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.
376 lines
9.3 KiB
C
376 lines
9.3 KiB
C
|
|
/* Implementation of the FINDLOC intrinsic
|
|
Copyright (C) 2018-2022 Free Software Foundation, Inc.
|
|
Contributed by Thomas König <tk@tkoenig.net>
|
|
|
|
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 <assert.h>
|
|
|
|
#if defined (HAVE_GFC_REAL_17)
|
|
extern void findloc0_r17 (gfc_array_index_type * const restrict retarray,
|
|
gfc_array_r17 * const restrict array, GFC_REAL_17 value,
|
|
GFC_LOGICAL_4);
|
|
export_proto(findloc0_r17);
|
|
|
|
void
|
|
findloc0_r17 (gfc_array_index_type * const restrict retarray,
|
|
gfc_array_r17 * const restrict array, GFC_REAL_17 value,
|
|
GFC_LOGICAL_4 back)
|
|
{
|
|
index_type count[GFC_MAX_DIMENSIONS];
|
|
index_type extent[GFC_MAX_DIMENSIONS];
|
|
index_type sstride[GFC_MAX_DIMENSIONS];
|
|
index_type dstride;
|
|
const GFC_REAL_17 *base;
|
|
index_type * restrict dest;
|
|
index_type rank;
|
|
index_type n;
|
|
index_type sz;
|
|
|
|
rank = GFC_DESCRIPTOR_RANK (array);
|
|
if (rank <= 0)
|
|
runtime_error ("Rank of array needs to be > 0");
|
|
|
|
if (retarray->base_addr == NULL)
|
|
{
|
|
GFC_DIMENSION_SET(retarray->dim[0], 0, rank-1, 1);
|
|
retarray->dtype.rank = 1;
|
|
retarray->offset = 0;
|
|
retarray->base_addr = xmallocarray (rank, sizeof (index_type));
|
|
}
|
|
else
|
|
{
|
|
if (unlikely (compile_options.bounds_check))
|
|
bounds_iforeach_return ((array_t *) retarray, (array_t *) array,
|
|
"FINDLOC");
|
|
}
|
|
|
|
dstride = GFC_DESCRIPTOR_STRIDE(retarray,0);
|
|
dest = retarray->base_addr;
|
|
|
|
/* Set the return value. */
|
|
for (n = 0; n < rank; n++)
|
|
dest[n * dstride] = 0;
|
|
|
|
sz = 1;
|
|
for (n = 0; n < rank; n++)
|
|
{
|
|
sstride[n] = GFC_DESCRIPTOR_STRIDE(array,n);
|
|
extent[n] = GFC_DESCRIPTOR_EXTENT(array,n);
|
|
sz *= extent[n];
|
|
if (extent[n] <= 0)
|
|
return;
|
|
}
|
|
|
|
for (n = 0; n < rank; n++)
|
|
count[n] = 0;
|
|
|
|
if (back)
|
|
{
|
|
base = array->base_addr + (sz - 1) * 1;
|
|
|
|
while (1)
|
|
{
|
|
do
|
|
{
|
|
if (unlikely(*base == value))
|
|
{
|
|
for (n = 0; n < rank; n++)
|
|
dest[n * dstride] = extent[n] - count[n];
|
|
|
|
return;
|
|
}
|
|
base -= sstride[0] * 1;
|
|
} while(++count[0] != extent[0]);
|
|
|
|
n = 0;
|
|
do
|
|
{
|
|
/* 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] * 1;
|
|
n++;
|
|
if (n >= rank)
|
|
return;
|
|
else
|
|
{
|
|
count[n]++;
|
|
base -= sstride[n] * 1;
|
|
}
|
|
} while (count[n] == extent[n]);
|
|
}
|
|
}
|
|
else
|
|
{
|
|
base = array->base_addr;
|
|
while (1)
|
|
{
|
|
do
|
|
{
|
|
if (unlikely(*base == value))
|
|
{
|
|
for (n = 0; n < rank; n++)
|
|
dest[n * dstride] = count[n] + 1;
|
|
|
|
return;
|
|
}
|
|
base += sstride[0] * 1;
|
|
} while(++count[0] != extent[0]);
|
|
|
|
n = 0;
|
|
do
|
|
{
|
|
/* 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] * 1;
|
|
n++;
|
|
if (n >= rank)
|
|
return;
|
|
else
|
|
{
|
|
count[n]++;
|
|
base += sstride[n] * 1;
|
|
}
|
|
} while (count[n] == extent[n]);
|
|
}
|
|
}
|
|
return;
|
|
}
|
|
|
|
extern void mfindloc0_r17 (gfc_array_index_type * const restrict retarray,
|
|
gfc_array_r17 * const restrict array, GFC_REAL_17 value,
|
|
gfc_array_l1 *const restrict, GFC_LOGICAL_4);
|
|
export_proto(mfindloc0_r17);
|
|
|
|
void
|
|
mfindloc0_r17 (gfc_array_index_type * const restrict retarray,
|
|
gfc_array_r17 * const restrict array, GFC_REAL_17 value,
|
|
gfc_array_l1 *const restrict mask, GFC_LOGICAL_4 back)
|
|
{
|
|
index_type count[GFC_MAX_DIMENSIONS];
|
|
index_type extent[GFC_MAX_DIMENSIONS];
|
|
index_type sstride[GFC_MAX_DIMENSIONS];
|
|
index_type mstride[GFC_MAX_DIMENSIONS];
|
|
index_type dstride;
|
|
const GFC_REAL_17 *base;
|
|
index_type * restrict dest;
|
|
GFC_LOGICAL_1 *mbase;
|
|
index_type rank;
|
|
index_type n;
|
|
int mask_kind;
|
|
index_type sz;
|
|
|
|
rank = GFC_DESCRIPTOR_RANK (array);
|
|
if (rank <= 0)
|
|
runtime_error ("Rank of array needs to be > 0");
|
|
|
|
if (retarray->base_addr == NULL)
|
|
{
|
|
GFC_DIMENSION_SET(retarray->dim[0], 0, rank-1, 1);
|
|
retarray->dtype.rank = 1;
|
|
retarray->offset = 0;
|
|
retarray->base_addr = xmallocarray (rank, sizeof (index_type));
|
|
}
|
|
else
|
|
{
|
|
if (unlikely (compile_options.bounds_check))
|
|
{
|
|
bounds_iforeach_return ((array_t *) retarray, (array_t *) array,
|
|
"FINDLOC");
|
|
bounds_equal_extents ((array_t *) mask, (array_t *) array,
|
|
"MASK argument", "FINDLOC");
|
|
}
|
|
}
|
|
|
|
mask_kind = GFC_DESCRIPTOR_SIZE (mask);
|
|
|
|
mbase = mask->base_addr;
|
|
|
|
if (mask_kind == 1 || mask_kind == 2 || mask_kind == 4 || mask_kind == 8
|
|
#ifdef HAVE_GFC_LOGICAL_16
|
|
|| mask_kind == 16
|
|
#endif
|
|
)
|
|
mbase = GFOR_POINTER_TO_L1 (mbase, mask_kind);
|
|
else
|
|
internal_error (NULL, "Funny sized logical array");
|
|
|
|
dstride = GFC_DESCRIPTOR_STRIDE(retarray,0);
|
|
dest = retarray->base_addr;
|
|
|
|
/* Set the return value. */
|
|
for (n = 0; n < rank; n++)
|
|
dest[n * dstride] = 0;
|
|
|
|
sz = 1;
|
|
for (n = 0; n < rank; n++)
|
|
{
|
|
sstride[n] = GFC_DESCRIPTOR_STRIDE(array,n);
|
|
mstride[n] = GFC_DESCRIPTOR_STRIDE_BYTES(mask,n);
|
|
extent[n] = GFC_DESCRIPTOR_EXTENT(array,n);
|
|
sz *= extent[n];
|
|
if (extent[n] <= 0)
|
|
return;
|
|
}
|
|
|
|
for (n = 0; n < rank; n++)
|
|
count[n] = 0;
|
|
|
|
if (back)
|
|
{
|
|
base = array->base_addr + (sz - 1) * 1;
|
|
mbase = mbase + (sz - 1) * mask_kind;
|
|
while (1)
|
|
{
|
|
do
|
|
{
|
|
if (unlikely(*mbase && *base == value))
|
|
{
|
|
for (n = 0; n < rank; n++)
|
|
dest[n * dstride] = extent[n] - count[n];
|
|
|
|
return;
|
|
}
|
|
base -= sstride[0] * 1;
|
|
mbase -= mstride[0];
|
|
} while(++count[0] != extent[0]);
|
|
|
|
n = 0;
|
|
do
|
|
{
|
|
/* 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] * 1;
|
|
mbase -= mstride[n] * extent[n];
|
|
n++;
|
|
if (n >= rank)
|
|
return;
|
|
else
|
|
{
|
|
count[n]++;
|
|
base -= sstride[n] * 1;
|
|
mbase += mstride[n];
|
|
}
|
|
} while (count[n] == extent[n]);
|
|
}
|
|
}
|
|
else
|
|
{
|
|
base = array->base_addr;
|
|
while (1)
|
|
{
|
|
do
|
|
{
|
|
if (unlikely(*mbase && *base == value))
|
|
{
|
|
for (n = 0; n < rank; n++)
|
|
dest[n * dstride] = count[n] + 1;
|
|
|
|
return;
|
|
}
|
|
base += sstride[0] * 1;
|
|
mbase += mstride[0];
|
|
} while(++count[0] != extent[0]);
|
|
|
|
n = 0;
|
|
do
|
|
{
|
|
/* 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] * 1;
|
|
mbase -= mstride[n] * extent[n];
|
|
n++;
|
|
if (n >= rank)
|
|
return;
|
|
else
|
|
{
|
|
count[n]++;
|
|
base += sstride[n]* 1;
|
|
mbase += mstride[n];
|
|
}
|
|
} while (count[n] == extent[n]);
|
|
}
|
|
}
|
|
return;
|
|
}
|
|
|
|
extern void sfindloc0_r17 (gfc_array_index_type * const restrict retarray,
|
|
gfc_array_r17 * const restrict array, GFC_REAL_17 value,
|
|
GFC_LOGICAL_4 *, GFC_LOGICAL_4);
|
|
export_proto(sfindloc0_r17);
|
|
|
|
void
|
|
sfindloc0_r17 (gfc_array_index_type * const restrict retarray,
|
|
gfc_array_r17 * const restrict array, GFC_REAL_17 value,
|
|
GFC_LOGICAL_4 * mask, GFC_LOGICAL_4 back)
|
|
{
|
|
index_type rank;
|
|
index_type dstride;
|
|
index_type * restrict dest;
|
|
index_type n;
|
|
|
|
if (mask == NULL || *mask)
|
|
{
|
|
findloc0_r17 (retarray, array, value, back);
|
|
return;
|
|
}
|
|
|
|
rank = GFC_DESCRIPTOR_RANK (array);
|
|
|
|
if (rank <= 0)
|
|
internal_error (NULL, "Rank of array needs to be > 0");
|
|
|
|
if (retarray->base_addr == NULL)
|
|
{
|
|
GFC_DIMENSION_SET(retarray->dim[0], 0, rank-1, 1);
|
|
retarray->dtype.rank = 1;
|
|
retarray->offset = 0;
|
|
retarray->base_addr = xmallocarray (rank, sizeof (index_type));
|
|
}
|
|
else if (unlikely (compile_options.bounds_check))
|
|
{
|
|
bounds_iforeach_return ((array_t *) retarray, (array_t *) array,
|
|
"FINDLOC");
|
|
}
|
|
|
|
dstride = GFC_DESCRIPTOR_STRIDE(retarray,0);
|
|
dest = retarray->base_addr;
|
|
for (n = 0; n<rank; n++)
|
|
dest[n * dstride] = 0 ;
|
|
}
|
|
|
|
#endif
|