Auto sync2gitlab import of gcc-8.5.0-12.el8.src.rpm

This commit is contained in:
James Antill 2022-05-26 07:19:30 -04:00
parent 9abefb3390
commit 09c111765b
36 changed files with 28322 additions and 1 deletions

3
.gitignore vendored Normal file
View File

@ -0,0 +1,3 @@
/gcc-8.5.0-20210514.tar.xz
/nvptx-newlib-aadc8eb0ec43b7cd0dd2dfb484bae63c8b05ef24.tar.xz
/nvptx-tools-c28050f60193b3b95a18866a96f03334e874e78f.tar.xz

1
EMPTY
View File

@ -1 +0,0 @@

3455
gcc.spec Normal file

File diff suppressed because it is too large Load Diff

1644
gcc8-Wbidi-chars.patch Normal file

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,27 @@
2017-02-25 Jakub Jelinek <jakub@redhat.com>
* configure.ac: When adding -Wno-format, also add -Wno-format-security.
* configure: Regenerated.
--- gcc/configure.ac.jj 2017-02-13 12:20:53.000000000 +0100
+++ gcc/configure.ac 2017-02-25 12:42:32.859175403 +0100
@@ -481,7 +481,7 @@ AC_ARG_ENABLE(build-format-warnings,
AS_HELP_STRING([--disable-build-format-warnings],[don't use -Wformat while building GCC]),
[],[enable_build_format_warnings=yes])
AS_IF([test $enable_build_format_warnings = no],
- [wf_opt=-Wno-format],[wf_opt=])
+ [wf_opt="-Wno-format -Wno-format-security"],[wf_opt=])
ACX_PROG_CXX_WARNING_OPTS(
m4_quote(m4_do([-W -Wall -Wno-narrowing -Wwrite-strings ],
[-Wcast-qual $wf_opt])), [loose_warn])
--- gcc/configure.jj 2017-02-13 12:20:52.000000000 +0100
+++ gcc/configure 2017-02-25 12:42:50.041946391 +0100
@@ -6647,7 +6647,7 @@ else
fi
if test $enable_build_format_warnings = no; then :
- wf_opt=-Wno-format
+ wf_opt="-Wno-format -Wno-format-security"
else
wf_opt=
fi

View File

@ -0,0 +1,105 @@
From 9c108bb84d3a2447dac730c455df658be0a2c751 Mon Sep 17 00:00:00 2001
From: Richard Sandiford <richard.sandiford@arm.com>
Date: Tue, 17 Aug 2021 15:15:27 +0100
Subject: [PATCH] aarch64: Add -mtune=neoverse-512tvb
To: gcc-patches@gcc.gnu.org
This patch adds an option to tune for Neoverse cores that have
a total vector bandwidth of 512 bits (4x128 for Advanced SIMD
and a vector-length-dependent equivalent for SVE). This is intended
to be a compromise between tuning aggressively for a single core like
Neoverse V1 (which can be too narrow) and tuning for AArch64 cores
in general (which can be too wide).
-mcpu=neoverse-512tvb is equivalent to -mcpu=neoverse-v1
-mtune=neoverse-512tvb.
gcc/
* doc/invoke.texi: Document -mtune=neoverse-512tvb and
-mcpu=neoverse-512tvb.
* config/aarch64/aarch64-cores.def (neoverse-512tvb): New entry.
* config/aarch64/aarch64-tune.md: Regenerate.
(cherry picked from commit 048039c49b96875144f67e7789fdea54abf7710b)
---
gcc/config/aarch64/aarch64-cores.def | 1 +
gcc/config/aarch64/aarch64-tune.md | 2 +-
gcc/doc/invoke.texi | 25 ++++++++++++++++++++++---
3 files changed, 24 insertions(+), 4 deletions(-)
diff --git a/gcc/config/aarch64/aarch64-cores.def b/gcc/config/aarch64/aarch64-cores.def
index dfb839c01cc..f348d31e22e 100644
--- a/gcc/config/aarch64/aarch64-cores.def
+++ b/gcc/config/aarch64/aarch64-cores.def
@@ -99,6 +99,7 @@ AARCH64_CORE("saphira", saphira, falkor, 8_3A, AARCH64_FL_FOR_ARCH8_3
/* ARM ('A') cores. */
AARCH64_CORE("zeus", zeus, cortexa57, 8_4A, AARCH64_FL_FOR_ARCH8_4 | AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_SVE | AARCH64_FL_RNG, neoversev1, 0x41, 0xd40, -1)
AARCH64_CORE("neoverse-v1", neoversev1, cortexa57, 8_4A, AARCH64_FL_FOR_ARCH8_4 | AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_SVE | AARCH64_FL_RNG, neoversev1, 0x41, 0xd40, -1)
+AARCH64_CORE("neoverse-512tvb", neoverse512tvb, cortexa57, 8_4A, AARCH64_FL_FOR_ARCH8_4 | AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_SVE | AARCH64_FL_RNG, neoversev1, INVALID_IMP, INVALID_CORE, -1)
/* Armv8.5-A Architecture Processors. */
AARCH64_CORE("neoverse-n2", neoversen2, cortexa57, 8_4A, AARCH64_FL_FOR_ARCH8_4 | AARCH64_FL_F16 | AARCH64_FL_SVE | AARCH64_FL_RNG, neoversen2, 0x41, 0xd49, -1)
diff --git a/gcc/config/aarch64/aarch64-tune.md b/gcc/config/aarch64/aarch64-tune.md
index 2d7c9aa4740..09b76480f0b 100644
--- a/gcc/config/aarch64/aarch64-tune.md
+++ b/gcc/config/aarch64/aarch64-tune.md
@@ -1,5 +1,5 @@
;; -*- buffer-read-only: t -*-
;; Generated automatically by gentune.sh from aarch64-cores.def
(define_attr "tune"
- "cortexa35,cortexa53,cortexa57,cortexa72,cortexa73,thunderx,thunderxt88p1,thunderxt88,thunderxt81,thunderxt83,xgene1,falkor,qdf24xx,exynosm1,thunderx2t99p1,vulcan,thunderx2t99,cortexa55,cortexa75,cortexa76,ares,neoversen1,saphira,zeus,neoversev1,neoversen2,cortexa57cortexa53,cortexa72cortexa53,cortexa73cortexa35,cortexa73cortexa53,cortexa75cortexa55"
+ "cortexa35,cortexa53,cortexa57,cortexa72,cortexa73,thunderx,thunderxt88p1,thunderxt88,thunderxt81,thunderxt83,xgene1,falkor,qdf24xx,exynosm1,thunderx2t99p1,vulcan,thunderx2t99,cortexa55,cortexa75,cortexa76,ares,neoversen1,saphira,zeus,neoversev1,neoverse512tvb,neoversen2,cortexa57cortexa53,cortexa72cortexa53,cortexa73cortexa35,cortexa73cortexa53,cortexa75cortexa55"
(const (symbol_ref "((enum attr_tune) aarch64_tune)")))
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 78ca7738df2..68fda03281a 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -14772,9 +14772,9 @@ performance of the code. Permissible values for this option are:
@samp{generic}, @samp{cortex-a35}, @samp{cortex-a53}, @samp{cortex-a55},
@samp{cortex-a57}, @samp{cortex-a72}, @samp{cortex-a73}, @samp{cortex-a75},
@samp{cortex-a76}, @samp{ares}, @samp{neoverse-n1}, @samp{neoverse-n2},
-@samp{neoverse-v1}, @samp{zeus}, @samp{exynos-m1}, @samp{falkor},
-@samp{qdf24xx}, @samp{saphira}, @samp{xgene1}, @samp{vulcan}, @samp{thunderx},
-@samp{thunderxt88}, @samp{thunderxt88p1}, @samp{thunderxt81},
+@samp{neoverse-v1}, @samp{zeus}, @samp{neoverse-512tvb}, @samp{exynos-m1},
+@samp{falkor}, @samp{qdf24xx}, @samp{saphira}, @samp{xgene1}, @samp{vulcan},
+@samp{thunderx}, @samp{thunderxt88}, @samp{thunderxt88p1}, @samp{thunderxt81},
@samp{thunderxt83}, @samp{thunderx2t99}, @samp{cortex-a57.cortex-a53},
@samp{cortex-a72.cortex-a53}, @samp{cortex-a73.cortex-a35},
@samp{cortex-a73.cortex-a53}, @samp{cortex-a75.cortex-a55},
@@ -14785,6 +14785,15 @@ The values @samp{cortex-a57.cortex-a53}, @samp{cortex-a72.cortex-a53},
@samp{cortex-a75.cortex-a55} specify that GCC should tune for a
big.LITTLE system.
+The value @samp{neoverse-512tvb} specifies that GCC should tune
+for Neoverse cores that (a) implement SVE and (b) have a total vector
+bandwidth of 512 bits per cycle. In other words, the option tells GCC to
+tune for Neoverse cores that can execute 4 128-bit Advanced SIMD arithmetic
+instructions a cycle and that can execute an equivalent number of SVE
+arithmetic instructions per cycle (2 for 256-bit SVE, 4 for 128-bit SVE).
+This is more general than tuning for a specific core like Neoverse V1
+but is more specific than the default tuning described below.
+
Additionally on native AArch64 GNU/Linux systems the value
@samp{native} tunes performance to the host system. This option has no effect
if the compiler is unable to recognize the processor of the host system.
@@ -14814,6 +14823,16 @@ by @option{-mtune}). Where this option is used in conjunction
with @option{-march} or @option{-mtune}, those options take precedence
over the appropriate part of this option.
+@option{-mcpu=neoverse-512tvb} is special in that it does not refer
+to a specific core, but instead refers to all Neoverse cores that
+(a) implement SVE and (b) have a total vector bandwidth of 512 bits
+a cycle. Unless overridden by @option{-march},
+@option{-mcpu=neoverse-512tvb} generates code that can run on a
+Neoverse V1 core, since Neoverse V1 is the first Neoverse core with
+these properties. Unless overridden by @option{-mtune},
+@option{-mcpu=neoverse-512tvb} tunes code in the same way as for
+@option{-mtune=neoverse-512tvb}.
+
@item -moverride=@var{string}
@opindex moverride
Override tuning decisions made by the back-end in response to a
--
2.25.1

117
gcc8-foffload-default.patch Normal file
View File

@ -0,0 +1,117 @@
2017-01-20 Jakub Jelinek <jakub@redhat.com>
* gcc.c (offload_targets_default): New variable.
(process_command): Set it if -foffload is defaulted.
(driver::maybe_putenv_OFFLOAD_TARGETS): Add OFFLOAD_TARGET_DEFAULT=1
into environment if -foffload has been defaulted.
* lto-wrapper.c (OFFLOAD_TARGET_DEFAULT_ENV): Define.
(compile_images_for_offload_targets): If OFFLOAD_TARGET_DEFAULT
is in the environment, don't fail if corresponding mkoffload
can't be found. Free and clear offload_names if no valid offload
is found.
libgomp/
* target.c (gomp_load_plugin_for_device): If a plugin can't be
dlopened, assume it has no devices silently.
--- gcc/gcc.c.jj 2017-01-17 10:28:40.000000000 +0100
+++ gcc/gcc.c 2017-01-20 16:26:29.649962902 +0100
@@ -290,6 +290,10 @@ static const char *spec_host_machine = D
static char *offload_targets = NULL;
+/* Set to true if -foffload has not been used and offload_targets
+ is set to the configured in default. */
+static bool offload_targets_default;
+
/* Nonzero if cross-compiling.
When -b is used, the value comes from the `specs' file. */
@@ -4457,7 +4461,10 @@ process_command (unsigned int decoded_op
/* If the user didn't specify any, default to all configured offload
targets. */
if (ENABLE_OFFLOADING && offload_targets == NULL)
- handle_foffload_option (OFFLOAD_TARGETS);
+ {
+ handle_foffload_option (OFFLOAD_TARGETS);
+ offload_targets_default = true;
+ }
if (output_file
&& strcmp (output_file, "-") != 0
@@ -7693,6 +7700,8 @@ driver::maybe_putenv_OFFLOAD_TARGETS ()
obstack_grow (&collect_obstack, offload_targets,
strlen (offload_targets) + 1);
xputenv (XOBFINISH (&collect_obstack, char *));
+ if (offload_targets_default)
+ xputenv ("OFFLOAD_TARGET_DEFAULT=1");
}
free (offload_targets);
--- gcc/lto-wrapper.c.jj 2017-01-01 12:45:34.000000000 +0100
+++ gcc/lto-wrapper.c 2017-01-20 16:34:18.294016997 +0100
@@ -52,6 +52,7 @@ along with GCC; see the file COPYING3.
/* Environment variable, used for passing the names of offload targets from GCC
driver to lto-wrapper. */
#define OFFLOAD_TARGET_NAMES_ENV "OFFLOAD_TARGET_NAMES"
+#define OFFLOAD_TARGET_DEFAULT_ENV "OFFLOAD_TARGET_DEFAULT"
enum lto_mode_d {
LTO_MODE_NONE, /* Not doing LTO. */
@@ -790,8 +791,10 @@ compile_images_for_offload_targets (unsi
if (!target_names)
return;
unsigned num_targets = parse_env_var (target_names, &names, NULL);
+ const char *target_names_default = getenv (OFFLOAD_TARGET_DEFAULT_ENV);
int next_name_entry = 0;
+ bool hsa_seen = false;
const char *compiler_path = getenv ("COMPILER_PATH");
if (!compiler_path)
goto out;
@@ -804,18 +807,32 @@ compile_images_for_offload_targets (unsi
/* HSA does not use LTO-like streaming and a different compiler, skip
it. */
if (strcmp (names[i], "hsa") == 0)
- continue;
+ {
+ hsa_seen = true;
+ continue;
+ }
offload_names[next_name_entry]
= compile_offload_image (names[i], compiler_path, in_argc, in_argv,
compiler_opts, compiler_opt_count,
linker_opts, linker_opt_count);
if (!offload_names[next_name_entry])
- fatal_error (input_location,
- "problem with building target image for %s\n", names[i]);
+ {
+ if (target_names_default != NULL)
+ continue;
+ fatal_error (input_location,
+ "problem with building target image for %s\n",
+ names[i]);
+ }
next_name_entry++;
}
+ if (next_name_entry == 0 && !hsa_seen)
+ {
+ free (offload_names);
+ offload_names = NULL;
+ }
+
out:
free_array_of_ptrs ((void **) names, num_targets);
}
--- libgomp/target.c.jj 2017-01-01 12:45:52.000000000 +0100
+++ libgomp/target.c 2017-01-20 20:12:13.756710875 +0100
@@ -2356,7 +2356,7 @@ gomp_load_plugin_for_device (struct gomp
void *plugin_handle = dlopen (plugin_name, RTLD_LAZY);
if (!plugin_handle)
- goto dl_fail;
+ return 0;
/* Check if all required functions are available in the plugin and store
their handlers. None of the symbols can legitimately be NULL,

124
gcc8-hack.patch Normal file
View File

@ -0,0 +1,124 @@
--- libada/Makefile.in.jj 2009-01-14 12:07:35.000000000 +0100
+++ libada/Makefile.in 2009-01-15 14:25:33.000000000 +0100
@@ -66,18 +66,40 @@ libsubdir := $(libdir)/gcc/$(target_nonc
ADA_RTS_DIR=$(GCC_DIR)/ada/rts$(subst /,_,$(MULTISUBDIR))
ADA_RTS_SUBDIR=./rts$(subst /,_,$(MULTISUBDIR))
+DEFAULTMULTIFLAGS :=
+ifeq ($(MULTISUBDIR),)
+targ:=$(subst -, ,$(target))
+arch:=$(word 1,$(targ))
+ifeq ($(words $(targ)),2)
+osys:=$(word 2,$(targ))
+else
+osys:=$(word 3,$(targ))
+endif
+ifeq ($(strip $(filter-out i%86 x86_64 powerpc% ppc% s390% sparc% linux%, $(arch) $(osys))),)
+ifeq ($(shell $(CC) $(CFLAGS) -print-multi-os-directory),../lib64)
+DEFAULTMULTIFLAGS := -m64
+else
+ifeq ($(strip $(filter-out s390%, $(arch))),)
+DEFAULTMULTIFLAGS := -m31
+else
+DEFAULTMULTIFLAGS := -m32
+endif
+endif
+endif
+endif
+
# exeext should not be used because it's the *host* exeext. We're building
# a *target* library, aren't we?!? Likewise for CC. Still, provide bogus
# definitions just in case something slips through the safety net provided
# by recursive make invocations in gcc/ada/Makefile.in
LIBADA_FLAGS_TO_PASS = \
"MAKEOVERRIDES=" \
- "LDFLAGS=$(LDFLAGS)" \
+ "LDFLAGS=$(LDFLAGS) $(DEFAULTMULTIFLAGS)" \
"LN_S=$(LN_S)" \
"SHELL=$(SHELL)" \
- "GNATLIBFLAGS=$(GNATLIBFLAGS) $(MULTIFLAGS)" \
- "GNATLIBCFLAGS=$(GNATLIBCFLAGS) $(MULTIFLAGS)" \
- "GNATLIBCFLAGS_FOR_C=$(GNATLIBCFLAGS_FOR_C) $(MULTIFLAGS)" \
+ "GNATLIBFLAGS=$(GNATLIBFLAGS) $(MULTIFLAGS) $(DEFAULTMULTIFLAGS)" \
+ "GNATLIBCFLAGS=$(GNATLIBCFLAGS) $(MULTIFLAGS) $(DEFAULTMULTIFLAGS)" \
+ "GNATLIBCFLAGS_FOR_C=$(GNATLIBCFLAGS_FOR_C) $(MULTIFLAGS) $(DEFAULTMULTIFLAGS)" \
"PICFLAG_FOR_TARGET=$(PICFLAG)" \
"THREAD_KIND=$(THREAD_KIND)" \
"TRACE=$(TRACE)" \
@@ -88,7 +110,7 @@ LIBADA_FLAGS_TO_PASS = \
"exeext=.exeext.should.not.be.used " \
'CC=the.host.compiler.should.not.be.needed' \
"GCC_FOR_TARGET=$(CC)" \
- "CFLAGS=$(CFLAGS)"
+ "CFLAGS=$(CFLAGS) $(DEFAULTMULTIFLAGS)"
# Rules to build gnatlib.
.PHONY: gnatlib gnatlib-plain gnatlib-sjlj gnatlib-zcx gnatlib-shared osconstool
--- config-ml.in.jj 2010-06-30 09:50:44.000000000 +0200
+++ config-ml.in 2010-07-02 21:24:17.994211151 +0200
@@ -511,6 +511,8 @@ multi-do:
ADAFLAGS="$(ADAFLAGS) $${flags}" \
prefix="$(prefix)" \
exec_prefix="$(exec_prefix)" \
+ mandir="$(mandir)" \
+ infodir="$(infodir)" \
GOCFLAGS="$(GOCFLAGS) $${flags}" \
CXXFLAGS="$(CXXFLAGS) $${flags}" \
LIBCFLAGS="$(LIBCFLAGS) $${flags}" \
--- libcpp/macro.c.jj 2015-01-14 11:01:34.000000000 +0100
+++ libcpp/macro.c 2015-01-14 14:22:19.286949884 +0100
@@ -2947,8 +2947,6 @@ create_iso_definition (cpp_reader *pfile
cpp_token *token;
const cpp_token *ctoken;
bool following_paste_op = false;
- const char *paste_op_error_msg =
- N_("'##' cannot appear at either end of a macro expansion");
unsigned int num_extra_tokens = 0;
/* Get the first token of the expansion (or the '(' of a
@@ -3059,7 +3057,8 @@ create_iso_definition (cpp_reader *pfile
function-like macros, but not at the end. */
if (following_paste_op)
{
- cpp_error (pfile, CPP_DL_ERROR, paste_op_error_msg);
+ cpp_error (pfile, CPP_DL_ERROR,
+ "'##' cannot appear at either end of a macro expansion");
return false;
}
break;
@@ -3072,7 +3071,8 @@ create_iso_definition (cpp_reader *pfile
function-like macros, but not at the beginning. */
if (macro->count == 1)
{
- cpp_error (pfile, CPP_DL_ERROR, paste_op_error_msg);
+ cpp_error (pfile, CPP_DL_ERROR,
+ "'##' cannot appear at either end of a macro expansion");
return false;
}
--- libcpp/expr.c.jj 2015-01-14 11:01:34.000000000 +0100
+++ libcpp/expr.c 2015-01-14 14:35:52.851002344 +0100
@@ -672,16 +672,17 @@ cpp_classify_number (cpp_reader *pfile,
if ((result & CPP_N_WIDTH) == CPP_N_LARGE
&& CPP_OPTION (pfile, cpp_warn_long_long))
{
- const char *message = CPP_OPTION (pfile, cplusplus)
- ? N_("use of C++11 long long integer constant")
- : N_("use of C99 long long integer constant");
-
if (CPP_OPTION (pfile, c99))
cpp_warning_with_line (pfile, CPP_W_LONG_LONG, virtual_location,
- 0, message);
+ 0, CPP_OPTION (pfile, cplusplus)
+ ? N_("use of C++11 long long integer constant")
+ : N_("use of C99 long long integer constant"));
else
cpp_pedwarning_with_line (pfile, CPP_W_LONG_LONG,
- virtual_location, 0, message);
+ virtual_location, 0,
+ CPP_OPTION (pfile, cplusplus)
+ ? N_("use of C++11 long long integer constant")
+ : N_("use of C99 long long integer constant"));
}
result |= CPP_N_INTEGER;

11
gcc8-i386-libgomp.patch Normal file
View File

@ -0,0 +1,11 @@
--- libgomp/configure.tgt.jj 2008-01-10 20:53:48.000000000 +0100
+++ libgomp/configure.tgt 2008-03-27 12:44:51.000000000 +0100
@@ -67,7 +67,7 @@ if test $enable_linux_futex = yes; then
;;
*)
if test -z "$with_arch"; then
- XCFLAGS="${XCFLAGS} -march=i486 -mtune=${target_cpu}"
+ XCFLAGS="${XCFLAGS} -march=i486 -mtune=generic"
fi
esac
;;

715
gcc8-isl-dl.patch Normal file
View File

@ -0,0 +1,715 @@
--- gcc/Makefile.in.jj 2015-06-06 10:00:25.000000000 +0200
+++ gcc/Makefile.in 2015-11-04 14:56:02.643536437 +0100
@@ -1046,7 +1046,7 @@ BUILD_LIBDEPS= $(BUILD_LIBIBERTY)
# and the system's installed libraries.
LIBS = @LIBS@ libcommon.a $(CPPLIB) $(LIBINTL) $(LIBICONV) $(LIBBACKTRACE) \
$(LIBIBERTY) $(LIBDECNUMBER) $(HOST_LIBS)
-BACKENDLIBS = $(ISLLIBS) $(GMPLIBS) $(PLUGINLIBS) $(HOST_LIBS) \
+BACKENDLIBS = $(if $(ISLLIBS),-ldl) $(GMPLIBS) $(PLUGINLIBS) $(HOST_LIBS) \
$(ZLIB)
# Any system libraries needed just for GNAT.
SYSLIBS = @GNAT_LIBEXC@
@@ -2196,6 +2196,15 @@ $(out_object_file): $(out_file)
$(common_out_object_file): $(common_out_file)
$(COMPILE) $<
$(POSTCOMPILE)
+
+graphite%.o : \
+ ALL_CFLAGS := -O $(filter-out -fkeep-inline-functions, $(ALL_CFLAGS))
+graphite.o : \
+ ALL_CFLAGS := -O $(filter-out -fkeep-inline-functions, $(ALL_CFLAGS))
+graphite%.o : \
+ ALL_CXXFLAGS := -O $(filter-out -fkeep-inline-functions, $(ALL_CXXFLAGS))
+graphite.o : \
+ ALL_CXXFLAGS := -O $(filter-out -fkeep-inline-functions, $(ALL_CXXFLAGS))
#
# Generate header and source files from the machine description,
# and compile them.
--- gcc/graphite.h.jj 2016-01-27 12:44:06.000000000 +0100
+++ gcc/graphite.h 2016-01-27 13:26:38.309876856 +0100
@@ -39,6 +39,590 @@ along with GCC; see the file COPYING3.
#include <isl/schedule_node.h>
#include <isl/id.h>
#include <isl/space.h>
+#include <isl/version.h>
+#include <dlfcn.h>
+
+#define DYNSYMS \
+ DYNSYM (isl_aff_add_coefficient_si); \
+ DYNSYM (isl_aff_free); \
+ DYNSYM (isl_aff_get_space); \
+ DYNSYM (isl_aff_set_coefficient_si); \
+ DYNSYM (isl_aff_set_constant_si); \
+ DYNSYM (isl_aff_zero_on_domain); \
+ DYNSYM (isl_band_free); \
+ DYNSYM (isl_band_get_children); \
+ DYNSYM (isl_band_get_partial_schedule); \
+ DYNSYM (isl_band_has_children); \
+ DYNSYM (isl_band_list_free); \
+ DYNSYM (isl_band_list_get_band); \
+ DYNSYM (isl_band_list_get_ctx); \
+ DYNSYM (isl_band_list_n_band); \
+ DYNSYM (isl_band_n_member); \
+ DYNSYM (isl_basic_map_add_constraint); \
+ DYNSYM (isl_basic_map_project_out); \
+ DYNSYM (isl_basic_map_universe); \
+ DYNSYM (isl_constraint_set_coefficient_si); \
+ DYNSYM (isl_constraint_set_constant_si); \
+ DYNSYM (isl_ctx_alloc); \
+ DYNSYM (isl_ctx_free); \
+ DYNSYM (isl_equality_alloc); \
+ DYNSYM (isl_id_alloc); \
+ DYNSYM (isl_id_copy); \
+ DYNSYM (isl_id_free); \
+ DYNSYM (isl_inequality_alloc); \
+ DYNSYM (isl_local_space_copy); \
+ DYNSYM (isl_local_space_free); \
+ DYNSYM (isl_local_space_from_space); \
+ DYNSYM (isl_local_space_range); \
+ DYNSYM (isl_map_add_constraint); \
+ DYNSYM (isl_map_add_dims); \
+ DYNSYM (isl_map_align_params); \
+ DYNSYM (isl_map_apply_range); \
+ DYNSYM (isl_map_copy); \
+ DYNSYM (isl_map_dim); \
+ DYNSYM (isl_map_dump); \
+ DYNSYM (isl_map_equate); \
+ DYNSYM (isl_map_fix_si); \
+ DYNSYM (isl_map_flat_product); \
+ DYNSYM (isl_map_flat_range_product); \
+ DYNSYM (isl_map_free); \
+ DYNSYM (isl_map_from_basic_map); \
+ DYNSYM (isl_map_from_pw_aff); \
+ DYNSYM (isl_map_from_union_map); \
+ DYNSYM (isl_map_get_ctx); \
+ DYNSYM (isl_map_get_space); \
+ DYNSYM (isl_map_get_tuple_id); \
+ DYNSYM (isl_map_insert_dims); \
+ DYNSYM (isl_map_intersect); \
+ DYNSYM (isl_map_intersect_domain); \
+ DYNSYM (isl_map_intersect_range); \
+ DYNSYM (isl_map_is_empty); \
+ DYNSYM (isl_map_lex_ge); \
+ DYNSYM (isl_map_lex_le); \
+ DYNSYM (isl_map_n_out); \
+ DYNSYM (isl_map_range); \
+ DYNSYM (isl_map_set_tuple_id); \
+ DYNSYM (isl_map_universe); \
+ DYNSYM (isl_options_set_on_error); \
+ DYNSYM (isl_options_set_schedule_serialize_sccs); \
+ DYNSYM (isl_printer_set_yaml_style); \
+ DYNSYM (isl_options_set_schedule_max_constant_term); \
+ DYNSYM (isl_options_set_schedule_maximize_band_depth); \
+ DYNSYM (isl_printer_free); \
+ DYNSYM (isl_printer_print_aff); \
+ DYNSYM (isl_printer_print_constraint); \
+ DYNSYM (isl_printer_print_map); \
+ DYNSYM (isl_printer_print_set); \
+ DYNSYM (isl_printer_to_file); \
+ DYNSYM (isl_pw_aff_add); \
+ DYNSYM (isl_pw_aff_alloc); \
+ DYNSYM (isl_pw_aff_copy); \
+ DYNSYM (isl_pw_aff_eq_set); \
+ DYNSYM (isl_pw_aff_free); \
+ DYNSYM (isl_pw_aff_from_aff); \
+ DYNSYM (isl_pw_aff_ge_set); \
+ DYNSYM (isl_pw_aff_gt_set); \
+ DYNSYM (isl_pw_aff_is_cst); \
+ DYNSYM (isl_pw_aff_le_set); \
+ DYNSYM (isl_pw_aff_lt_set); \
+ DYNSYM (isl_pw_aff_mul); \
+ DYNSYM (isl_pw_aff_ne_set); \
+ DYNSYM (isl_pw_aff_nonneg_set); \
+ DYNSYM (isl_pw_aff_set_tuple_id); \
+ DYNSYM (isl_pw_aff_sub); \
+ DYNSYM (isl_pw_aff_zero_set); \
+ DYNSYM (isl_schedule_free); \
+ DYNSYM (isl_schedule_get_band_forest); \
+ DYNSYM (isl_set_add_constraint); \
+ DYNSYM (isl_set_add_dims); \
+ DYNSYM (isl_set_apply); \
+ DYNSYM (isl_set_coalesce); \
+ DYNSYM (isl_set_copy); \
+ DYNSYM (isl_set_dim); \
+ DYNSYM (isl_set_fix_si); \
+ DYNSYM (isl_set_free); \
+ DYNSYM (isl_set_get_space); \
+ DYNSYM (isl_set_get_tuple_id); \
+ DYNSYM (isl_set_intersect); \
+ DYNSYM (isl_set_is_empty); \
+ DYNSYM (isl_set_n_dim); \
+ DYNSYM (isl_set_nat_universe); \
+ DYNSYM (isl_set_project_out); \
+ DYNSYM (isl_set_set_tuple_id); \
+ DYNSYM (isl_set_universe); \
+ DYNSYM (isl_space_add_dims); \
+ DYNSYM (isl_space_alloc); \
+ DYNSYM (isl_space_copy); \
+ DYNSYM (isl_space_dim); \
+ DYNSYM (isl_space_domain); \
+ DYNSYM (isl_space_find_dim_by_id); \
+ DYNSYM (isl_space_free); \
+ DYNSYM (isl_space_from_domain); \
+ DYNSYM (isl_space_get_tuple_id); \
+ DYNSYM (isl_space_params_alloc); \
+ DYNSYM (isl_space_range); \
+ DYNSYM (isl_space_set_alloc); \
+ DYNSYM (isl_space_set_dim_id); \
+ DYNSYM (isl_space_set_tuple_id); \
+ DYNSYM (isl_union_map_add_map); \
+ DYNSYM (isl_union_map_align_params); \
+ DYNSYM (isl_union_map_apply_domain); \
+ DYNSYM (isl_union_map_apply_range); \
+ DYNSYM (isl_union_map_compute_flow); \
+ DYNSYM (isl_union_map_copy); \
+ DYNSYM (isl_union_map_empty); \
+ DYNSYM (isl_union_map_flat_range_product); \
+ DYNSYM (isl_union_map_foreach_map); \
+ DYNSYM (isl_union_map_free); \
+ DYNSYM (isl_union_map_from_map); \
+ DYNSYM (isl_union_map_get_ctx); \
+ DYNSYM (isl_union_map_get_space); \
+ DYNSYM (isl_union_map_gist_domain); \
+ DYNSYM (isl_union_map_gist_range); \
+ DYNSYM (isl_union_map_intersect_domain); \
+ DYNSYM (isl_union_map_is_empty); \
+ DYNSYM (isl_union_map_subtract); \
+ DYNSYM (isl_union_map_union); \
+ DYNSYM (isl_union_set_add_set); \
+ DYNSYM (isl_union_set_compute_schedule); \
+ DYNSYM (isl_union_set_copy); \
+ DYNSYM (isl_union_set_empty); \
+ DYNSYM (isl_union_set_from_set); \
+ DYNSYM (isl_aff_add_constant_val); \
+ DYNSYM (isl_aff_get_coefficient_val); \
+ DYNSYM (isl_aff_get_ctx); \
+ DYNSYM (isl_aff_mod_val); \
+ DYNSYM (isl_ast_build_ast_from_schedule); \
+ DYNSYM (isl_ast_build_free); \
+ DYNSYM (isl_ast_build_from_context); \
+ DYNSYM (isl_ast_build_get_ctx); \
+ DYNSYM (isl_ast_build_get_schedule); \
+ DYNSYM (isl_ast_build_get_schedule_space); \
+ DYNSYM (isl_ast_build_set_before_each_for); \
+ DYNSYM (isl_ast_build_set_options); \
+ DYNSYM (isl_ast_expr_free); \
+ DYNSYM (isl_ast_expr_from_val); \
+ DYNSYM (isl_ast_expr_get_ctx); \
+ DYNSYM (isl_ast_expr_get_id); \
+ DYNSYM (isl_ast_expr_get_op_arg); \
+ DYNSYM (isl_ast_expr_get_op_n_arg); \
+ DYNSYM (isl_ast_expr_get_op_type); \
+ DYNSYM (isl_ast_expr_get_type); \
+ DYNSYM (isl_ast_expr_get_val); \
+ DYNSYM (isl_ast_expr_sub); \
+ DYNSYM (isl_ast_node_block_get_children); \
+ DYNSYM (isl_ast_node_for_get_body); \
+ DYNSYM (isl_ast_node_for_get_cond); \
+ DYNSYM (isl_ast_node_for_get_inc); \
+ DYNSYM (isl_ast_node_for_get_init); \
+ DYNSYM (isl_ast_node_for_get_iterator); \
+ DYNSYM (isl_ast_node_free); \
+ DYNSYM (isl_ast_node_get_annotation); \
+ DYNSYM (isl_ast_node_get_type); \
+ DYNSYM (isl_ast_node_if_get_cond); \
+ DYNSYM (isl_ast_node_if_get_else); \
+ DYNSYM (isl_ast_node_if_get_then); \
+ DYNSYM (isl_ast_node_list_free); \
+ DYNSYM (isl_ast_node_list_get_ast_node); \
+ DYNSYM (isl_ast_node_list_n_ast_node); \
+ DYNSYM (isl_ast_node_user_get_expr); \
+ DYNSYM (isl_constraint_set_coefficient_val); \
+ DYNSYM (isl_constraint_set_constant_val); \
+ DYNSYM (isl_id_get_user); \
+ DYNSYM (isl_local_space_get_ctx); \
+ DYNSYM (isl_map_fix_val); \
+ DYNSYM (isl_options_set_ast_build_atomic_upper_bound); \
+ DYNSYM (isl_printer_print_ast_node); \
+ DYNSYM (isl_printer_print_str); \
+ DYNSYM (isl_printer_set_output_format); \
+ DYNSYM (isl_pw_aff_mod_val); \
+ DYNSYM (isl_schedule_constraints_compute_schedule); \
+ DYNSYM (isl_schedule_constraints_on_domain); \
+ DYNSYM (isl_schedule_constraints_set_coincidence); \
+ DYNSYM (isl_schedule_constraints_set_proximity); \
+ DYNSYM (isl_schedule_constraints_set_validity); \
+ DYNSYM (isl_set_get_dim_id); \
+ DYNSYM (isl_set_max_val); \
+ DYNSYM (isl_set_min_val); \
+ DYNSYM (isl_set_params); \
+ DYNSYM (isl_space_align_params); \
+ DYNSYM (isl_space_map_from_domain_and_range); \
+ DYNSYM (isl_space_set_tuple_name); \
+ DYNSYM (isl_space_wrap); \
+ DYNSYM (isl_union_map_from_domain_and_range); \
+ DYNSYM (isl_union_map_range); \
+ DYNSYM (isl_union_set_union); \
+ DYNSYM (isl_union_set_universe); \
+ DYNSYM (isl_val_2exp); \
+ DYNSYM (isl_val_add_ui); \
+ DYNSYM (isl_val_copy); \
+ DYNSYM (isl_val_free); \
+ DYNSYM (isl_val_int_from_si); \
+ DYNSYM (isl_val_int_from_ui); \
+ DYNSYM (isl_val_mul); \
+ DYNSYM (isl_val_neg); \
+ DYNSYM (isl_val_sub); \
+ DYNSYM (isl_printer_print_union_map); \
+ DYNSYM (isl_pw_aff_get_ctx); \
+ DYNSYM (isl_val_is_int); \
+ DYNSYM (isl_ctx_get_max_operations); \
+ DYNSYM (isl_ctx_set_max_operations); \
+ DYNSYM (isl_ctx_last_error); \
+ DYNSYM (isl_ctx_reset_operations); \
+ DYNSYM (isl_map_coalesce); \
+ DYNSYM (isl_printer_print_schedule); \
+ DYNSYM (isl_set_set_dim_id); \
+ DYNSYM (isl_union_map_coalesce); \
+ DYNSYM (isl_multi_val_set_val); \
+ DYNSYM (isl_multi_val_zero); \
+ DYNSYM (isl_options_set_schedule_max_coefficient); \
+ DYNSYM (isl_options_set_tile_scale_tile_loops); \
+ DYNSYM (isl_schedule_copy); \
+ DYNSYM (isl_schedule_get_map); \
+ DYNSYM (isl_schedule_map_schedule_node_bottom_up); \
+ DYNSYM (isl_schedule_node_band_get_permutable); \
+ DYNSYM (isl_schedule_node_band_get_space); \
+ DYNSYM (isl_schedule_node_band_tile); \
+ DYNSYM (isl_schedule_node_child); \
+ DYNSYM (isl_schedule_node_free); \
+ DYNSYM (isl_schedule_node_get_child); \
+ DYNSYM (isl_schedule_node_get_ctx); \
+ DYNSYM (isl_schedule_node_get_type); \
+ DYNSYM (isl_schedule_node_n_children); \
+ DYNSYM (isl_union_map_is_equal); \
+ DYNSYM (isl_union_access_info_compute_flow); \
+ DYNSYM (isl_union_access_info_from_sink); \
+ DYNSYM (isl_union_access_info_set_may_source); \
+ DYNSYM (isl_union_access_info_set_must_source); \
+ DYNSYM (isl_union_access_info_set_schedule); \
+ DYNSYM (isl_union_flow_free); \
+ DYNSYM (isl_union_flow_get_may_dependence); \
+ DYNSYM (isl_union_flow_get_must_dependence); \
+ DYNSYM (isl_aff_var_on_domain); \
+ DYNSYM (isl_multi_aff_from_aff); \
+ DYNSYM (isl_schedule_get_ctx); \
+ DYNSYM (isl_multi_aff_set_tuple_id); \
+ DYNSYM (isl_multi_aff_dim); \
+ DYNSYM (isl_schedule_get_domain); \
+ DYNSYM (isl_union_set_is_empty); \
+ DYNSYM (isl_union_set_get_space); \
+ DYNSYM (isl_union_pw_multi_aff_empty); \
+ DYNSYM (isl_union_set_foreach_set); \
+ DYNSYM (isl_union_set_free); \
+ DYNSYM (isl_multi_union_pw_aff_from_union_pw_multi_aff); \
+ DYNSYM (isl_multi_union_pw_aff_apply_multi_aff); \
+ DYNSYM (isl_schedule_insert_partial_schedule); \
+ DYNSYM (isl_union_pw_multi_aff_free); \
+ DYNSYM (isl_pw_multi_aff_project_out_map); \
+ DYNSYM (isl_union_pw_multi_aff_add_pw_multi_aff); \
+ DYNSYM (isl_schedule_from_domain); \
+ DYNSYM (isl_schedule_sequence); \
+ DYNSYM (isl_ast_build_node_from_schedule); \
+ DYNSYM (isl_ast_node_mark_get_node); \
+ DYNSYM (isl_schedule_node_band_member_get_ast_loop_type); \
+ DYNSYM (isl_schedule_node_band_member_set_ast_loop_type); \
+ DYNSYM (isl_val_n_abs_num_chunks); \
+ DYNSYM (isl_val_get_abs_num_chunks); \
+ DYNSYM (isl_val_int_from_chunks); \
+ DYNSYM (isl_val_is_neg); \
+ DYNSYM (isl_version); \
+ DYNSYM (isl_options_get_on_error); \
+ DYNSYM (isl_ctx_reset_error);
+
+extern struct isl_pointers_s__
+{
+ bool inited;
+ void *h;
+#define DYNSYM(x) __typeof (x) *p_##x
+ DYNSYMS
+#undef DYNSYM
+} isl_pointers__;
+
+#define isl_aff_add_coefficient_si (*isl_pointers__.p_isl_aff_add_coefficient_si)
+#define isl_aff_free (*isl_pointers__.p_isl_aff_free)
+#define isl_aff_get_space (*isl_pointers__.p_isl_aff_get_space)
+#define isl_aff_set_coefficient_si (*isl_pointers__.p_isl_aff_set_coefficient_si)
+#define isl_aff_set_constant_si (*isl_pointers__.p_isl_aff_set_constant_si)
+#define isl_aff_zero_on_domain (*isl_pointers__.p_isl_aff_zero_on_domain)
+#define isl_band_free (*isl_pointers__.p_isl_band_free)
+#define isl_band_get_children (*isl_pointers__.p_isl_band_get_children)
+#define isl_band_get_partial_schedule (*isl_pointers__.p_isl_band_get_partial_schedule)
+#define isl_band_has_children (*isl_pointers__.p_isl_band_has_children)
+#define isl_band_list_free (*isl_pointers__.p_isl_band_list_free)
+#define isl_band_list_get_band (*isl_pointers__.p_isl_band_list_get_band)
+#define isl_band_list_get_ctx (*isl_pointers__.p_isl_band_list_get_ctx)
+#define isl_band_list_n_band (*isl_pointers__.p_isl_band_list_n_band)
+#define isl_band_n_member (*isl_pointers__.p_isl_band_n_member)
+#define isl_basic_map_add_constraint (*isl_pointers__.p_isl_basic_map_add_constraint)
+#define isl_basic_map_project_out (*isl_pointers__.p_isl_basic_map_project_out)
+#define isl_basic_map_universe (*isl_pointers__.p_isl_basic_map_universe)
+#define isl_constraint_set_coefficient_si (*isl_pointers__.p_isl_constraint_set_coefficient_si)
+#define isl_constraint_set_constant_si (*isl_pointers__.p_isl_constraint_set_constant_si)
+#define isl_ctx_alloc (*isl_pointers__.p_isl_ctx_alloc)
+#define isl_ctx_free (*isl_pointers__.p_isl_ctx_free)
+#define isl_equality_alloc (*isl_pointers__.p_isl_equality_alloc)
+#define isl_id_alloc (*isl_pointers__.p_isl_id_alloc)
+#define isl_id_copy (*isl_pointers__.p_isl_id_copy)
+#define isl_id_free (*isl_pointers__.p_isl_id_free)
+#define isl_inequality_alloc (*isl_pointers__.p_isl_inequality_alloc)
+#define isl_local_space_copy (*isl_pointers__.p_isl_local_space_copy)
+#define isl_local_space_free (*isl_pointers__.p_isl_local_space_free)
+#define isl_local_space_from_space (*isl_pointers__.p_isl_local_space_from_space)
+#define isl_local_space_range (*isl_pointers__.p_isl_local_space_range)
+#define isl_map_add_constraint (*isl_pointers__.p_isl_map_add_constraint)
+#define isl_map_add_dims (*isl_pointers__.p_isl_map_add_dims)
+#define isl_map_align_params (*isl_pointers__.p_isl_map_align_params)
+#define isl_map_apply_range (*isl_pointers__.p_isl_map_apply_range)
+#define isl_map_copy (*isl_pointers__.p_isl_map_copy)
+#define isl_map_dim (*isl_pointers__.p_isl_map_dim)
+#define isl_map_dump (*isl_pointers__.p_isl_map_dump)
+#define isl_map_equate (*isl_pointers__.p_isl_map_equate)
+#define isl_map_fix_si (*isl_pointers__.p_isl_map_fix_si)
+#define isl_map_flat_product (*isl_pointers__.p_isl_map_flat_product)
+#define isl_map_flat_range_product (*isl_pointers__.p_isl_map_flat_range_product)
+#define isl_map_free (*isl_pointers__.p_isl_map_free)
+#define isl_map_from_basic_map (*isl_pointers__.p_isl_map_from_basic_map)
+#define isl_map_from_pw_aff (*isl_pointers__.p_isl_map_from_pw_aff)
+#define isl_map_from_union_map (*isl_pointers__.p_isl_map_from_union_map)
+#define isl_map_get_ctx (*isl_pointers__.p_isl_map_get_ctx)
+#define isl_map_get_space (*isl_pointers__.p_isl_map_get_space)
+#define isl_map_get_tuple_id (*isl_pointers__.p_isl_map_get_tuple_id)
+#define isl_map_insert_dims (*isl_pointers__.p_isl_map_insert_dims)
+#define isl_map_intersect (*isl_pointers__.p_isl_map_intersect)
+#define isl_map_intersect_domain (*isl_pointers__.p_isl_map_intersect_domain)
+#define isl_map_intersect_range (*isl_pointers__.p_isl_map_intersect_range)
+#define isl_map_is_empty (*isl_pointers__.p_isl_map_is_empty)
+#define isl_map_lex_ge (*isl_pointers__.p_isl_map_lex_ge)
+#define isl_map_lex_le (*isl_pointers__.p_isl_map_lex_le)
+#define isl_map_n_out (*isl_pointers__.p_isl_map_n_out)
+#define isl_map_range (*isl_pointers__.p_isl_map_range)
+#define isl_map_set_tuple_id (*isl_pointers__.p_isl_map_set_tuple_id)
+#define isl_map_universe (*isl_pointers__.p_isl_map_universe)
+#define isl_options_set_on_error (*isl_pointers__.p_isl_options_set_on_error)
+#define isl_options_set_schedule_serialize_sccs (*isl_pointers__.p_isl_options_set_schedule_serialize_sccs)
+#define isl_printer_set_yaml_style (*isl_pointers__.p_isl_printer_set_yaml_style)
+#define isl_options_set_schedule_max_constant_term (*isl_pointers__.p_isl_options_set_schedule_max_constant_term)
+#define isl_options_set_schedule_maximize_band_depth (*isl_pointers__.p_isl_options_set_schedule_maximize_band_depth)
+#define isl_printer_free (*isl_pointers__.p_isl_printer_free)
+#define isl_printer_print_aff (*isl_pointers__.p_isl_printer_print_aff)
+#define isl_printer_print_constraint (*isl_pointers__.p_isl_printer_print_constraint)
+#define isl_printer_print_map (*isl_pointers__.p_isl_printer_print_map)
+#define isl_printer_print_set (*isl_pointers__.p_isl_printer_print_set)
+#define isl_printer_to_file (*isl_pointers__.p_isl_printer_to_file)
+#define isl_pw_aff_add (*isl_pointers__.p_isl_pw_aff_add)
+#define isl_pw_aff_alloc (*isl_pointers__.p_isl_pw_aff_alloc)
+#define isl_pw_aff_copy (*isl_pointers__.p_isl_pw_aff_copy)
+#define isl_pw_aff_eq_set (*isl_pointers__.p_isl_pw_aff_eq_set)
+#define isl_pw_aff_free (*isl_pointers__.p_isl_pw_aff_free)
+#define isl_pw_aff_from_aff (*isl_pointers__.p_isl_pw_aff_from_aff)
+#define isl_pw_aff_ge_set (*isl_pointers__.p_isl_pw_aff_ge_set)
+#define isl_pw_aff_gt_set (*isl_pointers__.p_isl_pw_aff_gt_set)
+#define isl_pw_aff_is_cst (*isl_pointers__.p_isl_pw_aff_is_cst)
+#define isl_pw_aff_le_set (*isl_pointers__.p_isl_pw_aff_le_set)
+#define isl_pw_aff_lt_set (*isl_pointers__.p_isl_pw_aff_lt_set)
+#define isl_pw_aff_mul (*isl_pointers__.p_isl_pw_aff_mul)
+#define isl_pw_aff_ne_set (*isl_pointers__.p_isl_pw_aff_ne_set)
+#define isl_pw_aff_nonneg_set (*isl_pointers__.p_isl_pw_aff_nonneg_set)
+#define isl_pw_aff_set_tuple_id (*isl_pointers__.p_isl_pw_aff_set_tuple_id)
+#define isl_pw_aff_sub (*isl_pointers__.p_isl_pw_aff_sub)
+#define isl_pw_aff_zero_set (*isl_pointers__.p_isl_pw_aff_zero_set)
+#define isl_schedule_free (*isl_pointers__.p_isl_schedule_free)
+#define isl_schedule_get_band_forest (*isl_pointers__.p_isl_schedule_get_band_forest)
+#define isl_set_add_constraint (*isl_pointers__.p_isl_set_add_constraint)
+#define isl_set_add_dims (*isl_pointers__.p_isl_set_add_dims)
+#define isl_set_apply (*isl_pointers__.p_isl_set_apply)
+#define isl_set_coalesce (*isl_pointers__.p_isl_set_coalesce)
+#define isl_set_copy (*isl_pointers__.p_isl_set_copy)
+#define isl_set_dim (*isl_pointers__.p_isl_set_dim)
+#define isl_set_fix_si (*isl_pointers__.p_isl_set_fix_si)
+#define isl_set_free (*isl_pointers__.p_isl_set_free)
+#define isl_set_get_space (*isl_pointers__.p_isl_set_get_space)
+#define isl_set_get_tuple_id (*isl_pointers__.p_isl_set_get_tuple_id)
+#define isl_set_intersect (*isl_pointers__.p_isl_set_intersect)
+#define isl_set_is_empty (*isl_pointers__.p_isl_set_is_empty)
+#define isl_set_n_dim (*isl_pointers__.p_isl_set_n_dim)
+#define isl_set_nat_universe (*isl_pointers__.p_isl_set_nat_universe)
+#define isl_set_project_out (*isl_pointers__.p_isl_set_project_out)
+#define isl_set_set_tuple_id (*isl_pointers__.p_isl_set_set_tuple_id)
+#define isl_set_universe (*isl_pointers__.p_isl_set_universe)
+#define isl_space_add_dims (*isl_pointers__.p_isl_space_add_dims)
+#define isl_space_alloc (*isl_pointers__.p_isl_space_alloc)
+#define isl_space_copy (*isl_pointers__.p_isl_space_copy)
+#define isl_space_dim (*isl_pointers__.p_isl_space_dim)
+#define isl_space_domain (*isl_pointers__.p_isl_space_domain)
+#define isl_space_find_dim_by_id (*isl_pointers__.p_isl_space_find_dim_by_id)
+#define isl_space_free (*isl_pointers__.p_isl_space_free)
+#define isl_space_from_domain (*isl_pointers__.p_isl_space_from_domain)
+#define isl_space_get_tuple_id (*isl_pointers__.p_isl_space_get_tuple_id)
+#define isl_space_params_alloc (*isl_pointers__.p_isl_space_params_alloc)
+#define isl_space_range (*isl_pointers__.p_isl_space_range)
+#define isl_space_set_alloc (*isl_pointers__.p_isl_space_set_alloc)
+#define isl_space_set_dim_id (*isl_pointers__.p_isl_space_set_dim_id)
+#define isl_space_set_tuple_id (*isl_pointers__.p_isl_space_set_tuple_id)
+#define isl_union_map_add_map (*isl_pointers__.p_isl_union_map_add_map)
+#define isl_union_map_align_params (*isl_pointers__.p_isl_union_map_align_params)
+#define isl_union_map_apply_domain (*isl_pointers__.p_isl_union_map_apply_domain)
+#define isl_union_map_apply_range (*isl_pointers__.p_isl_union_map_apply_range)
+#define isl_union_map_compute_flow (*isl_pointers__.p_isl_union_map_compute_flow)
+#define isl_union_map_copy (*isl_pointers__.p_isl_union_map_copy)
+#define isl_union_map_empty (*isl_pointers__.p_isl_union_map_empty)
+#define isl_union_map_flat_range_product (*isl_pointers__.p_isl_union_map_flat_range_product)
+#define isl_union_map_foreach_map (*isl_pointers__.p_isl_union_map_foreach_map)
+#define isl_union_map_free (*isl_pointers__.p_isl_union_map_free)
+#define isl_union_map_from_map (*isl_pointers__.p_isl_union_map_from_map)
+#define isl_union_map_get_ctx (*isl_pointers__.p_isl_union_map_get_ctx)
+#define isl_union_map_get_space (*isl_pointers__.p_isl_union_map_get_space)
+#define isl_union_map_gist_domain (*isl_pointers__.p_isl_union_map_gist_domain)
+#define isl_union_map_gist_range (*isl_pointers__.p_isl_union_map_gist_range)
+#define isl_union_map_intersect_domain (*isl_pointers__.p_isl_union_map_intersect_domain)
+#define isl_union_map_is_empty (*isl_pointers__.p_isl_union_map_is_empty)
+#define isl_union_map_subtract (*isl_pointers__.p_isl_union_map_subtract)
+#define isl_union_map_union (*isl_pointers__.p_isl_union_map_union)
+#define isl_union_set_add_set (*isl_pointers__.p_isl_union_set_add_set)
+#define isl_union_set_compute_schedule (*isl_pointers__.p_isl_union_set_compute_schedule)
+#define isl_union_set_copy (*isl_pointers__.p_isl_union_set_copy)
+#define isl_union_set_empty (*isl_pointers__.p_isl_union_set_empty)
+#define isl_union_set_from_set (*isl_pointers__.p_isl_union_set_from_set)
+#define isl_aff_add_constant_val (*isl_pointers__.p_isl_aff_add_constant_val)
+#define isl_aff_get_coefficient_val (*isl_pointers__.p_isl_aff_get_coefficient_val)
+#define isl_aff_get_ctx (*isl_pointers__.p_isl_aff_get_ctx)
+#define isl_aff_mod_val (*isl_pointers__.p_isl_aff_mod_val)
+#define isl_ast_build_ast_from_schedule (*isl_pointers__.p_isl_ast_build_ast_from_schedule)
+#define isl_ast_build_free (*isl_pointers__.p_isl_ast_build_free)
+#define isl_ast_build_from_context (*isl_pointers__.p_isl_ast_build_from_context)
+#define isl_ast_build_get_ctx (*isl_pointers__.p_isl_ast_build_get_ctx)
+#define isl_ast_build_get_schedule (*isl_pointers__.p_isl_ast_build_get_schedule)
+#define isl_ast_build_get_schedule_space (*isl_pointers__.p_isl_ast_build_get_schedule_space)
+#define isl_ast_build_set_before_each_for (*isl_pointers__.p_isl_ast_build_set_before_each_for)
+#define isl_ast_build_set_options (*isl_pointers__.p_isl_ast_build_set_options)
+#define isl_ast_expr_free (*isl_pointers__.p_isl_ast_expr_free)
+#define isl_ast_expr_from_val (*isl_pointers__.p_isl_ast_expr_from_val)
+#define isl_ast_expr_get_ctx (*isl_pointers__.p_isl_ast_expr_get_ctx)
+#define isl_ast_expr_get_id (*isl_pointers__.p_isl_ast_expr_get_id)
+#define isl_ast_expr_get_op_arg (*isl_pointers__.p_isl_ast_expr_get_op_arg)
+#define isl_ast_expr_get_op_n_arg (*isl_pointers__.p_isl_ast_expr_get_op_n_arg)
+#define isl_ast_expr_get_op_type (*isl_pointers__.p_isl_ast_expr_get_op_type)
+#define isl_ast_expr_get_type (*isl_pointers__.p_isl_ast_expr_get_type)
+#define isl_ast_expr_get_val (*isl_pointers__.p_isl_ast_expr_get_val)
+#define isl_ast_expr_sub (*isl_pointers__.p_isl_ast_expr_sub)
+#define isl_ast_node_block_get_children (*isl_pointers__.p_isl_ast_node_block_get_children)
+#define isl_ast_node_for_get_body (*isl_pointers__.p_isl_ast_node_for_get_body)
+#define isl_ast_node_for_get_cond (*isl_pointers__.p_isl_ast_node_for_get_cond)
+#define isl_ast_node_for_get_inc (*isl_pointers__.p_isl_ast_node_for_get_inc)
+#define isl_ast_node_for_get_init (*isl_pointers__.p_isl_ast_node_for_get_init)
+#define isl_ast_node_for_get_iterator (*isl_pointers__.p_isl_ast_node_for_get_iterator)
+#define isl_ast_node_free (*isl_pointers__.p_isl_ast_node_free)
+#define isl_ast_node_get_annotation (*isl_pointers__.p_isl_ast_node_get_annotation)
+#define isl_ast_node_get_type (*isl_pointers__.p_isl_ast_node_get_type)
+#define isl_ast_node_if_get_cond (*isl_pointers__.p_isl_ast_node_if_get_cond)
+#define isl_ast_node_if_get_else (*isl_pointers__.p_isl_ast_node_if_get_else)
+#define isl_ast_node_if_get_then (*isl_pointers__.p_isl_ast_node_if_get_then)
+#define isl_ast_node_list_free (*isl_pointers__.p_isl_ast_node_list_free)
+#define isl_ast_node_list_get_ast_node (*isl_pointers__.p_isl_ast_node_list_get_ast_node)
+#define isl_ast_node_list_n_ast_node (*isl_pointers__.p_isl_ast_node_list_n_ast_node)
+#define isl_ast_node_user_get_expr (*isl_pointers__.p_isl_ast_node_user_get_expr)
+#define isl_constraint_set_coefficient_val (*isl_pointers__.p_isl_constraint_set_coefficient_val)
+#define isl_constraint_set_constant_val (*isl_pointers__.p_isl_constraint_set_constant_val)
+#define isl_id_get_user (*isl_pointers__.p_isl_id_get_user)
+#define isl_local_space_get_ctx (*isl_pointers__.p_isl_local_space_get_ctx)
+#define isl_map_fix_val (*isl_pointers__.p_isl_map_fix_val)
+#define isl_options_set_ast_build_atomic_upper_bound (*isl_pointers__.p_isl_options_set_ast_build_atomic_upper_bound)
+#define isl_printer_print_ast_node (*isl_pointers__.p_isl_printer_print_ast_node)
+#define isl_printer_print_str (*isl_pointers__.p_isl_printer_print_str)
+#define isl_printer_set_output_format (*isl_pointers__.p_isl_printer_set_output_format)
+#define isl_pw_aff_mod_val (*isl_pointers__.p_isl_pw_aff_mod_val)
+#define isl_schedule_constraints_compute_schedule (*isl_pointers__.p_isl_schedule_constraints_compute_schedule)
+#define isl_schedule_constraints_on_domain (*isl_pointers__.p_isl_schedule_constraints_on_domain)
+#define isl_schedule_constraints_set_coincidence (*isl_pointers__.p_isl_schedule_constraints_set_coincidence)
+#define isl_schedule_constraints_set_proximity (*isl_pointers__.p_isl_schedule_constraints_set_proximity)
+#define isl_schedule_constraints_set_validity (*isl_pointers__.p_isl_schedule_constraints_set_validity)
+#define isl_set_get_dim_id (*isl_pointers__.p_isl_set_get_dim_id)
+#define isl_set_max_val (*isl_pointers__.p_isl_set_max_val)
+#define isl_set_min_val (*isl_pointers__.p_isl_set_min_val)
+#define isl_set_params (*isl_pointers__.p_isl_set_params)
+#define isl_space_align_params (*isl_pointers__.p_isl_space_align_params)
+#define isl_space_map_from_domain_and_range (*isl_pointers__.p_isl_space_map_from_domain_and_range)
+#define isl_space_set_tuple_name (*isl_pointers__.p_isl_space_set_tuple_name)
+#define isl_space_wrap (*isl_pointers__.p_isl_space_wrap)
+#define isl_union_map_from_domain_and_range (*isl_pointers__.p_isl_union_map_from_domain_and_range)
+#define isl_union_map_range (*isl_pointers__.p_isl_union_map_range)
+#define isl_union_set_union (*isl_pointers__.p_isl_union_set_union)
+#define isl_union_set_universe (*isl_pointers__.p_isl_union_set_universe)
+#define isl_val_2exp (*isl_pointers__.p_isl_val_2exp)
+#define isl_val_add_ui (*isl_pointers__.p_isl_val_add_ui)
+#define isl_val_copy (*isl_pointers__.p_isl_val_copy)
+#define isl_val_free (*isl_pointers__.p_isl_val_free)
+#define isl_val_int_from_si (*isl_pointers__.p_isl_val_int_from_si)
+#define isl_val_int_from_ui (*isl_pointers__.p_isl_val_int_from_ui)
+#define isl_val_mul (*isl_pointers__.p_isl_val_mul)
+#define isl_val_neg (*isl_pointers__.p_isl_val_neg)
+#define isl_val_sub (*isl_pointers__.p_isl_val_sub)
+#define isl_printer_print_union_map (*isl_pointers__.p_isl_printer_print_union_map)
+#define isl_pw_aff_get_ctx (*isl_pointers__.p_isl_pw_aff_get_ctx)
+#define isl_val_is_int (*isl_pointers__.p_isl_val_is_int)
+#define isl_ctx_get_max_operations (*isl_pointers__.p_isl_ctx_get_max_operations)
+#define isl_ctx_set_max_operations (*isl_pointers__.p_isl_ctx_set_max_operations)
+#define isl_ctx_last_error (*isl_pointers__.p_isl_ctx_last_error)
+#define isl_ctx_reset_operations (*isl_pointers__.p_isl_ctx_reset_operations)
+#define isl_map_coalesce (*isl_pointers__.p_isl_map_coalesce)
+#define isl_printer_print_schedule (*isl_pointers__.p_isl_printer_print_schedule)
+#define isl_set_set_dim_id (*isl_pointers__.p_isl_set_set_dim_id)
+#define isl_union_map_coalesce (*isl_pointers__.p_isl_union_map_coalesce)
+#define isl_multi_val_set_val (*isl_pointers__.p_isl_multi_val_set_val)
+#define isl_multi_val_zero (*isl_pointers__.p_isl_multi_val_zero)
+#define isl_options_set_schedule_max_coefficient (*isl_pointers__.p_isl_options_set_schedule_max_coefficient)
+#define isl_options_set_tile_scale_tile_loops (*isl_pointers__.p_isl_options_set_tile_scale_tile_loops)
+#define isl_schedule_copy (*isl_pointers__.p_isl_schedule_copy)
+#define isl_schedule_get_map (*isl_pointers__.p_isl_schedule_get_map)
+#define isl_schedule_map_schedule_node_bottom_up (*isl_pointers__.p_isl_schedule_map_schedule_node_bottom_up)
+#define isl_schedule_node_band_get_permutable (*isl_pointers__.p_isl_schedule_node_band_get_permutable)
+#define isl_schedule_node_band_get_space (*isl_pointers__.p_isl_schedule_node_band_get_space)
+#define isl_schedule_node_band_tile (*isl_pointers__.p_isl_schedule_node_band_tile)
+#define isl_schedule_node_child (*isl_pointers__.p_isl_schedule_node_child)
+#define isl_schedule_node_free (*isl_pointers__.p_isl_schedule_node_free)
+#define isl_schedule_node_get_child (*isl_pointers__.p_isl_schedule_node_get_child)
+#define isl_schedule_node_get_ctx (*isl_pointers__.p_isl_schedule_node_get_ctx)
+#define isl_schedule_node_get_type (*isl_pointers__.p_isl_schedule_node_get_type)
+#define isl_schedule_node_n_children (*isl_pointers__.p_isl_schedule_node_n_children)
+#define isl_union_map_is_equal (*isl_pointers__.p_isl_union_map_is_equal)
+#define isl_union_access_info_compute_flow (*isl_pointers__.p_isl_union_access_info_compute_flow)
+#define isl_union_access_info_from_sink (*isl_pointers__.p_isl_union_access_info_from_sink)
+#define isl_union_access_info_set_may_source (*isl_pointers__.p_isl_union_access_info_set_may_source)
+#define isl_union_access_info_set_must_source (*isl_pointers__.p_isl_union_access_info_set_must_source)
+#define isl_union_access_info_set_schedule (*isl_pointers__.p_isl_union_access_info_set_schedule)
+#define isl_union_flow_free (*isl_pointers__.p_isl_union_flow_free)
+#define isl_union_flow_get_may_dependence (*isl_pointers__.p_isl_union_flow_get_may_dependence)
+#define isl_union_flow_get_must_dependence (*isl_pointers__.p_isl_union_flow_get_must_dependence)
+#define isl_aff_var_on_domain (*isl_pointers__.p_isl_aff_var_on_domain)
+#define isl_multi_aff_from_aff (*isl_pointers__.p_isl_multi_aff_from_aff)
+#define isl_schedule_get_ctx (*isl_pointers__.p_isl_schedule_get_ctx)
+#define isl_multi_aff_set_tuple_id (*isl_pointers__.p_isl_multi_aff_set_tuple_id)
+#define isl_multi_aff_dim (*isl_pointers__.p_isl_multi_aff_dim)
+#define isl_schedule_get_domain (*isl_pointers__.p_isl_schedule_get_domain)
+#define isl_union_set_is_empty (*isl_pointers__.p_isl_union_set_is_empty)
+#define isl_union_set_get_space (*isl_pointers__.p_isl_union_set_get_space)
+#define isl_union_pw_multi_aff_empty (*isl_pointers__.p_isl_union_pw_multi_aff_empty)
+#define isl_union_set_foreach_set (*isl_pointers__.p_isl_union_set_foreach_set)
+#define isl_union_set_free (*isl_pointers__.p_isl_union_set_free)
+#define isl_multi_union_pw_aff_from_union_pw_multi_aff (*isl_pointers__.p_isl_multi_union_pw_aff_from_union_pw_multi_aff)
+#define isl_multi_union_pw_aff_apply_multi_aff (*isl_pointers__.p_isl_multi_union_pw_aff_apply_multi_aff)
+#define isl_schedule_insert_partial_schedule (*isl_pointers__.p_isl_schedule_insert_partial_schedule)
+#define isl_union_pw_multi_aff_free (*isl_pointers__.p_isl_union_pw_multi_aff_free)
+#define isl_pw_multi_aff_project_out_map (*isl_pointers__.p_isl_pw_multi_aff_project_out_map)
+#define isl_union_pw_multi_aff_add_pw_multi_aff (*isl_pointers__.p_isl_union_pw_multi_aff_add_pw_multi_aff)
+#define isl_schedule_from_domain (*isl_pointers__.p_isl_schedule_from_domain)
+#define isl_schedule_sequence (*isl_pointers__.p_isl_schedule_sequence)
+#define isl_ast_build_node_from_schedule (*isl_pointers__.p_isl_ast_build_node_from_schedule)
+#define isl_ast_node_mark_get_node (*isl_pointers__.p_isl_ast_node_mark_get_node)
+#define isl_schedule_node_band_member_get_ast_loop_type (*isl_pointers__.p_isl_schedule_node_band_member_get_ast_loop_type)
+#define isl_schedule_node_band_member_set_ast_loop_type (*isl_pointers__.p_isl_schedule_node_band_member_set_ast_loop_type)
+#define isl_val_n_abs_num_chunks (*isl_pointers__.p_isl_val_n_abs_num_chunks)
+#define isl_val_get_abs_num_chunks (*isl_pointers__.p_isl_val_get_abs_num_chunks)
+#define isl_val_int_from_chunks (*isl_pointers__.p_isl_val_int_from_chunks)
+#define isl_val_is_neg (*isl_pointers__.p_isl_val_is_neg)
+#define isl_version (*isl_pointers__.p_isl_version)
+#define isl_options_get_on_error (*isl_pointers__.p_isl_options_get_on_error)
+#define isl_ctx_reset_error (*isl_pointers__.p_isl_ctx_reset_error)
typedef struct poly_dr *poly_dr_p;
@@ -461,5 +1045,6 @@ extern void build_scops (vec<scop_p> *);
extern void dot_all_sese (FILE *, vec<sese_l> &);
extern void dot_sese (sese_l &);
extern void dot_cfg ();
+extern const char *get_isl_version (bool);
#endif
--- gcc/graphite.c.jj 2015-11-04 14:15:32.000000000 +0100
+++ gcc/graphite.c 2015-11-04 14:56:02.645536409 +0100
@@ -60,6 +60,35 @@ along with GCC; see the file COPYING3.
#include "tree-into-ssa.h"
#include "graphite.h"
+__typeof (isl_pointers__) isl_pointers__;
+
+static bool
+init_isl_pointers (void)
+{
+ void *h;
+
+ if (isl_pointers__.inited)
+ return isl_pointers__.h != NULL;
+ h = dlopen ("libisl.so.15", RTLD_LAZY);
+ isl_pointers__.h = h;
+ if (h == NULL)
+ return false;
+#define DYNSYM(x) \
+ do \
+ { \
+ union { __typeof (isl_pointers__.p_##x) p; void *q; } u; \
+ u.q = dlsym (h, #x); \
+ if (u.q == NULL) \
+ return false; \
+ isl_pointers__.p_##x = u.p; \
+ } \
+ while (0)
+ DYNSYMS
+#undef DYNSYM
+ isl_pointers__.inited = true;
+ return true;
+}
+
/* Print global statistics to FILE. */
static void
@@ -365,6 +394,15 @@ graphite_transform_loops (void)
if (parallelized_function_p (cfun->decl))
return;
+ if (number_of_loops (cfun) <= 1)
+ return;
+
+ if (!init_isl_pointers ())
+ {
+ sorry ("Graphite loop optimizations cannot be used");
+ return;
+ }
+
calculate_dominance_info (CDI_DOMINATORS);
/* We rely on post-dominators during merging of SESE regions so those
@@ -455,6 +493,14 @@ graphite_transform_loops (void)
}
}
+const char *
+get_isl_version (bool force)
+{
+ if (force)
+ init_isl_pointers ();
+ return (isl_pointers__.inited && isl_version) ? isl_version () : "none";
+}
+
#else /* If isl is not available: #ifndef HAVE_isl. */
static void
--- gcc/toplev.c.jj 2017-02-19 13:02:31.000000000 +0100
+++ gcc/toplev.c 2017-02-19 16:50:25.536301350 +0100
@@ -94,6 +94,7 @@ along with GCC; see the file COPYING3.
#ifdef HAVE_isl
#include <isl/version.h>
+extern const char *get_isl_version (bool);
#endif
static void general_init (const char *, bool);
@@ -683,7 +684,7 @@ print_version (FILE *file, const char *i
#ifndef HAVE_isl
"none"
#else
- isl_version ()
+ get_isl_version (*indent == 0)
#endif
);
if (strcmp (GCC_GMP_STRINGIFY_VERSION, gmp_version))

View File

@ -0,0 +1,14 @@
--- libgcc/config/t-slibgcc.mp 2018-10-03 16:07:00.336990246 -0400
+++ libgcc/config/t-slibgcc 2018-10-03 16:06:26.719946740 -0400
@@ -30,9 +30,10 @@ SHLIB_LC = -lc
SHLIB_MAKE_SOLINK = $(LN_S) $(SHLIB_SONAME) $(SHLIB_DIR)/$(SHLIB_SOLINK)
SHLIB_INSTALL_SOLINK = $(LN_S) $(SHLIB_SONAME) \
$(DESTDIR)$(slibdir)$(SHLIB_SLIBDIR_QUAL)/$(SHLIB_SOLINK)
+SHLIB_EXTRA_LDFLAGS = -Wl,-z,relro -Wl,-z,now
SHLIB_LINK = $(CC) $(LIBGCC2_CFLAGS) -shared -nodefaultlibs \
- $(SHLIB_LDFLAGS) \
+ $(SHLIB_LDFLAGS) $(SHLIB_EXTRA_LDFLAGS) \
-o $(SHLIB_DIR)/$(SHLIB_SONAME).tmp @multilib_flags@ \
$(SHLIB_OBJS) $(SHLIB_LC) && \
rm -f $(SHLIB_DIR)/$(SHLIB_SOLINK) && \

10068
gcc8-libgomp-20190503.patch Normal file

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,17 @@
2008-06-09 Jakub Jelinek <jakub@redhat.com>
* omp.h.in (omp_nest_lock_t): Fix up for Linux multilibs.
--- libgomp/omp.h.in.jj 2008-06-09 13:34:05.000000000 +0200
+++ libgomp/omp.h.in 2008-06-09 13:34:48.000000000 +0200
@@ -42,8 +42,8 @@ typedef struct
typedef struct
{
- unsigned char _x[@OMP_NEST_LOCK_SIZE@]
- __attribute__((__aligned__(@OMP_NEST_LOCK_ALIGN@)));
+ unsigned char _x[8 + sizeof (void *)]
+ __attribute__((__aligned__(sizeof (void *))));
} omp_nest_lock_t;
#endif

View File

@ -0,0 +1,41 @@
--- libgomp/testsuite/libgomp-test-support.exp.in.jj 2018-04-25 09:40:31.323655308 +0200
+++ libgomp/testsuite/libgomp-test-support.exp.in 2019-04-25 20:01:50.028243827 +0200
@@ -2,4 +2,5 @@ set cuda_driver_include "@CUDA_DRIVER_IN
set cuda_driver_lib "@CUDA_DRIVER_LIB@"
set hsa_runtime_lib "@HSA_RUNTIME_LIB@"
+set offload_plugins "@offload_plugins@"
set offload_targets "@offload_targets@"
--- libgomp/testsuite/lib/libgomp.exp.jj 2018-04-25 09:40:31.584655429 +0200
+++ libgomp/testsuite/lib/libgomp.exp 2019-05-24 11:41:51.015822702 +0200
@@ -40,7 +40,7 @@ load_file libgomp-test-support.exp
# Populate offload_targets_s (offloading targets separated by a space), and
# offload_targets_s_openacc (the same, but with OpenACC names; OpenACC spells
# some of them a little differently).
-set offload_targets_s [split $offload_targets ","]
+set offload_targets_s [split $offload_plugins ","]
set offload_targets_s_openacc {}
foreach offload_target_openacc $offload_targets_s {
# Translate to OpenACC names, or skip if not yet supported.
@@ -137,8 +137,8 @@ proc libgomp_init { args } {
# Add liboffloadmic build directory in LD_LIBRARY_PATH to support
# non-fallback testing for Intel MIC targets
- global offload_targets
- if { [string match "*,intelmic,*" ",$offload_targets,"] } {
+ global offload_plugins
+ if { [string match "*,intelmic,*" ",$offload_plugins,"] } {
append always_ld_library_path ":${blddir}/../liboffloadmic/.libs"
append always_ld_library_path ":${blddir}/../liboffloadmic/plugin/.libs"
# libstdc++ is required by liboffloadmic
@@ -362,8 +362,8 @@ proc check_effective_target_offload_devi
# Return 1 if configured for nvptx offloading.
proc check_effective_target_openacc_nvidia_accel_configured { } {
- global offload_targets
- if { ![string match "*,nvptx,*" ",$offload_targets,"] } {
+ global offload_plugins
+ if { ![string match "*,nvptx,*" ",$offload_plugins,"] } {
return 0
}
# PR libgomp/65099: Currently, we only support offloading in 64-bit

24
gcc8-libstdc++-docs.patch Normal file
View File

@ -0,0 +1,24 @@
--- libstdc++-v3/doc/html/index.html.jj 2011-01-03 12:53:21.282829010 +0100
+++ libstdc++-v3/doc/html/index.html 2011-01-04 18:06:28.999851145 +0100
@@ -5,6 +5,8 @@
<a class="link" href="https://www.fsf.org" target="_top">FSF
</a>
</p><p>
+ Release 8.5.0
+ </p><p>
Permission is granted to copy, distribute and/or modify this
document under the terms of the GNU Free Documentation
License, Version 1.2 or any later version published by the
--- libstdc++-v3/doc/html/api.html.jj 2011-01-03 12:53:21.000000000 +0100
+++ libstdc++-v3/doc/html/api.html 2011-01-04 18:12:01.672757784 +0100
@@ -20,7 +20,9 @@
member functions for the library classes, finding out what is in a
particular include file, looking at inheritance diagrams, etc.
</p><p>
- The API documentation, rendered into HTML, can be viewed online
+ The API documentation, rendered into HTML, can be viewed locally
+ <a class="link" href="api/index.html" target="_top">for the 8.5.0 release</a>,
+ online
<a class="link" href="http://gcc.gnu.org/onlinedocs/" target="_top">for each GCC release</a>
and
<a class="link" href="http://gcc.gnu.org/onlinedocs/libstdc++/latest-doxygen/index.html" target="_top">

View File

@ -0,0 +1,27 @@
libtool sucks.
--- ltmain.sh.jj 2007-12-07 14:53:21.000000000 +0100
+++ ltmain.sh 2008-09-05 21:51:48.000000000 +0200
@@ -5394,6 +5394,7 @@ EOF
rpath="$finalize_rpath"
test "$mode" != relink && rpath="$compile_rpath$rpath"
for libdir in $rpath; do
+ case "$libdir" in /usr/lib|/usr/lib64|/usr/lib/../lib|/usr/lib/../lib64) continue;; esac
if test -n "$hardcode_libdir_flag_spec"; then
if test -n "$hardcode_libdir_separator"; then
if test -z "$hardcode_libdirs"; then
@@ -6071,6 +6072,7 @@ EOF
rpath=
hardcode_libdirs=
for libdir in $compile_rpath $finalize_rpath; do
+ case "$libdir" in /usr/lib|/usr/lib64|/usr/lib/../lib|/usr/lib/../lib64) continue;; esac
if test -n "$hardcode_libdir_flag_spec"; then
if test -n "$hardcode_libdir_separator"; then
if test -z "$hardcode_libdirs"; then
@@ -6120,6 +6122,7 @@ EOF
rpath=
hardcode_libdirs=
for libdir in $finalize_rpath; do
+ case "$libdir" in /usr/lib|/usr/lib64|/usr/lib/../lib|/usr/lib/../lib64) continue;; esac
if test -n "$hardcode_libdir_flag_spec"; then
if test -n "$hardcode_libdir_separator"; then
if test -z "$hardcode_libdirs"; then

17
gcc8-mcet.patch Normal file
View File

@ -0,0 +1,17 @@
2018-04-24 Jakub Jelinek <jakub@redhat.com>
* config/i386/i386.opt (mcet): Remporarily re-add as alias to -mshstk.
--- gcc/config/i386/i386.opt (revision 259613)
+++ gcc/config/i386/i386.opt (revision 259612)
@@ -1006,6 +1006,10 @@ mgeneral-regs-only
Target Report RejectNegative Mask(GENERAL_REGS_ONLY) Var(ix86_target_flags) Save
Generate code which uses only the general registers.
+mcet
+Target Undocumented Alias(mshstk)
+;; Deprecated
+
mshstk
Target Report Mask(ISA_SHSTK) Var(ix86_isa_flags) Save
Enable shadow stack built-in functions from Control-flow Enforcement

50
gcc8-no-add-needed.patch Normal file
View File

@ -0,0 +1,50 @@
2010-02-08 Roland McGrath <roland@redhat.com>
* config/rs6000/sysv4.h (LINK_EH_SPEC): Pass --no-add-needed to the
linker.
* config/gnu-user.h (LINK_EH_SPEC): Likewise.
* config/alpha/elf.h (LINK_EH_SPEC): Likewise.
* config/ia64/linux.h (LINK_EH_SPEC): Likewise.
--- gcc/config/alpha/elf.h.jj 2011-01-03 12:52:31.118056764 +0100
+++ gcc/config/alpha/elf.h 2011-01-04 18:14:10.931874160 +0100
@@ -168,5 +168,5 @@ extern int alpha_this_gpdisp_sequence_nu
I imagine that other systems will catch up. In the meantime, it
doesn't harm to make sure that the data exists to be used later. */
#if defined(HAVE_LD_EH_FRAME_HDR)
-#define LINK_EH_SPEC "%{!static|static-pie:--eh-frame-hdr} "
+#define LINK_EH_SPEC "--no-add-needed %{!static|static-pie:--eh-frame-hdr} "
#endif
--- gcc/config/ia64/linux.h.jj 2011-01-03 13:02:11.462994522 +0100
+++ gcc/config/ia64/linux.h 2011-01-04 18:14:10.931874160 +0100
@@ -76,7 +76,7 @@ do { \
Signalize that because we have fde-glibc, we don't need all C shared libs
linked against -lgcc_s. */
#undef LINK_EH_SPEC
-#define LINK_EH_SPEC ""
+#define LINK_EH_SPEC "--no-add-needed "
#undef TARGET_INIT_LIBFUNCS
#define TARGET_INIT_LIBFUNCS ia64_soft_fp_init_libfuncs
--- gcc/config/gnu-user.h.jj 2011-01-03 12:53:03.739057299 +0100
+++ gcc/config/gnu-user.h 2011-01-04 18:14:10.932814884 +0100
@@ -133,7 +133,7 @@ see the files COPYING3 and COPYING.RUNTI
#define LIB_SPEC GNU_USER_TARGET_LIB_SPEC
#if defined(HAVE_LD_EH_FRAME_HDR)
-#define LINK_EH_SPEC "%{!static|static-pie:--eh-frame-hdr} "
+#define LINK_EH_SPEC "--no-add-needed %{!static|static-pie:--eh-frame-hdr} "
#endif
#undef LINK_GCC_C_SEQUENCE_SPEC
--- gcc/config/rs6000/sysv4.h.jj 2011-01-03 13:02:18.255994215 +0100
+++ gcc/config/rs6000/sysv4.h 2011-01-04 18:14:10.933888871 +0100
@@ -816,7 +816,7 @@ ENDIAN_SELECT(" -mbig", " -mlittle", DEF
-dynamic-linker " GNU_USER_DYNAMIC_LINKER "}}"
#if defined(HAVE_LD_EH_FRAME_HDR)
-# define LINK_EH_SPEC "%{!static|static-pie:--eh-frame-hdr} "
+# define LINK_EH_SPEC "--no-add-needed %{!static|static-pie:--eh-frame-hdr} "
#endif
#define CPP_OS_LINUX_SPEC "-D__unix__ -D__gnu_linux__ -D__linux__ \

844
gcc8-pch-tweaks.patch Normal file
View File

@ -0,0 +1,844 @@
commit fe7c3ecff1f9c0520090a77fa824d8c5d9dbec12
Author: Jakub Jelinek <jakub@redhat.com>
Date: Fri Dec 3 11:03:30 2021 +0100
pch: Add support for PCH for relocatable executables [PR71934]
So, if we want to make PCH work for PIEs, I'd say we can:
1) add a new GTY option, say callback, which would act like
skip for non-PCH and for PCH would make us skip it but
remember for address bias translation
2) drop the skip for tree_translation_unit_decl::language
3) change get_unnamed_section to have const char * as
last argument instead of const void *, change
unnamed_section::data also to const char * and update
everything related to that
4) maybe add a host hook whether it is ok to support binaries
changing addresses (the only thing I'm worried is if
some host that uses function descriptors allocates them
dynamically instead of having them somewhere in the
executable)
5) maybe add a gengtype warning if it sees in GTY tracked
structure a function pointer without that new callback
option
Here is 1), 2), 3) implemented.
Note, on stdc++.h.gch/O2g.gch there are just those 10 relocations without
the second patch, with it a few more, but nothing huge. And for non-PIEs
there isn't really any extra work on the load side except freading two scalar
values and fseek.
2021-12-03 Jakub Jelinek <jakub@redhat.com>
PR pch/71934
gcc/
* ggc.h (gt_pch_note_callback): Declare.
* gengtype.h (enum typekind): Add TYPE_CALLBACK.
(callback_type): Declare.
* gengtype.c (dbgprint_count_type_at): Handle TYPE_CALLBACK.
(callback_type): New variable.
(process_gc_options): Add CALLBACK argument, handle callback
option.
(set_gc_used_type): Adjust process_gc_options caller, if callback,
set type to &callback_type.
(output_mangled_typename): Handle TYPE_CALLBACK.
(walk_type): Likewise. Handle callback option.
(write_types_process_field): Handle TYPE_CALLBACK.
(write_types_local_user_process_field): Likewise.
(write_types_local_process_field): Likewise.
(write_root): Likewise.
(dump_typekind): Likewise.
(dump_type): Likewise.
* gengtype-state.c (type_lineloc): Handle TYPE_CALLBACK.
(state_writer::write_state_callback_type): New method.
(state_writer::write_state_type): Handle TYPE_CALLBACK.
(read_state_callback_type): New function.
(read_state_type): Handle TYPE_CALLBACK.
* ggc-common.c (callback_vec): New variable.
(gt_pch_note_callback): New function.
(gt_pch_save): Stream out gt_pch_save function address and relocation
table.
(gt_pch_restore): Stream in saved gt_pch_save function address and
relocation table and apply relocations if needed.
* doc/gty.texi (callback): Document new GTY option.
* varasm.c (get_unnamed_section): Change callback argument's type and
last argument's type from const void * to const char *.
(output_section_asm_op): Change argument's type from const void *
to const char *, remove unnecessary cast.
* tree-core.h (struct tree_translation_unit_decl): Drop GTY((skip))
from language member.
* output.h (unnamed_section_callback): Change argument type from
const void * to const char *.
(struct unnamed_section): Use GTY((callback)) instead of GTY((skip))
for callback member. Change data member type from const void *
to const char *.
(struct noswitch_section): Use GTY((callback)) instead of GTY((skip))
for callback member.
(get_unnamed_section): Change callback argument's type and
last argument's type from const void * to const char *.
(output_section_asm_op): Change argument's type from const void *
to const char *.
* config/avr/avr.c (avr_output_progmem_section_asm_op): Likewise.
Remove unneeded cast.
* config/darwin.c (output_objc_section_asm_op): Change argument's type
from const void * to const char *.
* config/pa/pa.c (som_output_text_section_asm_op): Likewise.
(som_output_comdat_data_section_asm_op): Likewise.
* config/rs6000/rs6000.c (rs6000_elf_output_toc_section_asm_op):
Likewise.
(rs6000_xcoff_output_readonly_section_asm_op): Likewise. Instead
of dereferencing directive hardcode variable names and decide based on
whether directive is NULL or not.
(rs6000_xcoff_output_readwrite_section_asm_op): Change argument's type
from const void * to const char *.
(rs6000_xcoff_output_tls_section_asm_op): Likewise. Instead
of dereferencing directive hardcode variable names and decide based on
whether directive is NULL or not.
(rs6000_xcoff_output_toc_section_asm_op): Change argument's type
from const void * to const char *.
(rs6000_xcoff_asm_init_sections): Adjust get_unnamed_section callers.
gcc/c-family/
* c-pch.c (struct c_pch_validity): Remove pch_init member.
(pch_init): Don't initialize v.pch_init.
(c_common_valid_pch): Don't warn and punt if .text addresses change.
libcpp/
* include/line-map.h (class line_maps): Add GTY((callback)) to
reallocator and round_alloc_size members.
commit 4dc6d19222581c77a174d44d97507d234fb7e39b
Author: Jakub Jelinek <jakub@redhat.com>
Date: Mon Dec 6 11:18:58 2021 +0100
avr: Fix AVR build [PR71934]
On Mon, Dec 06, 2021 at 11:00:30AM +0100, Martin Liška wrote:
> Jakub, I think the patch broke avr-linux target:
>
> g++ -fno-PIE -c -g -DIN_GCC -DCROSS_DIRECTORY_STRUCTURE -fno-exceptions -fno-rtti -fasynchronous-unwind-tables -W -Wall -Wno-narrowing -Wwrite-strings -Wcast-qual -Wno-erro
> /home/marxin/Programming/gcc/gcc/config/avr/avr.c: In function void avr_output_data_section_asm_op(const void*):
> /home/marxin/Programming/gcc/gcc/config/avr/avr.c:10097:26: error: invalid conversion from const void* to const char* [-fpermissive]
This patch fixes that.
2021-12-06 Jakub Jelinek <jakub@redhat.com>
PR pch/71934
* config/avr/avr.c (avr_output_data_section_asm_op,
avr_output_bss_section_asm_op): Change argument type from const void *
to const char *.
diff --git a/gcc/c-family/c-pch.c b/gcc/c-family/c-pch.c
index 5da60423354..2cafa1387bb 100644
--- a/gcc/c-family/c-pch.c
+++ b/gcc/c-family/c-pch.c
@@ -58,7 +58,6 @@ struct c_pch_validity
{
unsigned char debug_info_type;
signed char match[MATCH_SIZE];
- void (*pch_init) (void);
size_t target_data_length;
};
@@ -123,7 +122,6 @@ pch_init (void)
gcc_assert (v.match[i] == *pch_matching[i].flag_var);
}
}
- v.pch_init = &pch_init;
target_validity = targetm.get_pch_validity (&v.target_data_length);
if (fwrite (partial_pch, IDENT_LENGTH, 1, f) != 1
@@ -287,20 +285,6 @@ c_common_valid_pch (cpp_reader *pfile, c
}
}
- /* If the text segment was not loaded at the same address as it was
- when the PCH file was created, function pointers loaded from the
- PCH will not be valid. We could in theory remap all the function
- pointers, but no support for that exists at present.
- Since we have the same executable, it should only be necessary to
- check one function. */
- if (v.pch_init != &pch_init)
- {
- if (cpp_get_options (pfile)->warn_invalid_pch)
- cpp_error (pfile, CPP_DL_WARNING,
- "%s: had text segment at different address", name);
- return 2;
- }
-
/* Check the target-specific validity data. */
{
void *this_file_data = xmalloc (v.target_data_length);
diff --git a/gcc/config/avr/avr.c b/gcc/config/avr/avr.c
index 200701a583c..6ba038881d6 100644
--- a/gcc/config/avr/avr.c
+++ b/gcc/config/avr/avr.c
@@ -10114,10 +10114,9 @@ avr_output_bss_section_asm_op (const void *data)
/* Unnamed section callback for progmem*.data sections. */
static void
-avr_output_progmem_section_asm_op (const void *data)
+avr_output_progmem_section_asm_op (const char *data)
{
- fprintf (asm_out_file, "\t.section\t%s,\"a\",@progbits\n",
- (const char*) data);
+ fprintf (asm_out_file, "\t.section\t%s,\"a\",@progbits\n", data);
}
diff --git a/gcc/config/darwin.c b/gcc/config/darwin.c
index c5ba7927ce1..8ad5b26c980 100644
--- a/gcc/config/darwin.c
+++ b/gcc/config/darwin.c
@@ -134,7 +134,7 @@ int emit_aligned_common = false;
DIRECTIVE is as for output_section_asm_op. */
static void
-output_objc_section_asm_op (const void *directive)
+output_objc_section_asm_op (const char *directive)
{
static bool been_here = false;
diff --git a/gcc/config/pa/pa.c b/gcc/config/pa/pa.c
index f22d25a4066..2b10ef34061 100644
--- a/gcc/config/pa/pa.c
+++ b/gcc/config/pa/pa.c
@@ -10009,7 +10009,7 @@ pa_arg_partial_bytes (cumulative_args_t cum_v, const function_arg_info &arg)
to the default text subspace. */
static void
-som_output_text_section_asm_op (const void *data ATTRIBUTE_UNUSED)
+som_output_text_section_asm_op (const char *data ATTRIBUTE_UNUSED)
{
gcc_assert (TARGET_SOM);
if (TARGET_GAS)
@@ -10053,7 +10053,7 @@ som_output_text_section_asm_op (const void *data ATTRIBUTE_UNUSED)
sections. This function is only used with SOM. */
static void
-som_output_comdat_data_section_asm_op (const void *data)
+som_output_comdat_data_section_asm_op (const char *data)
{
in_section = NULL;
output_section_asm_op (data);
diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
index 945157b1c1a..34089743759 100644
--- a/gcc/config/rs6000/rs6000.c
+++ b/gcc/config/rs6000/rs6000.c
@@ -20599,7 +20599,7 @@ rs6000_ms_bitfield_layout_p (const_tree record_type)
/* A get_unnamed_section callback, used for switching to toc_section. */
static void
-rs6000_elf_output_toc_section_asm_op (const void *data ATTRIBUTE_UNUSED)
+rs6000_elf_output_toc_section_asm_op (const char *data ATTRIBUTE_UNUSED)
{
if ((DEFAULT_ABI == ABI_AIX || DEFAULT_ABI == ABI_ELFv2)
&& TARGET_MINIMAL_TOC)
@@ -21303,35 +21303,39 @@ rs6000_xcoff_asm_globalize_label (FILE *stream, const char *name)
points to the section string variable. */
static void
-rs6000_xcoff_output_readonly_section_asm_op (const void *directive)
+rs6000_xcoff_output_readonly_section_asm_op (const char *directive)
{
fprintf (asm_out_file, "\t.csect %s[RO],%s\n",
- *(const char *const *) directive,
+ directive
+ ? xcoff_private_rodata_section_name
+ : xcoff_read_only_section_name,
XCOFF_CSECT_DEFAULT_ALIGNMENT_STR);
}
/* Likewise for read-write sections. */
static void
-rs6000_xcoff_output_readwrite_section_asm_op (const void *directive)
+rs6000_xcoff_output_readwrite_section_asm_op (const char *)
{
fprintf (asm_out_file, "\t.csect %s[RW],%s\n",
- *(const char *const *) directive,
+ xcoff_private_data_section_name,
XCOFF_CSECT_DEFAULT_ALIGNMENT_STR);
}
static void
-rs6000_xcoff_output_tls_section_asm_op (const void *directive)
+rs6000_xcoff_output_tls_section_asm_op (const char *directive)
{
fprintf (asm_out_file, "\t.csect %s[TL],%s\n",
- *(const char *const *) directive,
+ directive
+ ? xcoff_private_data_section_name
+ : xcoff_tls_data_section_name,
XCOFF_CSECT_DEFAULT_ALIGNMENT_STR);
}
/* A get_unnamed_section callback, used for switching to toc_section. */
static void
-rs6000_xcoff_output_toc_section_asm_op (const void *data ATTRIBUTE_UNUSED)
+rs6000_xcoff_output_toc_section_asm_op (const char *data ATTRIBUTE_UNUSED)
{
if (TARGET_MINIMAL_TOC)
{
@@ -21358,26 +21362,26 @@ rs6000_xcoff_asm_init_sections (void)
{
read_only_data_section
= get_unnamed_section (0, rs6000_xcoff_output_readonly_section_asm_op,
- &xcoff_read_only_section_name);
+ NULL);
private_data_section
= get_unnamed_section (SECTION_WRITE,
rs6000_xcoff_output_readwrite_section_asm_op,
- &xcoff_private_data_section_name);
+ NULL);
read_only_private_data_section
= get_unnamed_section (0, rs6000_xcoff_output_readonly_section_asm_op,
- &xcoff_private_rodata_section_name);
+ "");
tls_data_section
= get_unnamed_section (SECTION_TLS,
rs6000_xcoff_output_tls_section_asm_op,
- &xcoff_tls_data_section_name);
+ NULL);
tls_private_data_section
= get_unnamed_section (SECTION_TLS,
rs6000_xcoff_output_tls_section_asm_op,
- &xcoff_private_data_section_name);
+ "");
toc_section
= get_unnamed_section (0, rs6000_xcoff_output_toc_section_asm_op, NULL);
diff --git a/gcc/doc/gty.texi b/gcc/doc/gty.texi
index b996ff2c44e..ca2c8404894 100644
--- a/gcc/doc/gty.texi
+++ b/gcc/doc/gty.texi
@@ -205,6 +205,15 @@ If @code{skip} is applied to a field, the type machinery will ignore it.
This is somewhat dangerous; the only safe use is in a union when one
field really isn't ever used.
+@findex callback
+@item callback
+
+@code{callback} should be applied to fields with pointer to function type
+and causes the field to be ignored similarly to @code{skip}, except when
+writing PCH and the field is non-NULL it will remember the field's address
+for relocation purposes if the process writing PCH has different load base
+from a process reading PCH.
+
@findex for_user
@item for_user
diff --git a/gcc/gengtype-state.c b/gcc/gengtype-state.c
index ac9d536963f..36a96e84574 100644
--- a/gcc/gengtype-state.c
+++ b/gcc/gengtype-state.c
@@ -57,6 +57,7 @@ type_lineloc (const_type_p ty)
case TYPE_STRING:
case TYPE_POINTER:
case TYPE_ARRAY:
+ case TYPE_CALLBACK:
return NULL;
default:
gcc_unreachable ();
@@ -171,6 +172,7 @@ private:
void write_state_version (const char *version);
void write_state_scalar_type (type_p current);
void write_state_string_type (type_p current);
+ void write_state_callback_type (type_p current);
void write_state_undefined_type (type_p current);
void write_state_struct_union_type (type_p current, const char *kindstr);
void write_state_struct_type (type_p current);
@@ -898,6 +900,20 @@ state_writer::write_state_string_type (type_p current)
fatal ("Unexpected type in write_state_string_type");
}
+/* Write the callback type. There is only one such thing! */
+void
+state_writer::write_state_callback_type (type_p current)
+{
+ if (current == &callback_type)
+ {
+ write_any_indent (0);
+ fprintf (state_file, "callback ");
+ write_state_common_type_content (current);
+ }
+ else
+ fatal ("Unexpected type in write_state_callback_type");
+}
+
/* Write an undefined type. */
void
state_writer::write_state_undefined_type (type_p current)
@@ -1143,6 +1159,9 @@ state_writer::write_state_type (type_p current)
case TYPE_STRING:
write_state_string_type (current);
break;
+ case TYPE_CALLBACK:
+ write_state_callback_type (current);
+ break;
}
}
@@ -1477,6 +1496,14 @@ read_state_string_type (type_p *type)
read_state_common_type_content (*type);
}
+/* Read the callback_type. */
+static void
+read_state_callback_type (type_p *type)
+{
+ *type = &callback_type;
+ read_state_common_type_content (*type);
+}
+
/* Read a lang_bitmap representing a set of GCC front-end languages. */
static void
@@ -1834,6 +1861,11 @@ read_state_type (type_p *current)
next_state_tokens (1);
read_state_string_type (current);
}
+ else if (state_token_is_name (t0, "callback"))
+ {
+ next_state_tokens (1);
+ read_state_callback_type (current);
+ }
else if (state_token_is_name (t0, "undefined"))
{
*current = XCNEW (struct type);
diff --git a/gcc/gengtype.c b/gcc/gengtype.c
index a77cfd92bfa..b9daaa43689 100644
--- a/gcc/gengtype.c
+++ b/gcc/gengtype.c
@@ -172,6 +172,7 @@ dbgprint_count_type_at (const char *fil, int lin, const char *msg, type_p t)
int nb_struct = 0, nb_union = 0, nb_array = 0, nb_pointer = 0;
int nb_lang_struct = 0;
int nb_user_struct = 0, nb_undefined = 0;
+ int nb_callback = 0;
type_p p = NULL;
for (p = t; p; p = p->next)
{
@@ -202,6 +203,9 @@ dbgprint_count_type_at (const char *fil, int lin, const char *msg, type_p t)
case TYPE_ARRAY:
nb_array++;
break;
+ case TYPE_CALLBACK:
+ nb_callback++;
+ break;
case TYPE_LANG_STRUCT:
nb_lang_struct++;
break;
@@ -217,6 +221,8 @@ dbgprint_count_type_at (const char *fil, int lin, const char *msg, type_p t)
fprintf (stderr, "@@%%@@ %d structs, %d unions\n", nb_struct, nb_union);
if (nb_pointer > 0 || nb_array > 0)
fprintf (stderr, "@@%%@@ %d pointers, %d arrays\n", nb_pointer, nb_array);
+ if (nb_callback > 0)
+ fprintf (stderr, "@@%%@@ %d callbacks\n", nb_callback);
if (nb_lang_struct > 0)
fprintf (stderr, "@@%%@@ %d lang_structs\n", nb_lang_struct);
if (nb_user_struct > 0)
@@ -495,6 +501,10 @@ struct type scalar_char = {
TYPE_SCALAR, 0, 0, 0, GC_USED, {0}
};
+struct type callback_type = {
+ TYPE_CALLBACK, 0, 0, 0, GC_USED, {0}
+};
+
/* Lists of various things. */
pair_p typedefs = NULL;
@@ -1464,7 +1474,7 @@ static void set_gc_used (pair_p);
static void
process_gc_options (options_p opt, enum gc_used_enum level, int *maybe_undef,
- int *length, int *skip, type_p *nested_ptr)
+ int *length, int *skip, int *callback, type_p *nested_ptr)
{
options_p o;
for (o = opt; o; o = o->next)
@@ -1478,6 +1488,8 @@ process_gc_options (options_p opt, enum gc_used_enum level, int *maybe_undef,
*length = 1;
else if (strcmp (o->name, "skip") == 0)
*skip = 1;
+ else if (strcmp (o->name, "callback") == 0)
+ *callback = 1;
else if (strcmp (o->name, "nested_ptr") == 0
&& o->kind == OPTION_NESTED)
*nested_ptr = ((const struct nested_ptr_data *) o->info.nested)->type;
@@ -1526,7 +1538,7 @@ set_gc_used_type (type_p t, enum gc_used_enum level,
type_p dummy2;
bool allow_undefined_field_types = (t->kind == TYPE_USER_STRUCT);
- process_gc_options (t->u.s.opt, level, &dummy, &dummy, &dummy,
+ process_gc_options (t->u.s.opt, level, &dummy, &dummy, &dummy, &dummy,
&dummy2);
if (t->u.s.base_class)
@@ -1542,9 +1554,10 @@ set_gc_used_type (type_p t, enum gc_used_enum level,
int maybe_undef = 0;
int length = 0;
int skip = 0;
+ int callback = 0;
type_p nested_ptr = NULL;
process_gc_options (f->opt, level, &maybe_undef, &length, &skip,
- &nested_ptr);
+ &callback, &nested_ptr);
if (nested_ptr && f->type->kind == TYPE_POINTER)
set_gc_used_type (nested_ptr, GC_POINTED_TO);
@@ -1554,6 +1567,8 @@ set_gc_used_type (type_p t, enum gc_used_enum level,
set_gc_used_type (f->type->u.p, GC_MAYBE_POINTED_TO);
else if (skip)
; /* target type is not used through this field */
+ else if (callback)
+ f->type = &callback_type;
else
set_gc_used_type (f->type, GC_USED, allow_undefined_field_types);
}
@@ -2519,6 +2534,7 @@ output_mangled_typename (outf_p of, const_type_p t)
{
case TYPE_NONE:
case TYPE_UNDEFINED:
+ case TYPE_CALLBACK:
gcc_unreachable ();
break;
case TYPE_POINTER:
@@ -2719,6 +2735,8 @@ walk_type (type_p t, struct walk_type_data *d)
;
else if (strcmp (oo->name, "for_user") == 0)
;
+ else if (strcmp (oo->name, "callback") == 0)
+ ;
else
error_at_line (d->line, "unknown option `%s'\n", oo->name);
@@ -2744,6 +2762,7 @@ walk_type (type_p t, struct walk_type_data *d)
{
case TYPE_SCALAR:
case TYPE_STRING:
+ case TYPE_CALLBACK:
d->process_field (t, d);
break;
@@ -3275,6 +3294,7 @@ write_types_process_field (type_p f, const struct walk_type_data *d)
break;
case TYPE_SCALAR:
+ case TYPE_CALLBACK:
break;
case TYPE_ARRAY:
@@ -3820,6 +3840,7 @@ write_types_local_user_process_field (type_p f, const struct walk_type_data *d)
break;
case TYPE_SCALAR:
+ case TYPE_CALLBACK:
break;
case TYPE_ARRAY:
@@ -3906,6 +3927,13 @@ write_types_local_process_field (type_p f, const struct walk_type_data *d)
case TYPE_SCALAR:
break;
+ case TYPE_CALLBACK:
+ oprintf (d->of, "%*sif ((void *)(%s) == this_obj)\n", d->indent, "",
+ d->prev_val[3]);
+ oprintf (d->of, "%*s gt_pch_note_callback (&(%s), this_obj);\n",
+ d->indent, "", d->val);
+ break;
+
case TYPE_ARRAY:
case TYPE_NONE:
case TYPE_UNDEFINED:
@@ -4434,6 +4462,7 @@ write_root (outf_p f, pair_p v, type_p type, const char *name, int has_length,
case TYPE_UNDEFINED:
case TYPE_UNION:
case TYPE_LANG_STRUCT:
+ case TYPE_CALLBACK:
error_at_line (line, "global `%s' is unimplemented type", name);
}
}
@@ -4728,6 +4757,9 @@ dump_typekind (int indent, enum typekind kind)
case TYPE_ARRAY:
printf ("TYPE_ARRAY");
break;
+ case TYPE_CALLBACK:
+ printf ("TYPE_CALLBACK");
+ break;
case TYPE_LANG_STRUCT:
printf ("TYPE_LANG_STRUCT");
break;
@@ -4894,6 +4926,7 @@ dump_type (int indent, type_p t)
t->u.scalar_is_char ? "true" : "false");
break;
case TYPE_STRING:
+ case TYPE_CALLBACK:
break;
case TYPE_STRUCT:
case TYPE_UNION:
diff --git a/gcc/gengtype.h b/gcc/gengtype.h
index 8a7a54957ea..8fa7064ca85 100644
--- a/gcc/gengtype.h
+++ b/gcc/gengtype.h
@@ -154,6 +154,9 @@ enum typekind {
TYPE_UNION, /* Type for GTY-ed discriminated unions. */
TYPE_POINTER, /* Pointer type to GTY-ed type. */
TYPE_ARRAY, /* Array of GTY-ed types. */
+ TYPE_CALLBACK, /* A function pointer that needs relocation if
+ the executable has been loaded at a different
+ address. */
TYPE_LANG_STRUCT, /* GCC front-end language specific structs.
Various languages may have homonymous but
different structs. */
@@ -331,6 +334,9 @@ extern struct type string_type;
extern struct type scalar_nonchar;
extern struct type scalar_char;
+/* The one and only TYPE_CALLBACK. */
+extern struct type callback_type;
+
/* Test if a type is a union, either a plain one or a language
specific one. */
#define UNION_P(x) \
diff --git a/gcc/ggc-common.c b/gcc/ggc-common.c
index b6abed1d9a2..7c998e95473 100644
--- a/gcc/ggc-common.c
+++ b/gcc/ggc-common.c
@@ -256,6 +256,7 @@ saving_hasher::equal (const ptr_data *p1
}
static hash_table<saving_hasher> *saving_htab;
+static vec<void *> callback_vec;
/* Register an object in the hash table. */
@@ -288,6 +289,23 @@ gt_pch_note_object (void *obj, void *not
return 1;
}
+/* Register address of a callback pointer. */
+void
+gt_pch_note_callback (void *obj, void *base)
+{
+ void *ptr;
+ memcpy (&ptr, obj, sizeof (void *));
+ if (ptr != NULL)
+ {
+ struct ptr_data *data
+ = (struct ptr_data *)
+ saving_htab->find_with_hash (base, POINTER_HASH (base));
+ gcc_assert (data);
+ callback_vec.safe_push ((char *) data->new_addr
+ + ((char *) obj - (char *) base));
+ }
+}
+
/* Register an object in the hash table. */
void
@@ -582,10 +600,20 @@ gt_pch_save (FILE *f)
ggc_pch_finish (state.d, state.f);
gt_pch_fixup_stringpool ();
+ unsigned num_callbacks = callback_vec.length ();
+ void (*pch_save) (FILE *) = &gt_pch_save;
+ if (fwrite (&pch_save, sizeof (pch_save), 1, f) != 1
+ || fwrite (&num_callbacks, sizeof (num_callbacks), 1, f) != 1
+ || (num_callbacks
+ && fwrite (callback_vec.address (), sizeof (void *), num_callbacks,
+ f) != num_callbacks))
+ fatal_error (input_location, "cannot write PCH file: %m");
+
XDELETE (state.ptrs);
XDELETE (this_object);
delete saving_htab;
saving_htab = NULL;
+ callback_vec.release ();
}
/* Read the state of the compiler back in from F. */
@@ -639,6 +667,30 @@ gt_pch_restore (FILE *f)
ggc_pch_read (f, mmi.preferred_base);
gt_pch_restore_stringpool ();
+
+ void (*pch_save) (FILE *);
+ unsigned num_callbacks;
+ if (fread (&pch_save, sizeof (pch_save), 1, f) != 1
+ || fread (&num_callbacks, sizeof (num_callbacks), 1, f) != 1)
+ fatal_error (input_location, "cannot read PCH file: %m");
+ if (pch_save != &gt_pch_save)
+ {
+ uintptr_t bias = (uintptr_t) &gt_pch_save - (uintptr_t) pch_save;
+ void **ptrs = XNEWVEC (void *, num_callbacks);
+ unsigned i;
+
+ if (fread (ptrs, sizeof (void *), num_callbacks, f) != num_callbacks)
+ fatal_error (input_location, "cannot read PCH file: %m");
+ for (i = 0; i < num_callbacks; ++i)
+ {
+ memcpy (&pch_save, ptrs[i], sizeof (pch_save));
+ pch_save = (void (*) (FILE *)) ((uintptr_t) pch_save + bias);
+ memcpy (ptrs[i], &pch_save, sizeof (pch_save));
+ }
+ XDELETE (ptrs);
+ }
+ else if (fseek (f, num_callbacks * sizeof (void *), SEEK_CUR) != 0)
+ fatal_error (input_location, "cannot read PCH file: %m");
}
/* Default version of HOST_HOOKS_GT_PCH_GET_ADDRESS when mmap is not present.
diff --git a/gcc/ggc.h b/gcc/ggc.h
index 5e921d957fd..c005f7e0412 100644
--- a/gcc/ggc.h
+++ b/gcc/ggc.h
@@ -46,6 +46,10 @@ typedef void (*gt_handle_reorder) (void *, void *, gt_pointer_operator,
/* Used by the gt_pch_n_* routines. Register an object in the hash table. */
extern int gt_pch_note_object (void *, void *, gt_note_pointers);
+/* Used by the gt_pch_p_* routines. Register address of a callback
+ pointer. */
+extern void gt_pch_note_callback (void *, void *);
+
/* Used by the gt_pch_n_* routines. Register that an object has a reorder
function. */
extern void gt_pch_note_reorder (void *, void *, gt_handle_reorder);
diff --git a/gcc/output.h b/gcc/output.h
index 8f6f15308f4..4a23795bf7e 100644
--- a/gcc/output.h
+++ b/gcc/output.h
@@ -456,7 +456,7 @@ struct GTY(()) named_section {
/* A callback that writes the assembly code for switching to an unnamed
section. The argument provides callback-specific data. */
-typedef void (*unnamed_section_callback) (const void *);
+typedef void (*unnamed_section_callback) (const char *);
/* Information about a SECTION_UNNAMED section. */
struct GTY(()) unnamed_section {
@@ -464,8 +464,8 @@ struct GTY(()) unnamed_section {
/* The callback used to switch to the section, and the data that
should be passed to the callback. */
- unnamed_section_callback GTY ((skip)) callback;
- const void *GTY ((skip)) data;
+ unnamed_section_callback GTY ((callback)) callback;
+ const char *data;
/* The next entry in the chain of unnamed sections. */
section *next;
@@ -489,7 +489,7 @@ struct GTY(()) noswitch_section {
struct section_common common;
/* The callback used to assemble decls in this section. */
- noswitch_section_callback GTY ((skip)) callback;
+ noswitch_section_callback GTY ((callback)) callback;
};
/* Information about a section, which may be named or unnamed. */
@@ -524,8 +524,8 @@ extern GTY(()) section *bss_noswitch_sec
extern GTY(()) section *in_section;
extern GTY(()) bool in_cold_section_p;
-extern section *get_unnamed_section (unsigned int, void (*) (const void *),
- const void *);
+extern section *get_unnamed_section (unsigned int, void (*) (const char *),
+ const char *);
extern section *get_section (const char *, unsigned int, tree);
extern section *get_named_section (tree, const char *, int);
extern section *get_variable_section (tree, bool);
@@ -546,7 +546,7 @@ extern section *get_cdtor_priority_secti
extern bool unlikely_text_section_p (section *);
extern void switch_to_section (section *);
-extern void output_section_asm_op (const void *);
+extern void output_section_asm_op (const char *);
extern void record_tm_clone_pair (tree, tree);
extern void finish_tm_clone_pairs (void);
diff --git a/gcc/tree-core.h b/gcc/tree-core.h
index 8ab119dc9a2..91ae5237d7e 100644
--- a/gcc/tree-core.h
+++ b/gcc/tree-core.h
@@ -1961,7 +1961,7 @@ struct GTY(()) tree_function_decl {
struct GTY(()) tree_translation_unit_decl {
struct tree_decl_common common;
/* Source language of this translation unit. Used for DWARF output. */
- const char * GTY((skip(""))) language;
+ const char *language;
/* TODO: Non-optimization used to build this translation unit. */
/* TODO: Root of a partial DWARF tree for global types and decls. */
};
diff --git a/gcc/varasm.c b/gcc/varasm.c
index 9315e2c6936..aff93ca5de9 100644
--- a/gcc/varasm.c
+++ b/gcc/varasm.c
@@ -250,8 +250,8 @@ object_block_hasher::hash (object_block *old)
/* Return a new unnamed section with the given fields. */
section *
-get_unnamed_section (unsigned int flags, void (*callback) (const void *),
- const void *data)
+get_unnamed_section (unsigned int flags, void (*callback) (const char *),
+ const char *data)
{
section *sect;
@@ -7778,9 +7778,9 @@ file_end_indicate_split_stack (void)
a get_unnamed_section callback. */
void
-output_section_asm_op (const void *directive)
+output_section_asm_op (const char *directive)
{
- fprintf (asm_out_file, "%s\n", (const char *) directive);
+ fprintf (asm_out_file, "%s\n", directive);
}
/* Emit assembly code to switch to section NEW_SECTION. Do nothing if
diff --git a/libcpp/include/line-map.h b/libcpp/include/line-map.h
index 8b5e2f82982..bc40e333579 100644
--- a/libcpp/include/line-map.h
+++ b/libcpp/include/line-map.h
@@ -758,11 +758,11 @@ struct GTY(()) line_maps {
/* If non-null, the allocator to use when resizing 'maps'. If null,
xrealloc is used. */
- line_map_realloc reallocator;
+ line_map_realloc GTY((callback)) reallocator;
/* The allocators' function used to know the actual size it
allocated, for a certain allocation size requested. */
- line_map_round_alloc_size_func round_alloc_size;
+ line_map_round_alloc_size_func GTY((callback)) round_alloc_size;
struct location_adhoc_data_map location_adhoc_data_map;
diff --git a/gcc/config/avr/avr.c b/gcc/config/avr/avr.c
index 6ba038881d6..1c2f7d564e7 100644
--- a/gcc/config/avr/avr.c
+++ b/gcc/config/avr/avr.c
@@ -10089,7 +10089,7 @@ avr_asm_asm_output_aligned_bss (FILE *file, tree decl, const char *name,
to track need of __do_copy_data. */
static void
-avr_output_data_section_asm_op (const void *data)
+avr_output_data_section_asm_op (const char *data)
{
avr_need_copy_data_p = true;
@@ -10102,7 +10102,7 @@ avr_output_data_section_asm_op (const void *data)
to track need of __do_clear_bss. */
static void
-avr_output_bss_section_asm_op (const void *data)
+avr_output_bss_section_asm_op (const char *data)
{
avr_need_clear_bss_p = true;

137
gcc8-pr100797.patch Normal file
View File

@ -0,0 +1,137 @@
commit ebfe8b28d40746ff33724bd5b9ade2552e619213
Author: Jason Merrill <jason@redhat.com>
Date: Thu May 27 23:54:52 2021 -0400
c++: 'this' adjustment for devirtualized call
My patch for 95719 made us do a better job of finding the actual virtual
function we want to call, but didn't update the 'this' pointer adjustment to
match.
This backport also incorporates a bit of the r11-1638 reorganization.
PR c++/100797
PR c++/95719
gcc/cp/ChangeLog:
* call.c (build_over_call): Adjust base_binfo in
resolves_to_fixed_type_p case.
gcc/testsuite/ChangeLog:
* g++.dg/inherit/virtual15.C: New test.
* g++.dg/inherit/virtual15a.C: New test.
--- gcc/cp/call.c
+++ gcc/cp/call.c
@@ -8309,19 +8309,6 @@ build_over_call (struct z_candidate *cand, int flags, tsubst_flags_t complain)
|| CLASSTYPE_FINAL (TYPE_METHOD_BASETYPE (TREE_TYPE (fn))))
flags |= LOOKUP_NONVIRTUAL;
- /* If we know the dynamic type of the object, look up the final overrider
- in the BINFO. */
- if (DECL_VINDEX (fn) && (flags & LOOKUP_NONVIRTUAL) == 0
- && resolves_to_fixed_type_p (arg))
- {
- tree binfo = cand->conversion_path;
- if (BINFO_TYPE (binfo) != DECL_CONTEXT (fn))
- binfo = lookup_base (binfo, DECL_CONTEXT (fn), ba_unique,
- NULL, complain);
- fn = lookup_vfn_in_binfo (DECL_VINDEX (fn), binfo);
- flags |= LOOKUP_NONVIRTUAL;
- }
-
/* [class.mfct.nonstatic]: If a nonstatic member function of a class
X is called for an object that is not of type X, or of a type
derived from X, the behavior is undefined.
@@ -8331,10 +8318,6 @@ build_over_call (struct z_candidate *cand, int flags, tsubst_flags_t complain)
gcc_assert (TYPE_PTR_P (parmtype));
/* Convert to the base in which the function was declared. */
gcc_assert (cand->conversion_path != NULL_TREE);
- converted_arg = build_base_path (PLUS_EXPR,
- arg,
- cand->conversion_path,
- 1, complain);
/* Check that the base class is accessible. */
if (!accessible_base_p (TREE_TYPE (argtype),
BINFO_TYPE (cand->conversion_path), true))
@@ -8349,10 +8332,33 @@ build_over_call (struct z_candidate *cand, int flags, tsubst_flags_t complain)
/* If fn was found by a using declaration, the conversion path
will be to the derived class, not the base declaring fn. We
must convert from derived to base. */
- base_binfo = lookup_base (TREE_TYPE (TREE_TYPE (converted_arg)),
+ base_binfo = lookup_base (cand->conversion_path,
TREE_TYPE (parmtype), ba_unique,
NULL, complain);
- converted_arg = build_base_path (PLUS_EXPR, converted_arg,
+
+ /* If we know the dynamic type of the object, look up the final overrider
+ in the BINFO. */
+ if (DECL_VINDEX (fn) && (flags & LOOKUP_NONVIRTUAL) == 0
+ && resolves_to_fixed_type_p (arg))
+ {
+ tree ov = lookup_vfn_in_binfo (DECL_VINDEX (fn), base_binfo);
+
+ /* And unwind base_binfo to match. If we don't find the type we're
+ looking for in BINFO_INHERITANCE_CHAIN, we're looking at diamond
+ inheritance; for now do a normal virtual call in that case. */
+ tree octx = DECL_CONTEXT (ov);
+ tree obinfo = base_binfo;
+ while (obinfo && !SAME_BINFO_TYPE_P (BINFO_TYPE (obinfo), octx))
+ obinfo = BINFO_INHERITANCE_CHAIN (obinfo);
+ if (obinfo)
+ {
+ fn = ov;
+ base_binfo = obinfo;
+ flags |= LOOKUP_NONVIRTUAL;
+ }
+ }
+
+ converted_arg = build_base_path (PLUS_EXPR, arg,
base_binfo, 1, complain);
argarray[j++] = converted_arg;
--- /dev/null
+++ gcc/testsuite/g++.dg/inherit/virtual15.C
@@ -0,0 +1,18 @@
+// PR c++/100797
+// { dg-do run }
+
+bool ok = false;
+struct S1 { virtual ~S1() {} };
+struct S2 { virtual void f1() = 0; };
+struct S3: S1, S2 {
+ void f1() { f2(); }
+ virtual void f2() = 0;
+};
+struct S4: S3 {
+ void f2() { ok = true; }
+ using S2::f1;
+};
+int main() {
+ S4().f1();
+ if (!ok) __builtin_abort ();
+}
--- /dev/null
+++ gcc/testsuite/g++.dg/inherit/virtual15a.C
@@ -0,0 +1,19 @@
+// PR c++/100797 plus diamond inheritance
+// { dg-do run }
+
+bool ok = false;
+struct S1 { virtual ~S1() {} };
+struct S2 { virtual void f1() = 0; };
+struct S3: S1, virtual S2 {
+ void f1() { f2(); }
+ virtual void f2() = 0;
+};
+struct SX: virtual S2 { };
+struct S4: SX, S3 {
+ void f2() { ok = true; }
+ using S2::f1;
+};
+int main() {
+ S4().f1();
+ if (!ok) __builtin_abort ();
+}

254
gcc8-pr96796.patch Normal file
View File

@ -0,0 +1,254 @@
commit 6001db79c477b03eacc7e7049560921fb54b7845
Author: Richard Sandiford <richard.sandiford@arm.com>
Date: Mon Sep 7 20:15:36 2020 +0100
lra: Avoid cycling on certain subreg reloads [PR96796]
This PR is about LRA cycling for a reload of the form:
----------------------------------------------------------------------------
Changing pseudo 196 in operand 1 of insn 103 on equiv [r105:DI*0x8+r140:DI]
Creating newreg=287, assigning class ALL_REGS to slow/invalid mem r287
Creating newreg=288, assigning class ALL_REGS to slow/invalid mem r288
103: r203:SI=r288:SI<<0x1+r196:DI#0
REG_DEAD r196:DI
Inserting slow/invalid mem reload before:
316: r287:DI=[r105:DI*0x8+r140:DI]
317: r288:SI=r287:DI#0
----------------------------------------------------------------------------
The problem is with r287. We rightly give it a broad starting class of
POINTER_AND_FP_REGS (reduced from ALL_REGS by preferred_reload_class).
However, we never make forward progress towards narrowing it down to
a specific choice of class (POINTER_REGS or FP_REGS).
I think in practice we rely on two things to narrow a reload pseudo's
class down to a specific choice:
(1) a restricted class is specified when the pseudo is created
This happens for input address reloads, where the class is taken
from the target's chosen base register class. It also happens
for simple REG reloads, where the class is taken from the chosen
alternative's constraints.
(2) uses of the reload pseudo as a direct input operand
In this case get_reload_reg tries to reuse the existing register
and narrow its class, instead of creating a new reload pseudo.
However, neither occurs here. As described above, r287 rightly
starts out with a wide choice of class, ultimately derived from
ALL_REGS, so we don't get (1). And as the comments in the PR
explain, r287 is never used as an input reload, only the subreg is,
so we don't get (2):
----------------------------------------------------------------------------
Choosing alt 13 in insn 317: (0) r (1) w {*movsi_aarch64}
Creating newreg=291, assigning class FP_REGS to r291
317: r288:SI=r291:SI
Inserting insn reload before:
320: r291:SI=r287:DI#0
----------------------------------------------------------------------------
IMO, in this case we should rely on the reload of r316 to narrow
down the class of r278. Currently we do:
----------------------------------------------------------------------------
Choosing alt 7 in insn 316: (0) r (1) m {*movdi_aarch64}
Creating newreg=289 from oldreg=287, assigning class GENERAL_REGS to r289
316: r289:DI=[r105:DI*0x8+r140:DI]
Inserting insn reload after:
318: r287:DI=r289:DI
---------------------------------------------------
i.e. we create a new pseudo register r289 and give *that* pseudo
GENERAL_REGS instead. This is because get_reload_reg only narrows
down the existing class for OP_IN and OP_INOUT, not OP_OUT.
But if we have a reload pseudo in a reload instruction and have chosen
a specific class for the reload pseudo, I think we should simply install
it for OP_OUT reloads too, if the class is a subset of the existing class.
We will need to pick such a register whatever happens (for r289 in the
example above). And as explained in the PR, doing this actually avoids
an unnecessary move via the FP registers too.
The patch is quite aggressive in that it does this for all reload
pseudos in all reload instructions. I wondered about reusing the
condition for a reload move in in_class_p:
INSN_UID (curr_insn) >= new_insn_uid_start
&& curr_insn_set != NULL
&& ((OBJECT_P (SET_SRC (curr_insn_set))
&& ! CONSTANT_P (SET_SRC (curr_insn_set)))
|| (GET_CODE (SET_SRC (curr_insn_set)) == SUBREG
&& OBJECT_P (SUBREG_REG (SET_SRC (curr_insn_set)))
&& ! CONSTANT_P (SUBREG_REG (SET_SRC (curr_insn_set)))))))
but I can't really justify that on first principles. I think we
should apply the rule consistently until we have a specific reason
for doing otherwise.
gcc/
PR rtl-optimization/96796
* lra-constraints.c (in_class_p): Add a default-false
allow_all_reload_class_changes_p parameter. Do not treat
reload moves specially when the parameter is true.
(get_reload_reg): Try to narrow the class of an existing OP_OUT
reload if we're reloading a reload pseudo in a reload instruction.
gcc/testsuite/
PR rtl-optimization/96796
* gcc.c-torture/compile/pr96796.c: New test.
diff --git a/gcc/lra-constraints.c b/gcc/lra-constraints.c
index 580da9c3ed6..161b721efb1 100644
--- a/gcc/lra-constraints.c
+++ b/gcc/lra-constraints.c
@@ -236,12 +236,17 @@ get_reg_class (int regno)
CL. Use elimination first if REG is a hard register. If REG is a
reload pseudo created by this constraints pass, assume that it will
be allocated a hard register from its allocno class, but allow that
- class to be narrowed to CL if it is currently a superset of CL.
+ class to be narrowed to CL if it is currently a superset of CL and
+ if either:
+
+ - ALLOW_ALL_RELOAD_CLASS_CHANGES_P is true or
+ - the instruction we're processing is not a reload move.
If NEW_CLASS is nonnull, set *NEW_CLASS to the new allocno class of
REGNO (reg), or NO_REGS if no change in its class was needed. */
static bool
-in_class_p (rtx reg, enum reg_class cl, enum reg_class *new_class)
+in_class_p (rtx reg, enum reg_class cl, enum reg_class *new_class,
+ bool allow_all_reload_class_changes_p = false)
{
enum reg_class rclass, common_class;
machine_mode reg_mode;
@@ -266,7 +271,8 @@ in_class_p (rtx reg, enum reg_class cl, enum reg_class *new_class)
typically moves that have many alternatives, and restricting
reload pseudos for one alternative may lead to situations
where other reload pseudos are no longer allocatable. */
- || (INSN_UID (curr_insn) >= new_insn_uid_start
+ || (!allow_all_reload_class_changes_p
+ && INSN_UID (curr_insn) >= new_insn_uid_start
&& curr_insn_set != NULL
&& ((OBJECT_P (SET_SRC (curr_insn_set))
&& ! CONSTANT_P (SET_SRC (curr_insn_set)))
@@ -551,13 +557,12 @@ init_curr_insn_input_reloads (void)
curr_insn_input_reloads_num = 0;
}
-/* Create a new pseudo using MODE, RCLASS, ORIGINAL or reuse already
- created input reload pseudo (only if TYPE is not OP_OUT). Don't
- reuse pseudo if IN_SUBREG_P is true and the reused pseudo should be
- wrapped up in SUBREG. The result pseudo is returned through
- RESULT_REG. Return TRUE if we created a new pseudo, FALSE if we
- reused the already created input reload pseudo. Use TITLE to
- describe new registers for debug purposes. */
+/* Create a new pseudo using MODE, RCLASS, ORIGINAL or reuse an existing
+ reload pseudo. Don't reuse an existing reload pseudo if IN_SUBREG_P
+ is true and the reused pseudo should be wrapped up in a SUBREG.
+ The result pseudo is returned through RESULT_REG. Return TRUE if we
+ created a new pseudo, FALSE if we reused an existing reload pseudo.
+ Use TITLE to describe new registers for debug purposes. */
static bool
get_reload_reg (enum op_type type, machine_mode mode, rtx original,
enum reg_class rclass, bool in_subreg_p,
@@ -616,6 +621,35 @@ get_reload_reg (enum op_type type, machine_mode mode, rtx original,
if (type == OP_OUT)
{
+ /* Output reload registers tend to start out with a conservative
+ choice of register class. Usually this is ALL_REGS, although
+ a target might narrow it (for performance reasons) through
+ targetm.preferred_reload_class. It's therefore quite common
+ for a reload instruction to require a more restrictive class
+ than the class that was originally assigned to the reload register.
+
+ In these situations, it's more efficient to refine the choice
+ of register class rather than create a second reload register.
+ This also helps to avoid cycling for registers that are only
+ used by reload instructions. */
+ if (REG_P (original)
+ && (int) REGNO (original) >= new_regno_start
+ && INSN_UID (curr_insn) >= new_insn_uid_start
+ && in_class_p (original, rclass, &new_class, true))
+ {
+ unsigned int regno = REGNO (original);
+ if (lra_dump_file != NULL)
+ {
+ fprintf (lra_dump_file, " Reuse r%d for output ", regno);
+ dump_value_slim (lra_dump_file, original, 1);
+ }
+ if (new_class != lra_get_allocno_class (regno))
+ lra_change_class (regno, new_class, ", change to", false);
+ if (lra_dump_file != NULL)
+ fprintf (lra_dump_file, "\n");
+ *result_reg = original;
+ return false;
+ }
*result_reg
= lra_create_new_reg_with_unique_value (mode, original, rclass, title);
return true;
diff --git a/gcc/testsuite/gcc.c-torture/compile/pr96796.c b/gcc/testsuite/gcc.c-torture/compile/pr96796.c
new file mode 100644
index 00000000000..8808e62fe77
--- /dev/null
+++ b/gcc/testsuite/gcc.c-torture/compile/pr96796.c
@@ -0,0 +1,55 @@
+/* { dg-additional-options "-fcommon" } */
+
+struct S0 {
+ signed f0 : 8;
+ unsigned f1;
+ unsigned f4;
+};
+struct S1 {
+ long f3;
+ char f4;
+} g_3_4;
+
+int g_5, func_1_l_32, func_50___trans_tmp_31;
+static struct S0 g_144, g_834, g_1255, g_1261;
+
+int g_273[120] = {};
+int *g_555;
+char **g_979;
+static int g_1092_0;
+static int g_1193;
+int safe_mul_func_int16_t_s_s(int si1, int si2) { return si1 * si2; }
+static struct S0 *func_50();
+int func_1() { func_50(g_3_4, g_5, func_1_l_32, 8, 3); }
+void safe_div_func_int64_t_s_s(int *);
+void safe_mod_func_uint32_t_u_u(struct S0);
+struct S0 *func_50(int p_51, struct S0 p_52, struct S1 p_53, int p_54,
+ int p_55) {
+ int __trans_tmp_30;
+ char __trans_tmp_22;
+ short __trans_tmp_19;
+ long l_985_1;
+ long l_1191[8];
+ safe_div_func_int64_t_s_s(g_273);
+ __builtin_printf((char*)g_1261.f4);
+ safe_mod_func_uint32_t_u_u(g_834);
+ g_144.f0 += 1;
+ for (;;) {
+ struct S1 l_1350 = {&l_1350};
+ for (; p_53.f3; p_53.f3 -= 1)
+ for (; g_1193 <= 2; g_1193 += 1) {
+ __trans_tmp_19 = safe_mul_func_int16_t_s_s(l_1191[l_985_1 + p_53.f3],
+ p_55 % (**g_979 = 10));
+ __trans_tmp_22 = g_1255.f1 * p_53.f4;
+ __trans_tmp_30 = __trans_tmp_19 + __trans_tmp_22;
+ if (__trans_tmp_30)
+ g_1261.f0 = p_51;
+ else {
+ g_1255.f0 = p_53.f3;
+ int *l_1422 = g_834.f0 = g_144.f4 != (*l_1422)++ > 0 < 0 ^ 51;
+ g_555 = ~0;
+ g_1092_0 |= func_50___trans_tmp_31;
+ }
+ }
+ }
+}

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,445 @@
--- gcc/config/aarch64/aarch64.c
+++ gcc/config/aarch64/aarch64.c
@@ -3799,7 +3799,14 @@ aarch64_output_probe_stack_range (rtx reg1, rtx reg2)
output_asm_insn ("sub\t%0, %0, %1", xops);
/* Probe at TEST_ADDR. */
- output_asm_insn ("str\txzr, [%0]", xops);
+ if (flag_stack_clash_protection)
+ {
+ gcc_assert (xops[0] == stack_pointer_rtx);
+ xops[1] = GEN_INT (PROBE_INTERVAL - 8);
+ output_asm_insn ("str\txzr, [%0, %1]", xops);
+ }
+ else
+ output_asm_insn ("str\txzr, [%0]", xops);
/* Test if TEST_ADDR == LAST_ADDR. */
xops[1] = reg2;
@@ -4589,6 +4596,133 @@ aarch64_set_handled_components (sbitmap components)
cfun->machine->reg_is_wrapped_separately[regno] = true;
}
+/* Allocate POLY_SIZE bytes of stack space using TEMP1 and TEMP2 as scratch
+ registers. */
+
+static void
+aarch64_allocate_and_probe_stack_space (rtx temp1, rtx temp2,
+ poly_int64 poly_size)
+{
+ HOST_WIDE_INT size;
+ if (!poly_size.is_constant (&size))
+ {
+ sorry ("stack probes for SVE frames");
+ return;
+ }
+
+ HOST_WIDE_INT probe_interval
+ = 1 << PARAM_VALUE (PARAM_STACK_CLASH_PROTECTION_PROBE_INTERVAL);
+ HOST_WIDE_INT guard_size
+ = 1 << PARAM_VALUE (PARAM_STACK_CLASH_PROTECTION_GUARD_SIZE);
+ HOST_WIDE_INT guard_used_by_caller = 1024;
+
+ /* SIZE should be large enough to require probing here. ie, it
+ must be larger than GUARD_SIZE - GUARD_USED_BY_CALLER.
+
+ We can allocate GUARD_SIZE - GUARD_USED_BY_CALLER as a single chunk
+ without any probing. */
+ gcc_assert (size >= guard_size - guard_used_by_caller);
+ aarch64_sub_sp (temp1, temp2, guard_size - guard_used_by_caller, true);
+ HOST_WIDE_INT orig_size = size;
+ size -= (guard_size - guard_used_by_caller);
+
+ HOST_WIDE_INT rounded_size = size & -probe_interval;
+ HOST_WIDE_INT residual = size - rounded_size;
+
+ /* We can handle a small number of allocations/probes inline. Otherwise
+ punt to a loop. */
+ if (rounded_size && rounded_size <= 4 * probe_interval)
+ {
+ /* We don't use aarch64_sub_sp here because we don't want to
+ repeatedly load TEMP1. */
+ rtx step = GEN_INT (-probe_interval);
+ if (probe_interval > ARITH_FACTOR)
+ {
+ emit_move_insn (temp1, step);
+ step = temp1;
+ }
+
+ for (HOST_WIDE_INT i = 0; i < rounded_size; i += probe_interval)
+ {
+ rtx_insn *insn = emit_insn (gen_add2_insn (stack_pointer_rtx, step));
+ add_reg_note (insn, REG_STACK_CHECK, const0_rtx);
+
+ if (probe_interval > ARITH_FACTOR)
+ {
+ RTX_FRAME_RELATED_P (insn) = 1;
+ rtx adj = plus_constant (Pmode, stack_pointer_rtx, -probe_interval);
+ add_reg_note (insn, REG_CFA_ADJUST_CFA,
+ gen_rtx_SET (stack_pointer_rtx, adj));
+ }
+
+ emit_stack_probe (plus_constant (Pmode, stack_pointer_rtx,
+ (probe_interval
+ - GET_MODE_SIZE (word_mode))));
+ emit_insn (gen_blockage ());
+ }
+ dump_stack_clash_frame_info (PROBE_INLINE, size != rounded_size);
+ }
+ else if (rounded_size)
+ {
+ /* Compute the ending address. */
+ unsigned int scratchreg = REGNO (temp1);
+ emit_move_insn (temp1, GEN_INT (-rounded_size));
+ rtx_insn *insn
+ = emit_insn (gen_add3_insn (temp1, stack_pointer_rtx, temp1));
+
+ /* For the initial allocation, we don't have a frame pointer
+ set up, so we always need CFI notes. If we're doing the
+ final allocation, then we may have a frame pointer, in which
+ case it is the CFA, otherwise we need CFI notes.
+
+ We can determine which allocation we are doing by looking at
+ the temporary register. IP0 is the initial allocation, IP1
+ is the final allocation. */
+ if (scratchreg == IP0_REGNUM || !frame_pointer_needed)
+ {
+ /* We want the CFA independent of the stack pointer for the
+ duration of the loop. */
+ add_reg_note (insn, REG_CFA_DEF_CFA,
+ plus_constant (Pmode, temp1,
+ (rounded_size + (orig_size - size))));
+ RTX_FRAME_RELATED_P (insn) = 1;
+ }
+
+ /* This allocates and probes the stack.
+
+ It also probes at a 4k interval regardless of the value of
+ PARAM_STACK_CLASH_PROTECTION_PROBE_INTERVAL. */
+ insn = emit_insn (gen_probe_stack_range (stack_pointer_rtx,
+ stack_pointer_rtx, temp1));
+
+ /* Now reset the CFA register if needed. */
+ if (scratchreg == IP0_REGNUM || !frame_pointer_needed)
+ {
+ add_reg_note (insn, REG_CFA_DEF_CFA,
+ plus_constant (Pmode, stack_pointer_rtx,
+ (rounded_size + (orig_size - size))));
+ RTX_FRAME_RELATED_P (insn) = 1;
+ }
+
+ emit_insn (gen_blockage ());
+ dump_stack_clash_frame_info (PROBE_LOOP, size != rounded_size);
+ }
+ else
+ dump_stack_clash_frame_info (PROBE_INLINE, size != rounded_size);
+
+ /* Handle any residuals.
+ Note that any residual must be probed. */
+ if (residual)
+ {
+ aarch64_sub_sp (temp1, temp2, residual, true);
+ add_reg_note (get_last_insn (), REG_STACK_CHECK, const0_rtx);
+ emit_stack_probe (plus_constant (Pmode, stack_pointer_rtx,
+ (residual - GET_MODE_SIZE (word_mode))));
+ emit_insn (gen_blockage ());
+ }
+ return;
+}
+
/* Add a REG_CFA_EXPRESSION note to INSN to say that register REG
is saved at BASE + OFFSET. */
@@ -4686,7 +4820,54 @@ aarch64_expand_prologue (void)
rtx ip0_rtx = gen_rtx_REG (Pmode, IP0_REGNUM);
rtx ip1_rtx = gen_rtx_REG (Pmode, IP1_REGNUM);
- aarch64_sub_sp (ip0_rtx, ip1_rtx, initial_adjust, true);
+ /* We do not fully protect aarch64 against stack clash style attacks
+ as doing so would be prohibitively expensive with less utility over
+ time as newer compilers are deployed.
+
+ We assume the guard is at least 64k. Furthermore, we assume that
+ the caller has not pushed the stack pointer more than 1k into
+ the guard. A caller that pushes the stack pointer than 1k into
+ the guard is considered invalid.
+
+ Note that the caller's ability to push the stack pointer into the
+ guard is a function of the number and size of outgoing arguments and/or
+ dynamic stack allocations due to the mandatory save of the link register
+ in the caller's frame.
+
+ With those assumptions the callee can allocate up to 63k of stack
+ space without probing.
+
+ When probing is needed, we emit a probe at the start of the prologue
+ and every PARAM_STACK_CLASH_PROTECTION_PROBE_INTERVAL bytes thereafter.
+
+ We have to track how much space has been allocated, but we do not
+ track stores into the stack as implicit probes except for the
+ fp/lr store. */
+ HOST_WIDE_INT guard_size
+ = 1 << PARAM_VALUE (PARAM_STACK_CLASH_PROTECTION_GUARD_SIZE);
+ HOST_WIDE_INT guard_used_by_caller = 1024;
+ if (flag_stack_clash_protection)
+ {
+ if (known_eq (frame_size, 0))
+ dump_stack_clash_frame_info (NO_PROBE_NO_FRAME, false);
+ else if (known_lt (initial_adjust, guard_size - guard_used_by_caller)
+ && known_lt (final_adjust, guard_size - guard_used_by_caller))
+ dump_stack_clash_frame_info (NO_PROBE_SMALL_FRAME, true);
+ }
+
+ /* In theory we should never have both an initial adjustment
+ and a callee save adjustment. Verify that is the case since the
+ code below does not handle it for -fstack-clash-protection. */
+ gcc_assert (known_eq (initial_adjust, 0) || callee_adjust == 0);
+
+ /* Only probe if the initial adjustment is larger than the guard
+ less the amount of the guard reserved for use by the caller's
+ outgoing args. */
+ if (flag_stack_clash_protection
+ && maybe_ge (initial_adjust, guard_size - guard_used_by_caller))
+ aarch64_allocate_and_probe_stack_space (ip0_rtx, ip1_rtx, initial_adjust);
+ else
+ aarch64_sub_sp (ip0_rtx, ip1_rtx, initial_adjust, true);
if (callee_adjust != 0)
aarch64_push_regs (reg1, reg2, callee_adjust);
@@ -4742,7 +4923,31 @@ aarch64_expand_prologue (void)
callee_adjust != 0 || emit_frame_chain);
aarch64_save_callee_saves (DFmode, callee_offset, V0_REGNUM, V31_REGNUM,
callee_adjust != 0 || emit_frame_chain);
- aarch64_sub_sp (ip1_rtx, ip0_rtx, final_adjust, !frame_pointer_needed);
+
+ /* We may need to probe the final adjustment as well. */
+ if (flag_stack_clash_protection && maybe_ne (final_adjust, 0))
+ {
+ /* First probe if the final adjustment is larger than the guard size
+ less the amount of the guard reserved for use by the caller's
+ outgoing args. */
+ if (maybe_ge (final_adjust, guard_size - guard_used_by_caller))
+ aarch64_allocate_and_probe_stack_space (ip1_rtx, ip0_rtx,
+ final_adjust);
+ else
+ aarch64_sub_sp (ip1_rtx, ip0_rtx, final_adjust, !frame_pointer_needed);
+
+ /* We must also probe if the final adjustment is larger than the guard
+ that is assumed used by the caller. This may be sub-optimal. */
+ if (maybe_ge (final_adjust, guard_used_by_caller))
+ {
+ if (dump_file)
+ fprintf (dump_file,
+ "Stack clash aarch64 large outgoing arg, probing\n");
+ emit_stack_probe (stack_pointer_rtx);
+ }
+ }
+ else
+ aarch64_sub_sp (ip1_rtx, ip0_rtx, final_adjust, !frame_pointer_needed);
}
/* Return TRUE if we can use a simple_return insn.
@@ -10476,6 +10681,12 @@ aarch64_override_options_internal (struct gcc_options *opts)
&& opts->x_optimize >= aarch64_tune_params.prefetch->default_opt_level)
opts->x_flag_prefetch_loop_arrays = 1;
+ /* We assume the guard page is 64k. */
+ maybe_set_param_value (PARAM_STACK_CLASH_PROTECTION_GUARD_SIZE,
+ 16,
+ opts->x_param_values,
+ global_options_set.x_param_values);
+
aarch64_override_options_after_change_1 (opts);
}
@@ -17161,6 +17372,28 @@ aarch64_sched_can_speculate_insn (rtx_insn *insn)
}
}
+/* It has been decided that to allow up to 1kb of outgoing argument
+ space to be allocated w/o probing. If more than 1kb of outgoing
+ argment space is allocated, then it must be probed and the last
+ probe must occur no more than 1kbyte away from the end of the
+ allocated space.
+
+ This implies that the residual part of an alloca allocation may
+ need probing in cases where the generic code might not otherwise
+ think a probe is needed.
+
+ This target hook returns TRUE when allocating RESIDUAL bytes of
+ alloca space requires an additional probe, otherwise FALSE is
+ returned. */
+
+static bool
+aarch64_stack_clash_protection_final_dynamic_probe (rtx residual)
+{
+ return (residual == CONST0_RTX (Pmode)
+ || GET_CODE (residual) != CONST_INT
+ || INTVAL (residual) >= 1024);
+}
+
/* Implement TARGET_COMPUTE_PRESSURE_CLASSES. */
static int
@@ -17669,6 +17902,10 @@ aarch64_libgcc_floating_mode_supported_p
#undef TARGET_CONSTANT_ALIGNMENT
#define TARGET_CONSTANT_ALIGNMENT aarch64_constant_alignment
+#undef TARGET_STACK_CLASH_PROTECTION_FINAL_DYNAMIC_PROBE
+#define TARGET_STACK_CLASH_PROTECTION_FINAL_DYNAMIC_PROBE \
+ aarch64_stack_clash_protection_final_dynamic_probe
+
#undef TARGET_COMPUTE_PRESSURE_CLASSES
#define TARGET_COMPUTE_PRESSURE_CLASSES aarch64_compute_pressure_classes
--- gcc/config/aarch64/aarch64.md
+++ gcc/config/aarch64/aarch64.md
@@ -5812,7 +5812,7 @@
)
(define_insn "probe_stack_range"
- [(set (match_operand:DI 0 "register_operand" "=r")
+ [(set (match_operand:DI 0 "register_operand" "=rk")
(unspec_volatile:DI [(match_operand:DI 1 "register_operand" "0")
(match_operand:DI 2 "register_operand" "r")]
UNSPECV_PROBE_STACK_RANGE))]
--- gcc/testsuite/gcc.target/aarch64/stack-check-12.c
+++ gcc/testsuite/gcc.target/aarch64/stack-check-12.c
@@ -0,0 +1,20 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fstack-clash-protection --param stack-clash-protection-guard-size=12" } */
+/* { dg-require-effective-target supports_stack_clash_protection } */
+
+extern void arf (unsigned long int *, unsigned long int *);
+void
+frob ()
+{
+ unsigned long int num[1000];
+ unsigned long int den[1000];
+ arf (den, num);
+}
+
+/* This verifies that the scheduler did not break the dependencies
+ by adjusting the offsets within the probe and that the scheduler
+ did not reorder around the stack probes. */
+/* { dg-final { scan-assembler-times "sub\\tsp, sp, #4096\\n\\tstr\\txzr, .sp, 4088." 3 } } */
+
+
+
--- gcc/testsuite/gcc.target/aarch64/stack-check-13.c
+++ gcc/testsuite/gcc.target/aarch64/stack-check-13.c
@@ -0,0 +1,28 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fstack-clash-protection --param stack-clash-protection-guard-size=12" } */
+/* { dg-require-effective-target supports_stack_clash_protection } */
+
+#define ARG32(X) X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X
+#define ARG192(X) ARG32(X),ARG32(X),ARG32(X),ARG32(X),ARG32(X),ARG32(X)
+void out1(ARG192(__int128));
+int t1(int);
+
+int t3(int x)
+{
+ if (x < 1000)
+ return t1 (x) + 1;
+
+ out1 (ARG192(1));
+ return 0;
+}
+
+
+
+/* This test creates a large (> 1k) outgoing argument area that needs
+ to be probed. We don't test the exact size of the space or the
+ exact offset to make the test a little less sensitive to trivial
+ output changes. */
+/* { dg-final { scan-assembler-times "sub\\tsp, sp, #....\\n\\tstr\\txzr, \\\[sp" 1 } } */
+
+
+
--- gcc/testsuite/gcc.target/aarch64/stack-check-14.c
+++ gcc/testsuite/gcc.target/aarch64/stack-check-14.c
@@ -0,0 +1,25 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fstack-clash-protection --param stack-clash-protection-guard-size=12" } */
+/* { dg-require-effective-target supports_stack_clash_protection } */
+
+int t1(int);
+
+int t2(int x)
+{
+ char *p = __builtin_alloca (4050);
+ x = t1 (x);
+ return p[x];
+}
+
+
+/* This test has a constant sized alloca that is smaller than the
+ probe interval. But it actually requires two probes instead
+ of one because of the optimistic assumptions we made in the
+ aarch64 prologue code WRT probing state.
+
+ The form can change quite a bit so we just check for two
+ probes without looking at the actual address. */
+/* { dg-final { scan-assembler-times "str\\txzr," 2 } } */
+
+
+
--- gcc/testsuite/gcc.target/aarch64/stack-check-15.c
+++ gcc/testsuite/gcc.target/aarch64/stack-check-15.c
@@ -0,0 +1,24 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fstack-clash-protection --param stack-clash-protection-guard-size=12" } */
+/* { dg-require-effective-target supports_stack_clash_protection } */
+
+int t1(int);
+
+int t2(int x)
+{
+ char *p = __builtin_alloca (x);
+ x = t1 (x);
+ return p[x];
+}
+
+
+/* This test has a variable sized alloca. It requires 3 probes.
+ One in the loop, one for the residual and at the end of the
+ alloca area.
+
+ The form can change quite a bit so we just check for two
+ probes without looking at the actual address. */
+/* { dg-final { scan-assembler-times "str\\txzr," 3 } } */
+
+
+
--- gcc/testsuite/lib/target-supports.exp
+++ gcc/testsuite/lib/target-supports.exp
@@ -9201,14 +9201,9 @@ proc check_effective_target_autoincdec { } {
#
proc check_effective_target_supports_stack_clash_protection { } {
- # Temporary until the target bits are fully ACK'd.
-# if { [istarget aarch*-*-*] } {
-# return 1
-# }
-
if { [istarget x86_64-*-*] || [istarget i?86-*-*]
|| [istarget powerpc*-*-*] || [istarget rs6000*-*-*]
- || [istarget s390*-*-*] } {
+ || [istarget aarch64*-**] || [istarget s390*-*-*] } {
return 1
}
return 0
@@ -9217,9 +9212,9 @@ proc check_effective_target_supports_stack_clash_protection { } {
# Return 1 if the target creates a frame pointer for non-leaf functions
# Note we ignore cases where we apply tail call optimization here.
proc check_effective_target_frame_pointer_for_non_leaf { } {
- if { [istarget aarch*-*-*] } {
- return 1
- }
+# if { [istarget aarch*-*-*] } {
+# return 1
+# }
# Solaris/x86 defaults to -fno-omit-frame-pointer.
if { [istarget i?86-*-solaris*] || [istarget x86_64-*-solaris*] } {

31
gcc8-rh1574936.patch Normal file
View File

@ -0,0 +1,31 @@
crt files and statically linked libgcc objects cause false positives
in annobin coverage, so we add the assembler flag to generate notes
for them.
The patch also adds notes to libgcc_s.so, but this is harmless because
these notes only confer that there is no other annobin markup.
2018-07-25 Florian Weimer <fweimer@redhat.com>
* Makefile.in (LIBGCC2_CFLAGS, CRTSTUFF_CFLAGS): Add
-Wa,--generate-missing-build-notes=yes.
--- libgcc/Makefile.in 2018-01-13 13:05:41.000000000 +0100
+++ libgcc/Makefile.in 2018-07-25 13:15:02.036226940 +0200
@@ -244,6 +244,7 @@
LIBGCC2_CFLAGS = -O2 $(LIBGCC2_INCLUDES) $(GCC_CFLAGS) $(HOST_LIBGCC2_CFLAGS) \
$(LIBGCC2_DEBUG_CFLAGS) -DIN_LIBGCC2 \
-fbuilding-libgcc -fno-stack-protector \
+ -Wa,--generate-missing-build-notes=yes \
$(INHIBIT_LIBC_CFLAGS)
# Additional options to use when compiling libgcc2.a.
@@ -297,6 +298,7 @@
$(NO_PIE_CFLAGS) -finhibit-size-directive -fno-inline -fno-exceptions \
-fno-zero-initialized-in-bss -fno-toplevel-reorder -fno-tree-vectorize \
-fbuilding-libgcc -fno-stack-protector $(FORCE_EXPLICIT_EH_REGISTRY) \
+ -Wa,--generate-missing-build-notes=yes \
$(INHIBIT_LIBC_CFLAGS)
# Extra flags to use when compiling crt{begin,end}.o.

406
gcc8-rh1668903-1.patch Normal file
View File

@ -0,0 +1,406 @@
commit 126dab7c9d84294f256b1f7bf91c24a9e7103249
Author: qinzhao <qinzhao@138bc75d-0d04-0410-961f-82ee72b054a4>
Date: Thu Nov 29 16:06:03 2018 +0000
Add a new option -flive-patching={inline-only-static|inline-clone}
to support live patching in GCC.
2018-11-29 qing zhao <qing.zhao@oracle.com>
gcc/ChangeLog:
* cif-code.def (EXTERN_LIVE_ONLY_STATIC): New CIF code.
* common.opt: Add -flive-patching flag.
* doc/invoke.texi: Document -flive-patching.
* flag-types.h (enum live_patching_level): New enum.
* ipa-inline.c (can_inline_edge_p): Disable external functions from
inlining when flag_live_patching is LIVE_PATCHING_INLINE_ONLY_STATIC.
* opts.c (control_options_for_live_patching): New function.
(finish_options): Make flag_live_patching incompatible with flag_lto.
Control IPA optimizations based on different levels of
flag_live_patching.
gcc/testsuite/ChangeLog:
* gcc.dg/live-patching-1.c: New test.
* gcc.dg/live-patching-2.c: New test.
* gcc.dg/live-patching-3.c: New test.
* gcc.dg/tree-ssa/writeonly-3.c: New test.
* gcc.target/i386/ipa-stack-alignment-2.c: New test.
git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@266627 138bc75d-0d04-0410-961f-82ee72b054a4
--- gcc/cif-code.def
+++ gcc/cif-code.def
@@ -132,6 +132,12 @@ DEFCIFCODE(USES_COMDAT_LOCAL, CIF_FINAL_ERROR,
DEFCIFCODE(ATTRIBUTE_MISMATCH, CIF_FINAL_ERROR,
N_("function attribute mismatch"))
+/* We can't inline because the user requests only static functions
+ but the function has external linkage for live patching purpose. */
+DEFCIFCODE(EXTERN_LIVE_ONLY_STATIC, CIF_FINAL_ERROR,
+ N_("function has external linkage when the user requests only"
+ " inlining static for live patching"))
+
/* We proved that the call is unreachable. */
DEFCIFCODE(UNREACHABLE, CIF_FINAL_ERROR,
N_("unreachable"))
--- gcc/common.opt
+++ gcc/common.opt
@@ -2181,6 +2181,24 @@ starts and when the destructor finishes.
flifetime-dse=
Common Joined RejectNegative UInteger Var(flag_lifetime_dse) Optimization IntegerRange(0, 2)
+flive-patching
+Common RejectNegative Alias(flive-patching=,inline-clone) Optimization
+
+flive-patching=
+Common Report Joined RejectNegative Enum(live_patching_level) Var(flag_live_patching) Init(LIVE_PATCHING_NONE) Optimization
+-flive-patching=[inline-only-static|inline-clone] Control IPA
+optimizations to provide a safe compilation for live-patching. At the same
+time, provides multiple-level control on the enabled IPA optimizations.
+
+Enum
+Name(live_patching_level) Type(enum live_patching_level) UnknownError(unknown Live-Patching Level %qs)
+
+EnumValue
+Enum(live_patching_level) String(inline-only-static) Value(LIVE_PATCHING_INLINE_ONLY_STATIC)
+
+EnumValue
+Enum(live_patching_level) String(inline-clone) Value(LIVE_PATCHING_INLINE_CLONE)
+
flive-range-shrinkage
Common Report Var(flag_live_range_shrinkage) Init(0) Optimization
Relief of register pressure through live range shrinkage.
--- gcc/doc/invoke.texi
+++ gcc/doc/invoke.texi
@@ -389,6 +389,7 @@ Objective-C and Objective-C++ Dialects}.
-fipa-bit-cp -fipa-vrp @gol
-fipa-pta -fipa-profile -fipa-pure-const -fipa-reference -fipa-icf @gol
-fira-algorithm=@var{algorithm} @gol
+-flive-patching=@var{level} @gol
-fira-region=@var{region} -fira-hoist-pressure @gol
-fira-loop-pressure -fno-ira-share-save-slots @gol
-fno-ira-share-spill-slots @gol
@@ -9291,6 +9292,65 @@ equivalences that are found only by GCC and equivalences found only by Gold.
This flag is enabled by default at @option{-O2} and @option{-Os}.
+@item -flive-patching=@var{level}
+@opindex flive-patching
+Control GCC's optimizations to provide a safe compilation for live-patching.
+
+If the compiler's optimization uses a function's body or information extracted
+from its body to optimize/change another function, the latter is called an
+impacted function of the former. If a function is patched, its impacted
+functions should be patched too.
+
+The impacted functions are decided by the compiler's interprocedural
+optimizations. For example, inlining a function into its caller, cloning
+a function and changing its caller to call this new clone, or extracting
+a function's pureness/constness information to optimize its direct or
+indirect callers, etc.
+
+Usually, the more IPA optimizations enabled, the larger the number of
+impacted functions for each function. In order to control the number of
+impacted functions and computed the list of impacted function easily,
+we provide control to partially enable IPA optimizations on two different
+levels.
+
+The @var{level} argument should be one of the following:
+
+@table @samp
+
+@item inline-clone
+
+Only enable inlining and cloning optimizations, which includes inlining,
+cloning, interprocedural scalar replacement of aggregates and partial inlining.
+As a result, when patching a function, all its callers and its clones'
+callers need to be patched as well.
+
+@option{-flive-patching=inline-clone} disables the following optimization flags:
+@gccoptlist{-fwhole-program -fipa-pta -fipa-reference -fipa-ra @gol
+-fipa-icf -fipa-icf-functions -fipa-icf-variables @gol
+-fipa-bit-cp -fipa-vrp -fipa-pure-const -fipa-reference-addressable @gol
+-fipa-stack-alignment}
+
+@item inline-only-static
+
+Only enable inlining of static functions.
+As a result, when patching a static function, all its callers need to be
+patches as well.
+
+In addition to all the flags that -flive-patching=inline-clone disables,
+@option{-flive-patching=inline-only-static} disables the following additional
+optimization flags:
+@gccoptlist{-fipa-cp-clone -fipa-sra -fpartial-inlining -fipa-cp}
+
+@end table
+
+When -flive-patching specified without any value, the default value
+is "inline-clone".
+
+This flag is disabled by default.
+
+Note that -flive-patching is not supported with link-time optimizer.
+(@option{-flto}).
+
@item -fisolate-erroneous-paths-dereference
@opindex fisolate-erroneous-paths-dereference
Detect paths that trigger erroneous or undefined behavior due to
--- gcc/flag-types.h
+++ gcc/flag-types.h
@@ -123,6 +123,14 @@ enum stack_reuse_level
SR_ALL
};
+/* The live patching level. */
+enum live_patching_level
+{
+ LIVE_PATCHING_NONE = 0,
+ LIVE_PATCHING_INLINE_ONLY_STATIC,
+ LIVE_PATCHING_INLINE_CLONE
+};
+
/* The algorithm used for basic block reordering. */
enum reorder_blocks_algorithm
{
--- gcc/ipa-inline.c
+++ gcc/ipa-inline.c
@@ -379,6 +379,12 @@ can_inline_edge_p (struct cgraph_edge *e, bool report,
e->inline_failed = CIF_ATTRIBUTE_MISMATCH;
inlinable = false;
}
+ else if (callee->externally_visible
+ && flag_live_patching == LIVE_PATCHING_INLINE_ONLY_STATIC)
+ {
+ e->inline_failed = CIF_EXTERN_LIVE_ONLY_STATIC;
+ inlinable = false;
+ }
if (!inlinable && report)
report_inline_failed_reason (e);
return inlinable;
--- gcc/opts.c
+++ gcc/opts.c
@@ -699,6 +699,152 @@ default_options_optimization (struct gcc
lang_mask, handlers, loc, dc);
}
+/* Control IPA optimizations based on different live patching LEVEL. */
+static void
+control_options_for_live_patching (struct gcc_options *opts,
+ struct gcc_options *opts_set,
+ enum live_patching_level level,
+ location_t loc)
+{
+ gcc_assert (level > LIVE_PATCHING_NONE);
+
+ switch (level)
+ {
+ case LIVE_PATCHING_INLINE_ONLY_STATIC:
+ if (opts_set->x_flag_ipa_cp_clone && opts->x_flag_ipa_cp_clone)
+ error_at (loc,
+ "%<-fipa-cp-clone%> is incompatible with "
+ "%<-flive-patching=inline-only-static%>");
+ else
+ opts->x_flag_ipa_cp_clone = 0;
+
+ if (opts_set->x_flag_ipa_sra && opts->x_flag_ipa_sra)
+ error_at (loc,
+ "%<-fipa-sra%> is incompatible with "
+ "%<-flive-patching=inline-only-static%>");
+ else
+ opts->x_flag_ipa_sra = 0;
+
+ if (opts_set->x_flag_partial_inlining && opts->x_flag_partial_inlining)
+ error_at (loc,
+ "%<-fpartial-inlining%> is incompatible with "
+ "%<-flive-patching=inline-only-static%>");
+ else
+ opts->x_flag_partial_inlining = 0;
+
+ if (opts_set->x_flag_ipa_cp && opts->x_flag_ipa_cp)
+ error_at (loc,
+ "%<-fipa-cp%> is incompatible with "
+ "%<-flive-patching=inline-only-static%>");
+ else
+ opts->x_flag_ipa_cp = 0;
+
+ /* FALLTHROUGH. */
+ case LIVE_PATCHING_INLINE_CLONE:
+ /* live patching should disable whole-program optimization. */
+ if (opts_set->x_flag_whole_program && opts->x_flag_whole_program)
+ error_at (loc,
+ "%<-fwhole-program%> is incompatible with "
+ "%<-flive-patching=inline-only-static|inline-clone%>");
+ else
+ opts->x_flag_whole_program = 0;
+
+ /* visibility change should be excluded by !flag_whole_program
+ && !in_lto_p && !flag_ipa_cp_clone && !flag_ipa_sra
+ && !flag_partial_inlining. */
+
+ if (opts_set->x_flag_ipa_pta && opts->x_flag_ipa_pta)
+ error_at (loc,
+ "%<-fipa-pta%> is incompatible with "
+ "%<-flive-patching=inline-only-static|inline-clone%>");
+ else
+ opts->x_flag_ipa_pta = 0;
+
+ if (opts_set->x_flag_ipa_reference && opts->x_flag_ipa_reference)
+ error_at (loc,
+ "%<-fipa-reference%> is incompatible with "
+ "%<-flive-patching=inline-only-static|inline-clone%>");
+ else
+ opts->x_flag_ipa_reference = 0;
+
+ if (opts_set->x_flag_ipa_ra && opts->x_flag_ipa_ra)
+ error_at (loc,
+ "%<-fipa-ra%> is incompatible with "
+ "%<-flive-patching=inline-only-static|inline-clone%>");
+ else
+ opts->x_flag_ipa_ra = 0;
+
+ if (opts_set->x_flag_ipa_icf && opts->x_flag_ipa_icf)
+ error_at (loc,
+ "%<-fipa-icf%> is incompatible with "
+ "%<-flive-patching=inline-only-static|inline-clone%>");
+ else
+ opts->x_flag_ipa_icf = 0;
+
+ if (opts_set->x_flag_ipa_icf_functions && opts->x_flag_ipa_icf_functions)
+ error_at (loc,
+ "%<-fipa-icf-functions%> is incompatible with "
+ "%<-flive-patching=inline-only-static|inline-clone%>");
+ else
+ opts->x_flag_ipa_icf_functions = 0;
+
+ if (opts_set->x_flag_ipa_icf_variables && opts->x_flag_ipa_icf_variables)
+ error_at (loc,
+ "%<-fipa-icf-variables%> is incompatible with "
+ "%<-flive-patching=inline-only-static|inline-clone%>");
+ else
+ opts->x_flag_ipa_icf_variables = 0;
+
+ if (opts_set->x_flag_ipa_bit_cp && opts->x_flag_ipa_bit_cp)
+ error_at (loc,
+ "%<-fipa-bit-cp%> is incompatible with "
+ "%<-flive-patching=inline-only-static|inline-clone%>");
+ else
+ opts->x_flag_ipa_bit_cp = 0;
+
+ if (opts_set->x_flag_ipa_vrp && opts->x_flag_ipa_vrp)
+ error_at (loc,
+ "%<-fipa-vrp%> is incompatible with "
+ "%<-flive-patching=inline-only-static|inline-clone%>");
+ else
+ opts->x_flag_ipa_vrp = 0;
+
+ if (opts_set->x_flag_ipa_pure_const && opts->x_flag_ipa_pure_const)
+ error_at (loc,
+ "%<-fipa-pure-const%> is incompatible with "
+ "%<-flive-patching=inline-only-static|inline-clone%>");
+ else
+ opts->x_flag_ipa_pure_const = 0;
+
+ /* FIXME: disable unreachable code removal. */
+
+ /* discovery of functions/variables with no address taken. */
+// GCC 8 doesn't have these options.
+#if 0
+ if (opts_set->x_flag_ipa_reference_addressable
+ && opts->x_flag_ipa_reference_addressable)
+ error_at (loc,
+ "%<-fipa-reference-addressable%> is incompatible with "
+ "%<-flive-patching=inline-only-static|inline-clone%>");
+ else
+ opts->x_flag_ipa_reference_addressable = 0;
+
+ /* ipa stack alignment propagation. */
+ if (opts_set->x_flag_ipa_stack_alignment
+ && opts->x_flag_ipa_stack_alignment)
+ error_at (loc,
+ "%<-fipa-stack-alignment%> is incompatible with "
+ "%<-flive-patching=inline-only-static|inline-clone%>");
+ else
+ opts->x_flag_ipa_stack_alignment = 0;
+#endif
+
+ break;
+ default:
+ gcc_unreachable ();
+ }
+}
+
/* After all options at LOC have been read into OPTS and OPTS_SET,
finalize settings of those options and diagnose incompatible
combinations. */
@@ -1057,6 +1203,18 @@ finish_options (struct gcc_options *opts
sorry ("transactional memory is not supported with "
"%<-fsanitize=kernel-address%>");
+ /* Currently live patching is not support for LTO. */
+ if (opts->x_flag_live_patching && opts->x_flag_lto)
+ sorry ("live patching is not supported with LTO");
+
+ /* Control IPA optimizations based on different -flive-patching level. */
+ if (opts->x_flag_live_patching)
+ {
+ control_options_for_live_patching (opts, opts_set,
+ opts->x_flag_live_patching,
+ loc);
+ }
+
/* Comes from final.c -- no real reason to change it. */
#define MAX_CODE_ALIGN 16
#define MAX_CODE_ALIGN_VALUE (1 << MAX_CODE_ALIGN)
--- /dev/null
+++ gcc/testsuite/gcc.dg/live-patching-1.c
@@ -0,0 +1,22 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -flive-patching=inline-only-static -fdump-ipa-inline" } */
+
+extern int sum, n, m;
+
+int foo (int a)
+{
+ return a + n;
+}
+
+static int bar (int b)
+{
+ return b * m;
+}
+
+int main()
+{
+ sum = foo (m) + bar (n);
+ return 0;
+}
+
+/* { dg-final { scan-ipa-dump "foo/0 function has external linkage when the user requests only inlining static for live patching" "inline" } } */
--- /dev/null
+++ gcc/testsuite/gcc.dg/live-patching-2.c
@@ -0,0 +1,9 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -flive-patching -flto" } */
+
+int main()
+{
+ return 0;
+}
+
+/* { dg-message "sorry, unimplemented: live patching is not supported with LTO" "-flive-patching and -flto together" { target *-*-* } 0 } */
--- /dev/null
+++ gcc/testsuite/gcc.dg/live-patching-3.c
@@ -0,0 +1,9 @@
+/* { dg-do compile } */
+/* { dg-options "-O1 -flive-patching -fwhole-program" } */
+
+int main()
+{
+ return 0;
+}
+
+/* { dg-message "'-fwhole-program' is incompatible with '-flive-patching=inline-only-static|inline-clone" "" {target "*-*-*"} 0 } */

73
gcc8-rh1668903-2.patch Normal file
View File

@ -0,0 +1,73 @@
commit 9939b2f79bd9b75b99080a17f3d6f1214d543477
Author: qinzhao <qinzhao@138bc75d-0d04-0410-961f-82ee72b054a4>
Date: Wed Apr 3 19:00:25 2019 +0000
2019-04-03 qing zhao <qing.zhao@oracle.com>
PR tree-optimization/89730
* ipa-inline.c (can_inline_edge_p): Delete the checking for
-flive-patching=inline-only-static.
(can_inline_edge_by_limits_p): Add the checking for
-flive-patching=inline-only-static and grant always_inline
even when -flive-patching=inline-only-static is specified.
* gcc.dg/live-patching-4.c: New test.
git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@270134 138bc75d-0d04-0410-961f-82ee72b054a4
--- gcc/ipa-inline.c
+++ gcc/ipa-inline.c
@@ -385,12 +385,6 @@ can_inline_edge_p (struct cgraph_edge *e, bool report,
e->inline_failed = CIF_ATTRIBUTE_MISMATCH;
inlinable = false;
}
- else if (callee->externally_visible
- && flag_live_patching == LIVE_PATCHING_INLINE_ONLY_STATIC)
- {
- e->inline_failed = CIF_EXTERN_LIVE_ONLY_STATIC;
- inlinable = false;
- }
if (!inlinable && report)
report_inline_failed_reason (e);
return inlinable;
@@ -433,6 +427,13 @@ can_inline_edge_by_limits_p (struct cgraph_edge *e, bool report,
DECL_ATTRIBUTES (caller->decl))
&& !caller_growth_limits (e))
inlinable = false;
+ else if (callee->externally_visible
+ && !DECL_DISREGARD_INLINE_LIMITS (callee->decl)
+ && flag_live_patching == LIVE_PATCHING_INLINE_ONLY_STATIC)
+ {
+ e->inline_failed = CIF_EXTERN_LIVE_ONLY_STATIC;
+ inlinable = false;
+ }
/* Don't inline a function with a higher optimization level than the
caller. FIXME: this is really just tip of iceberg of handling
optimization attribute. */
--- /dev/null
+++ gcc/testsuite/gcc.dg/live-patching-4.c
@@ -0,0 +1,23 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -flive-patching=inline-only-static -fdump-tree-einline-optimized" } */
+
+extern int sum, n, m;
+
+extern inline __attribute__((always_inline)) int foo (int a);
+inline __attribute__((always_inline)) int foo (int a)
+{
+ return a + n;
+}
+
+static int bar (int b)
+{
+ return b * m;
+}
+
+int main()
+{
+ sum = foo (m) + bar (n);
+ return 0;
+}
+
+/* { dg-final { scan-tree-dump "Inlining foo into main" "einline" } } */

85
gcc8-rh1668903-3.patch Normal file
View File

@ -0,0 +1,85 @@
commit 77e6311332590004c5aec82ceeb45e4d4d93f690
Author: redi <redi@138bc75d-0d04-0410-961f-82ee72b054a4>
Date: Thu Apr 11 08:52:22 2019 +0000
Clarify documentation for -flive-patching
* doc/invoke.texi (Optimize Options): Clarify -flive-patching docs.
git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@270276 138bc75d-0d04-0410-961f-82ee72b054a4
--- gcc/doc/invoke.texi
+++ gcc/doc/invoke.texi
@@ -9367,24 +9367,24 @@ This flag is enabled by default at @option{-O2} and @option{-Os}.
@item -flive-patching=@var{level}
@opindex flive-patching
-Control GCC's optimizations to provide a safe compilation for live-patching.
+Control GCC's optimizations to produce output suitable for live-patching.
If the compiler's optimization uses a function's body or information extracted
from its body to optimize/change another function, the latter is called an
impacted function of the former. If a function is patched, its impacted
functions should be patched too.
-The impacted functions are decided by the compiler's interprocedural
-optimizations. For example, inlining a function into its caller, cloning
-a function and changing its caller to call this new clone, or extracting
-a function's pureness/constness information to optimize its direct or
-indirect callers, etc.
+The impacted functions are determined by the compiler's interprocedural
+optimizations. For example, a caller is impacted when inlining a function
+into its caller,
+cloning a function and changing its caller to call this new clone,
+or extracting a function's pureness/constness information to optimize
+its direct or indirect callers, etc.
Usually, the more IPA optimizations enabled, the larger the number of
impacted functions for each function. In order to control the number of
-impacted functions and computed the list of impacted function easily,
-we provide control to partially enable IPA optimizations on two different
-levels.
+impacted functions and more easily compute the list of impacted function,
+IPA optimizations can be partially enabled at two different levels.
The @var{level} argument should be one of the following:
@@ -9395,7 +9395,7 @@ The @var{level} argument should be one of the following:
Only enable inlining and cloning optimizations, which includes inlining,
cloning, interprocedural scalar replacement of aggregates and partial inlining.
As a result, when patching a function, all its callers and its clones'
-callers need to be patched as well.
+callers are impacted, therefore need to be patched as well.
@option{-flive-patching=inline-clone} disables the following optimization flags:
@gccoptlist{-fwhole-program -fipa-pta -fipa-reference -fipa-ra @gol
@@ -9406,22 +9406,23 @@ callers need to be patched as well.
@item inline-only-static
Only enable inlining of static functions.
-As a result, when patching a static function, all its callers need to be
-patches as well.
+As a result, when patching a static function, all its callers are impacted
+and so need to be patched as well.
-In addition to all the flags that -flive-patching=inline-clone disables,
+In addition to all the flags that @option{-flive-patching=inline-clone}
+disables,
@option{-flive-patching=inline-only-static} disables the following additional
optimization flags:
@gccoptlist{-fipa-cp-clone -fipa-sra -fpartial-inlining -fipa-cp}
@end table
-When -flive-patching specified without any value, the default value
-is "inline-clone".
+When @option{-flive-patching} is specified without any value, the default value
+is @var{inline-clone}.
This flag is disabled by default.
-Note that -flive-patching is not supported with link-time optimizer.
+Note that @option{-flive-patching} is not supported with link-time optimization
(@option{-flto}).
@item -fisolate-erroneous-paths-dereference

93
gcc8-rh1670535.patch Normal file
View File

@ -0,0 +1,93 @@
2018-11-08 Roman Geissler <roman.geissler@amadeus.com>
* collect2.c (linker_select): Add USE_LLD_LD.
(ld_suffixes): Add ld.lld.
(main): Handle -fuse-ld=lld.
* common.opt (-fuse-ld=lld): New option.
* doc/invoke.texi (-fuse-ld=lld): Document.
* opts.c (common_handle_option): Handle OPT_fuse_ld_lld.
--- gcc/collect2.c
+++ gcc/collect2.c
@@ -831,6 +831,7 @@ main (int argc, char **argv)
USE_PLUGIN_LD,
USE_GOLD_LD,
USE_BFD_LD,
+ USE_LLD_LD,
USE_LD_MAX
} selected_linker = USE_DEFAULT_LD;
static const char *const ld_suffixes[USE_LD_MAX] =
@@ -838,7 +839,8 @@ main (int argc, char **argv)
"ld",
PLUGIN_LD_SUFFIX,
"ld.gold",
- "ld.bfd"
+ "ld.bfd",
+ "ld.lld"
};
static const char *const real_ld_suffix = "real-ld";
static const char *const collect_ld_suffix = "collect-ld";
@@ -1007,6 +1009,8 @@ main (int argc, char **argv)
selected_linker = USE_BFD_LD;
else if (strcmp (argv[i], "-fuse-ld=gold") == 0)
selected_linker = USE_GOLD_LD;
+ else if (strcmp (argv[i], "-fuse-ld=lld") == 0)
+ selected_linker = USE_LLD_LD;
#ifdef COLLECT_EXPORT_LIST
/* These flags are position independent, although their order
@@ -1096,7 +1100,8 @@ main (int argc, char **argv)
/* Maybe we know the right file to use (if not cross). */
ld_file_name = 0;
#ifdef DEFAULT_LINKER
- if (selected_linker == USE_BFD_LD || selected_linker == USE_GOLD_LD)
+ if (selected_linker == USE_BFD_LD || selected_linker == USE_GOLD_LD ||
+ selected_linker == USE_LLD_LD)
{
char *linker_name;
# ifdef HOST_EXECUTABLE_SUFFIX
@@ -1315,7 +1320,7 @@ main (int argc, char **argv)
else if (!use_collect_ld
&& strncmp (arg, "-fuse-ld=", 9) == 0)
{
- /* Do not pass -fuse-ld={bfd|gold} to the linker. */
+ /* Do not pass -fuse-ld={bfd|gold|lld} to the linker. */
ld1--;
ld2--;
}
--- gcc/common.opt
+++ gcc/common.opt
@@ -2732,6 +2732,10 @@ fuse-ld=gold
Common Driver Negative(fuse-ld=bfd)
Use the gold linker instead of the default linker.
+fuse-ld=lld
+Common Driver Negative(fuse-ld=lld)
+Use the lld LLVM linker instead of the default linker.
+
fuse-linker-plugin
Common Undocumented Var(flag_use_linker_plugin)
--- gcc/doc/invoke.texi
+++ gcc/doc/invoke.texi
@@ -12610,6 +12610,10 @@ Use the @command{bfd} linker instead of the default linker.
@opindex fuse-ld=gold
Use the @command{gold} linker instead of the default linker.
+@item -fuse-ld=lld
+@opindex fuse-ld=lld
+Use the LLVM @command{lld} linker instead of the default linker.
+
@cindex Libraries
@item -l@var{library}
@itemx -l @var{library}
--- gcc/opts.c
+++ gcc/opts.c
@@ -2557,6 +2557,7 @@ common_handle_option (struct gcc_options *opts,
case OPT_fuse_ld_bfd:
case OPT_fuse_ld_gold:
+ case OPT_fuse_ld_lld:
case OPT_fuse_linker_plugin:
/* No-op. Used by the driver and passed to us because it starts with f.*/
break;

64
gcc8-rh1960701.patch Normal file
View File

@ -0,0 +1,64 @@
--- gcc/cp/call.c
+++ gcc/cp/call.c
@@ -6904,7 +6904,7 @@ convert_like_real (conversion *convs, tree expr, tree fn, int argnum,
elttype = cp_build_qualified_type
(elttype, cp_type_quals (elttype) | TYPE_QUAL_CONST);
array = build_array_of_n_type (elttype, len);
- array = finish_compound_literal (array, new_ctor, complain, fcl_c99);
+ array = finish_compound_literal (array, new_ctor, complain);
/* Take the address explicitly rather than via decay_conversion
to avoid the error about taking the address of a temporary. */
array = cp_build_addr_expr (array, complain);
@@ -10984,13 +10984,11 @@ set_up_extended_ref_temp (tree decl, tree expr, vec<tree, va_gc> **cleanups,
lvalue-rvalue conversion applied to "a glvalue of literal type
that refers to a non-volatile temporary object initialized
with a constant expression". Rather than try to communicate
- that this VAR_DECL is a temporary, just mark it constexpr.
-
- Currently this is only useful for initializer_list temporaries,
- since reference vars can't appear in constant expressions. */
+ that this VAR_DECL is a temporary, just mark it constexpr. */
DECL_DECLARED_CONSTEXPR_P (var) = true;
DECL_INITIALIZED_BY_CONSTANT_EXPRESSION_P (var) = true;
TREE_CONSTANT (var) = true;
+ TREE_READONLY (var) = true;
}
DECL_INITIAL (var) = init;
init = NULL_TREE;
--- gcc/cp/tree.c
+++ gcc/cp/tree.c
@@ -442,6 +442,14 @@ build_target_expr (tree decl, tree value, tsubst_flags_t complain)
|| useless_type_conversion_p (TREE_TYPE (decl),
TREE_TYPE (value)));
+ /* Set TREE_READONLY for optimization, such as gimplify_init_constructor
+ moving a constant aggregate into .rodata. */
+ if (CP_TYPE_CONST_NON_VOLATILE_P (type)
+ && !TYPE_HAS_NONTRIVIAL_DESTRUCTOR (type)
+ && !VOID_TYPE_P (TREE_TYPE (value))
+ && reduced_constant_expression_p (value))
+ TREE_READONLY (decl) = true;
+
if (complain & tf_no_cleanup)
/* The caller is building a new-expr and does not need a cleanup. */
t = NULL_TREE;
--- /dev/null
+++ gcc/testsuite/g++.dg/cpp1y/pr95226.C
@@ -0,0 +1,17 @@
+// PR c++/95226
+// { dg-do run { target c++14 } }
+
+#include <vector>
+
+struct T {
+ unsigned a;
+ float b {8.};
+};
+
+int main()
+{
+ T t = {1};
+ std::vector<T> tt = {{1}, {2}};
+ if (t.a != 1 || t.b != 8.0f || tt[0].a != 1 || tt[0].b != 8.0f || tt[1].a != 2 || tt[1].b != 8.0f)
+ __builtin_abort ();
+}

70
gcc8-rh1981822.patch Normal file
View File

@ -0,0 +1,70 @@
From 55f40d968b0bd3be4478a9481e829a99ee0fa04f Mon Sep 17 00:00:00 2001
From: Jason Merrill <jason@redhat.com>
Date: Mon, 5 Apr 2021 22:50:44 -0400
Subject: [PATCH] c++: mangling of lambdas in default args [PR91241]
In this testcase, the parms remembered in LAMBDA_EXPR_EXTRA_SCOPE are no
longer the parms of the FUNCTION_DECL they have as their DECL_CONTEXT, so we
were mangling both lambdas as parm #0. But since the parms are numbered
from right to left we don't need to need to find them in the FUNCTION_DECL,
we can measure their own DECL_CHAIN.
gcc/cp/ChangeLog:
PR c++/91241
* mangle.c (write_compact_number): Add sanity check.
(write_local_name): Use list_length for parm number.
gcc/testsuite/ChangeLog:
PR c++/91241
* g++.dg/abi/lambda-defarg1.C: New test.
---
gcc/cp/mangle.c | 11 ++---------
gcc/testsuite/g++.dg/abi/lambda-defarg1.C | 11 +++++++++++
2 files changed, 13 insertions(+), 9 deletions(-)
create mode 100644 gcc/testsuite/g++.dg/abi/lambda-defarg1.C
--- gcc/cp/mangle.c
+++ gcc/cp/mangle.c
@@ -1628,6 +1628,7 @@ write_literal_operator_name (tree identifier)
static void
write_compact_number (int num)
{
+ gcc_checking_assert (num >= 0);
if (num > 0)
write_unsigned_number (num - 1);
write_char ('_');
@@ -2027,15 +2028,7 @@ write_local_name (tree function, const tree local_entity,
/* For this purpose, parameters are numbered from right-to-left. */
if (parm)
{
- tree t;
- int i = 0;
- for (t = DECL_ARGUMENTS (function); t; t = DECL_CHAIN (t))
- {
- if (t == parm)
- i = 1;
- else if (i)
- ++i;
- }
+ int i = list_length (parm);
write_char ('d');
write_compact_number (i - 1);
}
--- /dev/null
+++ gcc/testsuite/g++.dg/abi/lambda-defarg1.C
@@ -0,0 +1,11 @@
+// PR c++/91241
+// { dg-do compile { target c++11 } }
+
+struct A {
+ int *b(const int & = []() -> int { return 0; }(),
+ const int & = []() -> int { return 0; }());
+};
+int *A::b(const int &, const int &) { b(); return 0; }
+// { dg-final { scan-assembler "_ZN1A1bERKiS1_" } }
+// { dg-final { scan-assembler "_ZZN1A1bERKiS1_Ed_NKUlvE_clEv" } }
+// { dg-final { scan-assembler "_ZZN1A1bERKiS1_Ed0_NKUlvE_clEv" } }
--
2.27.0

101
gcc8-rh2028609.patch Normal file
View File

@ -0,0 +1,101 @@
The cprop_hardreg pass is built around the assumption that accessing a
register in a narrower mode is the same as accessing the lowpart of
the register. This unfortunately is not true for vector registers on
IBM Z. This caused a miscompile of LLVM with GCC 8.5. The problem
could not be reproduced with upstream GCC unfortunately but we have to
assume that it is latent there. The right fix would require
substantial changes to the cprop pass and is certainly something we
would want for our platform. But since this would not be acceptable
for older GCCs I'll go with what Vladimir proposed in the RedHat BZ
and introduce a hopefully temporary and undocumented target hook to
disable that specific transformation in regcprop.c.
--- a/gcc/config/s390/s390.c
+++ b/gcc/config/s390/s390.c
@@ -10488,6 +10488,18 @@ s390_hard_regno_mode_ok (unsigned int regno, machine_mode mode)
return false;
}
+/* Implement TARGET_NARROW_MODE_REFERS_LOW_PART_P. */
+
+static bool
+s390_narrow_mode_refers_low_part_p (unsigned int regno)
+{
+ if (reg_classes_intersect_p (VEC_REGS, REGNO_REG_CLASS (regno)))
+ return false;
+
+ return true;
+}
+
+
/* Implement TARGET_MODES_TIEABLE_P. */
static bool
@@ -16956,6 +16968,9 @@ s390_case_values_threshold (void)
#undef TARGET_CASE_VALUES_THRESHOLD
#define TARGET_CASE_VALUES_THRESHOLD s390_case_values_threshold
+#undef TARGET_NARROW_MODE_REFERS_LOW_PART_P
+#define TARGET_NARROW_MODE_REFERS_LOW_PART_P s390_narrow_mode_refers_low_part_p
+
struct gcc_target targetm = TARGET_INITIALIZER;
#include "gt-s390.h"
--- a/gcc/regcprop.c
+++ b/gcc/regcprop.c
@@ -426,7 +426,8 @@ maybe_mode_change (machine_mode orig_mode, machine_mode copy_mode,
if (orig_mode == new_mode)
return gen_raw_REG (new_mode, regno);
- else if (mode_change_ok (orig_mode, new_mode, regno))
+ else if (mode_change_ok (orig_mode, new_mode, regno)
+ && targetm.narrow_mode_refers_low_part_p (copy_regno))
{
int copy_nregs = hard_regno_nregs (copy_regno, copy_mode);
int use_nregs = hard_regno_nregs (copy_regno, new_mode);
--- a/gcc/target.def
+++ b/gcc/target.def
@@ -5446,6 +5446,16 @@ value that the middle-end intended.",
bool, (machine_mode from, machine_mode to, reg_class_t rclass),
hook_bool_mode_mode_reg_class_t_true)
+/* This hook is used to work around a problem in regcprop. Hardcoded
+assumptions currently prevent it from working correctly for targets
+where the low part of a multi-word register doesn't align to accessing
+the register with a narrower mode. */
+DEFHOOK_UNDOC
+(narrow_mode_refers_low_part_p,
+"",
+bool, (unsigned int regno),
+hook_bool_uint_true)
+
/* Change pseudo allocno class calculated by IRA. */
DEFHOOK
(ira_change_pseudo_allocno_class,
--- a/gcc/hooks.h
+++ b/gcc/hooks.h
@@ -86,6 +86,7 @@ extern void hook_void_tree (tree);
extern void hook_void_tree_treeptr (tree, tree *);
extern void hook_void_int_int (int, int);
extern void hook_void_gcc_optionsp (struct gcc_options *);
+extern bool hook_bool_uint_true (unsigned int);
extern bool hook_bool_uint_uintp_false (unsigned int, unsigned int *);
extern int hook_int_uint_mode_1 (unsigned int, machine_mode);
--- a/gcc/hooks.c
+++ b/gcc/hooks.c
@@ -498,6 +498,14 @@ hook_void_gcc_optionsp (struct gcc_optio
{
}
+/* Generic hook that takes an unsigned int and returns true. */
+
+bool
+hook_bool_uint_true (unsigned int)
+{
+ return true;
+}
+
/* Generic hook that takes an unsigned int, an unsigned int pointer and
returns false. */

View File

@ -0,0 +1,40 @@
--- gcc/config.gcc.jj 2008-04-24 15:42:46.000000000 -0500
+++ gcc/config.gcc 2008-04-24 15:44:51.000000000 -0500
@@ -2790,7 +2790,7 @@ sparc-*-rtems*)
tm_file="${tm_file} dbxelf.h elfos.h sparc/sysv4.h sparc/sp-elf.h sparc/rtemself.h rtems.h newlib-stdint.h"
tmake_file="${tmake_file} sparc/t-sparc sparc/t-rtems"
;;
-sparc-*-linux*)
+sparc-*-linux* | sparcv9-*-linux*)
tm_file="${tm_file} dbxelf.h elfos.h sparc/sysv4.h gnu-user.h linux.h glibc-stdint.h sparc/tso.h"
extra_options="${extra_options} sparc/long-double-switch.opt"
case ${target} in
@@ -2844,7 +2844,7 @@ sparc64-*-rtems*)
extra_options="${extra_options}"
tmake_file="${tmake_file} sparc/t-sparc sparc/t-rtems-64"
;;
-sparc64-*-linux*)
+sparc64*-*-linux*)
tm_file="sparc/biarch64.h ${tm_file} dbxelf.h elfos.h sparc/sysv4.h gnu-user.h linux.h glibc-stdint.h sparc/default64.h sparc/linux64.h sparc/tso.h"
extra_options="${extra_options} sparc/long-double-switch.opt"
tmake_file="${tmake_file} sparc/t-sparc sparc/t-linux64"
--- libgcc/config.host.jj 2008-04-24 15:46:19.000000000 -0500
+++ libgcc/config.host 2008-04-24 15:46:49.000000000 -0500
@@ -1002,7 +1002,7 @@ sparc-*-elf*)
tmake_file="${tmake_file} t-fdpbit t-crtfm"
extra_parts="$extra_parts crti.o crtn.o crtfastmath.o"
;;
-sparc-*-linux*) # SPARC's running GNU/Linux, libc6
+sparc-*-linux* | sparcv9-*-linux*) # SPARC's running GNU/Linux, libc6
tmake_file="${tmake_file} t-crtfm"
if test "${host_address}" = 64; then
tmake_file="$tmake_file sparc/t-linux64"
@@ -1050,7 +1050,7 @@ sparc64-*-freebsd*|ultrasparc-*-freebsd*
tmake_file="$tmake_file t-crtfm"
extra_parts="$extra_parts crtfastmath.o"
;;
-sparc64-*-linux*) # 64-bit SPARC's running GNU/Linux
+sparc64*-*-linux*) # 64-bit SPARC's running GNU/Linux
extra_parts="$extra_parts crtfastmath.o"
tmake_file="${tmake_file} t-crtfm sparc/t-linux"
if test "${host_address}" = 64; then

11
nvptx-tools-build.patch Normal file
View File

@ -0,0 +1,11 @@
--- nvptx-tools/nvptx-as.c.jj 2017-01-20 12:40:18.000000000 +0100
+++ nvptx-tools/nvptx-as.c 2017-01-20 12:43:53.864271442 +0100
@@ -939,7 +939,7 @@ fork_execute (const char *prog, char *co
fatal_error ("%s: %m", errmsg);
}
else
- fatal_error (errmsg);
+ fatal_error ("%s", errmsg);
}
do_wait (prog, pex);
}

32
nvptx-tools-glibc.patch Normal file
View File

@ -0,0 +1,32 @@
--- nvptx-tools/configure.ac.jj 2017-01-13 12:48:31.000000000 +0100
+++ nvptx-tools/configure.ac 2017-05-03 10:26:57.076092259 +0200
@@ -66,6 +66,8 @@ CPPFLAGS=$save_CPPFLAGS
LDFLAGS=$save_LDFLAGS
LIBS=$save_LIBS
+AC_CHECK_DECLS(getopt)
+
AC_CONFIG_SUBDIRS([libiberty])
AC_CONFIG_FILES([Makefile dejagnu.exp])
AC_OUTPUT
--- nvptx-tools/configure.jj 2017-01-13 12:48:54.000000000 +0100
+++ nvptx-tools/configure 2017-05-03 10:27:13.503876809 +0200
@@ -3963,6 +3963,18 @@ CPPFLAGS=$save_CPPFLAGS
LDFLAGS=$save_LDFLAGS
LIBS=$save_LIBS
+ac_fn_c_check_decl "$LINENO" "getopt" "ac_cv_have_decl_getopt" "$ac_includes_default"
+if test "x$ac_cv_have_decl_getopt" = x""yes; then :
+ ac_have_decl=1
+else
+ ac_have_decl=0
+fi
+
+cat >>confdefs.h <<_ACEOF
+#define HAVE_DECL_GETOPT $ac_have_decl
+_ACEOF
+
+
subdirs="$subdirs libiberty"

947
nvptx-tools-no-ptxas.patch Normal file
View File

@ -0,0 +1,947 @@
--- nvptx-tools/configure.ac
+++ nvptx-tools/configure.ac
@@ -51,6 +51,7 @@ LIBS="$LIBS -lcuda"
AC_CHECK_FUNCS([[cuGetErrorName] [cuGetErrorString]])
AC_CHECK_DECLS([[cuGetErrorName], [cuGetErrorString]],
[], [], [[#include <cuda.h>]])
+AC_CHECK_HEADERS(unistd.h sys/stat.h)
AC_MSG_CHECKING([for extra programs to build requiring -lcuda])
NVPTX_RUN=
--- nvptx-tools/include/libiberty.h
+++ nvptx-tools/include/libiberty.h
@@ -390,6 +390,17 @@ extern void hex_init (void);
/* Save files used for communication between processes. */
#define PEX_SAVE_TEMPS 0x4
+/* Max number of alloca bytes per call before we must switch to malloc.
+
+ ?? Swiped from gnulib's regex_internal.h header. Is this actually
+ the case? This number seems arbitrary, though sane.
+
+ The OS usually guarantees only one guard page at the bottom of the stack,
+ and a page size can be as small as 4096 bytes. So we cannot safely
+ allocate anything larger than 4096 bytes. Also care for the possibility
+ of a few compiler-allocated temporary stack slots. */
+#define MAX_ALLOCA_SIZE 4032
+
/* Prepare to execute one or more programs, with standard output of
each program fed to standard input of the next.
FLAGS As above.
--- nvptx-tools/nvptx-as.c
+++ nvptx-tools/nvptx-as.c
@@ -30,6 +30,9 @@
#include <string.h>
#include <wait.h>
#include <unistd.h>
+#ifdef HAVE_SYS_STAT_H
+#include <sys/stat.h>
+#endif
#include <errno.h>
#define obstack_chunk_alloc malloc
#define obstack_chunk_free free
@@ -42,6 +45,38 @@
#include "version.h"
+#ifndef R_OK
+#define R_OK 4
+#define W_OK 2
+#define X_OK 1
+#endif
+
+#ifndef DIR_SEPARATOR
+# define DIR_SEPARATOR '/'
+#endif
+
+#if defined (_WIN32) || defined (__MSDOS__) \
+ || defined (__DJGPP__) || defined (__OS2__)
+# define HAVE_DOS_BASED_FILE_SYSTEM
+# define HAVE_HOST_EXECUTABLE_SUFFIX
+# define HOST_EXECUTABLE_SUFFIX ".exe"
+# ifndef DIR_SEPARATOR_2
+# define DIR_SEPARATOR_2 '\\'
+# endif
+# define PATH_SEPARATOR ';'
+#else
+# define PATH_SEPARATOR ':'
+#endif
+
+#ifndef DIR_SEPARATOR_2
+# define IS_DIR_SEPARATOR(ch) ((ch) == DIR_SEPARATOR)
+#else
+# define IS_DIR_SEPARATOR(ch) \
+ (((ch) == DIR_SEPARATOR) || ((ch) == DIR_SEPARATOR_2))
+#endif
+
+#define DIR_UP ".."
+
static const char *outname = NULL;
static void __attribute__ ((format (printf, 1, 2)))
@@ -816,7 +851,7 @@ traverse (void **slot, void *data)
}
static void
-process (FILE *in, FILE *out)
+process (FILE *in, FILE *out, int verify, const char *outname)
{
symbol_table = htab_create (500, hash_string_hash, hash_string_eq,
NULL);
@@ -824,6 +859,18 @@ process (FILE *in, FILE *out)
const char *input = read_file (in);
Token *tok = tokenize (input);
+ /* By default, when ptxas is not in PATH, do minimalistic verification,
+ just require that the first non-comment directive is .version. */
+ if (verify < 0)
+ {
+ size_t i;
+ for (i = 0; tok[i].kind == K_comment; i++)
+ ;
+ if (tok[i].kind != K_dotted || !is_keyword (&tok[i], "version"))
+ fatal_error ("missing .version directive at start of file '%s'",
+ outname);
+ }
+
do
tok = parse_file (tok);
while (tok->kind);
@@ -897,9 +944,83 @@ fork_execute (const char *prog, char *const *argv)
do_wait (prog, pex);
}
+/* Determine if progname is available in PATH. */
+static bool
+program_available (const char *progname)
+{
+ char *temp = getenv ("PATH");
+ if (temp)
+ {
+ char *startp, *endp, *nstore, *alloc_ptr = NULL;
+ size_t prefixlen = strlen (temp) + 1;
+ size_t len;
+ if (prefixlen < 2)
+ prefixlen = 2;
+
+ len = prefixlen + strlen (progname) + 1;
+#ifdef HAVE_HOST_EXECUTABLE_SUFFIX
+ len += strlen (HOST_EXECUTABLE_SUFFIX);
+#endif
+ if (len < MAX_ALLOCA_SIZE)
+ nstore = (char *) alloca (len);
+ else
+ alloc_ptr = nstore = (char *) malloc (len);
+
+ startp = endp = temp;
+ while (1)
+ {
+ if (*endp == PATH_SEPARATOR || *endp == 0)
+ {
+ if (endp == startp)
+ {
+ nstore[0] = '.';
+ nstore[1] = DIR_SEPARATOR;
+ nstore[2] = '\0';
+ }
+ else
+ {
+ memcpy (nstore, startp, endp - startp);
+ if (! IS_DIR_SEPARATOR (endp[-1]))
+ {
+ nstore[endp - startp] = DIR_SEPARATOR;
+ nstore[endp - startp + 1] = 0;
+ }
+ else
+ nstore[endp - startp] = 0;
+ }
+ strcat (nstore, progname);
+ if (! access (nstore, X_OK)
+#ifdef HAVE_HOST_EXECUTABLE_SUFFIX
+ || ! access (strcat (nstore, HOST_EXECUTABLE_SUFFIX), X_OK)
+#endif
+ )
+ {
+#if defined (HAVE_SYS_STAT_H) && defined (S_ISREG)
+ struct stat st;
+ if (stat (nstore, &st) >= 0 && S_ISREG (st.st_mode))
+#endif
+ {
+ free (alloc_ptr);
+ return true;
+ }
+ }
+
+ if (*endp == 0)
+ break;
+ endp = startp = endp + 1;
+ }
+ else
+ endp++;
+ }
+ free (alloc_ptr);
+ }
+ return false;
+}
+
static struct option long_options[] = {
{"traditional-format", no_argument, 0, 0 },
{"save-temps", no_argument, 0, 0 },
+ {"verify", no_argument, 0, 0 },
{"no-verify", no_argument, 0, 0 },
{"help", no_argument, 0, 'h' },
{"version", no_argument, 0, 'V' },
@@ -912,7 +1033,7 @@ main (int argc, char **argv)
FILE *in = stdin;
FILE *out = stdout;
bool verbose __attribute__((unused)) = false;
- bool verify = true;
+ int verify = -1;
const char *smver = "sm_30";
int o;
@@ -923,7 +1044,9 @@ main (int argc, char **argv)
{
case 0:
if (option_index == 2)
- verify = false;
+ verify = 1;
+ else if (option_index == 3)
+ verify = 0;
break;
case 'v':
verbose = true;
@@ -948,7 +1071,8 @@ Usage: nvptx-none-as [option...] [asmfile]\n\
Options:\n\
-o FILE Write output to FILE\n\
-v Be verbose\n\
+ --verify Do verify output is acceptable to ptxas\n\
--no-verify Do not verify output is acceptable to ptxas\n\
--help Print this help and exit\n\
--version Print version number and exit\n\
\n\
@@ -983,11 +1108,17 @@ This program has absolutely no warranty.\n",
if (!in)
fatal_error ("cannot open input ptx file");
- process (in, out);
- if (outname)
+ if (outname == NULL)
+ verify = 0;
+ else if (verify == -1)
+ if (program_available ("ptxas"))
+ verify = 1;
+
+ process (in, out, verify, outname);
+ if (outname)
fclose (out);
- if (verify && outname)
+ if (verify > 0)
{
struct obstack argv_obstack;
obstack_init (&argv_obstack);
--- nvptx-tools/configure
+++ nvptx-tools/configure
@@ -168,7 +168,8 @@ test x\$exitcode = x0 || exit 1"
as_suggested=" as_lineno_1=";as_suggested=$as_suggested$LINENO;as_suggested=$as_suggested" as_lineno_1a=\$LINENO
as_lineno_2=";as_suggested=$as_suggested$LINENO;as_suggested=$as_suggested" as_lineno_2a=\$LINENO
eval 'test \"x\$as_lineno_1'\$as_run'\" != \"x\$as_lineno_2'\$as_run'\" &&
- test \"x\`expr \$as_lineno_1'\$as_run' + 1\`\" = \"x\$as_lineno_2'\$as_run'\"' || exit 1"
+ test \"x\`expr \$as_lineno_1'\$as_run' + 1\`\" = \"x\$as_lineno_2'\$as_run'\"' || exit 1
+test \$(( 1 + 1 )) = 2 || exit 1"
if (eval "$as_required") 2>/dev/null; then :
as_have_required=yes
else
@@ -552,11 +553,50 @@ PACKAGE_URL=
ac_unique_file="nvptx-tools"
ac_unique_file="nvptx-as.c"
+# Factoring default headers for most tests.
+ac_includes_default="\
+#include <stdio.h>
+#ifdef HAVE_SYS_TYPES_H
+# include <sys/types.h>
+#endif
+#ifdef HAVE_SYS_STAT_H
+# include <sys/stat.h>
+#endif
+#ifdef STDC_HEADERS
+# include <stdlib.h>
+# include <stddef.h>
+#else
+# ifdef HAVE_STDLIB_H
+# include <stdlib.h>
+# endif
+#endif
+#ifdef HAVE_STRING_H
+# if !defined STDC_HEADERS && defined HAVE_MEMORY_H
+# include <memory.h>
+# endif
+# include <string.h>
+#endif
+#ifdef HAVE_STRINGS_H
+# include <strings.h>
+#endif
+#ifdef HAVE_INTTYPES_H
+# include <inttypes.h>
+#endif
+#ifdef HAVE_STDINT_H
+# include <stdint.h>
+#endif
+#ifdef HAVE_UNISTD_H
+# include <unistd.h>
+#endif"
+
enable_option_checking=no
ac_subst_vars='LTLIBOBJS
LIBOBJS
subdirs
NVPTX_RUN
+EGREP
+GREP
+CPP
CUDA_DRIVER_LDFLAGS
CUDA_DRIVER_CPPFLAGS
AR
@@ -635,7 +675,8 @@ LIBS
CPPFLAGS
CXX
CXXFLAGS
-CCC'
+CCC
+CPP'
ac_subdirs_all='libiberty'
# Initialize some variables set by options.
@@ -1267,6 +1308,7 @@ Some influential environment variables:
you have headers in a nonstandard directory <include dir>
CXX C++ compiler command
CXXFLAGS C++ compiler flags
+ CPP C preprocessor
Use these variables to override the choices made by `configure' or to help
it to find libraries and programs with nonstandard names/locations.
@@ -1575,6 +1617,203 @@ $as_echo "$ac_res" >&6; }
eval $as_lineno_stack; test "x$as_lineno_stack" = x && { as_lineno=; unset as_lineno;}
} # ac_fn_c_check_decl
+
+# ac_fn_c_try_cpp LINENO
+# ----------------------
+# Try to preprocess conftest.$ac_ext, and return whether this succeeded.
+ac_fn_c_try_cpp ()
+{
+ as_lineno=${as_lineno-"$1"} as_lineno_stack=as_lineno_stack=$as_lineno_stack
+ if { { ac_try="$ac_cpp conftest.$ac_ext"
+case "(($ac_try" in
+ *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;;
+ *) ac_try_echo=$ac_try;;
+esac
+eval ac_try_echo="\"\$as_me:${as_lineno-$LINENO}: $ac_try_echo\""
+$as_echo "$ac_try_echo"; } >&5
+ (eval "$ac_cpp conftest.$ac_ext") 2>conftest.err
+ ac_status=$?
+ if test -s conftest.err; then
+ grep -v '^ *+' conftest.err >conftest.er1
+ cat conftest.er1 >&5
+ mv -f conftest.er1 conftest.err
+ fi
+ $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5
+ test $ac_status = 0; } >/dev/null && {
+ test -z "$ac_c_preproc_warn_flag$ac_c_werror_flag" ||
+ test ! -s conftest.err
+ }; then :
+ ac_retval=0
+else
+ $as_echo "$as_me: failed program was:" >&5
+sed 's/^/| /' conftest.$ac_ext >&5
+
+ ac_retval=1
+fi
+ eval $as_lineno_stack; test "x$as_lineno_stack" = x && { as_lineno=; unset as_lineno;}
+ return $ac_retval
+
+} # ac_fn_c_try_cpp
+
+# ac_fn_c_check_header_mongrel LINENO HEADER VAR INCLUDES
+# -------------------------------------------------------
+# Tests whether HEADER exists, giving a warning if it cannot be compiled using
+# the include files in INCLUDES and setting the cache variable VAR
+# accordingly.
+ac_fn_c_check_header_mongrel ()
+{
+ as_lineno=${as_lineno-"$1"} as_lineno_stack=as_lineno_stack=$as_lineno_stack
+ if { as_var=$3; eval "test \"\${$as_var+set}\" = set"; }; then :
+ { $as_echo "$as_me:${as_lineno-$LINENO}: checking for $2" >&5
+$as_echo_n "checking for $2... " >&6; }
+if { as_var=$3; eval "test \"\${$as_var+set}\" = set"; }; then :
+ $as_echo_n "(cached) " >&6
+fi
+eval ac_res=\$$3
+ { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_res" >&5
+$as_echo "$ac_res" >&6; }
+else
+ # Is the header compilable?
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking $2 usability" >&5
+$as_echo_n "checking $2 usability... " >&6; }
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h. */
+$4
+#include <$2>
+_ACEOF
+if ac_fn_c_try_compile "$LINENO"; then :
+ ac_header_compiler=yes
+else
+ ac_header_compiler=no
+fi
+rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_header_compiler" >&5
+$as_echo "$ac_header_compiler" >&6; }
+
+# Is the header present?
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking $2 presence" >&5
+$as_echo_n "checking $2 presence... " >&6; }
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h. */
+#include <$2>
+_ACEOF
+if ac_fn_c_try_cpp "$LINENO"; then :
+ ac_header_preproc=yes
+else
+ ac_header_preproc=no
+fi
+rm -f conftest.err conftest.$ac_ext
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_header_preproc" >&5
+$as_echo "$ac_header_preproc" >&6; }
+
+# So? What about this header?
+case $ac_header_compiler:$ac_header_preproc:$ac_c_preproc_warn_flag in #((
+ yes:no: )
+ { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: $2: accepted by the compiler, rejected by the preprocessor!" >&5
+$as_echo "$as_me: WARNING: $2: accepted by the compiler, rejected by the preprocessor!" >&2;}
+ { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: $2: proceeding with the compiler's result" >&5
+$as_echo "$as_me: WARNING: $2: proceeding with the compiler's result" >&2;}
+ ;;
+ no:yes:* )
+ { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: $2: present but cannot be compiled" >&5
+$as_echo "$as_me: WARNING: $2: present but cannot be compiled" >&2;}
+ { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: $2: check for missing prerequisite headers?" >&5
+$as_echo "$as_me: WARNING: $2: check for missing prerequisite headers?" >&2;}
+ { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: $2: see the Autoconf documentation" >&5
+$as_echo "$as_me: WARNING: $2: see the Autoconf documentation" >&2;}
+ { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: $2: section \"Present But Cannot Be Compiled\"" >&5
+$as_echo "$as_me: WARNING: $2: section \"Present But Cannot Be Compiled\"" >&2;}
+ { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: $2: proceeding with the compiler's result" >&5
+$as_echo "$as_me: WARNING: $2: proceeding with the compiler's result" >&2;}
+ ;;
+esac
+ { $as_echo "$as_me:${as_lineno-$LINENO}: checking for $2" >&5
+$as_echo_n "checking for $2... " >&6; }
+if { as_var=$3; eval "test \"\${$as_var+set}\" = set"; }; then :
+ $as_echo_n "(cached) " >&6
+else
+ eval "$3=\$ac_header_compiler"
+fi
+eval ac_res=\$$3
+ { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_res" >&5
+$as_echo "$ac_res" >&6; }
+fi
+ eval $as_lineno_stack; test "x$as_lineno_stack" = x && { as_lineno=; unset as_lineno;}
+
+} # ac_fn_c_check_header_mongrel
+
+# ac_fn_c_try_run LINENO
+# ----------------------
+# Try to link conftest.$ac_ext, and return whether this succeeded. Assumes
+# that executables *can* be run.
+ac_fn_c_try_run ()
+{
+ as_lineno=${as_lineno-"$1"} as_lineno_stack=as_lineno_stack=$as_lineno_stack
+ if { { ac_try="$ac_link"
+case "(($ac_try" in
+ *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;;
+ *) ac_try_echo=$ac_try;;
+esac
+eval ac_try_echo="\"\$as_me:${as_lineno-$LINENO}: $ac_try_echo\""
+$as_echo "$ac_try_echo"; } >&5
+ (eval "$ac_link") 2>&5
+ ac_status=$?
+ $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5
+ test $ac_status = 0; } && { ac_try='./conftest$ac_exeext'
+ { { case "(($ac_try" in
+ *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;;
+ *) ac_try_echo=$ac_try;;
+esac
+eval ac_try_echo="\"\$as_me:${as_lineno-$LINENO}: $ac_try_echo\""
+$as_echo "$ac_try_echo"; } >&5
+ (eval "$ac_try") 2>&5
+ ac_status=$?
+ $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5
+ test $ac_status = 0; }; }; then :
+ ac_retval=0
+else
+ $as_echo "$as_me: program exited with status $ac_status" >&5
+ $as_echo "$as_me: failed program was:" >&5
+sed 's/^/| /' conftest.$ac_ext >&5
+
+ ac_retval=$ac_status
+fi
+ rm -rf conftest.dSYM conftest_ipa8_conftest.oo
+ eval $as_lineno_stack; test "x$as_lineno_stack" = x && { as_lineno=; unset as_lineno;}
+ return $ac_retval
+
+} # ac_fn_c_try_run
+
+# ac_fn_c_check_header_compile LINENO HEADER VAR INCLUDES
+# -------------------------------------------------------
+# Tests whether HEADER exists and can be compiled using the include files in
+# INCLUDES, setting the cache variable VAR accordingly.
+ac_fn_c_check_header_compile ()
+{
+ as_lineno=${as_lineno-"$1"} as_lineno_stack=as_lineno_stack=$as_lineno_stack
+ { $as_echo "$as_me:${as_lineno-$LINENO}: checking for $2" >&5
+$as_echo_n "checking for $2... " >&6; }
+if { as_var=$3; eval "test \"\${$as_var+set}\" = set"; }; then :
+ $as_echo_n "(cached) " >&6
+else
+ cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h. */
+$4
+#include <$2>
+_ACEOF
+if ac_fn_c_try_compile "$LINENO"; then :
+ eval "$3=yes"
+else
+ eval "$3=no"
+fi
+rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext
+fi
+eval ac_res=\$$3
+ { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_res" >&5
+$as_echo "$ac_res" >&6; }
+ eval $as_lineno_stack; test "x$as_lineno_stack" = x && { as_lineno=; unset as_lineno;}
+
+} # ac_fn_c_check_header_compile
cat >config.log <<_ACEOF
This file contains any messages produced by compilers while
running configure, to aid debugging if configure makes a mistake.
@@ -3284,6 +3523,418 @@ cat >>confdefs.h <<_ACEOF
#define HAVE_DECL_CUGETERRORSTRING $ac_have_decl
_ACEOF
+ac_ext=c
+ac_cpp='$CPP $CPPFLAGS'
+ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5'
+ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5'
+ac_compiler_gnu=$ac_cv_c_compiler_gnu
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking how to run the C preprocessor" >&5
+$as_echo_n "checking how to run the C preprocessor... " >&6; }
+# On Suns, sometimes $CPP names a directory.
+if test -n "$CPP" && test -d "$CPP"; then
+ CPP=
+fi
+if test -z "$CPP"; then
+ if test "${ac_cv_prog_CPP+set}" = set; then :
+ $as_echo_n "(cached) " >&6
+else
+ # Double quotes because CPP needs to be expanded
+ for CPP in "$CC -E" "$CC -E -traditional-cpp" "/lib/cpp"
+ do
+ ac_preproc_ok=false
+for ac_c_preproc_warn_flag in '' yes
+do
+ # Use a header file that comes with gcc, so configuring glibc
+ # with a fresh cross-compiler works.
+ # Prefer <limits.h> to <assert.h> if __STDC__ is defined, since
+ # <limits.h> exists even on freestanding compilers.
+ # On the NeXT, cc -E runs the code through the compiler's parser,
+ # not just through cpp. "Syntax error" is here to catch this case.
+ cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h. */
+#ifdef __STDC__
+# include <limits.h>
+#else
+# include <assert.h>
+#endif
+ Syntax error
+_ACEOF
+if ac_fn_c_try_cpp "$LINENO"; then :
+
+else
+ # Broken: fails on valid input.
+continue
+fi
+rm -f conftest.err conftest.$ac_ext
+
+ # OK, works on sane cases. Now check whether nonexistent headers
+ # can be detected and how.
+ cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h. */
+#include <ac_nonexistent.h>
+_ACEOF
+if ac_fn_c_try_cpp "$LINENO"; then :
+ # Broken: success on invalid input.
+continue
+else
+ # Passes both tests.
+ac_preproc_ok=:
+break
+fi
+rm -f conftest.err conftest.$ac_ext
+
+done
+# Because of `break', _AC_PREPROC_IFELSE's cleaning code was skipped.
+rm -f conftest.err conftest.$ac_ext
+if $ac_preproc_ok; then :
+ break
+fi
+
+ done
+ ac_cv_prog_CPP=$CPP
+
+fi
+ CPP=$ac_cv_prog_CPP
+else
+ ac_cv_prog_CPP=$CPP
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $CPP" >&5
+$as_echo "$CPP" >&6; }
+ac_preproc_ok=false
+for ac_c_preproc_warn_flag in '' yes
+do
+ # Use a header file that comes with gcc, so configuring glibc
+ # with a fresh cross-compiler works.
+ # Prefer <limits.h> to <assert.h> if __STDC__ is defined, since
+ # <limits.h> exists even on freestanding compilers.
+ # On the NeXT, cc -E runs the code through the compiler's parser,
+ # not just through cpp. "Syntax error" is here to catch this case.
+ cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h. */
+#ifdef __STDC__
+# include <limits.h>
+#else
+# include <assert.h>
+#endif
+ Syntax error
+_ACEOF
+if ac_fn_c_try_cpp "$LINENO"; then :
+
+else
+ # Broken: fails on valid input.
+continue
+fi
+rm -f conftest.err conftest.$ac_ext
+
+ # OK, works on sane cases. Now check whether nonexistent headers
+ # can be detected and how.
+ cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h. */
+#include <ac_nonexistent.h>
+_ACEOF
+if ac_fn_c_try_cpp "$LINENO"; then :
+ # Broken: success on invalid input.
+continue
+else
+ # Passes both tests.
+ac_preproc_ok=:
+break
+fi
+rm -f conftest.err conftest.$ac_ext
+
+done
+# Because of `break', _AC_PREPROC_IFELSE's cleaning code was skipped.
+rm -f conftest.err conftest.$ac_ext
+if $ac_preproc_ok; then :
+
+else
+ { { $as_echo "$as_me:${as_lineno-$LINENO}: error: in \`$ac_pwd':" >&5
+$as_echo "$as_me: error: in \`$ac_pwd':" >&2;}
+as_fn_error "C preprocessor \"$CPP\" fails sanity check
+See \`config.log' for more details." "$LINENO" 5; }
+fi
+
+ac_ext=c
+ac_cpp='$CPP $CPPFLAGS'
+ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5'
+ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5'
+ac_compiler_gnu=$ac_cv_c_compiler_gnu
+
+
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for grep that handles long lines and -e" >&5
+$as_echo_n "checking for grep that handles long lines and -e... " >&6; }
+if test "${ac_cv_path_GREP+set}" = set; then :
+ $as_echo_n "(cached) " >&6
+else
+ if test -z "$GREP"; then
+ ac_path_GREP_found=false
+ # Loop through the user's path and test for each of PROGNAME-LIST
+ as_save_IFS=$IFS; IFS=$PATH_SEPARATOR
+for as_dir in $PATH$PATH_SEPARATOR/usr/xpg4/bin
+do
+ IFS=$as_save_IFS
+ test -z "$as_dir" && as_dir=.
+ for ac_prog in grep ggrep; do
+ for ac_exec_ext in '' $ac_executable_extensions; do
+ ac_path_GREP="$as_dir/$ac_prog$ac_exec_ext"
+ { test -f "$ac_path_GREP" && $as_test_x "$ac_path_GREP"; } || continue
+# Check for GNU ac_path_GREP and select it if it is found.
+ # Check for GNU $ac_path_GREP
+case `"$ac_path_GREP" --version 2>&1` in
+*GNU*)
+ ac_cv_path_GREP="$ac_path_GREP" ac_path_GREP_found=:;;
+*)
+ ac_count=0
+ $as_echo_n 0123456789 >"conftest.in"
+ while :
+ do
+ cat "conftest.in" "conftest.in" >"conftest.tmp"
+ mv "conftest.tmp" "conftest.in"
+ cp "conftest.in" "conftest.nl"
+ $as_echo 'GREP' >> "conftest.nl"
+ "$ac_path_GREP" -e 'GREP$' -e '-(cannot match)-' < "conftest.nl" >"conftest.out" 2>/dev/null || break
+ diff "conftest.out" "conftest.nl" >/dev/null 2>&1 || break
+ as_fn_arith $ac_count + 1 && ac_count=$as_val
+ if test $ac_count -gt ${ac_path_GREP_max-0}; then
+ # Best one so far, save it but keep looking for a better one
+ ac_cv_path_GREP="$ac_path_GREP"
+ ac_path_GREP_max=$ac_count
+ fi
+ # 10*(2^10) chars as input seems more than enough
+ test $ac_count -gt 10 && break
+ done
+ rm -f conftest.in conftest.tmp conftest.nl conftest.out;;
+esac
+
+ $ac_path_GREP_found && break 3
+ done
+ done
+ done
+IFS=$as_save_IFS
+ if test -z "$ac_cv_path_GREP"; then
+ as_fn_error "no acceptable grep could be found in $PATH$PATH_SEPARATOR/usr/xpg4/bin" "$LINENO" 5
+ fi
+else
+ ac_cv_path_GREP=$GREP
+fi
+
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_path_GREP" >&5
+$as_echo "$ac_cv_path_GREP" >&6; }
+ GREP="$ac_cv_path_GREP"
+
+
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for egrep" >&5
+$as_echo_n "checking for egrep... " >&6; }
+if test "${ac_cv_path_EGREP+set}" = set; then :
+ $as_echo_n "(cached) " >&6
+else
+ if echo a | $GREP -E '(a|b)' >/dev/null 2>&1
+ then ac_cv_path_EGREP="$GREP -E"
+ else
+ if test -z "$EGREP"; then
+ ac_path_EGREP_found=false
+ # Loop through the user's path and test for each of PROGNAME-LIST
+ as_save_IFS=$IFS; IFS=$PATH_SEPARATOR
+for as_dir in $PATH$PATH_SEPARATOR/usr/xpg4/bin
+do
+ IFS=$as_save_IFS
+ test -z "$as_dir" && as_dir=.
+ for ac_prog in egrep; do
+ for ac_exec_ext in '' $ac_executable_extensions; do
+ ac_path_EGREP="$as_dir/$ac_prog$ac_exec_ext"
+ { test -f "$ac_path_EGREP" && $as_test_x "$ac_path_EGREP"; } || continue
+# Check for GNU ac_path_EGREP and select it if it is found.
+ # Check for GNU $ac_path_EGREP
+case `"$ac_path_EGREP" --version 2>&1` in
+*GNU*)
+ ac_cv_path_EGREP="$ac_path_EGREP" ac_path_EGREP_found=:;;
+*)
+ ac_count=0
+ $as_echo_n 0123456789 >"conftest.in"
+ while :
+ do
+ cat "conftest.in" "conftest.in" >"conftest.tmp"
+ mv "conftest.tmp" "conftest.in"
+ cp "conftest.in" "conftest.nl"
+ $as_echo 'EGREP' >> "conftest.nl"
+ "$ac_path_EGREP" 'EGREP$' < "conftest.nl" >"conftest.out" 2>/dev/null || break
+ diff "conftest.out" "conftest.nl" >/dev/null 2>&1 || break
+ as_fn_arith $ac_count + 1 && ac_count=$as_val
+ if test $ac_count -gt ${ac_path_EGREP_max-0}; then
+ # Best one so far, save it but keep looking for a better one
+ ac_cv_path_EGREP="$ac_path_EGREP"
+ ac_path_EGREP_max=$ac_count
+ fi
+ # 10*(2^10) chars as input seems more than enough
+ test $ac_count -gt 10 && break
+ done
+ rm -f conftest.in conftest.tmp conftest.nl conftest.out;;
+esac
+
+ $ac_path_EGREP_found && break 3
+ done
+ done
+ done
+IFS=$as_save_IFS
+ if test -z "$ac_cv_path_EGREP"; then
+ as_fn_error "no acceptable egrep could be found in $PATH$PATH_SEPARATOR/usr/xpg4/bin" "$LINENO" 5
+ fi
+else
+ ac_cv_path_EGREP=$EGREP
+fi
+
+ fi
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_path_EGREP" >&5
+$as_echo "$ac_cv_path_EGREP" >&6; }
+ EGREP="$ac_cv_path_EGREP"
+
+
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for ANSI C header files" >&5
+$as_echo_n "checking for ANSI C header files... " >&6; }
+if test "${ac_cv_header_stdc+set}" = set; then :
+ $as_echo_n "(cached) " >&6
+else
+ cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h. */
+#include <stdlib.h>
+#include <stdarg.h>
+#include <string.h>
+#include <float.h>
+
+int
+main ()
+{
+
+ ;
+ return 0;
+}
+_ACEOF
+if ac_fn_c_try_compile "$LINENO"; then :
+ ac_cv_header_stdc=yes
+else
+ ac_cv_header_stdc=no
+fi
+rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext
+
+if test $ac_cv_header_stdc = yes; then
+ # SunOS 4.x string.h does not declare mem*, contrary to ANSI.
+ cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h. */
+#include <string.h>
+
+_ACEOF
+if (eval "$ac_cpp conftest.$ac_ext") 2>&5 |
+ $EGREP "memchr" >/dev/null 2>&1; then :
+
+else
+ ac_cv_header_stdc=no
+fi
+rm -f conftest*
+
+fi
+
+if test $ac_cv_header_stdc = yes; then
+ # ISC 2.0.2 stdlib.h does not declare free, contrary to ANSI.
+ cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h. */
+#include <stdlib.h>
+
+_ACEOF
+if (eval "$ac_cpp conftest.$ac_ext") 2>&5 |
+ $EGREP "free" >/dev/null 2>&1; then :
+
+else
+ ac_cv_header_stdc=no
+fi
+rm -f conftest*
+
+fi
+
+if test $ac_cv_header_stdc = yes; then
+ # /bin/cc in Irix-4.0.5 gets non-ANSI ctype macros unless using -ansi.
+ if test "$cross_compiling" = yes; then :
+ :
+else
+ cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h. */
+#include <ctype.h>
+#include <stdlib.h>
+#if ((' ' & 0x0FF) == 0x020)
+# define ISLOWER(c) ('a' <= (c) && (c) <= 'z')
+# define TOUPPER(c) (ISLOWER(c) ? 'A' + ((c) - 'a') : (c))
+#else
+# define ISLOWER(c) \
+ (('a' <= (c) && (c) <= 'i') \
+ || ('j' <= (c) && (c) <= 'r') \
+ || ('s' <= (c) && (c) <= 'z'))
+# define TOUPPER(c) (ISLOWER(c) ? ((c) | 0x40) : (c))
+#endif
+
+#define XOR(e, f) (((e) && !(f)) || (!(e) && (f)))
+int
+main ()
+{
+ int i;
+ for (i = 0; i < 256; i++)
+ if (XOR (islower (i), ISLOWER (i))
+ || toupper (i) != TOUPPER (i))
+ return 2;
+ return 0;
+}
+_ACEOF
+if ac_fn_c_try_run "$LINENO"; then :
+
+else
+ ac_cv_header_stdc=no
+fi
+rm -f core *.core core.conftest.* gmon.out bb.out conftest$ac_exeext \
+ conftest.$ac_objext conftest.beam conftest.$ac_ext
+fi
+
+fi
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_header_stdc" >&5
+$as_echo "$ac_cv_header_stdc" >&6; }
+if test $ac_cv_header_stdc = yes; then
+
+$as_echo "#define STDC_HEADERS 1" >>confdefs.h
+
+fi
+
+# On IRIX 5.3, sys/types and inttypes.h are conflicting.
+for ac_header in sys/types.h sys/stat.h stdlib.h string.h memory.h strings.h \
+ inttypes.h stdint.h unistd.h
+do :
+ as_ac_Header=`$as_echo "ac_cv_header_$ac_header" | $as_tr_sh`
+ac_fn_c_check_header_compile "$LINENO" "$ac_header" "$as_ac_Header" "$ac_includes_default
+"
+eval as_val=\$$as_ac_Header
+ if test "x$as_val" = x""yes; then :
+ cat >>confdefs.h <<_ACEOF
+#define `$as_echo "HAVE_$ac_header" | $as_tr_cpp` 1
+_ACEOF
+
+fi
+
+done
+
+
+for ac_header in unistd.h sys/stat.h
+do :
+ as_ac_Header=`$as_echo "ac_cv_header_$ac_header" | $as_tr_sh`
+ac_fn_c_check_header_mongrel "$LINENO" "$ac_header" "$as_ac_Header" "$ac_includes_default"
+eval as_val=\$$as_ac_Header
+ if test "x$as_val" = x""yes; then :
+ cat >>confdefs.h <<_ACEOF
+#define `$as_echo "HAVE_$ac_header" | $as_tr_cpp` 1
+_ACEOF
+
+fi
+
+done
+
{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for extra programs to build requiring -lcuda" >&5
$as_echo_n "checking for extra programs to build requiring -lcuda... " >&6; }

3
sources Normal file
View File

@ -0,0 +1,3 @@
SHA512 (gcc-8.5.0-20210514.tar.xz) = 4811dbcbdce8fe0fa8bc1fdca024988a1a75ac89e3efc675fe991b81032c220ab4bd1bc530bb99f6209ffeca67581a198de82f7253530de8c24a2a81770eb4ea
SHA512 (nvptx-newlib-aadc8eb0ec43b7cd0dd2dfb484bae63c8b05ef24.tar.xz) = 94f7089365296f7dfa485107b4143bebc850a81586f3460fd896bbbb6ba099a00217d4042133424fd2183b352132f4fd367e6a60599bdae2a26dfd48a77d0e04
SHA512 (nvptx-tools-c28050f60193b3b95a18866a96f03334e874e78f.tar.xz) = a688cb12cf805950a5abbb13b52f45c81dbee98e310b7ed57ae20e76dbfa5964a16270148374a6426d177db71909d28360490f091c86a5d19d4faa5127beeee1