re PR fortran/52473 (CSHIFT slow - inline it?)
2017-06-24 Thomas Koenig <tkoenig@gcc.gnu.org>
PR fortran/52473
* Makefile.am: Add i_cshift1a_c. Add rules to generate files
from cshift1a.m4.
* Makefile.in: Regenerated.
* m4/cshift1a.m4: New file.
* m4/cshift.m4 (cshift1): Split up inner loop by removing
condition. Use memcpy where possible. Call helper functions
based on dtype.
* libgfortran.h: Add prototypes for cshift1_16_c10,
cshift1_16_c16, cshift1_16_c4, cshift1_16_c8, cshift1_16_i1,
cshift1_16_i16, cshift1_16_i2, cshift1_16_i4, cshift1_16_i8,
cshift1_16_r10, cshift1_16_r16, cshift1_16_r4, cshift1_16_r8,
cshift1_4_c10, cshift1_4_c16, cshift1_4_c4, cshift1_4_c8,
cshift1_4_i1, cshift1_4_i16, cshift1_4_i2, cshift1_4_i4,
cshift1_4_i8, cshift1_4_r10, cshift1_4_r16, cshift1_4_r4,
cshift1_4_r8, cshift1_8_c10, cshift1_8_c16, cshift1_8_c4,
cshift1_8_c8, cshift1_8_i1, cshift1_8_i16, cshift1_8_i2,
cshift1_8_i4, cshift1_8_i8, cshift1_8_r10, cshift1_8_r16,
cshift1_8_r4 and cshift1_8_r8.
* generated/cshift1_16_c10.c: New file, generated from cshift1a.m4.
* generated/cshift1_16_c16.c: New file, generated from cshift1a.m4.
* generated/cshift1_16_c4.c: New file, generated from cshift1a.m4.
* generated/cshift1_16_c8.c: New file, generated from cshift1a.m4.
* generated/cshift1_16_i1.c: New file, generated from cshift1a.m4.
* generated/cshift1_16_i16.c: New file, generated from cshift1a.m4.
* generated/cshift1_16_i2.c: New file, generated from cshift1a.m4.
* generated/cshift1_16_i4.c: New file, generated from cshift1a.m4.
* generated/cshift1_16_i8.c: New file, generated from cshift1a.m4.
* generated/cshift1_16_r10.c: New file, generated from cshift1a.m4.
* generated/cshift1_16_r16.c: New file, generated from cshift1a.m4.
* generated/cshift1_16_r4.c: New file, generated from cshift1a.m4.
* generated/cshift1_16_r8.c: New file, generated from cshift1a.m4.
* generated/cshift1_4_c10.c: New file, generated from cshift1a.m4.
* generated/cshift1_4_c16.c: New file, generated from cshift1a.m4.
* generated/cshift1_4_c4.c: New file, generated from cshift1a.m4.
* generated/cshift1_4_c8.c: New file, generated from cshift1a.m4.
* generated/cshift1_4_i1.c: New file, generated from cshift1a.m4.
* generated/cshift1_4_i16.c: New file, generated from cshift1a.m4.
* generated/cshift1_4_i2.c: New file, generated from cshift1a.m4.
* generated/cshift1_4_i4.c: New file, generated from cshift1a.m4.
* generated/cshift1_4_i8.c: New file, generated from cshift1a.m4.
* generated/cshift1_4_r10.c: New file, generated from cshift1a.m4.
* generated/cshift1_4_r16.c: New file, generated from cshift1a.m4.
* generated/cshift1_4_r4.c: New file, generated from cshift1a.m4.
* generated/cshift1_4_r8.c: New file, generated from cshift1a.m4.
* generated/cshift1_8_c10.c: New file, generated from cshift1a.m4.
* generated/cshift1_8_c16.c: New file, generated from cshift1a.m4.
* generated/cshift1_8_c4.c: New file, generated from cshift1a.m4.
* generated/cshift1_8_c8.c: New file, generated from cshift1a.m4.
* generated/cshift1_8_i1.c: New file, generated from cshift1a.m4.
* generated/cshift1_8_i16.c: New file, generated from cshift1a.m4.
* generated/cshift1_8_i2.c: New file, generated from cshift1a.m4.
* generated/cshift1_8_i4.c: New file, generated from cshift1a.m4.
* generated/cshift1_8_i8.c: New file, generated from cshift1a.m4.
* generated/cshift1_8_r10.c: New file, generated from cshift1a.m4.
* generated/cshift1_8_r16.c: New file, generated from cshift1a.m4.
* generated/cshift1_8_r4.c: New file, generated from cshift1a.m4.
* generated/cshift1_8_r8.c: New file, generated from cshift1a.m4.
2017-06-24 Thomas Koenig <tkoenig@gcc.gnu.org>
PR fortran/52473
* gfortran.dg/cshift_2.f90: New test.
From-SVN: r249620
2017-06-24 09:07:56 +02:00
|
|
|
/* Implementation of the CSHIFT intrinsic.
|
2021-01-04 10:26:59 +01:00
|
|
|
Copyright (C) 2017-2021 Free Software Foundation, Inc.
|
re PR fortran/52473 (CSHIFT slow - inline it?)
2017-06-24 Thomas Koenig <tkoenig@gcc.gnu.org>
PR fortran/52473
* Makefile.am: Add i_cshift1a_c. Add rules to generate files
from cshift1a.m4.
* Makefile.in: Regenerated.
* m4/cshift1a.m4: New file.
* m4/cshift.m4 (cshift1): Split up inner loop by removing
condition. Use memcpy where possible. Call helper functions
based on dtype.
* libgfortran.h: Add prototypes for cshift1_16_c10,
cshift1_16_c16, cshift1_16_c4, cshift1_16_c8, cshift1_16_i1,
cshift1_16_i16, cshift1_16_i2, cshift1_16_i4, cshift1_16_i8,
cshift1_16_r10, cshift1_16_r16, cshift1_16_r4, cshift1_16_r8,
cshift1_4_c10, cshift1_4_c16, cshift1_4_c4, cshift1_4_c8,
cshift1_4_i1, cshift1_4_i16, cshift1_4_i2, cshift1_4_i4,
cshift1_4_i8, cshift1_4_r10, cshift1_4_r16, cshift1_4_r4,
cshift1_4_r8, cshift1_8_c10, cshift1_8_c16, cshift1_8_c4,
cshift1_8_c8, cshift1_8_i1, cshift1_8_i16, cshift1_8_i2,
cshift1_8_i4, cshift1_8_i8, cshift1_8_r10, cshift1_8_r16,
cshift1_8_r4 and cshift1_8_r8.
* generated/cshift1_16_c10.c: New file, generated from cshift1a.m4.
* generated/cshift1_16_c16.c: New file, generated from cshift1a.m4.
* generated/cshift1_16_c4.c: New file, generated from cshift1a.m4.
* generated/cshift1_16_c8.c: New file, generated from cshift1a.m4.
* generated/cshift1_16_i1.c: New file, generated from cshift1a.m4.
* generated/cshift1_16_i16.c: New file, generated from cshift1a.m4.
* generated/cshift1_16_i2.c: New file, generated from cshift1a.m4.
* generated/cshift1_16_i4.c: New file, generated from cshift1a.m4.
* generated/cshift1_16_i8.c: New file, generated from cshift1a.m4.
* generated/cshift1_16_r10.c: New file, generated from cshift1a.m4.
* generated/cshift1_16_r16.c: New file, generated from cshift1a.m4.
* generated/cshift1_16_r4.c: New file, generated from cshift1a.m4.
* generated/cshift1_16_r8.c: New file, generated from cshift1a.m4.
* generated/cshift1_4_c10.c: New file, generated from cshift1a.m4.
* generated/cshift1_4_c16.c: New file, generated from cshift1a.m4.
* generated/cshift1_4_c4.c: New file, generated from cshift1a.m4.
* generated/cshift1_4_c8.c: New file, generated from cshift1a.m4.
* generated/cshift1_4_i1.c: New file, generated from cshift1a.m4.
* generated/cshift1_4_i16.c: New file, generated from cshift1a.m4.
* generated/cshift1_4_i2.c: New file, generated from cshift1a.m4.
* generated/cshift1_4_i4.c: New file, generated from cshift1a.m4.
* generated/cshift1_4_i8.c: New file, generated from cshift1a.m4.
* generated/cshift1_4_r10.c: New file, generated from cshift1a.m4.
* generated/cshift1_4_r16.c: New file, generated from cshift1a.m4.
* generated/cshift1_4_r4.c: New file, generated from cshift1a.m4.
* generated/cshift1_4_r8.c: New file, generated from cshift1a.m4.
* generated/cshift1_8_c10.c: New file, generated from cshift1a.m4.
* generated/cshift1_8_c16.c: New file, generated from cshift1a.m4.
* generated/cshift1_8_c4.c: New file, generated from cshift1a.m4.
* generated/cshift1_8_c8.c: New file, generated from cshift1a.m4.
* generated/cshift1_8_i1.c: New file, generated from cshift1a.m4.
* generated/cshift1_8_i16.c: New file, generated from cshift1a.m4.
* generated/cshift1_8_i2.c: New file, generated from cshift1a.m4.
* generated/cshift1_8_i4.c: New file, generated from cshift1a.m4.
* generated/cshift1_8_i8.c: New file, generated from cshift1a.m4.
* generated/cshift1_8_r10.c: New file, generated from cshift1a.m4.
* generated/cshift1_8_r16.c: New file, generated from cshift1a.m4.
* generated/cshift1_8_r4.c: New file, generated from cshift1a.m4.
* generated/cshift1_8_r8.c: New file, generated from cshift1a.m4.
2017-06-24 Thomas Koenig <tkoenig@gcc.gnu.org>
PR fortran/52473
* gfortran.dg/cshift_2.f90: New test.
From-SVN: r249620
2017-06-24 09:07:56 +02:00
|
|
|
Contributed by Thomas Koenig <tkoenig@gcc.gnu.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"
|
|
|
|
#include <string.h>
|
|
|
|
|
|
|
|
#if defined (HAVE_GFC_COMPLEX_10) && defined (HAVE_GFC_INTEGER_4)
|
|
|
|
|
|
|
|
void
|
|
|
|
cshift1_4_c10 (gfc_array_c10 * const restrict ret,
|
|
|
|
const gfc_array_c10 * const restrict array,
|
|
|
|
const gfc_array_i4 * const restrict h,
|
|
|
|
const GFC_INTEGER_4 * const restrict pwhich)
|
|
|
|
{
|
|
|
|
/* r.* indicates the return array. */
|
|
|
|
index_type rstride[GFC_MAX_DIMENSIONS];
|
|
|
|
index_type rstride0;
|
|
|
|
index_type roffset;
|
|
|
|
GFC_COMPLEX_10 *rptr;
|
|
|
|
GFC_COMPLEX_10 *dest;
|
|
|
|
/* s.* indicates the source array. */
|
|
|
|
index_type sstride[GFC_MAX_DIMENSIONS];
|
|
|
|
index_type sstride0;
|
|
|
|
index_type soffset;
|
|
|
|
const GFC_COMPLEX_10 *sptr;
|
|
|
|
const GFC_COMPLEX_10 *src;
|
|
|
|
/* h.* indicates the shift array. */
|
|
|
|
index_type hstride[GFC_MAX_DIMENSIONS];
|
|
|
|
index_type hstride0;
|
|
|
|
const GFC_INTEGER_4 *hptr;
|
|
|
|
|
|
|
|
index_type count[GFC_MAX_DIMENSIONS];
|
|
|
|
index_type extent[GFC_MAX_DIMENSIONS];
|
|
|
|
index_type rs_ex[GFC_MAX_DIMENSIONS];
|
|
|
|
index_type ss_ex[GFC_MAX_DIMENSIONS];
|
|
|
|
index_type hs_ex[GFC_MAX_DIMENSIONS];
|
|
|
|
|
|
|
|
index_type dim;
|
|
|
|
index_type len;
|
|
|
|
index_type n;
|
|
|
|
int which;
|
|
|
|
GFC_INTEGER_4 sh;
|
|
|
|
|
|
|
|
/* Bounds checking etc is already done by the caller. */
|
|
|
|
|
|
|
|
if (pwhich)
|
|
|
|
which = *pwhich - 1;
|
|
|
|
else
|
|
|
|
which = 0;
|
|
|
|
|
|
|
|
extent[0] = 1;
|
|
|
|
count[0] = 0;
|
|
|
|
n = 0;
|
|
|
|
|
|
|
|
/* Initialized for avoiding compiler warnings. */
|
|
|
|
roffset = 1;
|
|
|
|
soffset = 1;
|
|
|
|
len = 0;
|
|
|
|
|
|
|
|
for (dim = 0; dim < GFC_DESCRIPTOR_RANK (array); dim++)
|
|
|
|
{
|
|
|
|
if (dim == which)
|
|
|
|
{
|
|
|
|
roffset = GFC_DESCRIPTOR_STRIDE(ret,dim);
|
|
|
|
if (roffset == 0)
|
|
|
|
roffset = 1;
|
|
|
|
soffset = GFC_DESCRIPTOR_STRIDE(array,dim);
|
|
|
|
if (soffset == 0)
|
|
|
|
soffset = 1;
|
|
|
|
len = GFC_DESCRIPTOR_EXTENT(array,dim);
|
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
|
|
|
count[n] = 0;
|
|
|
|
extent[n] = GFC_DESCRIPTOR_EXTENT(array,dim);
|
|
|
|
rstride[n] = GFC_DESCRIPTOR_STRIDE(ret,dim);
|
|
|
|
sstride[n] = GFC_DESCRIPTOR_STRIDE(array,dim);
|
|
|
|
hstride[n] = GFC_DESCRIPTOR_STRIDE(h,n);
|
|
|
|
rs_ex[n] = rstride[n] * extent[n];
|
|
|
|
ss_ex[n] = sstride[n] * extent[n];
|
|
|
|
hs_ex[n] = hstride[n] * extent[n];
|
|
|
|
n++;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if (sstride[0] == 0)
|
|
|
|
sstride[0] = 1;
|
|
|
|
if (rstride[0] == 0)
|
|
|
|
rstride[0] = 1;
|
|
|
|
if (hstride[0] == 0)
|
|
|
|
hstride[0] = 1;
|
|
|
|
|
|
|
|
dim = GFC_DESCRIPTOR_RANK (array);
|
|
|
|
rstride0 = rstride[0];
|
|
|
|
sstride0 = sstride[0];
|
|
|
|
hstride0 = hstride[0];
|
|
|
|
rptr = ret->base_addr;
|
|
|
|
sptr = array->base_addr;
|
|
|
|
hptr = h->base_addr;
|
|
|
|
|
|
|
|
while (rptr)
|
|
|
|
{
|
|
|
|
/* Do the shift for this dimension. */
|
|
|
|
sh = *hptr;
|
|
|
|
/* Normal case should be -len < sh < len; try to
|
|
|
|
avoid the expensive remainder operation if possible. */
|
|
|
|
if (sh < 0)
|
|
|
|
sh += len;
|
|
|
|
if (unlikely(sh >= len || sh < 0))
|
|
|
|
{
|
|
|
|
sh = sh % len;
|
|
|
|
if (sh < 0)
|
|
|
|
sh += len;
|
|
|
|
}
|
|
|
|
src = &sptr[sh * soffset];
|
|
|
|
dest = rptr;
|
|
|
|
if (soffset == 1 && roffset == 1)
|
|
|
|
{
|
|
|
|
size_t len1 = sh * sizeof (GFC_COMPLEX_10);
|
|
|
|
size_t len2 = (len - sh) * sizeof (GFC_COMPLEX_10);
|
|
|
|
memcpy (rptr, sptr + sh, len2);
|
|
|
|
memcpy (rptr + (len - sh), sptr, len1);
|
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
|
|
|
for (n = 0; n < len - sh; n++)
|
|
|
|
{
|
|
|
|
*dest = *src;
|
|
|
|
dest += roffset;
|
|
|
|
src += soffset;
|
|
|
|
}
|
|
|
|
for (src = sptr, n = 0; n < sh; n++)
|
|
|
|
{
|
|
|
|
*dest = *src;
|
|
|
|
dest += roffset;
|
|
|
|
src += soffset;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Advance to the next section. */
|
|
|
|
rptr += rstride0;
|
|
|
|
sptr += sstride0;
|
|
|
|
hptr += hstride0;
|
|
|
|
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;
|
|
|
|
rptr -= rs_ex[n];
|
|
|
|
sptr -= ss_ex[n];
|
|
|
|
hptr -= hs_ex[n];
|
|
|
|
n++;
|
|
|
|
if (n >= dim - 1)
|
|
|
|
{
|
|
|
|
/* Break out of the loop. */
|
|
|
|
rptr = NULL;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
|
|
|
count[n]++;
|
|
|
|
rptr += rstride[n];
|
|
|
|
sptr += sstride[n];
|
|
|
|
hptr += hstride[n];
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
#endif
|