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.
220 lines
5.4 KiB
C
220 lines
5.4 KiB
C
/* Implementation of the NORM2 intrinsic
|
|
Copyright (C) 2010-2022 Free Software Foundation, Inc.
|
|
Contributed by Tobias Burnus <burnus@net-b.de>
|
|
|
|
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"
|
|
|
|
|
|
|
|
#if defined (HAVE_GFC_REAL_17) && defined (HAVE_GFC_REAL_17) && 1 /* FIXME: figure this out later. */ && 1 /* FIXME: figure this out later. */
|
|
|
|
#if defined(POWER_IEEE128)
|
|
#define MATHFUNC(funcname) __ ## funcname ## ieee128
|
|
#else
|
|
#define MATHFUNC(funcname) funcname ## q
|
|
#endif
|
|
|
|
|
|
extern void norm2_r17 (gfc_array_r17 * const restrict,
|
|
gfc_array_r17 * const restrict, const index_type * const restrict);
|
|
export_proto(norm2_r17);
|
|
|
|
void
|
|
norm2_r17 (gfc_array_r17 * const restrict retarray,
|
|
gfc_array_r17 * 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_REAL_17 * restrict base;
|
|
GFC_REAL_17 * restrict dest;
|
|
index_type rank;
|
|
index_type n;
|
|
index_type len;
|
|
index_type delta;
|
|
index_type dim;
|
|
int continue_loop;
|
|
|
|
/* 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 NORM 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;
|
|
retarray->dtype.rank = rank;
|
|
|
|
alloc_size = GFC_DESCRIPTOR_STRIDE(retarray,rank-1) * extent[rank-1];
|
|
|
|
retarray->base_addr = xmallocarray (alloc_size, sizeof (GFC_REAL_17));
|
|
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"
|
|
" NORM 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", "NORM");
|
|
}
|
|
|
|
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_REAL_17 * restrict src;
|
|
GFC_REAL_17 result;
|
|
src = base;
|
|
{
|
|
|
|
GFC_REAL_17 scale;
|
|
result = 0;
|
|
scale = 1;
|
|
if (len <= 0)
|
|
*dest = 0;
|
|
else
|
|
{
|
|
#if ! defined HAVE_BACK_ARG
|
|
for (n = 0; n < len; n++, src += delta)
|
|
{
|
|
#endif
|
|
|
|
if (*src != 0)
|
|
{
|
|
GFC_REAL_17 absX, val;
|
|
absX = MATHFUNC(fabs) (*src);
|
|
if (scale < absX)
|
|
{
|
|
val = scale / absX;
|
|
result = 1 + result * val * val;
|
|
scale = absX;
|
|
}
|
|
else
|
|
{
|
|
val = absX / scale;
|
|
result += val * val;
|
|
}
|
|
}
|
|
}
|
|
result = scale * MATHFUNC(sqrt) (result);
|
|
*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];
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
#endif
|