49ad4d2c30
This prepares the library side for REAL(KIND=17). It is not yet tested, but at least compiles cleanly on POWER 9 and x86_64. 2021-10-19 Thomas Koenig <tkoenig@gcc.gnu.org> * Makefile.am: Add _r17 and _c17 files. Build them with -mabi=ieeelongdouble on POWER. * Makefile.in: Regenerate. * configure: Regenerate. * configure.ac: New flag HAVE_REAL_17. * kinds-override.h: (HAVE_GFC_REAL_17): New macro. (HAVE_GFC_COMPLEX_17): New macro. (GFC_REAL_17_HUGE): New macro. (GFC_REAL_17_LITERAL_SUFFIX): New macro. (GFC_REAL_17_LITERAL): New macro. (GFC_REAL_17_DIGITS): New macro. (GFC_REAL_17_RADIX): New macro. * libgfortran.h (POWER_IEEE128): New macro. (gfc_array_r17): Typedef. (GFC_DTYPE_REAL_17): New macro. (GFC_DTYPE_COMPLEX_17): New macro. (__acoshieee128): Prototype. (__acosieee128): Prototype. (__asinhieee128): Prototype. (__asinieee128): Prototype. (__atan2ieee128): Prototype. (__atanhieee128): Prototype. (__atanieee128): Prototype. (__coshieee128): Prototype. (__cosieee128): Prototype. (__erfieee128): Prototype. (__expieee128): Prototype. (__fabsieee128): Prototype. (__jnieee128): Prototype. (__log10ieee128): Prototype. (__logieee128): Prototype. (__powieee128): Prototype. (__sinhieee128): Prototype. (__sinieee128): Prototype. (__sqrtieee128): Prototype. (__tanhieee128): Prototype. (__tanieee128): Prototype. (__ynieee128): Prototype. * m4/mtype.m4: Make a bit more readable. Add KIND=17. * generated/_abs_c17.F90: New file. * generated/_abs_r17.F90: New file. * generated/_acos_r17.F90: New file. * generated/_acosh_r17.F90: New file. * generated/_aimag_c17.F90: New file. * generated/_aint_r17.F90: New file. * generated/_anint_r17.F90: New file. * generated/_asin_r17.F90: New file. * generated/_asinh_r17.F90: New file. * generated/_atan2_r17.F90: New file. * generated/_atan_r17.F90: New file. * generated/_atanh_r17.F90: New file. * generated/_conjg_c17.F90: New file. * generated/_cos_c17.F90: New file. * generated/_cos_r17.F90: New file. * generated/_cosh_r17.F90: New file. * generated/_dim_r17.F90: New file. * generated/_exp_c17.F90: New file. * generated/_exp_r17.F90: New file. * generated/_log10_r17.F90: New file. * generated/_log_c17.F90: New file. * generated/_log_r17.F90: New file. * generated/_mod_r17.F90: New file. * generated/_sign_r17.F90: New file. * generated/_sin_c17.F90: New file. * generated/_sin_r17.F90: New file. * generated/_sinh_r17.F90: New file. * generated/_sqrt_c17.F90: New file. * generated/_sqrt_r17.F90: New file. * generated/_tan_r17.F90: New file. * generated/_tanh_r17.F90: New file. * generated/bessel_r17.c: New file. * generated/cshift0_c17.c: New file. * generated/cshift0_r17.c: New file. * generated/cshift1_16_c17.c: New file. * generated/cshift1_16_r17.c: New file. * generated/cshift1_4_c17.c: New file. * generated/cshift1_4_r17.c: New file. * generated/cshift1_8_c17.c: New file. * generated/cshift1_8_r17.c: New file. * generated/findloc0_c17.c: New file. * generated/findloc0_r17.c: New file. * generated/findloc1_c17.c: New file. * generated/findloc1_r17.c: New file. * generated/in_pack_c17.c: New file. * generated/in_pack_r17.c: New file. * generated/in_unpack_c17.c: New file. * generated/in_unpack_r17.c: New file. * generated/matmul_c17.c: New file. * generated/matmul_r17.c: New file. * generated/matmulavx128_c17.c: New file. * generated/matmulavx128_r17.c: New file. * generated/maxloc0_16_r17.c: New file. * generated/maxloc0_4_r17.c: New file. * generated/maxloc0_8_r17.c: New file. * generated/maxloc1_16_r17.c: New file. * generated/maxloc1_4_r17.c: New file. * generated/maxloc1_8_r17.c: New file. * generated/maxval_r17.c: New file. * generated/minloc0_16_r17.c: New file. * generated/minloc0_4_r17.c: New file. * generated/minloc0_8_r17.c: New file. * generated/minloc1_16_r17.c: New file. * generated/minloc1_4_r17.c: New file. * generated/minloc1_8_r17.c: New file. * generated/minval_r17.c: New file. * generated/norm2_r17.c: New file. * generated/pack_c17.c: New file. * generated/pack_r17.c: New file. * generated/pow_c17_i16.c: New file. * generated/pow_c17_i4.c: New file. * generated/pow_c17_i8.c: New file. * generated/pow_r17_i16.c: New file. * generated/pow_r17_i4.c: New file. * generated/pow_r17_i8.c: New file. * generated/product_c17.c: New file. * generated/product_r17.c: New file. * generated/reshape_c17.c: New file. * generated/reshape_r17.c: New file. * generated/spread_c17.c: New file. * generated/spread_r17.c: New file. * generated/sum_c17.c: New file. * generated/sum_r17.c: New file. * generated/unpack_c17.c: New file. * generated/unpack_r17.c: New file.
243 lines
5.9 KiB
C
243 lines
5.9 KiB
C
/* Helper function for cshift functions.
|
|
Copyright (C) 2008-2022 Free Software Foundation, Inc.
|
|
Contributed by Thomas Koenig <tkoenig@gcc.gnu.org>
|
|
|
|
This file is part of the GNU Fortran 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_17)
|
|
|
|
void
|
|
cshift0_c17 (gfc_array_c17 *ret, const gfc_array_c17 *array, ptrdiff_t shift,
|
|
int which)
|
|
{
|
|
/* r.* indicates the return array. */
|
|
index_type rstride[GFC_MAX_DIMENSIONS];
|
|
index_type rstride0;
|
|
index_type roffset;
|
|
GFC_COMPLEX_17 *rptr;
|
|
|
|
/* s.* indicates the source array. */
|
|
index_type sstride[GFC_MAX_DIMENSIONS];
|
|
index_type sstride0;
|
|
index_type soffset;
|
|
const GFC_COMPLEX_17 *sptr;
|
|
|
|
index_type count[GFC_MAX_DIMENSIONS];
|
|
index_type extent[GFC_MAX_DIMENSIONS];
|
|
index_type dim;
|
|
index_type len;
|
|
index_type n;
|
|
|
|
bool do_blocked;
|
|
index_type r_ex, a_ex;
|
|
|
|
which = which - 1;
|
|
sstride[0] = 0;
|
|
rstride[0] = 0;
|
|
|
|
extent[0] = 1;
|
|
count[0] = 0;
|
|
n = 0;
|
|
/* Initialized for avoiding compiler warnings. */
|
|
roffset = 1;
|
|
soffset = 1;
|
|
len = 0;
|
|
|
|
r_ex = 1;
|
|
a_ex = 1;
|
|
|
|
if (which > 0)
|
|
{
|
|
/* Test if both ret and array are contiguous. */
|
|
do_blocked = true;
|
|
dim = GFC_DESCRIPTOR_RANK (array);
|
|
for (n = 0; n < dim; n ++)
|
|
{
|
|
index_type rs, as;
|
|
rs = GFC_DESCRIPTOR_STRIDE (ret, n);
|
|
if (rs != r_ex)
|
|
{
|
|
do_blocked = false;
|
|
break;
|
|
}
|
|
as = GFC_DESCRIPTOR_STRIDE (array, n);
|
|
if (as != a_ex)
|
|
{
|
|
do_blocked = false;
|
|
break;
|
|
}
|
|
r_ex *= GFC_DESCRIPTOR_EXTENT (ret, n);
|
|
a_ex *= GFC_DESCRIPTOR_EXTENT (array, n);
|
|
}
|
|
}
|
|
else
|
|
do_blocked = false;
|
|
|
|
n = 0;
|
|
|
|
if (do_blocked)
|
|
{
|
|
/* For contiguous arrays, use the relationship that
|
|
|
|
dimension(n1,n2,n3) :: a, b
|
|
b = cshift(a,sh,3)
|
|
|
|
can be dealt with as if
|
|
|
|
dimension(n1*n2*n3) :: an, bn
|
|
bn = cshift(a,sh*n1*n2,1)
|
|
|
|
we can used a more blocked algorithm for dim>1. */
|
|
sstride[0] = 1;
|
|
rstride[0] = 1;
|
|
roffset = 1;
|
|
soffset = 1;
|
|
len = GFC_DESCRIPTOR_STRIDE(array, which)
|
|
* GFC_DESCRIPTOR_EXTENT(array, which);
|
|
shift *= GFC_DESCRIPTOR_STRIDE(array, which);
|
|
for (dim = which + 1; dim < GFC_DESCRIPTOR_RANK (array); dim++)
|
|
{
|
|
count[n] = 0;
|
|
extent[n] = GFC_DESCRIPTOR_EXTENT(array,dim);
|
|
rstride[n] = GFC_DESCRIPTOR_STRIDE(ret,dim);
|
|
sstride[n] = GFC_DESCRIPTOR_STRIDE(array,dim);
|
|
n++;
|
|
}
|
|
dim = GFC_DESCRIPTOR_RANK (array) - which;
|
|
}
|
|
else
|
|
{
|
|
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);
|
|
n++;
|
|
}
|
|
}
|
|
if (sstride[0] == 0)
|
|
sstride[0] = 1;
|
|
if (rstride[0] == 0)
|
|
rstride[0] = 1;
|
|
|
|
dim = GFC_DESCRIPTOR_RANK (array);
|
|
}
|
|
|
|
rstride0 = rstride[0];
|
|
sstride0 = sstride[0];
|
|
rptr = ret->base_addr;
|
|
sptr = array->base_addr;
|
|
|
|
/* Avoid the costly modulo for trivially in-bound shifts. */
|
|
if (shift < 0 || shift >= len)
|
|
{
|
|
shift = len == 0 ? 0 : shift % (ptrdiff_t)len;
|
|
if (shift < 0)
|
|
shift += len;
|
|
}
|
|
|
|
while (rptr)
|
|
{
|
|
/* Do the shift for this dimension. */
|
|
|
|
/* If elements are contiguous, perform the operation
|
|
in two block moves. */
|
|
if (soffset == 1 && roffset == 1)
|
|
{
|
|
size_t len1 = shift * sizeof (GFC_COMPLEX_17);
|
|
size_t len2 = (len - shift) * sizeof (GFC_COMPLEX_17);
|
|
memcpy (rptr, sptr + shift, len2);
|
|
memcpy (rptr + (len - shift), sptr, len1);
|
|
}
|
|
else
|
|
{
|
|
/* Otherwise, we will have to perform the copy one element at
|
|
a time. */
|
|
GFC_COMPLEX_17 *dest = rptr;
|
|
const GFC_COMPLEX_17 *src = &sptr[shift * soffset];
|
|
|
|
for (n = 0; n < len - shift; n++)
|
|
{
|
|
*dest = *src;
|
|
dest += roffset;
|
|
src += soffset;
|
|
}
|
|
for (src = sptr, n = 0; n < shift; n++)
|
|
{
|
|
*dest = *src;
|
|
dest += roffset;
|
|
src += soffset;
|
|
}
|
|
}
|
|
|
|
/* Advance to the next section. */
|
|
rptr += rstride0;
|
|
sptr += sstride0;
|
|
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];
|
|
sptr -= sstride[n] * extent[n];
|
|
n++;
|
|
if (n >= dim - 1)
|
|
{
|
|
/* Break out of the loop. */
|
|
rptr = NULL;
|
|
break;
|
|
}
|
|
else
|
|
{
|
|
count[n]++;
|
|
rptr += rstride[n];
|
|
sptr += sstride[n];
|
|
}
|
|
}
|
|
}
|
|
|
|
return;
|
|
}
|
|
|
|
#endif
|