133d0d422e
As mentioned by Joseph in PR105101, glibc 2.26 or later has on x86
(both -m32/-m64), powerpc64le, ia64 and mips support for
*f128 math/complex APIs plus strtof128 and strfromf128, and these APIs allow
us to avoid libquadmath for Fortran purposes on these architectures,
replace *q math/complex APIs, strtof128 instead of strtoflt128 and,
while strfromf128 unfortunately isn't a perfect replacement to
quadmath_snprintf, it can be made to work.
The advantage of this is that when configured against such glibcs
(2.26 is now almost 5 years old), we can avoid linking against an extra shared
library and the math support in glibc is maintained better than libquadmath.
We need both a compiler change (so that for glibc 2.26+ it uses *f128 APIs
instead of *q) and library change.
The above mentioned problem with strfromf128 is that the strfrom* functions
are severely restricted versions of snprintf. In libgfortran, we handle
!isfinite differently and just use snprintf/quadmath_snprintf for
%+-#.*{L,Q}{f,e} printing.
strfrom* doesn't allow +, -, # modifiers and it only supports .34 or
similar precision, not .* . The L/Q etc. letters are omitted.
The + is there to force + sign at the start if it is positive.
Workaround in the patch is to add the + at the start manually for
!signbit (val).
The - (left alignment instead of right) I don't understand why we need it,
when minimum field width isn't specified (for strfrom* can't be specified),
no padding is ever added anywhere I believe.
The # is to force adding . - workaround is to search for first . or e or '\0'
character, if it is '\0', just append ., if it is e, insert . before e and
memmove the rest (which is just a few bytes, e, +/- and at most a few digits)
one byte later.
The .* case is handled by creating the format string for strfrom* by
snprintf into a temporary buffer.
As requested, this patch also switches from using __float128 type in
libgfortran to _Float128 which is equivalent on all arches that support
__float128.
The change is done in a backwards compatible change, when GCC is configured
against glibc 2.26 or newer, libgfortran.so.5 itself doesn't link against
-lquadmath nor uses any libquadmath APIs, libgfortran.a doesn't use any
libquadmath APIs either. User programs and libraries when being linked
by gfortran driver are linked against -lgfortran and -lquadmath, but
the latter only in the --as-needed linker mode, which means it needs
to be around during linking and will be linked in if there are any
calls to math/complex functions with real(kind=16) or complex(kind=16)
in compilation units compiled by older versions of gcc, but if either
user code doesn't call those math/complex functions for the largest
supported kind, or the code is recompiled by gcc with this change in,
libquadmath won't be linked in.
2022-06-28 Jakub Jelinek <jakub@redhat.com>
gcc/fortran/
* gfortran.h (gfc_real_info): Add use_iec_60559 bitfield.
* trans-types.h (gfc_real16_use_iec_60559): Declare.
* trans-types.cc (gfc_real16_use_iec_60559): Define.
(gfc_init_kinds): When building powerpc64le-linux libgfortran
on glibc 2.26 to 2.31, set gfc_real16_use_iec_60559 and
use_iec_60559.
(gfc_build_real_type): Set gfc_real16_use_iec_60559 and use_iec_60559
on glibc 2.26 or later.
* trans-intrinsic.cc (gfc_build_intrinsic_lib_fndecls): Adjust
comment. Handle gfc_real16_use_iec_60559.
(gfc_get_intrinsic_lib_fndecl): Handle use_iec_60559.
libgfortran/
* configure.ac: Check for strtof128 and strfromf128.
Check for math and complex *f128 functions. Set
have_iec_60559_libc_support to yes if *f128 support is around, for
--enable-libquadmath-support default to "default" rather than yes if
have_iec_60559_libc_support is yes.
* acinclude.m4 (LIBGFOR_CHECK_FLOAT128): Test
_Float128/_Complex _Float128 rather than __float128 and
_Complex float __attribute__((mode(TC))). If libquadmath support
is defaulted and have_iec_60559_libc_support is yes, define and subst
USE_IEC_60559. Remove unused LIBGFOR_BUILD_QUAD conditional.
* Makefile.am (kinds.h): Pass @USE_IEC_60559@ as an extra
mk-kinds-h.sh argument.
* mk-kinds-h.sh: Accept 4th use_iec_60559 argument. Use
_Float128/_Complex _Float128 types instead of __float128 and
_Complex float __attribute__((mode(TC))), and if use_iec_60559 is yes,
use f128 suffix instead of q and define GFC_REAL_16_USE_IEC_60559.
* kinds-override.h: Use _Float128/_Complex _Float128 types instead of
__float128 and _Complex float __attribute__((mode(TC))), if
USE_IEC_60559 is defined, use f128 suffixes instead of q and
define GFC_REAL_17_USE_IEC_60559.
* libgfortran.h: Don't include quadmath_weak.h if USE_IEC_60559 is
defined.
(GFC_REAL_16_INFINITY, GFC_REAL_16_QUIET_NAN): Define
for GFC_REAL_16_USE_IEC_60559 differently.
* caf/single.c (convert_type): Use _Float128/_Complex _Float128
instead of __float128 and _Complex float __attribute__((mode(TC))).
For HAVE_GFC_REAL_10 when HAVE_GFC_REAL_16 isn't defined use
_Complex long double instead of long double.
* ieee/issignaling_fallback.h (ieee854_float128_shape_type): Use
_Float128 instead of __float128.
(__issignalingf128): Change argument type to _Float128.
(issignaling): Use _Float128 instead of __float128 in _Generic.
* intrinsics/cshift0.c (cshift0): Use _Float128 instead of __float128
in a comment. Fix a comment typo, logn double -> long double.
* intrinsics/erfc_scaled.c (_THRESH, _M_2_SQRTPI, _INF, _ERFC, _EXP):
Use different definitions if GFC_REAL_16_USE_IEC_60559.
(_THRESH, _M_2_SQRTPI): Use GFC_REAL_17_LITERAL macro.
(_ERFC, _EXP): Use different definitions if GFC_REAL_17_USE_IEC_60559.
* intrinsics/spread_generic.c (spread, spread_scalar): Use _Float128
instead of __float128 in a comment. Fix a comment typo,
logn double -> long double.
* intrinsics/trigd.c (ENABLE_SIND, ENABLE_COSD, ENABLE_TAND): Handle
GFC_REAL_16_USE_IEC_60559.
* intrinsics/pack_generic.c (pack): Use _Float128 instead of
__float128 in a comment. Fix a comment typo, logn double ->
long double.
* intrinsics/unpack_generic.c (unpack1, unpack0): Likewise.
* runtime/in_pack_generic.c (internal_pack): Likewise.
* runtime/in_unpack_generic.c (internal_unpack): Likewise.
* io/read.c (convert_real, convert_infnan): Handle
GFC_REAL_16_USE_IEC_60559 and GFC_REAL_17_USE_IEC_60559.
* io/transfer128.c (tmp1, tmp2): Don't define if libquadmath
isn't needed.
* io/write_float.def (gfor_strfromf128): New function.
(DTOA2Q, FDTOA2Q): Define differently if
GFC_REAL_16_USE_IEC_60559 or GFC_REAL_17_USE_IEC_60559.
* m4/mtype.m4: Use different suffix if GFC_REAL_16_USE_IEC_60559
or GFC_REAL_17_USE_IEC_60559.
* config.h.in: Regenerated.
* configure: Regenerated.
* Makefile.in: Regenerated.
* generated/bessel_r16.c: Regenerated.
* generated/bessel_r17.c: Regenerated.
* generated/norm2_r16.c: Regenerated.
* generated/norm2_r17.c: Regenerated.
660 lines
19 KiB
C
660 lines
19 KiB
C
/* Generic implementation of the PACK intrinsic
|
|
Copyright (C) 2002-2022 Free Software Foundation, Inc.
|
|
Contributed 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>
|
|
|
|
/* PACK is specified as follows:
|
|
|
|
13.14.80 PACK (ARRAY, MASK, [VECTOR])
|
|
|
|
Description: Pack an array into an array of rank one under the
|
|
control of a mask.
|
|
|
|
Class: Transformational function.
|
|
|
|
Arguments:
|
|
ARRAY may be of any type. It shall not be scalar.
|
|
MASK shall be of type LOGICAL. It shall be conformable with ARRAY.
|
|
VECTOR (optional) shall be of the same type and type parameters
|
|
as ARRAY. VECTOR shall have at least as many elements as
|
|
there are true elements in MASK. If MASK is a scalar
|
|
with the value true, VECTOR shall have at least as many
|
|
elements as there are in ARRAY.
|
|
|
|
Result Characteristics: The result is an array of rank one with the
|
|
same type and type parameters as ARRAY. If VECTOR is present, the
|
|
result size is that of VECTOR; otherwise, the result size is the
|
|
number /t/ of true elements in MASK unless MASK is scalar with the
|
|
value true, in which case the result size is the size of ARRAY.
|
|
|
|
Result Value: Element /i/ of the result is the element of ARRAY
|
|
that corresponds to the /i/th true element of MASK, taking elements
|
|
in array element order, for /i/ = 1, 2, ..., /t/. If VECTOR is
|
|
present and has size /n/ > /t/, element /i/ of the result has the
|
|
value VECTOR(/i/), for /i/ = /t/ + 1, ..., /n/.
|
|
|
|
Examples: The nonzero elements of an array M with the value
|
|
| 0 0 0 |
|
|
| 9 0 0 | may be "gathered" by the function PACK. The result of
|
|
| 0 0 7 |
|
|
PACK (M, MASK = M.NE.0) is [9,7] and the result of PACK (M, M.NE.0,
|
|
VECTOR = (/ 2,4,6,8,10,12 /)) is [9,7,6,8,10,12].
|
|
|
|
There are two variants of the PACK intrinsic: one, where MASK is
|
|
array valued, and the other one where MASK is scalar. */
|
|
|
|
static void
|
|
pack_internal (gfc_array_char *ret, const gfc_array_char *array,
|
|
const gfc_array_l1 *mask, const gfc_array_char *vector,
|
|
index_type size)
|
|
{
|
|
/* r.* indicates the return array. */
|
|
index_type rstride0;
|
|
char * restrict rptr;
|
|
/* s.* indicates the source array. */
|
|
index_type sstride[GFC_MAX_DIMENSIONS];
|
|
index_type sstride0;
|
|
const char *sptr;
|
|
/* 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];
|
|
bool zero_sized;
|
|
index_type n;
|
|
index_type dim;
|
|
index_type nelem;
|
|
index_type total;
|
|
int mask_kind;
|
|
|
|
dim = GFC_DESCRIPTOR_RANK (array);
|
|
|
|
sptr = array->base_addr;
|
|
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
|
|
)
|
|
{
|
|
/* Don't 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");
|
|
|
|
zero_sized = false;
|
|
for (n = 0; n < dim; n++)
|
|
{
|
|
count[n] = 0;
|
|
extent[n] = GFC_DESCRIPTOR_EXTENT(array,n);
|
|
if (extent[n] <= 0)
|
|
zero_sized = true;
|
|
sstride[n] = GFC_DESCRIPTOR_STRIDE_BYTES(array,n);
|
|
mstride[n] = GFC_DESCRIPTOR_STRIDE_BYTES(mask,n);
|
|
}
|
|
if (sstride[0] == 0)
|
|
sstride[0] = size;
|
|
if (mstride[0] == 0)
|
|
mstride[0] = mask_kind;
|
|
|
|
if (zero_sized)
|
|
sptr = NULL;
|
|
else
|
|
sptr = array->base_addr;
|
|
|
|
if (ret->base_addr == NULL || unlikely (compile_options.bounds_check))
|
|
{
|
|
/* Count the elements, either for allocating memory or
|
|
for bounds checking. */
|
|
|
|
if (vector != NULL)
|
|
{
|
|
/* The return array will have as many
|
|
elements as there are in VECTOR. */
|
|
total = GFC_DESCRIPTOR_EXTENT(vector,0);
|
|
}
|
|
else
|
|
{
|
|
/* We have to count the true elements in MASK. */
|
|
|
|
total = count_0 (mask);
|
|
}
|
|
|
|
if (ret->base_addr == NULL)
|
|
{
|
|
/* Setup the array descriptor. */
|
|
GFC_DIMENSION_SET(ret->dim[0], 0, total-1, 1);
|
|
|
|
ret->offset = 0;
|
|
/* xmallocarray allocates a single byte for zero size. */
|
|
ret->base_addr = xmallocarray (total, size);
|
|
|
|
if (total == 0)
|
|
return; /* In this case, nothing remains to be done. */
|
|
}
|
|
else
|
|
{
|
|
/* We come here because of range checking. */
|
|
index_type ret_extent;
|
|
|
|
ret_extent = GFC_DESCRIPTOR_EXTENT(ret,0);
|
|
if (total != ret_extent)
|
|
runtime_error ("Incorrect extent in return value of PACK intrinsic;"
|
|
" is %ld, should be %ld", (long int) total,
|
|
(long int) ret_extent);
|
|
}
|
|
}
|
|
|
|
rstride0 = GFC_DESCRIPTOR_STRIDE_BYTES(ret,0);
|
|
if (rstride0 == 0)
|
|
rstride0 = size;
|
|
sstride0 = sstride[0];
|
|
mstride0 = mstride[0];
|
|
rptr = ret->base_addr;
|
|
|
|
while (sptr && mptr)
|
|
{
|
|
/* Test this element. */
|
|
if (*mptr)
|
|
{
|
|
/* Add it. */
|
|
memcpy (rptr, sptr, size);
|
|
rptr += rstride0;
|
|
}
|
|
/* Advance to the next element. */
|
|
sptr += sstride0;
|
|
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. */
|
|
sptr -= sstride[n] * extent[n];
|
|
mptr -= mstride[n] * extent[n];
|
|
n++;
|
|
if (n >= dim)
|
|
{
|
|
/* Break out of the loop. */
|
|
sptr = NULL;
|
|
break;
|
|
}
|
|
else
|
|
{
|
|
count[n]++;
|
|
sptr += sstride[n];
|
|
mptr += mstride[n];
|
|
}
|
|
}
|
|
}
|
|
|
|
/* Add any remaining elements from VECTOR. */
|
|
if (vector)
|
|
{
|
|
n = GFC_DESCRIPTOR_EXTENT(vector,0);
|
|
nelem = ((rptr - ret->base_addr) / rstride0);
|
|
if (n > nelem)
|
|
{
|
|
sstride0 = GFC_DESCRIPTOR_STRIDE_BYTES(vector,0);
|
|
if (sstride0 == 0)
|
|
sstride0 = size;
|
|
|
|
sptr = vector->base_addr + sstride0 * nelem;
|
|
n -= nelem;
|
|
while (n--)
|
|
{
|
|
memcpy (rptr, sptr, size);
|
|
rptr += rstride0;
|
|
sptr += sstride0;
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
extern void pack (gfc_array_char *, const gfc_array_char *,
|
|
const gfc_array_l1 *, const gfc_array_char *);
|
|
export_proto(pack);
|
|
|
|
void
|
|
pack (gfc_array_char *ret, const gfc_array_char *array,
|
|
const gfc_array_l1 *mask, const gfc_array_char *vector)
|
|
{
|
|
index_type type_size;
|
|
index_type size;
|
|
|
|
type_size = GFC_DTYPE_TYPE_SIZE(array);
|
|
|
|
switch(type_size)
|
|
{
|
|
case GFC_DTYPE_LOGICAL_1:
|
|
case GFC_DTYPE_INTEGER_1:
|
|
pack_i1 ((gfc_array_i1 *) ret, (gfc_array_i1 *) array,
|
|
(gfc_array_l1 *) mask, (gfc_array_i1 *) vector);
|
|
return;
|
|
|
|
case GFC_DTYPE_LOGICAL_2:
|
|
case GFC_DTYPE_INTEGER_2:
|
|
pack_i2 ((gfc_array_i2 *) ret, (gfc_array_i2 *) array,
|
|
(gfc_array_l1 *) mask, (gfc_array_i2 *) vector);
|
|
return;
|
|
|
|
case GFC_DTYPE_LOGICAL_4:
|
|
case GFC_DTYPE_INTEGER_4:
|
|
pack_i4 ((gfc_array_i4 *) ret, (gfc_array_i4 *) array,
|
|
(gfc_array_l1 *) mask, (gfc_array_i4 *) vector);
|
|
return;
|
|
|
|
case GFC_DTYPE_LOGICAL_8:
|
|
case GFC_DTYPE_INTEGER_8:
|
|
pack_i8 ((gfc_array_i8 *) ret, (gfc_array_i8 *) array,
|
|
(gfc_array_l1 *) mask, (gfc_array_i8 *) vector);
|
|
return;
|
|
|
|
#ifdef HAVE_GFC_INTEGER_16
|
|
case GFC_DTYPE_LOGICAL_16:
|
|
case GFC_DTYPE_INTEGER_16:
|
|
pack_i16 ((gfc_array_i16 *) ret, (gfc_array_i16 *) array,
|
|
(gfc_array_l1 *) mask, (gfc_array_i16 *) vector);
|
|
return;
|
|
#endif
|
|
|
|
case GFC_DTYPE_REAL_4:
|
|
pack_r4 ((gfc_array_r4 *) ret, (gfc_array_r4 *) array,
|
|
(gfc_array_l1 *) mask, (gfc_array_r4 *) vector);
|
|
return;
|
|
|
|
case GFC_DTYPE_REAL_8:
|
|
pack_r8 ((gfc_array_r8 *) ret, (gfc_array_r8 *) array,
|
|
(gfc_array_l1 *) mask, (gfc_array_r8 *) vector);
|
|
return;
|
|
|
|
/* FIXME: This here is a hack, which will have to be removed when
|
|
the array descriptor is reworked. Currently, we don't store the
|
|
kind value for the type, but only the size. Because on targets with
|
|
_Float128, we have sizeof(long double) == sizeof(_Float128),
|
|
we cannot discriminate here and have to fall back to the generic
|
|
handling (which is suboptimal). */
|
|
#if !defined(GFC_REAL_16_IS_FLOAT128)
|
|
# ifdef HAVE_GFC_REAL_10
|
|
case GFC_DTYPE_REAL_10:
|
|
pack_r10 ((gfc_array_r10 *) ret, (gfc_array_r10 *) array,
|
|
(gfc_array_l1 *) mask, (gfc_array_r10 *) vector);
|
|
return;
|
|
# endif
|
|
|
|
# ifdef HAVE_GFC_REAL_16
|
|
case GFC_DTYPE_REAL_16:
|
|
pack_r16 ((gfc_array_r16 *) ret, (gfc_array_r16 *) array,
|
|
(gfc_array_l1 *) mask, (gfc_array_r16 *) vector);
|
|
return;
|
|
# endif
|
|
#endif
|
|
|
|
case GFC_DTYPE_COMPLEX_4:
|
|
pack_c4 ((gfc_array_c4 *) ret, (gfc_array_c4 *) array,
|
|
(gfc_array_l1 *) mask, (gfc_array_c4 *) vector);
|
|
return;
|
|
|
|
case GFC_DTYPE_COMPLEX_8:
|
|
pack_c8 ((gfc_array_c8 *) ret, (gfc_array_c8 *) array,
|
|
(gfc_array_l1 *) mask, (gfc_array_c8 *) vector);
|
|
return;
|
|
|
|
/* FIXME: This here is a hack, which will have to be removed when
|
|
the array descriptor is reworked. Currently, we don't store the
|
|
kind value for the type, but only the size. Because on targets with
|
|
_Float128, we have sizeof(long double) == sizeof(_Float128),
|
|
we cannot discriminate here and have to fall back to the generic
|
|
handling (which is suboptimal). */
|
|
#if !defined(GFC_REAL_16_IS_FLOAT128)
|
|
# ifdef HAVE_GFC_COMPLEX_10
|
|
case GFC_DTYPE_COMPLEX_10:
|
|
pack_c10 ((gfc_array_c10 *) ret, (gfc_array_c10 *) array,
|
|
(gfc_array_l1 *) mask, (gfc_array_c10 *) vector);
|
|
return;
|
|
# endif
|
|
|
|
# ifdef HAVE_GFC_COMPLEX_16
|
|
case GFC_DTYPE_COMPLEX_16:
|
|
pack_c16 ((gfc_array_c16 *) ret, (gfc_array_c16 *) array,
|
|
(gfc_array_l1 *) mask, (gfc_array_c16 *) vector);
|
|
return;
|
|
# endif
|
|
#endif
|
|
}
|
|
|
|
/* For other types, let's check the actual alignment of the data pointers.
|
|
If they are aligned, we can safely call the unpack functions. */
|
|
|
|
switch (GFC_DESCRIPTOR_SIZE (array))
|
|
{
|
|
case 1:
|
|
pack_i1 ((gfc_array_i1 *) ret, (gfc_array_i1 *) array,
|
|
(gfc_array_l1 *) mask, (gfc_array_i1 *) vector);
|
|
return;
|
|
|
|
case 2:
|
|
if (GFC_UNALIGNED_2(ret->base_addr) || GFC_UNALIGNED_2(array->base_addr)
|
|
|| (vector && GFC_UNALIGNED_2(vector->base_addr)))
|
|
break;
|
|
else
|
|
{
|
|
pack_i2 ((gfc_array_i2 *) ret, (gfc_array_i2 *) array,
|
|
(gfc_array_l1 *) mask, (gfc_array_i2 *) vector);
|
|
return;
|
|
}
|
|
|
|
case 4:
|
|
if (GFC_UNALIGNED_4(ret->base_addr) || GFC_UNALIGNED_4(array->base_addr)
|
|
|| (vector && GFC_UNALIGNED_4(vector->base_addr)))
|
|
break;
|
|
else
|
|
{
|
|
pack_i4 ((gfc_array_i4 *) ret, (gfc_array_i4 *) array,
|
|
(gfc_array_l1 *) mask, (gfc_array_i4 *) vector);
|
|
return;
|
|
}
|
|
|
|
case 8:
|
|
if (GFC_UNALIGNED_8(ret->base_addr) || GFC_UNALIGNED_8(array->base_addr)
|
|
|| (vector && GFC_UNALIGNED_8(vector->base_addr)))
|
|
break;
|
|
else
|
|
{
|
|
pack_i8 ((gfc_array_i8 *) ret, (gfc_array_i8 *) array,
|
|
(gfc_array_l1 *) mask, (gfc_array_i8 *) vector);
|
|
return;
|
|
}
|
|
|
|
#ifdef HAVE_GFC_INTEGER_16
|
|
case 16:
|
|
if (GFC_UNALIGNED_16(ret->base_addr) || GFC_UNALIGNED_16(array->base_addr)
|
|
|| (vector && GFC_UNALIGNED_16(vector->base_addr)))
|
|
break;
|
|
else
|
|
{
|
|
pack_i16 ((gfc_array_i16 *) ret, (gfc_array_i16 *) array,
|
|
(gfc_array_l1 *) mask, (gfc_array_i16 *) vector);
|
|
return;
|
|
}
|
|
#endif
|
|
default:
|
|
break;
|
|
}
|
|
|
|
size = GFC_DESCRIPTOR_SIZE (array);
|
|
pack_internal (ret, array, mask, vector, size);
|
|
}
|
|
|
|
|
|
extern void pack_char (gfc_array_char *, GFC_INTEGER_4, const gfc_array_char *,
|
|
const gfc_array_l1 *, const gfc_array_char *,
|
|
GFC_INTEGER_4, GFC_INTEGER_4);
|
|
export_proto(pack_char);
|
|
|
|
void
|
|
pack_char (gfc_array_char *ret,
|
|
GFC_INTEGER_4 ret_length __attribute__((unused)),
|
|
const gfc_array_char *array, const gfc_array_l1 *mask,
|
|
const gfc_array_char *vector, GFC_INTEGER_4 array_length,
|
|
GFC_INTEGER_4 vector_length __attribute__((unused)))
|
|
{
|
|
pack_internal (ret, array, mask, vector, array_length);
|
|
}
|
|
|
|
|
|
extern void pack_char4 (gfc_array_char *, GFC_INTEGER_4, const gfc_array_char *,
|
|
const gfc_array_l1 *, const gfc_array_char *,
|
|
GFC_INTEGER_4, GFC_INTEGER_4);
|
|
export_proto(pack_char4);
|
|
|
|
void
|
|
pack_char4 (gfc_array_char *ret,
|
|
GFC_INTEGER_4 ret_length __attribute__((unused)),
|
|
const gfc_array_char *array, const gfc_array_l1 *mask,
|
|
const gfc_array_char *vector, GFC_INTEGER_4 array_length,
|
|
GFC_INTEGER_4 vector_length __attribute__((unused)))
|
|
{
|
|
pack_internal (ret, array, mask, vector, array_length * sizeof (gfc_char4_t));
|
|
}
|
|
|
|
|
|
static void
|
|
pack_s_internal (gfc_array_char *ret, const gfc_array_char *array,
|
|
const GFC_LOGICAL_4 *mask, const gfc_array_char *vector,
|
|
index_type size)
|
|
{
|
|
/* r.* indicates the return array. */
|
|
index_type rstride0;
|
|
char *rptr;
|
|
/* s.* indicates the source array. */
|
|
index_type sstride[GFC_MAX_DIMENSIONS];
|
|
index_type sstride0;
|
|
const char *sptr;
|
|
|
|
index_type count[GFC_MAX_DIMENSIONS];
|
|
index_type extent[GFC_MAX_DIMENSIONS];
|
|
index_type n;
|
|
index_type dim;
|
|
index_type ssize;
|
|
index_type nelem;
|
|
index_type total;
|
|
|
|
dim = GFC_DESCRIPTOR_RANK (array);
|
|
/* Initialize sstride[0] to avoid -Wmaybe-uninitialized
|
|
complaints. */
|
|
sstride[0] = size;
|
|
ssize = 1;
|
|
for (n = 0; n < dim; n++)
|
|
{
|
|
count[n] = 0;
|
|
extent[n] = GFC_DESCRIPTOR_EXTENT(array,n);
|
|
if (extent[n] < 0)
|
|
extent[n] = 0;
|
|
|
|
sstride[n] = GFC_DESCRIPTOR_STRIDE_BYTES(array,n);
|
|
ssize *= extent[n];
|
|
}
|
|
if (sstride[0] == 0)
|
|
sstride[0] = size;
|
|
|
|
sstride0 = sstride[0];
|
|
|
|
if (ssize != 0)
|
|
sptr = array->base_addr;
|
|
else
|
|
sptr = NULL;
|
|
|
|
if (ret->base_addr == NULL)
|
|
{
|
|
/* Allocate the memory for the result. */
|
|
|
|
if (vector != NULL)
|
|
{
|
|
/* The return array will have as many elements as there are
|
|
in vector. */
|
|
total = GFC_DESCRIPTOR_EXTENT(vector,0);
|
|
if (total <= 0)
|
|
{
|
|
total = 0;
|
|
vector = NULL;
|
|
}
|
|
}
|
|
else
|
|
{
|
|
if (*mask)
|
|
{
|
|
/* The result array will have as many elements as the input
|
|
array. */
|
|
total = extent[0];
|
|
for (n = 1; n < dim; n++)
|
|
total *= extent[n];
|
|
}
|
|
else
|
|
/* The result array will be empty. */
|
|
total = 0;
|
|
}
|
|
|
|
/* Setup the array descriptor. */
|
|
GFC_DIMENSION_SET(ret->dim[0],0,total-1,1);
|
|
|
|
ret->offset = 0;
|
|
|
|
ret->base_addr = xmallocarray (total, size);
|
|
|
|
if (total == 0)
|
|
return;
|
|
}
|
|
|
|
rstride0 = GFC_DESCRIPTOR_STRIDE_BYTES(ret,0);
|
|
if (rstride0 == 0)
|
|
rstride0 = size;
|
|
rptr = ret->base_addr;
|
|
|
|
/* The remaining possibilities are now:
|
|
If MASK is .TRUE., we have to copy the source array into the
|
|
result array. We then have to fill it up with elements from VECTOR.
|
|
If MASK is .FALSE., we have to copy VECTOR into the result
|
|
array. If VECTOR were not present we would have already returned. */
|
|
|
|
if (*mask && ssize != 0)
|
|
{
|
|
while (sptr)
|
|
{
|
|
/* Add this element. */
|
|
memcpy (rptr, sptr, size);
|
|
rptr += rstride0;
|
|
|
|
/* Advance to the next element. */
|
|
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. */
|
|
sptr -= sstride[n] * extent[n];
|
|
n++;
|
|
if (n >= dim)
|
|
{
|
|
/* Break out of the loop. */
|
|
sptr = NULL;
|
|
break;
|
|
}
|
|
else
|
|
{
|
|
count[n]++;
|
|
sptr += sstride[n];
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
/* Add any remaining elements from VECTOR. */
|
|
if (vector)
|
|
{
|
|
n = GFC_DESCRIPTOR_EXTENT(vector,0);
|
|
nelem = ((rptr - ret->base_addr) / rstride0);
|
|
if (n > nelem)
|
|
{
|
|
sstride0 = GFC_DESCRIPTOR_STRIDE_BYTES(vector,0);
|
|
if (sstride0 == 0)
|
|
sstride0 = size;
|
|
|
|
sptr = vector->base_addr + sstride0 * nelem;
|
|
n -= nelem;
|
|
while (n--)
|
|
{
|
|
memcpy (rptr, sptr, size);
|
|
rptr += rstride0;
|
|
sptr += sstride0;
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
extern void pack_s (gfc_array_char *ret, const gfc_array_char *array,
|
|
const GFC_LOGICAL_4 *, const gfc_array_char *);
|
|
export_proto(pack_s);
|
|
|
|
void
|
|
pack_s (gfc_array_char *ret, const gfc_array_char *array,
|
|
const GFC_LOGICAL_4 *mask, const gfc_array_char *vector)
|
|
{
|
|
pack_s_internal (ret, array, mask, vector, GFC_DESCRIPTOR_SIZE (array));
|
|
}
|
|
|
|
|
|
extern void pack_s_char (gfc_array_char *ret, GFC_INTEGER_4,
|
|
const gfc_array_char *array, const GFC_LOGICAL_4 *,
|
|
const gfc_array_char *, GFC_INTEGER_4,
|
|
GFC_INTEGER_4);
|
|
export_proto(pack_s_char);
|
|
|
|
void
|
|
pack_s_char (gfc_array_char *ret,
|
|
GFC_INTEGER_4 ret_length __attribute__((unused)),
|
|
const gfc_array_char *array, const GFC_LOGICAL_4 *mask,
|
|
const gfc_array_char *vector, GFC_INTEGER_4 array_length,
|
|
GFC_INTEGER_4 vector_length __attribute__((unused)))
|
|
{
|
|
pack_s_internal (ret, array, mask, vector, array_length);
|
|
}
|
|
|
|
|
|
extern void pack_s_char4 (gfc_array_char *ret, GFC_INTEGER_4,
|
|
const gfc_array_char *array, const GFC_LOGICAL_4 *,
|
|
const gfc_array_char *, GFC_INTEGER_4,
|
|
GFC_INTEGER_4);
|
|
export_proto(pack_s_char4);
|
|
|
|
void
|
|
pack_s_char4 (gfc_array_char *ret,
|
|
GFC_INTEGER_4 ret_length __attribute__((unused)),
|
|
const gfc_array_char *array, const GFC_LOGICAL_4 *mask,
|
|
const gfc_array_char *vector, GFC_INTEGER_4 array_length,
|
|
GFC_INTEGER_4 vector_length __attribute__((unused)))
|
|
{
|
|
pack_s_internal (ret, array, mask, vector,
|
|
array_length * sizeof (gfc_char4_t));
|
|
}
|