gcc/libgfortran/generated/unpack_r17.c
Thomas Koenig 49ad4d2c30 Prepare library for REAL(KIND=17).
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.
2022-01-11 23:39:54 +01:00

334 lines
8.7 KiB
C

/* Specific implementation of the UNPACK intrinsic
Copyright (C) 2008-2022 Free Software Foundation, Inc.
Contributed by Thomas Koenig <tkoenig@gcc.gnu.org>, based on
unpack_generic.c 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
unpack0_r17 (gfc_array_r17 *ret, const gfc_array_r17 *vector,
const gfc_array_l1 *mask, const GFC_REAL_17 *fptr)
{
/* r.* indicates the return array. */
index_type rstride[GFC_MAX_DIMENSIONS];
index_type rstride0;
index_type rs;
GFC_REAL_17 * restrict rptr;
/* v.* indicates the vector array. */
index_type vstride0;
GFC_REAL_17 *vptr;
/* Value for field, this is constant. */
const GFC_REAL_17 fval = *fptr;
/* m.* indicates the mask array. */
index_type mstride[GFC_MAX_DIMENSIONS];
index_type mstride0;
const GFC_LOGICAL_1 *mptr;
index_type count[GFC_MAX_DIMENSIONS];
index_type extent[GFC_MAX_DIMENSIONS];
index_type n;
index_type dim;
int empty;
int mask_kind;
empty = 0;
mptr = mask->base_addr;
/* Use the same loop for all logical types, by using GFC_LOGICAL_1
and using shifting to address size and endian issues. */
mask_kind = GFC_DESCRIPTOR_SIZE (mask);
if (mask_kind == 1 || mask_kind == 2 || mask_kind == 4 || mask_kind == 8
#ifdef HAVE_GFC_LOGICAL_16
|| mask_kind == 16
#endif
)
{
/* Do not convert a NULL pointer as we use test for NULL below. */
if (mptr)
mptr = GFOR_POINTER_TO_L1 (mptr, mask_kind);
}
else
runtime_error ("Funny sized logical array");
/* Initialize to avoid -Wmaybe-uninitialized complaints. */
rstride[0] = 1;
if (ret->base_addr == NULL)
{
/* The front end has signalled that we need to populate the
return array descriptor. */
dim = GFC_DESCRIPTOR_RANK (mask);
rs = 1;
for (n = 0; n < dim; n++)
{
count[n] = 0;
GFC_DIMENSION_SET(ret->dim[n], 0,
GFC_DESCRIPTOR_EXTENT(mask,n) - 1, rs);
extent[n] = GFC_DESCRIPTOR_EXTENT(ret,n);
empty = empty || extent[n] <= 0;
rstride[n] = GFC_DESCRIPTOR_STRIDE(ret,n);
mstride[n] = GFC_DESCRIPTOR_STRIDE_BYTES(mask,n);
rs *= extent[n];
}
ret->offset = 0;
ret->base_addr = xmallocarray (rs, sizeof (GFC_REAL_17));
}
else
{
dim = GFC_DESCRIPTOR_RANK (ret);
for (n = 0; n < dim; n++)
{
count[n] = 0;
extent[n] = GFC_DESCRIPTOR_EXTENT(ret,n);
empty = empty || extent[n] <= 0;
rstride[n] = GFC_DESCRIPTOR_STRIDE(ret,n);
mstride[n] = GFC_DESCRIPTOR_STRIDE_BYTES(mask,n);
}
if (rstride[0] == 0)
rstride[0] = 1;
}
if (empty)
return;
if (mstride[0] == 0)
mstride[0] = 1;
vstride0 = GFC_DESCRIPTOR_STRIDE(vector,0);
if (vstride0 == 0)
vstride0 = 1;
rstride0 = rstride[0];
mstride0 = mstride[0];
rptr = ret->base_addr;
vptr = vector->base_addr;
while (rptr)
{
if (*mptr)
{
/* From vector. */
*rptr = *vptr;
vptr += vstride0;
}
else
{
/* From field. */
*rptr = fval;
}
/* Advance to the next element. */
rptr += rstride0;
mptr += mstride0;
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];
mptr -= mstride[n] * extent[n];
n++;
if (n >= dim)
{
/* Break out of the loop. */
rptr = NULL;
break;
}
else
{
count[n]++;
rptr += rstride[n];
mptr += mstride[n];
}
}
}
}
void
unpack1_r17 (gfc_array_r17 *ret, const gfc_array_r17 *vector,
const gfc_array_l1 *mask, const gfc_array_r17 *field)
{
/* r.* indicates the return array. */
index_type rstride[GFC_MAX_DIMENSIONS];
index_type rstride0;
index_type rs;
GFC_REAL_17 * restrict rptr;
/* v.* indicates the vector array. */
index_type vstride0;
GFC_REAL_17 *vptr;
/* f.* indicates the field array. */
index_type fstride[GFC_MAX_DIMENSIONS];
index_type fstride0;
const GFC_REAL_17 *fptr;
/* m.* indicates the mask array. */
index_type mstride[GFC_MAX_DIMENSIONS];
index_type mstride0;
const GFC_LOGICAL_1 *mptr;
index_type count[GFC_MAX_DIMENSIONS];
index_type extent[GFC_MAX_DIMENSIONS];
index_type n;
index_type dim;
int empty;
int mask_kind;
empty = 0;
mptr = mask->base_addr;
/* Use the same loop for all logical types, by using GFC_LOGICAL_1
and using shifting to address size and endian issues. */
mask_kind = GFC_DESCRIPTOR_SIZE (mask);
if (mask_kind == 1 || mask_kind == 2 || mask_kind == 4 || mask_kind == 8
#ifdef HAVE_GFC_LOGICAL_16
|| mask_kind == 16
#endif
)
{
/* Do not convert a NULL pointer as we use test for NULL below. */
if (mptr)
mptr = GFOR_POINTER_TO_L1 (mptr, mask_kind);
}
else
runtime_error ("Funny sized logical array");
/* Initialize to avoid -Wmaybe-uninitialized complaints. */
rstride[0] = 1;
if (ret->base_addr == NULL)
{
/* The front end has signalled that we need to populate the
return array descriptor. */
dim = GFC_DESCRIPTOR_RANK (mask);
rs = 1;
for (n = 0; n < dim; n++)
{
count[n] = 0;
GFC_DIMENSION_SET(ret->dim[n], 0,
GFC_DESCRIPTOR_EXTENT(mask,n) - 1, rs);
extent[n] = GFC_DESCRIPTOR_EXTENT(ret,n);
empty = empty || extent[n] <= 0;
rstride[n] = GFC_DESCRIPTOR_STRIDE(ret,n);
fstride[n] = GFC_DESCRIPTOR_STRIDE(field,n);
mstride[n] = GFC_DESCRIPTOR_STRIDE_BYTES(mask,n);
rs *= extent[n];
}
ret->offset = 0;
ret->base_addr = xmallocarray (rs, sizeof (GFC_REAL_17));
}
else
{
dim = GFC_DESCRIPTOR_RANK (ret);
for (n = 0; n < dim; n++)
{
count[n] = 0;
extent[n] = GFC_DESCRIPTOR_EXTENT(ret,n);
empty = empty || extent[n] <= 0;
rstride[n] = GFC_DESCRIPTOR_STRIDE(ret,n);
fstride[n] = GFC_DESCRIPTOR_STRIDE(field,n);
mstride[n] = GFC_DESCRIPTOR_STRIDE_BYTES(mask,n);
}
if (rstride[0] == 0)
rstride[0] = 1;
}
if (empty)
return;
if (fstride[0] == 0)
fstride[0] = 1;
if (mstride[0] == 0)
mstride[0] = 1;
vstride0 = GFC_DESCRIPTOR_STRIDE(vector,0);
if (vstride0 == 0)
vstride0 = 1;
rstride0 = rstride[0];
fstride0 = fstride[0];
mstride0 = mstride[0];
rptr = ret->base_addr;
fptr = field->base_addr;
vptr = vector->base_addr;
while (rptr)
{
if (*mptr)
{
/* From vector. */
*rptr = *vptr;
vptr += vstride0;
}
else
{
/* From field. */
*rptr = *fptr;
}
/* Advance to the next element. */
rptr += rstride0;
fptr += fstride0;
mptr += mstride0;
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];
fptr -= fstride[n] * extent[n];
mptr -= mstride[n] * extent[n];
n++;
if (n >= dim)
{
/* Break out of the loop. */
rptr = NULL;
break;
}
else
{
count[n]++;
rptr += rstride[n];
fptr += fstride[n];
mptr += mstride[n];
}
}
}
}
#endif