], 0, extent[n] - 1, str);
|
|
|
|
}
|
|
|
|
alloc_size = GFC_DESCRIPTOR_STRIDE(retarray,rank-1) * extent[rank-1];
|
|
|
|
retarray->offset = 0;
|
|
GFC_DTYPE_COPY_SETRANK(retarray,array,rank);
|
|
|
|
if (alloc_size == 0)
|
|
{
|
|
/* Make sure we have a zero-sized array. */
|
|
GFC_DIMENSION_SET(retarray->dim[0], 0, -1, 1);
|
|
return;
|
|
}
|
|
else
|
|
retarray->base_addr = xmallocarray (alloc_size, sizeof (GFC_COMPLEX_10));
|
|
|
|
}
|
|
else
|
|
{
|
|
if (rank != GFC_DESCRIPTOR_RANK (retarray))
|
|
runtime_error ("rank of return array incorrect in SUM intrinsic");
|
|
|
|
if (unlikely (compile_options.bounds_check))
|
|
{
|
|
bounds_ifunction_return ((array_t *) retarray, extent,
|
|
"return value", "SUM");
|
|
bounds_equal_extents ((array_t *) mask, (array_t *) array,
|
|
"MASK argument", "SUM");
|
|
}
|
|
}
|
|
|
|
for (n = 0; n < rank; n++)
|
|
{
|
|
count[n] = 0;
|
|
dstride[n] = GFC_DESCRIPTOR_STRIDE(retarray,n);
|
|
if (extent[n] <= 0)
|
|
return;
|
|
}
|
|
|
|
dest = retarray->base_addr;
|
|
base = array->base_addr;
|
|
|
|
while (base)
|
|
{
|
|
const GFC_COMPLEX_10 * restrict src;
|
|
const GFC_LOGICAL_1 * restrict msrc;
|
|
GFC_COMPLEX_10 result;
|
|
src = base;
|
|
msrc = mbase;
|
|
{
|
|
|
|
result = 0;
|
|
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 loop. */
|
|
base = NULL;
|
|
break;
|
|
}
|
|
else
|
|
{
|
|
count[n]++;
|
|
base += sstride[n];
|
|
mbase += mstride[n];
|
|
dest += dstride[n];
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
|
|
extern void ssum_c10 (gfc_array_c10 * const restrict,
|
|
gfc_array_c10 * const restrict, const index_type * const restrict,
|
|
GFC_LOGICAL_4 *);
|
|
export_proto(ssum_c10);
|
|
|
|
void
|
|
ssum_c10 (gfc_array_c10 * const restrict retarray,
|
|
gfc_array_c10 * const restrict array,
|
|
const index_type * const restrict pdim,
|
|
GFC_LOGICAL_4 * mask)
|
|
{
|
|
index_type count[GFC_MAX_DIMENSIONS];
|
|
index_type extent[GFC_MAX_DIMENSIONS];
|
|
index_type dstride[GFC_MAX_DIMENSIONS];
|
|
GFC_COMPLEX_10 * restrict dest;
|
|
index_type rank;
|
|
index_type n;
|
|
index_type dim;
|
|
|
|
|
|
if (*mask)
|
|
{
|
|
#ifdef HAVE_BACK_ARG
|
|
sum_c10 (retarray, array, pdim, back);
|
|
#else
|
|
sum_c10 (retarray, array, pdim);
|
|
#endif
|
|
return;
|
|
}
|
|
/* Make dim zero based to avoid confusion. */
|
|
dim = (*pdim) - 1;
|
|
rank = GFC_DESCRIPTOR_RANK (array) - 1;
|
|
|
|
if (unlikely (dim < 0 || dim > rank))
|
|
{
|
|
runtime_error ("Dim argument incorrect in SUM intrinsic: "
|
|
"is %ld, should be between 1 and %ld",
|
|
(long int) dim + 1, (long int) rank + 1);
|
|
}
|
|
|
|
for (n = 0; n < dim; n++)
|
|
{
|
|
extent[n] = GFC_DESCRIPTOR_EXTENT(array,n);
|
|
|
|
if (extent[n] <= 0)
|
|
extent[n] = 0;
|
|
}
|
|
|
|
for (n = dim; n < rank; n++)
|
|
{
|
|
extent[n] =
|
|
GFC_DESCRIPTOR_EXTENT(array,n + 1);
|
|
|
|
if (extent[n] <= 0)
|
|
extent[n] = 0;
|
|
}
|
|
|
|
if (retarray->base_addr == NULL)
|
|
{
|
|
size_t alloc_size, str;
|
|
|
|
for (n = 0; n < rank; n++)
|
|
{
|
|
if (n == 0)
|
|
str = 1;
|
|
else
|
|
str = GFC_DESCRIPTOR_STRIDE(retarray,n-1) * extent[n-1];
|
|
|
|
GFC_DIMENSION_SET(retarray->dim[n], 0, extent[n] - 1, str);
|
|
|
|
}
|
|
|
|
retarray->offset = 0;
|
|
GFC_DTYPE_COPY_SETRANK(retarray,array,rank);
|
|
|
|
alloc_size = GFC_DESCRIPTOR_STRIDE(retarray,rank-1) * extent[rank-1];
|
|
|
|
if (alloc_size == 0)
|
|
{
|
|
/* Make sure we have a zero-sized array. */
|
|
GFC_DIMENSION_SET(retarray->dim[0], 0, -1, 1);
|
|
return;
|
|
}
|
|
else
|
|
retarray->base_addr = xmallocarray (alloc_size, sizeof (GFC_COMPLEX_10));
|
|
}
|
|
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 (unlikely (compile_options.bounds_check))
|
|
{
|
|
for (n=0; n < rank; n++)
|
|
{
|
|
index_type ret_extent;
|
|
|
|
ret_extent = GFC_DESCRIPTOR_EXTENT(retarray,n);
|
|
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] = GFC_DESCRIPTOR_STRIDE(retarray,n);
|
|
}
|
|
|
|
dest = retarray->base_addr;
|
|
|
|
while(1)
|
|
{
|
|
*dest = 0;
|
|
count[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. */
|
|
dest -= dstride[n] * extent[n];
|
|
n++;
|
|
if (n >= rank)
|
|
return;
|
|
else
|
|
{
|
|
count[n]++;
|
|
dest += dstride[n];
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
#endif
|