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.
267 lines
6.7 KiB
C
267 lines
6.7 KiB
C
/* Special implementation of the SPREAD intrinsic
|
|
Copyright (C) 2008-2022 Free Software Foundation, Inc.
|
|
Contributed by Thomas Koenig <tkoenig@gcc.gnu.org>, based on
|
|
spread_generic.c written by Paul Brook <paul@nowt.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.
|
|
|
|
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/>. */
|
|
|
|
#include "libgfortran.h"
|
|
#include <string.h>
|
|
|
|
|
|
#if defined (HAVE_GFC_REAL_17)
|
|
|
|
void
|
|
spread_r17 (gfc_array_r17 *ret, const gfc_array_r17 *source,
|
|
const index_type along, const index_type pncopies)
|
|
{
|
|
/* r.* indicates the return array. */
|
|
index_type rstride[GFC_MAX_DIMENSIONS];
|
|
index_type rstride0;
|
|
index_type rdelta = 0;
|
|
index_type rrank;
|
|
index_type rs;
|
|
GFC_REAL_17 *rptr;
|
|
GFC_REAL_17 * restrict dest;
|
|
/* s.* indicates the source array. */
|
|
index_type sstride[GFC_MAX_DIMENSIONS];
|
|
index_type sstride0;
|
|
index_type srank;
|
|
const GFC_REAL_17 *sptr;
|
|
|
|
index_type count[GFC_MAX_DIMENSIONS];
|
|
index_type extent[GFC_MAX_DIMENSIONS];
|
|
index_type n;
|
|
index_type dim;
|
|
index_type ncopies;
|
|
|
|
srank = GFC_DESCRIPTOR_RANK(source);
|
|
|
|
rrank = srank + 1;
|
|
if (rrank > GFC_MAX_DIMENSIONS)
|
|
runtime_error ("return rank too large in spread()");
|
|
|
|
if (along > rrank)
|
|
runtime_error ("dim outside of rank in spread()");
|
|
|
|
ncopies = pncopies;
|
|
|
|
if (ret->base_addr == NULL)
|
|
{
|
|
|
|
size_t ub, stride;
|
|
|
|
/* The front end has signalled that we need to populate the
|
|
return array descriptor. */
|
|
ret->dtype.rank = rrank;
|
|
|
|
dim = 0;
|
|
rs = 1;
|
|
for (n = 0; n < rrank; n++)
|
|
{
|
|
stride = rs;
|
|
if (n == along - 1)
|
|
{
|
|
ub = ncopies - 1;
|
|
rdelta = rs;
|
|
rs *= ncopies;
|
|
}
|
|
else
|
|
{
|
|
count[dim] = 0;
|
|
extent[dim] = GFC_DESCRIPTOR_EXTENT(source,dim);
|
|
sstride[dim] = GFC_DESCRIPTOR_STRIDE(source,dim);
|
|
rstride[dim] = rs;
|
|
|
|
ub = extent[dim] - 1;
|
|
rs *= extent[dim];
|
|
dim++;
|
|
}
|
|
GFC_DIMENSION_SET(ret->dim[n], 0, ub, stride);
|
|
}
|
|
ret->offset = 0;
|
|
|
|
/* xmallocarray allocates a single byte for zero size. */
|
|
ret->base_addr = xmallocarray (rs, sizeof(GFC_REAL_17));
|
|
if (rs <= 0)
|
|
return;
|
|
}
|
|
else
|
|
{
|
|
int zero_sized;
|
|
|
|
zero_sized = 0;
|
|
|
|
dim = 0;
|
|
if (GFC_DESCRIPTOR_RANK(ret) != rrank)
|
|
runtime_error ("rank mismatch in spread()");
|
|
|
|
if (unlikely (compile_options.bounds_check))
|
|
{
|
|
for (n = 0; n < rrank; n++)
|
|
{
|
|
index_type ret_extent;
|
|
|
|
ret_extent = GFC_DESCRIPTOR_EXTENT(ret,n);
|
|
if (n == along - 1)
|
|
{
|
|
rdelta = GFC_DESCRIPTOR_STRIDE(ret,n);
|
|
|
|
if (ret_extent != ncopies)
|
|
runtime_error("Incorrect extent in return value of SPREAD"
|
|
" intrinsic in dimension %ld: is %ld,"
|
|
" should be %ld", (long int) n+1,
|
|
(long int) ret_extent, (long int) ncopies);
|
|
}
|
|
else
|
|
{
|
|
count[dim] = 0;
|
|
extent[dim] = GFC_DESCRIPTOR_EXTENT(source,dim);
|
|
if (ret_extent != extent[dim])
|
|
runtime_error("Incorrect extent in return value of SPREAD"
|
|
" intrinsic in dimension %ld: is %ld,"
|
|
" should be %ld", (long int) n+1,
|
|
(long int) ret_extent,
|
|
(long int) extent[dim]);
|
|
|
|
if (extent[dim] <= 0)
|
|
zero_sized = 1;
|
|
sstride[dim] = GFC_DESCRIPTOR_STRIDE(source,dim);
|
|
rstride[dim] = GFC_DESCRIPTOR_STRIDE(ret,n);
|
|
dim++;
|
|
}
|
|
}
|
|
}
|
|
else
|
|
{
|
|
for (n = 0; n < rrank; n++)
|
|
{
|
|
if (n == along - 1)
|
|
{
|
|
rdelta = GFC_DESCRIPTOR_STRIDE(ret,n);
|
|
}
|
|
else
|
|
{
|
|
count[dim] = 0;
|
|
extent[dim] = GFC_DESCRIPTOR_EXTENT(source,dim);
|
|
if (extent[dim] <= 0)
|
|
zero_sized = 1;
|
|
sstride[dim] = GFC_DESCRIPTOR_STRIDE(source,dim);
|
|
rstride[dim] = GFC_DESCRIPTOR_STRIDE(ret,n);
|
|
dim++;
|
|
}
|
|
}
|
|
}
|
|
|
|
if (zero_sized)
|
|
return;
|
|
|
|
if (sstride[0] == 0)
|
|
sstride[0] = 1;
|
|
}
|
|
sstride0 = sstride[0];
|
|
rstride0 = rstride[0];
|
|
rptr = ret->base_addr;
|
|
sptr = source->base_addr;
|
|
|
|
while (sptr)
|
|
{
|
|
/* Spread this element. */
|
|
dest = rptr;
|
|
for (n = 0; n < ncopies; n++)
|
|
{
|
|
*dest = *sptr;
|
|
dest += rdelta;
|
|
}
|
|
/* Advance to the next element. */
|
|
sptr += sstride0;
|
|
rptr += rstride0;
|
|
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. */
|
|
sptr -= sstride[n] * extent[n];
|
|
rptr -= rstride[n] * extent[n];
|
|
n++;
|
|
if (n >= srank)
|
|
{
|
|
/* Break out of the loop. */
|
|
sptr = NULL;
|
|
break;
|
|
}
|
|
else
|
|
{
|
|
count[n]++;
|
|
sptr += sstride[n];
|
|
rptr += rstride[n];
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
/* This version of spread_internal treats the special case of a scalar
|
|
source. This is much simpler than the more general case above. */
|
|
|
|
void
|
|
spread_scalar_r17 (gfc_array_r17 *ret, const GFC_REAL_17 *source,
|
|
const index_type along, const index_type ncopies)
|
|
{
|
|
GFC_REAL_17 * restrict dest;
|
|
index_type stride;
|
|
|
|
if (GFC_DESCRIPTOR_RANK (ret) != 1)
|
|
runtime_error ("incorrect destination rank in spread()");
|
|
|
|
if (along > 1)
|
|
runtime_error ("dim outside of rank in spread()");
|
|
|
|
if (ret->base_addr == NULL)
|
|
{
|
|
ret->base_addr = xmallocarray (ncopies, sizeof (GFC_REAL_17));
|
|
ret->offset = 0;
|
|
GFC_DIMENSION_SET(ret->dim[0], 0, ncopies - 1, 1);
|
|
}
|
|
else
|
|
{
|
|
if (ncopies - 1 > (GFC_DESCRIPTOR_EXTENT(ret,0) - 1)
|
|
/ GFC_DESCRIPTOR_STRIDE(ret,0))
|
|
runtime_error ("dim too large in spread()");
|
|
}
|
|
|
|
dest = ret->base_addr;
|
|
stride = GFC_DESCRIPTOR_STRIDE(ret,0);
|
|
|
|
for (index_type n = 0; n < ncopies; n++)
|
|
{
|
|
*dest = *source;
|
|
dest += stride;
|
|
}
|
|
}
|
|
|
|
#endif
|
|
|