[PATCH] libgfortran: Use __builtin_issignaling in libgfortran
Hi!
The following patch makes use of the new __builtin_issignaling,
so it no longer needs the fallback implementation and can use
the builtin even where glibc provides the macro.
Bootstrapped/regtested on x86_64-linux, i686-linux, powerpc64le-linux
and powerpc64le-linux, ok for trunk?
2022-08-15 Jakub Jelinek
* ieee/ieee_helper.c: Don't include issignaling_fallback.h.
(CLASSMACRO): Use __builtin_issignaling instead of issignaling.
* ieee/issignaling_fallback.h: Removed.
--- libgfortran/ieee/ieee_helper.c.jj 2022-06-27 15:34:47.111928150 +0200
+++ libgfortran/ieee/ieee_helper.c 2022-08-12 13:21:00.922306862 +0200
@@ -26,13 +26,6 @@ see the files COPYING3 and COPYING.RUNTI
#include "libgfortran.h"
-/* Check support for issignaling macro. If not, we include our own
- fallback implementation. */
-#ifndef issignaling
-# include "issignaling_fallback.h"
-#endif
-
-
/* Prototypes. */
extern int ieee_class_helper_4 (GFC_REAL_4 *);
@@ -94,7 +87,7 @@ enum {
\
if (res == IEEE_QUIET_NAN) \
{ \
- if (issignaling (*value)) \
+ if (__builtin_issignaling (*value)) \
return IEEE_SIGNALING_NAN; \
else \
return IEEE_QUIET_NAN; \
--- libgfortran/ieee/issignaling_fallback.h.jj 2022-06-28 13:14:45.332799201
+0200
+++ libgfortran/ieee/issignaling_fallback.h 2022-08-12 13:20:17.784877531
+0200
@@ -1,251 +0,0 @@
-/* Fallback implementation of issignaling macro.
- Copyright (C) 2022 Free Software Foundation, Inc.
- Contributed by Francois-Xavier Coudert
-
-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
-
[PATCH] fortran: Expand ieee_arithmetic module's ieee_class inline [PR106579]
Hi!
The following patch expands IEEE_CLASS inline in the FE, using the
__builtin_fpclassify, __builtin_signbit and the new __builtin_issignaling
builtins.
Bootstrapped/regtested on x86_64-linux, i686-linux, powerpc64le-linux
and powerpc64-linux, ok for trunk?
2022-08-15 Jakub Jelinek
PR fortran/106579
gcc/fortran/
* f95-lang.cc (gfc_init_builtin_functions): Initialize
BUILT_IN_FPCLASSIFY.
* libgfortran.h (IEEE_OTHER_VALUE, IEEE_SIGNALING_NAN,
IEEE_QUIET_NAN, IEEE_NEGATIVE_INF, IEEE_NEGATIVE_NORMAL,
IEEE_NEGATIVE_DENORMAL, IEEE_NEGATIVE_SUBNORMAL,
IEEE_NEGATIVE_ZERO, IEEE_POSITIVE_ZERO, IEEE_POSITIVE_DENORMAL,
IEEE_POSITIVE_SUBNORMAL, IEEE_POSITIVE_NORMAL, IEEE_POSITIVE_INF):
New enum.
* trans-intrinsic.cc (conv_intrinsic_ieee_class): New function.
(gfc_conv_ieee_arithmetic_function): Handle ieee_class.
libgfortran/
* ieee/ieee_helper.c (IEEE_OTHER_VALUE, IEEE_SIGNALING_NAN,
IEEE_QUIET_NAN, IEEE_NEGATIVE_INF, IEEE_NEGATIVE_NORMAL,
IEEE_NEGATIVE_DENORMAL, IEEE_NEGATIVE_SUBNORMAL,
IEEE_NEGATIVE_ZERO, IEEE_POSITIVE_ZERO, IEEE_POSITIVE_DENORMAL,
IEEE_POSITIVE_SUBNORMAL, IEEE_POSITIVE_NORMAL, IEEE_POSITIVE_INF):
Move to gcc/fortran/libgfortran.h.
--- gcc/fortran/f95-lang.cc.jj 2022-08-12 17:06:33.906598328 +0200
+++ gcc/fortran/f95-lang.cc 2022-08-12 18:39:47.727073699 +0200
@@ -1017,8 +1017,9 @@ gfc_init_builtin_functions (void)
"__builtin_issignaling", ATTR_CONST_NOTHROW_LEAF_LIST);
gfc_define_builtin ("__builtin_signbit", ftype, BUILT_IN_SIGNBIT,
"__builtin_signbit", ATTR_CONST_NOTHROW_LEAF_LIST);
+ gfc_define_builtin ("__builtin_fpclassify", ftype, BUILT_IN_FPCLASSIFY,
+ "__builtin_fpclassify", ATTR_CONST_NOTHROW_LEAF_LIST);
- ftype = build_function_type (integer_type_node, NULL_TREE);
gfc_define_builtin ("__builtin_isless", ftype, BUILT_IN_ISLESS,
"__builtin_isless", ATTR_CONST_NOTHROW_LEAF_LIST);
gfc_define_builtin ("__builtin_islessequal", ftype, BUILT_IN_ISLESSEQUAL,
--- gcc/fortran/libgfortran.h.jj2022-05-31 11:33:51.550250610 +0200
+++ gcc/fortran/libgfortran.h 2022-08-12 17:22:33.210947170 +0200
@@ -187,3 +187,23 @@ typedef enum
BT_ASSUMED, BT_UNION, BT_BOZ
}
bt;
+
+/* Enumeration of the possible floating-point types. These values
+ correspond to the hidden arguments of the IEEE_CLASS_TYPE
+ derived-type of IEEE_ARITHMETIC. */
+
+enum {
+ IEEE_OTHER_VALUE = 0,
+ IEEE_SIGNALING_NAN,
+ IEEE_QUIET_NAN,
+ IEEE_NEGATIVE_INF,
+ IEEE_NEGATIVE_NORMAL,
+ IEEE_NEGATIVE_DENORMAL,
+ IEEE_NEGATIVE_SUBNORMAL = IEEE_NEGATIVE_DENORMAL,
+ IEEE_NEGATIVE_ZERO,
+ IEEE_POSITIVE_ZERO,
+ IEEE_POSITIVE_DENORMAL,
+ IEEE_POSITIVE_SUBNORMAL = IEEE_POSITIVE_DENORMAL,
+ IEEE_POSITIVE_NORMAL,
+ IEEE_POSITIVE_INF
+};
--- gcc/fortran/trans-intrinsic.cc.jj 2022-06-28 13:14:45.322799333 +0200
+++ gcc/fortran/trans-intrinsic.cc 2022-08-12 18:51:28.095927643 +0200
@@ -10013,6 +10013,78 @@ conv_intrinsic_ieee_copy_sign (gfc_se *
}
+/* Generate code for IEEE_CLASS. */
+
+static void
+conv_intrinsic_ieee_class (gfc_se *se, gfc_expr *expr)
+{
+ tree arg, c, t1, t2, t3, t4;
+
+ /* Convert arg, evaluate it only once. */
+ conv_ieee_function_args (se, expr, &arg, 1);
+ arg = gfc_evaluate_now (arg, &se->pre);
+
+ c = build_call_expr_loc (input_location,
+ builtin_decl_explicit (BUILT_IN_FPCLASSIFY), 6,
+ build_int_cst (integer_type_node, IEEE_QUIET_NAN),
+ build_int_cst (integer_type_node,
+ IEEE_POSITIVE_INF),
+ build_int_cst (integer_type_node,
+ IEEE_POSITIVE_NORMAL),
+ build_int_cst (integer_type_node,
+ IEEE_POSITIVE_DENORMAL),
+ build_int_cst (integer_type_node,
+ IEEE_POSITIVE_ZERO),
+ arg);
+ c = gfc_evaluate_now (c, &se->pre);
+ t1 = fold_build2_loc (input_location, EQ_EXPR, logical_type_node,
+ c, build_int_cst (integer_type_node,
+ IEEE_QUIET_NAN));
+ t2 = build_call_expr_loc (input_location,
+ builtin_decl_explicit (BUILT_IN_ISSIGNALING), 1,
+ arg);
+ t2 = fold_build2_loc (input_location, NE_EXPR, logical_type_node,
+ t2, build_zero_cst (TREE_TYPE (t2)));
+ t1 = fold_build2_loc (input_location, TRUTH_AND_EXPR,
+ logical_type_node, t1, t2);
+ t3 = fold_build2_loc (input_location, GE_EXPR, logical_type_node,
+ c, build_int_cst (integer_type_node,
+ IEEE_POSITIVE_ZERO));
+ t4 = build_call_e
[PATCH] fortran: Expand ieee_arithmetic module's ieee_value inline [PR106579]
Hi!
The following patch expands IEEE_VALUE function inline in the FE.
Bootstrapped/regtested on x86_64-linux, i686-linux, powerpc64le-linux
and powerpc64-linux, ok for trunk?
2022-08-15 Jakub Jelinek
PR fortran/106579
* trans-intrinsic.cc: Include realmpfr.h.
(conv_intrinsic_ieee_value): New function.
(gfc_conv_ieee_arithmetic_function): Handle ieee_value.
--- gcc/fortran/trans-intrinsic.cc.jj 2022-08-12 18:51:28.095927643 +0200
+++ gcc/fortran/trans-intrinsic.cc 2022-08-13 13:24:37.446768877 +0200
@@ -41,6 +41,7 @@ along with GCC; see the file COPYING3.
#include "trans-array.h"
#include "dependency.h"/* For CAF array alias analysis. */
#include "attribs.h"
+#include "realmpfr.h"
/* Only for gfc_trans_assign and gfc_trans_pointer_assign. */
@@ -10085,6 +10086,115 @@ conv_intrinsic_ieee_class (gfc_se *se, g
}
+/* Generate code for IEEE_VALUE. */
+
+static void
+conv_intrinsic_ieee_value (gfc_se *se, gfc_expr *expr)
+{
+ tree args[2], arg, ret, tmp;
+ stmtblock_t body;
+
+ /* Convert args, evaluate the second one only once. */
+ conv_ieee_function_args (se, expr, args, 2);
+ arg = gfc_evaluate_now (args[1], &se->pre);
+
+ tree type = TREE_TYPE (arg);
+ gcc_assert (TREE_CODE (type) == RECORD_TYPE);
+ tree field = NULL_TREE;
+ for (tree f = TYPE_FIELDS (type); f != NULL_TREE; f = DECL_CHAIN (f))
+if (TREE_CODE (f) == FIELD_DECL)
+ {
+ gcc_assert (field == NULL_TREE);
+ field = f;
+ }
+ gcc_assert (field);
+ arg = fold_build3_loc (input_location, COMPONENT_REF, TREE_TYPE (field),
+arg, field, NULL_TREE);
+ arg = gfc_evaluate_now (arg, &se->pre);
+
+ type = gfc_typenode_for_spec (&expr->ts);
+ gcc_assert (TREE_CODE (type) == REAL_TYPE);
+ ret = gfc_create_var (type, NULL);
+
+ gfc_init_block (&body);
+
+ tree end_label = gfc_build_label_decl (NULL_TREE);
+ for (int c = IEEE_SIGNALING_NAN; c <= IEEE_POSITIVE_INF; ++c)
+{
+ tree label = gfc_build_label_decl (NULL_TREE);
+ tree low = build_int_cst (TREE_TYPE (arg), c);
+ tmp = build_case_label (low, low, label);
+ gfc_add_expr_to_block (&body, tmp);
+
+ REAL_VALUE_TYPE real;
+ int k;
+ switch (c)
+ {
+ case IEEE_SIGNALING_NAN:
+ real_nan (&real, "", 0, TYPE_MODE (type));
+ break;
+ case IEEE_QUIET_NAN:
+ real_nan (&real, "", 1, TYPE_MODE (type));
+ break;
+ case IEEE_NEGATIVE_INF:
+ real_inf (&real);
+ real = real_value_negate (&real);
+ break;
+ case IEEE_NEGATIVE_NORMAL:
+ real_from_integer (&real, TYPE_MODE (type), -42, SIGNED);
+ break;
+ case IEEE_NEGATIVE_DENORMAL:
+ k = gfc_validate_kind (BT_REAL, expr->ts.kind, false);
+ real_from_mpfr (&real, gfc_real_kinds[k].tiny,
+ type, GFC_RND_MODE);
+ real_arithmetic (&real, RDIV_EXPR, &real, &dconst2);
+ real = real_value_negate (&real);
+ break;
+ case IEEE_NEGATIVE_ZERO:
+ real_from_integer (&real, TYPE_MODE (type), 0, SIGNED);
+ real = real_value_negate (&real);
+ break;
+ case IEEE_POSITIVE_ZERO:
+ /* Make this also the default: label. */
+ label = gfc_build_label_decl (NULL_TREE);
+ tmp = build_case_label (NULL_TREE, NULL_TREE, label);
+ gfc_add_expr_to_block (&body, tmp);
+ real_from_integer (&real, TYPE_MODE (type), 0, SIGNED);
+ break;
+ case IEEE_POSITIVE_DENORMAL:
+ k = gfc_validate_kind (BT_REAL, expr->ts.kind, false);
+ real_from_mpfr (&real, gfc_real_kinds[k].tiny,
+ type, GFC_RND_MODE);
+ real_arithmetic (&real, RDIV_EXPR, &real, &dconst2);
+ break;
+ case IEEE_POSITIVE_NORMAL:
+ real_from_integer (&real, TYPE_MODE (type), 42, SIGNED);
+ break;
+ case IEEE_POSITIVE_INF:
+ real_inf (&real);
+ break;
+ default:
+ gcc_unreachable ();
+ }
+
+ tree val = build_real (type, real);
+ gfc_add_modify (&body, ret, val);
+
+ tmp = build1_v (GOTO_EXPR, end_label);
+ gfc_add_expr_to_block (&body, tmp);
+}
+
+ tmp = gfc_finish_block (&body);
+ tmp = fold_build2_loc (input_location, SWITCH_EXPR, NULL_TREE, arg, tmp);
+ gfc_add_expr_to_block (&se->pre, tmp);
+
+ tmp = build1_v (LABEL_EXPR, end_label);
+ gfc_add_expr_to_block (&se->pre, tmp);
+
+ se->expr = ret;
+}
+
+
/* Generate code for an intrinsic function from the IEEE_ARITHMETIC
module. */
@@ -10117,6 +10227,8 @@ gfc_conv_ieee_arithmetic_function (gfc_s
conv_intrinsic_ieee_logb_rint (se, expr, BUILT_IN_RINT);
else if (startswith (name, "ieee_class_") && ISDIGIT (name[11]))
conv_intrinsic_ieee_class (se, expr);
+ else if (startswith (name, "ieee_value_") && ISDIGIT (name[11]))
+conv_intrinsic_ieee_value (se, expr);
else
/* It is not among the functio
[PATCH, OpenMP, Fortran] requires unified_shared_memory 1/2: adjust libgfortran memory allocators
Hi, this patch is to fix the case where 'requires unified_shared_memory' doesn't work due to memory allocator mismatch. Currently this is only for OG12 (devel/omp/gcc-12), but will apply to mainline as well once those requires patches get in. Basically, under 'requires unified_shared_memory' enables the usm_transform pass, which transforms some of the expanded Fortran intrinsic code that uses __builtin_free() into 'omp_free (..., ompx_unified_shared_mem_alloc)'. The intention is to make all dynamic memory allocation use the OpenMP unified_shared_memory allocator, but there is a big gap in this, namely libgfortran. What happens in some tests are that libgfortran allocates stuff using normal malloc(), and the usm_transform generates code that frees the stuff using omp_free(), and chaos ensues. So the proper fix we believe is: to make it possible to move the entire libgfortran on to unified_shared_memory. This first patch is a mostly mechanical patch to change all references of malloc/free/calloc/realloc in libgfortran into xmalloc/xfree/xcalloc/xrealloc in libgfortran/runtime/memory.c, as well as strdup uses into a new internal xstrdup. All of libgfortran is adjusted this way, except libgfortran/caf, which is an independent library outside of libgfortran.so. The second patch of this series will present a way to switch the references of allocators in libgfortran/runtime/memory.c from the normal glibc malloc/free/etc. to omp_alloc/omp_free/etc. when 'requires unified_shared_memory' is detected. Tested on devel/omp/gcc-12. Plans is to commit there soon, but also seeking approval for mainline once the requires stuff goes in. Thanks, Chung-Lin 2022-08-15 Chung-Lin Tang libgfortran/ChangeLog: * m4/matmul_internal.m4: Adjust malloc/free to xmalloc/xfree. * generated/matmul_c10.c: Regenerate. * generated/matmul_c16.c: Likewise. * generated/matmul_c17.c: Likewise. * generated/matmul_c4.c: Likewise. * generated/matmul_c8.c: Likewise. * generated/matmul_i1.c: Likewise. * generated/matmul_i16.c: Likewise. * generated/matmul_i2.c: Likewise. * generated/matmul_i4.c: Likewise. * generated/matmul_i8.c: Likewise. * generated/matmul_r10.c: Likewise. * generated/matmul_r16.c: Likewise. * generated/matmul_r17.c: Likewise. * generated/matmul_r4.c: Likewise. * generated/matmul_r8.c: Likewise. * generated/matmulavx128_c10.c: Likewise. * generated/matmulavx128_c16.c: Likewise. * generated/matmulavx128_c17.c: Likewise. * generated/matmulavx128_c4.c: Likewise. * generated/matmulavx128_c8.c: Likewise. * generated/matmulavx128_i1.c: Likewise. * generated/matmulavx128_i16.c: Likewise. * generated/matmulavx128_i2.c: Likewise. * generated/matmulavx128_i4.c: Likewise. * generated/matmulavx128_i8.c: Likewise. * generated/matmulavx128_r10.c: Likewise. * generated/matmulavx128_r16.c: Likewise. * generated/matmulavx128_r17.c: Likewise. * generated/matmulavx128_r4.c: Likewise. * generated/matmulavx128_r8.c: Likewise. * intrinsics/access.c (access_func): Adjust free to xfree. * intrinsics/chdir.c (chdir_i4_sub): Likewise. (chdir_i8_sub): Likewise. * intrinsics/chmod.c (chmod_func): Likewise. * intrinsics/date_and_time.c (secnds): Likewise. * intrinsics/env.c (PREFIX(getenv)): Likewise. (get_environment_variable_i4): Likewise. * intrinsics/execute_command_line.c (execute_command_line): Likewise. * intrinsics/getcwd.c (getcwd_i4_sub): Likewise. * intrinsics/getlog.c (PREFIX(getlog)): Likewise. * intrinsics/link.c (link_internal): Likewise. * intrinsics/move_alloc.c (move_alloc): Likewise. * intrinsics/perror.c (perror_sub): Likewise. * intrinsics/random.c (constructor_random): Likewise. * intrinsics/rename.c (rename_internal): Likewise. * intrinsics/stat.c (stat_i4_sub_0): Likewise. (stat_i8_sub_0): Likewise. * intrinsics/symlnk.c (symlnk_internal): Likewise. * intrinsics/system.c (system_sub): Likewise. * intrinsics/unlink.c (unlink_i4_sub): Likewise. * io/async.c (update_pdt): Likewise. (async_io): Likewise. (free_async_unit): Likewise. (init_async_unit): Adjust calloc to xcalloc. (enqueue_done_id): Likewise. (enqueue_done): Likewise. (enqueue_close): Likewise. * io/async.h (MUTEX_DEBUG_ADD): Adjust malloc/free to xmalloc/xfree. * io/close.c (st_close): Adjust strdup/free to xstrdup/xfree. * io/fbuf.c (fbuf_destroy): Adjust free to xfree. * io/format.c (free_format_hash_table): Likewise. (save_parsed_format): Likewise. (free_format): Likewise. (free_format_data): Likewise. * io/intrinsics.c (ttynam):
[PATCH, OpenMP, Fortran] requires unified_shared_memory 2/2: insert USM allocators into libgfortran
After the first libgfortran memory allocator preparation patch, this is the actual patch that organizes unified_shared_memory allocation into libgfortran. In the current OpenMP requires implementation, the requires_mask is collected through offload LTO processing, and presented to libgomp when registering offload images through GOMP_offload_register_ver() (called by the mkoffload generated constructor linked into the program binary) This means that the only reliable place to access omp_requires_mask is in GOMP_offload_register_ver, however since it is called through an ELF constructor in the *main program*, this runs later than libgfortran/runtime/main.c:init() constructor, and because some libgfortran init actions there start allocating memory, this can cause more deallocation errors later. Another issue is that CUDA appears to be registering some cleanup actions using atexit(), which forces libgomp to register gomp_target_fini() using atexit as well (to properly run before the underlying CUDA stuff disappears). This happens to us here as well. So to summarize we need to: (1) order libgfortran init actions after omp_requires_mask processing is done, and (2) order libgfortran cleanup actions before gomp_target_fini, to properly deallocate stuff without crashing. The above explanation is for why there's a little new set of definitions, as well as callback registering functions exported from libgomp to libgfortran, basically to register libgfortran init/fini actions into libgomp to run. Inside GOMP_offload_register_ver, after omp_requires_mask processing is done, we call into libgfortran through a new _gfortran_mem_allocators_init function to insert the omp_free/alloc/etc. based allocators into the Fortran runtime, when GOMP_REQUIRES_UNIFIED_SHARED_MEMORY is set. All symbol references between libgfortran/libgomp are defined with weak symbols. Test of the weak symbols are also used to determine if the other library exists in this program. A final issue is: the case where we have an OpenMP program that does NOT have offloading. We cannot passively determine in libgomp/libgfortran whether offloading exists or not, only the main program itself can, by seeing if the hidden __OFFLOAD_TABLE__ exists. When we do init/fini libgomp callback registering for OpenMP programs, those with no offloading will not have those callback properly run (because of no offload image loading) Therefore the solution here is a constructor added into the crtoffloadend.o fragment that does a "null" call of GOMP_offload_register_ver, solely for triggering the post-offload_register callbacks when __OFFLOAD_TABLE__ is NULL. (and because of this, the crtoffloadend.o Makefile rule is adjusted to compile with PIC) I know this is a big pile of yarn wrt how the main program/libgomp/libgfortran interacts, but it's finally working. Again tested without regressions. Preparing to commit to devel/omp/gcc-12, and seeking approval for mainline when the requires patches are in. Thanks, Chung-Lin 2022-08-15 Chung-Lin Tang libgcc/ * Makefile.in (crtoffloadend$(objext)): Add $(PICFLAG) to compile rule. * offloadstuff.c (GOMP_offload_register_ver): Add declaration of weak symbol. (__OFFLOAD_TABLE__): Likewise. (init_non_offload): New function. libgfortran/ * gfortran.map (GFORTRAN_13): New namespace. (_gfortran_mem_allocators_init): New name inside GFORTRAN_13. * libgfortran.h (mem_allocators_init): New exported declaration. * runtime/main.c (do_init): Rename from init, add run-once guard code. (cleanup): Add run-once guard code. (GOMP_post_offload_register_callback): Declare weak symbol. (GOMP_pre_gomp_target_fini_callback): Likewise. (init): New constructor to register offload callbacks, or call do_init when not OpenMP. * runtime/memory.c (gfortran_malloc): New pointer variable. (gfortran_calloc): Likewise. (gfortran_realloc): Likewise. (gfortran_free): Likewise. (mem_allocators_init): New function. (xmalloc): Use gfortran_malloc. (xmallocarray): Use gfortran_malloc. (xcalloc): Use gfortran_calloc. (xrealloc): Use gfortran_realloc. (xfree): Use gfortran_free. libgomp/ * libgomp.map (GOMP_5.1.2): New version namespace. (GOMP_post_offload_register_callback): New name inside GOMP_5.1.2. (GOMP_pre_gomp_target_fini_callback): Likewise. (GOMP_DEFINE_CALLBACK_SET): Macro to define callback set. (post_offload_register): Define callback set for after offload image register. (pre_gomp_target_fini): Define callback set for before gomp_target_fini is called. (libgfortran_malloc_usm): New function. (libgfortran_calloc_usm): Likewise (libgfortran_realloc_usm): Likewise (libgfortran_free_usm): Likewise. (_gfortran_mem_allocators_init): De
Re: [PATCH, OpenMP, Fortran] requires unified_shared_memory 2/2: insert USM allocators into libgfortran
On 2022/8/15 7:06 PM, Chung-Lin Tang wrote: I know this is a big pile of yarn wrt how the main program/libgomp/libgfortran interacts, but it's finally working. Again tested without regressions. Preparing to commit to devel/omp/gcc-12, and seeking approval for mainline when the requires patches are in. Just realized that I don't have the new testcases added in this patch. Will supplement them later :P Thanks, Chung-Lin
Re: [PATCH] libgfortran: Use __builtin_issignaling in libgfortran
Hi Jakub, The following patch makes use of the new __builtin_issignaling, so it no longer needs the fallback implementation and can use the builtin even where glibc provides the macro. Bootstrapped/regtested on x86_64-linux, i686-linux, powerpc64le-linux and powerpc64le-linux, ok for trunk? OK. Can you mention PR 105105 in the ChangeLog when you commit? Thanks for the patch! Best regards Thomas
Re: [PATCH] fortran: Expand ieee_arithmetic module's ieee_class inline [PR106579]
Question to the Fortran maintainers: Do you know if the standard allows IEEE_CLASS and IEEE_VALUE to be used as procedure pointers? I think not, because they do not follow (in F2008) the standard constraint C729 / R740. If so, we need to keep these functions implementations in libgfortran for now (for ABI compatibility) but can remove them at the next breakage. Is one planned? Where is this tracked, is it still at https://gcc.gnu.org/wiki/LibgfortranAbiCleanup or do we have another place (e.g. in bugzilla)? Thanks, FX
Re: [PATCH] fortran: Expand ieee_arithmetic module's ieee_value inline [PR106579]
Hi Jakub,
I have two questions, on this and the ieee_class patch:
> + tree type = TREE_TYPE (arg);
> + gcc_assert (TREE_CODE (type) == RECORD_TYPE);
> + tree field = NULL_TREE;
> + for (tree f = TYPE_FIELDS (type); f != NULL_TREE; f = DECL_CHAIN (f))
> +if (TREE_CODE (f) == FIELD_DECL)
> + {
> + gcc_assert (field == NULL_TREE);
> + field = f;
> + }
> + gcc_assert (field);
Why looping over fields? The class type is a simple type with only one member
(and it should be an integer, we can assert that).
> + case IEEE_POSITIVE_ZERO:
> + /* Make this also the default: label. */
> + label = gfc_build_label_decl (NULL_TREE);
> + tmp = build_case_label (NULL_TREE, NULL_TREE, label);
> + gfc_add_expr_to_block (&body, tmp);
> + real_from_integer (&real, TYPE_MODE (type), 0, SIGNED);
> + break;
Do we need a default label? It’s not like this is a more likely case than
anything else…
Thanks,
FX
Re: [PATCH] fortran: Expand ieee_arithmetic module's ieee_class inline [PR106579]
On Mon, Aug 15, 2022 at 09:47:45PM +0200, FX wrote: > Question to the Fortran maintainers: > > Do you know if the standard allows IEEE_CLASS and IEEE_VALUE to be used as > procedure pointers? I think not, because they do not follow (in F2008) the > standard constraint C729 / R740. > > If so, we need to keep these functions implementations in libgfortran for now > (for ABI compatibility) but can remove them at the next breakage. Is one > planned? Where is this tracked, is it still at > https://gcc.gnu.org/wiki/LibgfortranAbiCleanup or do we have another place > (e.g. in bugzilla)? Both are elemental generic procedures, and we have Procedure pointer %qs at %L shall not be elemental and Interface %qs at %L may not be generic errors for these 2 cases (trying to create procedure pointer to elemental and trying to create procedure pointer to generic procedure). Jakub
Re: [PATCH] fortran: Expand ieee_arithmetic module's ieee_value inline [PR106579]
On Mon, Aug 15, 2022 at 10:00:02PM +0200, FX wrote:
> I have two questions, on this and the ieee_class patch:
>
>
> > + tree type = TREE_TYPE (arg);
> > + gcc_assert (TREE_CODE (type) == RECORD_TYPE);
> > + tree field = NULL_TREE;
> > + for (tree f = TYPE_FIELDS (type); f != NULL_TREE; f = DECL_CHAIN (f))
> > +if (TREE_CODE (f) == FIELD_DECL)
> > + {
> > + gcc_assert (field == NULL_TREE);
> > + field = f;
> > + }
> > + gcc_assert (field);
>
> Why looping over fields? The class type is a simple type with only one member
> (and it should be an integer, we can assert that).
I wanted to make sure it has exactly one field.
The ieee_arithmetic.F90 module in libgfortran surely does that, but I've
been worrying about some user overriding that module with something
different. At least in the C/C++ FEs we had in the past tons of bugs filed
for when some builtin made some assumptions about some headers and data
types in those and then somebody running a testcase that violated that.
Even failed gcc_assertion isn't the best answer to that, ideally one would
verify that upfront and then either error, sorry or ignore the call (leave
it as is). In that last case, it might be better to do the check on the
gfortran FE types instead of trees (verify the return type or second
argument type is ieee_class_type derived type with a single integral
(hidden) field).
> > + case IEEE_POSITIVE_ZERO:
> > + /* Make this also the default: label. */
> > + label = gfc_build_label_decl (NULL_TREE);
> > + tmp = build_case_label (NULL_TREE, NULL_TREE, label);
> > + gfc_add_expr_to_block (&body, tmp);
> > + real_from_integer (&real, TYPE_MODE (type), 0, SIGNED);
> > + break;
>
> Do we need a default label? It’s not like this is a more likely case than
> anything else…
The libgfortran version had default: label:
switch (type) \
{ \
case IEEE_SIGNALING_NAN: \
return __builtin_nans ## SUFFIX (""); \
case IEEE_QUIET_NAN: \
return __builtin_nan ## SUFFIX (""); \
case IEEE_NEGATIVE_INF: \
return - __builtin_inf ## SUFFIX (); \
case IEEE_NEGATIVE_NORMAL: \
return -42; \
case IEEE_NEGATIVE_DENORMAL: \
return -(GFC_REAL_ ## TYPE ## _TINY) / 2; \
case IEEE_NEGATIVE_ZERO: \
return -(GFC_REAL_ ## TYPE) 0; \
case IEEE_POSITIVE_ZERO: \
return 0; \
case IEEE_POSITIVE_DENORMAL: \
return (GFC_REAL_ ## TYPE ## _TINY) / 2; \
case IEEE_POSITIVE_NORMAL: \
return 42; \
case IEEE_POSITIVE_INF: \
return __builtin_inf ## SUFFIX (); \
default: \
return 0; \
} \
and I've tried to traslate that into what it generates.
There is at least the IEEE_OTHER_VALUE (aka 0) value
that isn't covered in the switch, but it is just an integer
under the hood, so it could have any other value.
Jakub
