gcc/libgfortran/generated/unpack_r10.c

334 lines
8.5 KiB
C
Raw Normal View History

re PR libfortran/32972 (performance of pack/unpack) 2007-03-23 Thomas Koenig <tkoenig@gcc.gnu.org PR libfortran/32972 * Makefile.am: Add new variable, i_unpack_c, containing unpack_i1.c, unpack_i2.c, unpack_i4.c, unpack_i8.c, unpack_i16.c, unpack_r4.c, unpack_r8.c, unpack_r10.c, unpack_r16.c, unpack_c4.c, unpack_c8.c, unpack_c10.c and unpack_c16.c Add i_unpack_c to gfor_built_src. Add rule to generate i_unpack_c from m4/unpack.m4. * Makefile.in: Regenerated. * libgfortran.h: Add prototypes for unpack0_i1, unpack0_i2, unpack0_i4, unpack0_i8, unpack0_i16, unpack0_r4, unpack0_r8, unpack0_r10, unpack0_r16, unpack0_c4, unpack0_c8, unpack0_c10, unpack0_c16, unpack1_i1, unpack1_i2, unpack1_i4, unpack1_i8, unpack1_i16, unpack1_r4, unpack1_r8, unpack1_r10, unpack1_r16, unpack1_c4, unpack1_c8, unpack1_c10 and unpack1_c16. * intrinsics/pack_generic.c (unpack1): Add calls to specific unpack1 functions. (unpack0): Add calls to specific unpack0 functions. * m4/unpack.m4: New file. * generated/unpack_i1.c: New file. * generated/unpack_i2.c: New file. * generated/unpack_i4.c: New file. * generated/unpack_i8.c: New file. * generated/unpack_i16.c: New file. * generated/unpack_r4.c: New file. * generated/unpack_r8.c: New file. * generated/unpack_r10.c: New file. * generated/unpack_r16.c: New file. * generated/unpack_c4.c: New file. * generated/unpack_c8.c: New file. * generated/unpack_c10.c: New file. * generated/unpack_c16.c: New file. 2007-03-23 Thomas Koenig <tkoenig@gcc.gnu.org PR libfortran/32972 * gfortran.dg/intrinsic_unpack_1.f90: New test case. * gfortran.dg/intrinsic_unpack_2.f90: New test case. * gfortran.dg/intrinsic_unpack_3.f90: New test case. From-SVN: r133469
2008-03-23 23:19:19 +01:00
/* Specific implementation of the UNPACK intrinsic
Copyright 2008, 2009 Free Software Foundation, Inc.
re PR libfortran/32972 (performance of pack/unpack) 2007-03-23 Thomas Koenig <tkoenig@gcc.gnu.org PR libfortran/32972 * Makefile.am: Add new variable, i_unpack_c, containing unpack_i1.c, unpack_i2.c, unpack_i4.c, unpack_i8.c, unpack_i16.c, unpack_r4.c, unpack_r8.c, unpack_r10.c, unpack_r16.c, unpack_c4.c, unpack_c8.c, unpack_c10.c and unpack_c16.c Add i_unpack_c to gfor_built_src. Add rule to generate i_unpack_c from m4/unpack.m4. * Makefile.in: Regenerated. * libgfortran.h: Add prototypes for unpack0_i1, unpack0_i2, unpack0_i4, unpack0_i8, unpack0_i16, unpack0_r4, unpack0_r8, unpack0_r10, unpack0_r16, unpack0_c4, unpack0_c8, unpack0_c10, unpack0_c16, unpack1_i1, unpack1_i2, unpack1_i4, unpack1_i8, unpack1_i16, unpack1_r4, unpack1_r8, unpack1_r10, unpack1_r16, unpack1_c4, unpack1_c8, unpack1_c10 and unpack1_c16. * intrinsics/pack_generic.c (unpack1): Add calls to specific unpack1 functions. (unpack0): Add calls to specific unpack0 functions. * m4/unpack.m4: New file. * generated/unpack_i1.c: New file. * generated/unpack_i2.c: New file. * generated/unpack_i4.c: New file. * generated/unpack_i8.c: New file. * generated/unpack_i16.c: New file. * generated/unpack_r4.c: New file. * generated/unpack_r8.c: New file. * generated/unpack_r10.c: New file. * generated/unpack_r16.c: New file. * generated/unpack_c4.c: New file. * generated/unpack_c8.c: New file. * generated/unpack_c10.c: New file. * generated/unpack_c16.c: New file. 2007-03-23 Thomas Koenig <tkoenig@gcc.gnu.org PR libfortran/32972 * gfortran.dg/intrinsic_unpack_1.f90: New test case. * gfortran.dg/intrinsic_unpack_2.f90: New test case. * gfortran.dg/intrinsic_unpack_3.f90: New test case. From-SVN: r133469
2008-03-23 23:19:19 +01:00
Contributed by Thomas Koenig <tkoenig@gcc.gnu.org>, based on
unpack_generic.c 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.
re PR libfortran/32972 (performance of pack/unpack) 2007-03-23 Thomas Koenig <tkoenig@gcc.gnu.org PR libfortran/32972 * Makefile.am: Add new variable, i_unpack_c, containing unpack_i1.c, unpack_i2.c, unpack_i4.c, unpack_i8.c, unpack_i16.c, unpack_r4.c, unpack_r8.c, unpack_r10.c, unpack_r16.c, unpack_c4.c, unpack_c8.c, unpack_c10.c and unpack_c16.c Add i_unpack_c to gfor_built_src. Add rule to generate i_unpack_c from m4/unpack.m4. * Makefile.in: Regenerated. * libgfortran.h: Add prototypes for unpack0_i1, unpack0_i2, unpack0_i4, unpack0_i8, unpack0_i16, unpack0_r4, unpack0_r8, unpack0_r10, unpack0_r16, unpack0_c4, unpack0_c8, unpack0_c10, unpack0_c16, unpack1_i1, unpack1_i2, unpack1_i4, unpack1_i8, unpack1_i16, unpack1_r4, unpack1_r8, unpack1_r10, unpack1_r16, unpack1_c4, unpack1_c8, unpack1_c10 and unpack1_c16. * intrinsics/pack_generic.c (unpack1): Add calls to specific unpack1 functions. (unpack0): Add calls to specific unpack0 functions. * m4/unpack.m4: New file. * generated/unpack_i1.c: New file. * generated/unpack_i2.c: New file. * generated/unpack_i4.c: New file. * generated/unpack_i8.c: New file. * generated/unpack_i16.c: New file. * generated/unpack_r4.c: New file. * generated/unpack_r8.c: New file. * generated/unpack_r10.c: New file. * generated/unpack_r16.c: New file. * generated/unpack_c4.c: New file. * generated/unpack_c8.c: New file. * generated/unpack_c10.c: New file. * generated/unpack_c16.c: New file. 2007-03-23 Thomas Koenig <tkoenig@gcc.gnu.org PR libfortran/32972 * gfortran.dg/intrinsic_unpack_1.f90: New test case. * gfortran.dg/intrinsic_unpack_2.f90: New test case. * gfortran.dg/intrinsic_unpack_3.f90: New test case. From-SVN: r133469
2008-03-23 23:19:19 +01:00
Ligbfortran 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/>. */
re PR libfortran/32972 (performance of pack/unpack) 2007-03-23 Thomas Koenig <tkoenig@gcc.gnu.org PR libfortran/32972 * Makefile.am: Add new variable, i_unpack_c, containing unpack_i1.c, unpack_i2.c, unpack_i4.c, unpack_i8.c, unpack_i16.c, unpack_r4.c, unpack_r8.c, unpack_r10.c, unpack_r16.c, unpack_c4.c, unpack_c8.c, unpack_c10.c and unpack_c16.c Add i_unpack_c to gfor_built_src. Add rule to generate i_unpack_c from m4/unpack.m4. * Makefile.in: Regenerated. * libgfortran.h: Add prototypes for unpack0_i1, unpack0_i2, unpack0_i4, unpack0_i8, unpack0_i16, unpack0_r4, unpack0_r8, unpack0_r10, unpack0_r16, unpack0_c4, unpack0_c8, unpack0_c10, unpack0_c16, unpack1_i1, unpack1_i2, unpack1_i4, unpack1_i8, unpack1_i16, unpack1_r4, unpack1_r8, unpack1_r10, unpack1_r16, unpack1_c4, unpack1_c8, unpack1_c10 and unpack1_c16. * intrinsics/pack_generic.c (unpack1): Add calls to specific unpack1 functions. (unpack0): Add calls to specific unpack0 functions. * m4/unpack.m4: New file. * generated/unpack_i1.c: New file. * generated/unpack_i2.c: New file. * generated/unpack_i4.c: New file. * generated/unpack_i8.c: New file. * generated/unpack_i16.c: New file. * generated/unpack_r4.c: New file. * generated/unpack_r8.c: New file. * generated/unpack_r10.c: New file. * generated/unpack_r16.c: New file. * generated/unpack_c4.c: New file. * generated/unpack_c8.c: New file. * generated/unpack_c10.c: New file. * generated/unpack_c16.c: New file. 2007-03-23 Thomas Koenig <tkoenig@gcc.gnu.org PR libfortran/32972 * gfortran.dg/intrinsic_unpack_1.f90: New test case. * gfortran.dg/intrinsic_unpack_2.f90: New test case. * gfortran.dg/intrinsic_unpack_3.f90: New test case. From-SVN: r133469
2008-03-23 23:19:19 +01:00
#include "libgfortran.h"
#include <stdlib.h>
#include <assert.h>
#include <string.h>
#if defined (HAVE_GFC_REAL_10)
void
unpack0_r10 (gfc_array_r10 *ret, const gfc_array_r10 *vector,
const gfc_array_l1 *mask, const GFC_REAL_10 *fptr)
{
/* r.* indicates the return array. */
index_type rstride[GFC_MAX_DIMENSIONS];
index_type rstride0;
index_type rs;
in_pack.m4 (internal_pack_'rtype_code`): Destination pointer is restrict. 2008-05-18 Thomas Koenig <tkoenig@gcc.gnu.org> * m4/in_pack.m4 (internal_pack_'rtype_code`): Destination pointer is restrict. * m4/transpose.m4 (transpose_'rtype_code`): Likewise. * m4/pack.m4 (pack_'rtype_code`): Likewise. * m4/spread.m4 (spread_'rtype_code`): Likewise. (spread_scalar_'rtype_code`): Likewise. * m4/iforeach.m4 (name`'rtype_qual`_'atype_code): Likewise. * m4/eoshift1.m4 (eoshift1): Likewise. * m4/eoshift3.m4 (eoshift3): Likewise. * m4/in_unpack.m4 (internal_unpack_'rtype_ccode`): Likewise. * m4/unpack.m4 (unpack0_'rtype_code`): Likewise. (unpack1_'rtype_code`): Likewise. * intrinsics/pack_generic.c (pack_generic.c): Likewise. * intrinsics/unpack_generic.c (unpack_internal): Likewise. * intrinsics/eoshift0.c (eoshift0): Likewise. * intrinsics/eoshift2.c (eoshift2): Likewise. * intrinsics/reshape_generic.c (reshape_internal): Likewise. * intrinsics/reshape_packed.c (reshape_packed): Likewise. * generated/eoshift1_16.c: Regenerated. * generated/eoshift1_4.c: Regenerated. * generated/eoshift1_8.c: Regenerated. * generated/eoshift3_16.c: Regenerated. * generated/eoshift3_4.c: Regenerated. * generated/eoshift3_8.c: Regenerated. * generated/in_pack_c10.c: Regenerated. * generated/in_pack_c16.c: Regenerated. * generated/in_pack_c4.c: Regenerated. * generated/in_pack_c8.c: Regenerated. * generated/in_pack_i1.c: Regenerated. * generated/in_pack_i16.c: Regenerated. * generated/in_pack_i2.c: Regenerated. * generated/in_pack_i4.c: Regenerated. * generated/in_pack_i8.c: Regenerated. * generated/in_pack_r10.c: Regenerated. * generated/in_pack_r16.c: Regenerated. * generated/in_pack_r4.c: Regenerated. * generated/in_pack_r8.c: Regenerated. * generated/in_unpack_c10.c: Regenerated. * generated/in_unpack_c16.c: Regenerated. * generated/in_unpack_c4.c: Regenerated. * generated/in_unpack_c8.c: Regenerated. * generated/in_unpack_i1.c: Regenerated. * generated/in_unpack_i16.c: Regenerated. * generated/in_unpack_i2.c: Regenerated. * generated/in_unpack_i4.c: Regenerated. * generated/in_unpack_i8.c: Regenerated. * generated/in_unpack_r10.c: Regenerated. * generated/in_unpack_r16.c: Regenerated. * generated/in_unpack_r4.c: Regenerated. * generated/in_unpack_r8.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/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/pack_c10.c: Regenerated. * generated/pack_c16.c: Regenerated. * generated/pack_c4.c: Regenerated. * generated/pack_c8.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_r10.c: Regenerated. * generated/pack_r16.c: Regenerated. * generated/pack_r4.c: Regenerated. * generated/pack_r8.c: Regenerated. * generated/spread_c10.c: Regenerated. * generated/spread_c16.c: Regenerated. * generated/spread_c4.c: Regenerated. * generated/spread_c8.c: Regenerated. * generated/spread_i1.c: Regenerated. * generated/spread_i16.c: Regenerated. * generated/spread_i2.c: Regenerated. * generated/spread_i4.c: Regenerated. * generated/spread_i8.c: Regenerated. * generated/spread_r10.c: Regenerated. * generated/spread_r16.c: Regenerated. * generated/spread_r4.c: Regenerated. * generated/spread_r8.c: Regenerated. * generated/transpose_c10.c: Regenerated. * generated/transpose_c16.c: Regenerated. * generated/transpose_c4.c: Regenerated. * generated/transpose_c8.c: Regenerated. * generated/transpose_i16.c: Regenerated. * generated/transpose_i4.c: Regenerated. * generated/transpose_i8.c: Regenerated. * generated/transpose_r10.c: Regenerated. * generated/transpose_r16.c: Regenerated. * generated/transpose_r4.c: Regenerated. * generated/transpose_r8.c: Regenerated. * generated/unpack_c10.c: Regenerated. * generated/unpack_c16.c: Regenerated. * generated/unpack_c4.c: Regenerated. * generated/unpack_c8.c: Regenerated. * generated/unpack_i1.c: Regenerated. * generated/unpack_i16.c: Regenerated. * generated/unpack_i2.c: Regenerated. * generated/unpack_i4.c: Regenerated. * generated/unpack_i8.c: Regenerated. * generated/unpack_r10.c: Regenerated. * generated/unpack_r16.c: Regenerated. * generated/unpack_r4.c: Regenerated. * generated/unpack_r8.c: Regenerated. From-SVN: r135512
2008-05-18 22:39:04 +02:00
GFC_REAL_10 * restrict rptr;
re PR libfortran/32972 (performance of pack/unpack) 2007-03-23 Thomas Koenig <tkoenig@gcc.gnu.org PR libfortran/32972 * Makefile.am: Add new variable, i_unpack_c, containing unpack_i1.c, unpack_i2.c, unpack_i4.c, unpack_i8.c, unpack_i16.c, unpack_r4.c, unpack_r8.c, unpack_r10.c, unpack_r16.c, unpack_c4.c, unpack_c8.c, unpack_c10.c and unpack_c16.c Add i_unpack_c to gfor_built_src. Add rule to generate i_unpack_c from m4/unpack.m4. * Makefile.in: Regenerated. * libgfortran.h: Add prototypes for unpack0_i1, unpack0_i2, unpack0_i4, unpack0_i8, unpack0_i16, unpack0_r4, unpack0_r8, unpack0_r10, unpack0_r16, unpack0_c4, unpack0_c8, unpack0_c10, unpack0_c16, unpack1_i1, unpack1_i2, unpack1_i4, unpack1_i8, unpack1_i16, unpack1_r4, unpack1_r8, unpack1_r10, unpack1_r16, unpack1_c4, unpack1_c8, unpack1_c10 and unpack1_c16. * intrinsics/pack_generic.c (unpack1): Add calls to specific unpack1 functions. (unpack0): Add calls to specific unpack0 functions. * m4/unpack.m4: New file. * generated/unpack_i1.c: New file. * generated/unpack_i2.c: New file. * generated/unpack_i4.c: New file. * generated/unpack_i8.c: New file. * generated/unpack_i16.c: New file. * generated/unpack_r4.c: New file. * generated/unpack_r8.c: New file. * generated/unpack_r10.c: New file. * generated/unpack_r16.c: New file. * generated/unpack_c4.c: New file. * generated/unpack_c8.c: New file. * generated/unpack_c10.c: New file. * generated/unpack_c16.c: New file. 2007-03-23 Thomas Koenig <tkoenig@gcc.gnu.org PR libfortran/32972 * gfortran.dg/intrinsic_unpack_1.f90: New test case. * gfortran.dg/intrinsic_unpack_2.f90: New test case. * gfortran.dg/intrinsic_unpack_3.f90: New test case. From-SVN: r133469
2008-03-23 23:19:19 +01:00
/* v.* indicates the vector array. */
index_type vstride0;
GFC_REAL_10 *vptr;
/* Value for field, this is constant. */
const GFC_REAL_10 fval = *fptr;
/* m.* indicates the mask array. */
index_type mstride[GFC_MAX_DIMENSIONS];
index_type mstride0;
const GFC_LOGICAL_1 *mptr;
index_type count[GFC_MAX_DIMENSIONS];
index_type extent[GFC_MAX_DIMENSIONS];
index_type n;
index_type dim;
int empty;
int mask_kind;
empty = 0;
mptr = mask->data;
/* Use the same loop for all logical types, by using GFC_LOGICAL_1
and using shifting to address size and endian issues. */
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
)
{
/* Do not convert a NULL pointer as we use test for NULL below. */
if (mptr)
mptr = GFOR_POINTER_TO_L1 (mptr, mask_kind);
}
else
runtime_error ("Funny sized logical array");
if (ret->data == NULL)
{
/* The front end has signalled that we need to populate the
return array descriptor. */
dim = GFC_DESCRIPTOR_RANK (mask);
rs = 1;
for (n = 0; n < dim; n++)
{
count[n] = 0;
ret->dim[n].stride = rs;
ret->dim[n].lbound = 0;
ret->dim[n].ubound = mask->dim[n].ubound - mask->dim[n].lbound;
extent[n] = ret->dim[n].ubound + 1;
empty = empty || extent[n] <= 0;
rstride[n] = ret->dim[n].stride;
mstride[n] = mask->dim[n].stride * mask_kind;
rs *= extent[n];
}
ret->offset = 0;
ret->data = internal_malloc_size (rs * sizeof (GFC_REAL_10));
}
else
{
dim = GFC_DESCRIPTOR_RANK (ret);
for (n = 0; n < dim; n++)
{
count[n] = 0;
extent[n] = ret->dim[n].ubound + 1 - ret->dim[n].lbound;
empty = empty || extent[n] <= 0;
rstride[n] = ret->dim[n].stride;
mstride[n] = mask->dim[n].stride * mask_kind;
}
if (rstride[0] == 0)
rstride[0] = 1;
}
if (empty)
return;
if (mstride[0] == 0)
mstride[0] = 1;
vstride0 = vector->dim[0].stride;
if (vstride0 == 0)
vstride0 = 1;
rstride0 = rstride[0];
mstride0 = mstride[0];
rptr = ret->data;
vptr = vector->data;
while (rptr)
{
if (*mptr)
{
/* From vector. */
*rptr = *vptr;
vptr += vstride0;
}
else
{
/* From field. */
*rptr = fval;
}
/* Advance to the next element. */
rptr += rstride0;
mptr += mstride0;
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 these products, but this is a less
frequently used path so probably not worth it. */
rptr -= rstride[n] * extent[n];
mptr -= mstride[n] * extent[n];
n++;
if (n >= dim)
{
/* Break out of the loop. */
rptr = NULL;
break;
}
else
{
count[n]++;
rptr += rstride[n];
mptr += mstride[n];
}
}
}
}
void
unpack1_r10 (gfc_array_r10 *ret, const gfc_array_r10 *vector,
const gfc_array_l1 *mask, const gfc_array_r10 *field)
{
/* r.* indicates the return array. */
index_type rstride[GFC_MAX_DIMENSIONS];
index_type rstride0;
index_type rs;
in_pack.m4 (internal_pack_'rtype_code`): Destination pointer is restrict. 2008-05-18 Thomas Koenig <tkoenig@gcc.gnu.org> * m4/in_pack.m4 (internal_pack_'rtype_code`): Destination pointer is restrict. * m4/transpose.m4 (transpose_'rtype_code`): Likewise. * m4/pack.m4 (pack_'rtype_code`): Likewise. * m4/spread.m4 (spread_'rtype_code`): Likewise. (spread_scalar_'rtype_code`): Likewise. * m4/iforeach.m4 (name`'rtype_qual`_'atype_code): Likewise. * m4/eoshift1.m4 (eoshift1): Likewise. * m4/eoshift3.m4 (eoshift3): Likewise. * m4/in_unpack.m4 (internal_unpack_'rtype_ccode`): Likewise. * m4/unpack.m4 (unpack0_'rtype_code`): Likewise. (unpack1_'rtype_code`): Likewise. * intrinsics/pack_generic.c (pack_generic.c): Likewise. * intrinsics/unpack_generic.c (unpack_internal): Likewise. * intrinsics/eoshift0.c (eoshift0): Likewise. * intrinsics/eoshift2.c (eoshift2): Likewise. * intrinsics/reshape_generic.c (reshape_internal): Likewise. * intrinsics/reshape_packed.c (reshape_packed): Likewise. * generated/eoshift1_16.c: Regenerated. * generated/eoshift1_4.c: Regenerated. * generated/eoshift1_8.c: Regenerated. * generated/eoshift3_16.c: Regenerated. * generated/eoshift3_4.c: Regenerated. * generated/eoshift3_8.c: Regenerated. * generated/in_pack_c10.c: Regenerated. * generated/in_pack_c16.c: Regenerated. * generated/in_pack_c4.c: Regenerated. * generated/in_pack_c8.c: Regenerated. * generated/in_pack_i1.c: Regenerated. * generated/in_pack_i16.c: Regenerated. * generated/in_pack_i2.c: Regenerated. * generated/in_pack_i4.c: Regenerated. * generated/in_pack_i8.c: Regenerated. * generated/in_pack_r10.c: Regenerated. * generated/in_pack_r16.c: Regenerated. * generated/in_pack_r4.c: Regenerated. * generated/in_pack_r8.c: Regenerated. * generated/in_unpack_c10.c: Regenerated. * generated/in_unpack_c16.c: Regenerated. * generated/in_unpack_c4.c: Regenerated. * generated/in_unpack_c8.c: Regenerated. * generated/in_unpack_i1.c: Regenerated. * generated/in_unpack_i16.c: Regenerated. * generated/in_unpack_i2.c: Regenerated. * generated/in_unpack_i4.c: Regenerated. * generated/in_unpack_i8.c: Regenerated. * generated/in_unpack_r10.c: Regenerated. * generated/in_unpack_r16.c: Regenerated. * generated/in_unpack_r4.c: Regenerated. * generated/in_unpack_r8.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/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/pack_c10.c: Regenerated. * generated/pack_c16.c: Regenerated. * generated/pack_c4.c: Regenerated. * generated/pack_c8.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_r10.c: Regenerated. * generated/pack_r16.c: Regenerated. * generated/pack_r4.c: Regenerated. * generated/pack_r8.c: Regenerated. * generated/spread_c10.c: Regenerated. * generated/spread_c16.c: Regenerated. * generated/spread_c4.c: Regenerated. * generated/spread_c8.c: Regenerated. * generated/spread_i1.c: Regenerated. * generated/spread_i16.c: Regenerated. * generated/spread_i2.c: Regenerated. * generated/spread_i4.c: Regenerated. * generated/spread_i8.c: Regenerated. * generated/spread_r10.c: Regenerated. * generated/spread_r16.c: Regenerated. * generated/spread_r4.c: Regenerated. * generated/spread_r8.c: Regenerated. * generated/transpose_c10.c: Regenerated. * generated/transpose_c16.c: Regenerated. * generated/transpose_c4.c: Regenerated. * generated/transpose_c8.c: Regenerated. * generated/transpose_i16.c: Regenerated. * generated/transpose_i4.c: Regenerated. * generated/transpose_i8.c: Regenerated. * generated/transpose_r10.c: Regenerated. * generated/transpose_r16.c: Regenerated. * generated/transpose_r4.c: Regenerated. * generated/transpose_r8.c: Regenerated. * generated/unpack_c10.c: Regenerated. * generated/unpack_c16.c: Regenerated. * generated/unpack_c4.c: Regenerated. * generated/unpack_c8.c: Regenerated. * generated/unpack_i1.c: Regenerated. * generated/unpack_i16.c: Regenerated. * generated/unpack_i2.c: Regenerated. * generated/unpack_i4.c: Regenerated. * generated/unpack_i8.c: Regenerated. * generated/unpack_r10.c: Regenerated. * generated/unpack_r16.c: Regenerated. * generated/unpack_r4.c: Regenerated. * generated/unpack_r8.c: Regenerated. From-SVN: r135512
2008-05-18 22:39:04 +02:00
GFC_REAL_10 * restrict rptr;
re PR libfortran/32972 (performance of pack/unpack) 2007-03-23 Thomas Koenig <tkoenig@gcc.gnu.org PR libfortran/32972 * Makefile.am: Add new variable, i_unpack_c, containing unpack_i1.c, unpack_i2.c, unpack_i4.c, unpack_i8.c, unpack_i16.c, unpack_r4.c, unpack_r8.c, unpack_r10.c, unpack_r16.c, unpack_c4.c, unpack_c8.c, unpack_c10.c and unpack_c16.c Add i_unpack_c to gfor_built_src. Add rule to generate i_unpack_c from m4/unpack.m4. * Makefile.in: Regenerated. * libgfortran.h: Add prototypes for unpack0_i1, unpack0_i2, unpack0_i4, unpack0_i8, unpack0_i16, unpack0_r4, unpack0_r8, unpack0_r10, unpack0_r16, unpack0_c4, unpack0_c8, unpack0_c10, unpack0_c16, unpack1_i1, unpack1_i2, unpack1_i4, unpack1_i8, unpack1_i16, unpack1_r4, unpack1_r8, unpack1_r10, unpack1_r16, unpack1_c4, unpack1_c8, unpack1_c10 and unpack1_c16. * intrinsics/pack_generic.c (unpack1): Add calls to specific unpack1 functions. (unpack0): Add calls to specific unpack0 functions. * m4/unpack.m4: New file. * generated/unpack_i1.c: New file. * generated/unpack_i2.c: New file. * generated/unpack_i4.c: New file. * generated/unpack_i8.c: New file. * generated/unpack_i16.c: New file. * generated/unpack_r4.c: New file. * generated/unpack_r8.c: New file. * generated/unpack_r10.c: New file. * generated/unpack_r16.c: New file. * generated/unpack_c4.c: New file. * generated/unpack_c8.c: New file. * generated/unpack_c10.c: New file. * generated/unpack_c16.c: New file. 2007-03-23 Thomas Koenig <tkoenig@gcc.gnu.org PR libfortran/32972 * gfortran.dg/intrinsic_unpack_1.f90: New test case. * gfortran.dg/intrinsic_unpack_2.f90: New test case. * gfortran.dg/intrinsic_unpack_3.f90: New test case. From-SVN: r133469
2008-03-23 23:19:19 +01:00
/* v.* indicates the vector array. */
index_type vstride0;
GFC_REAL_10 *vptr;
/* f.* indicates the field array. */
index_type fstride[GFC_MAX_DIMENSIONS];
index_type fstride0;
const GFC_REAL_10 *fptr;
/* m.* indicates the mask array. */
index_type mstride[GFC_MAX_DIMENSIONS];
index_type mstride0;
const GFC_LOGICAL_1 *mptr;
index_type count[GFC_MAX_DIMENSIONS];
index_type extent[GFC_MAX_DIMENSIONS];
index_type n;
index_type dim;
int empty;
int mask_kind;
empty = 0;
mptr = mask->data;
/* Use the same loop for all logical types, by using GFC_LOGICAL_1
and using shifting to address size and endian issues. */
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
)
{
/* Do not convert a NULL pointer as we use test for NULL below. */
if (mptr)
mptr = GFOR_POINTER_TO_L1 (mptr, mask_kind);
}
else
runtime_error ("Funny sized logical array");
if (ret->data == NULL)
{
/* The front end has signalled that we need to populate the
return array descriptor. */
dim = GFC_DESCRIPTOR_RANK (mask);
rs = 1;
for (n = 0; n < dim; n++)
{
count[n] = 0;
ret->dim[n].stride = rs;
ret->dim[n].lbound = 0;
ret->dim[n].ubound = mask->dim[n].ubound - mask->dim[n].lbound;
extent[n] = ret->dim[n].ubound + 1;
empty = empty || extent[n] <= 0;
rstride[n] = ret->dim[n].stride;
fstride[n] = field->dim[n].stride;
mstride[n] = mask->dim[n].stride * mask_kind;
rs *= extent[n];
}
ret->offset = 0;
ret->data = internal_malloc_size (rs * sizeof (GFC_REAL_10));
}
else
{
dim = GFC_DESCRIPTOR_RANK (ret);
for (n = 0; n < dim; n++)
{
count[n] = 0;
extent[n] = ret->dim[n].ubound + 1 - ret->dim[n].lbound;
empty = empty || extent[n] <= 0;
rstride[n] = ret->dim[n].stride;
fstride[n] = field->dim[n].stride;
mstride[n] = mask->dim[n].stride * mask_kind;
}
if (rstride[0] == 0)
rstride[0] = 1;
}
if (empty)
return;
if (fstride[0] == 0)
fstride[0] = 1;
if (mstride[0] == 0)
mstride[0] = 1;
vstride0 = vector->dim[0].stride;
if (vstride0 == 0)
vstride0 = 1;
rstride0 = rstride[0];
fstride0 = fstride[0];
mstride0 = mstride[0];
rptr = ret->data;
fptr = field->data;
vptr = vector->data;
while (rptr)
{
if (*mptr)
{
/* From vector. */
*rptr = *vptr;
vptr += vstride0;
}
else
{
/* From field. */
*rptr = *fptr;
}
/* Advance to the next element. */
rptr += rstride0;
fptr += fstride0;
mptr += mstride0;
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 these products, but this is a less
frequently used path so probably not worth it. */
rptr -= rstride[n] * extent[n];
fptr -= fstride[n] * extent[n];
mptr -= mstride[n] * extent[n];
n++;
if (n >= dim)
{
/* Break out of the loop. */
rptr = NULL;
break;
}
else
{
count[n]++;
rptr += rstride[n];
fptr += fstride[n];
mptr += mstride[n];
}
}
}
}
#endif