From c455522ac5d8ab41e5d11f8997678e042ff48e87 Mon Sep 17 00:00:00 2001
From: Thomas Schwinge <thomas@codesourcery.com>
Date: Thu, 7 Apr 2022 23:10:16 +0200
Subject: [PATCH] libgomp nvptx plugin: Split 'PLUGIN_NVPTX_DYNAMIC' into
'PLUGIN_NVPTX_INCLUDE_SYSTEM_CUDA_H' and 'PLUGIN_NVPTX_LINK_LIBCUDA'
Including the GCC-shipped 'include/cuda/cuda.h' vs. system <cuda.h> and
'dlopen'ing the CUDA Driver library vs. linking it are separate concerns.
libgomp/
* plugin/Makefrag.am: Handle 'PLUGIN_NVPTX_DYNAMIC'.
* plugin/configfrag.ac (PLUGIN_NVPTX_DYNAMIC): Change
'AC_DEFINE_UNQUOTED' into 'AM_CONDITIONAL'.
* plugin/plugin-nvptx.c: Split 'PLUGIN_NVPTX_DYNAMIC' into
'PLUGIN_NVPTX_INCLUDE_SYSTEM_CUDA_H' and
'PLUGIN_NVPTX_LINK_LIBCUDA'.
* Makefile.in: Regenerate.
* config.h.in: Likewise.
* configure: Likewise.
---
libgomp/Makefile.in | 26 +++++++++++++++++++-------
libgomp/config.h.in | 4 ----
libgomp/configure | 21 +++++++++++++++------
libgomp/plugin/Makefrag.am | 16 +++++++++++++++-
libgomp/plugin/configfrag.ac | 3 +--
libgomp/plugin/plugin-nvptx.c | 4 ++--
6 files changed, 52 insertions(+), 22 deletions(-)
@@ -119,8 +119,16 @@ build_triplet = @build@
host_triplet = @host@
target_triplet = @target@
@PLUGIN_NVPTX_TRUE@am__append_1 = libgomp-plugin-nvptx.la
-@PLUGIN_GCN_TRUE@am__append_2 = libgomp-plugin-gcn.la
-@USE_FORTRAN_TRUE@am__append_3 = openacc.f90
+
+# Including the GCC-shipped 'include/cuda/cuda.h' vs. system <cuda.h>.
+@PLUGIN_NVPTX_DYNAMIC_FALSE@@PLUGIN_NVPTX_TRUE@am__append_2 = -DPLUGIN_NVPTX_INCLUDE_SYSTEM_CUDA_H \
+@PLUGIN_NVPTX_DYNAMIC_FALSE@@PLUGIN_NVPTX_TRUE@ -DPLUGIN_NVPTX_LINK_LIBCUDA
+
+# 'dlopen'ing the CUDA Driver library vs. linking it.
+@PLUGIN_NVPTX_DYNAMIC_TRUE@@PLUGIN_NVPTX_TRUE@am__append_3 = $(PLUGIN_NVPTX_LIBS)
+@PLUGIN_NVPTX_DYNAMIC_FALSE@@PLUGIN_NVPTX_TRUE@am__append_4 = $(PLUGIN_NVPTX_LIBS)
+@PLUGIN_GCN_TRUE@am__append_5 = libgomp-plugin-gcn.la
+@USE_FORTRAN_TRUE@am__append_6 = openacc.f90
subdir = .
ACLOCAL_M4 = $(top_srcdir)/aclocal.m4
am__aclocal_m4_deps = $(top_srcdir)/../config/acx.m4 \
@@ -197,8 +205,10 @@ libgomp_plugin_gcn_la_LINK = $(LIBTOOL) $(AM_V_lt) --tag=CC \
$(libgomp_plugin_gcn_la_LDFLAGS) $(LDFLAGS) -o $@
@PLUGIN_GCN_TRUE@am_libgomp_plugin_gcn_la_rpath = -rpath \
@PLUGIN_GCN_TRUE@ $(toolexeclibdir)
+@PLUGIN_NVPTX_DYNAMIC_TRUE@@PLUGIN_NVPTX_TRUE@am__DEPENDENCIES_2 = $(am__DEPENDENCIES_1)
+@PLUGIN_NVPTX_DYNAMIC_FALSE@@PLUGIN_NVPTX_TRUE@am__DEPENDENCIES_3 = $(am__DEPENDENCIES_1)
@PLUGIN_NVPTX_TRUE@libgomp_plugin_nvptx_la_DEPENDENCIES = libgomp.la \
-@PLUGIN_NVPTX_TRUE@ $(am__DEPENDENCIES_1)
+@PLUGIN_NVPTX_TRUE@ $(am__DEPENDENCIES_2) $(am__DEPENDENCIES_3)
@PLUGIN_NVPTX_TRUE@am_libgomp_plugin_nvptx_la_OBJECTS = \
@PLUGIN_NVPTX_TRUE@ libgomp_plugin_nvptx_la-plugin-nvptx.lo
libgomp_plugin_nvptx_la_OBJECTS = \
@@ -533,7 +543,7 @@ libsubincludedir = $(libdir)/gcc/$(target_alias)/$(gcc_version)/include
AM_CPPFLAGS = $(addprefix -I, $(search_path))
AM_CFLAGS = $(XCFLAGS)
AM_LDFLAGS = $(XLDFLAGS) $(SECTION_LDFLAGS) $(OPT_LDFLAGS)
-toolexeclib_LTLIBRARIES = libgomp.la $(am__append_1) $(am__append_2)
+toolexeclib_LTLIBRARIES = libgomp.la $(am__append_1) $(am__append_5)
nodist_toolexeclib_HEADERS = libgomp.spec
# -Wc is only a libtool option.
@@ -559,16 +569,18 @@ libgomp_la_SOURCES = alloc.c atomic.c barrier.c critical.c env.c \
oacc-parallel.c oacc-host.c oacc-init.c oacc-mem.c \
oacc-async.c oacc-plugin.c oacc-cuda.c priority_queue.c \
affinity-fmt.c teams.c allocator.c oacc-profiling.c \
- oacc-target.c $(am__append_3)
+ oacc-target.c $(am__append_6)
# Nvidia PTX OpenACC plugin.
@PLUGIN_NVPTX_TRUE@libgomp_plugin_nvptx_version_info = -version-info $(libtool_VERSION)
@PLUGIN_NVPTX_TRUE@libgomp_plugin_nvptx_la_SOURCES = plugin/plugin-nvptx.c
-@PLUGIN_NVPTX_TRUE@libgomp_plugin_nvptx_la_CPPFLAGS = $(AM_CPPFLAGS) $(PLUGIN_NVPTX_CPPFLAGS)
+@PLUGIN_NVPTX_TRUE@libgomp_plugin_nvptx_la_CPPFLAGS = $(AM_CPPFLAGS) \
+@PLUGIN_NVPTX_TRUE@ $(PLUGIN_NVPTX_CPPFLAGS) $(am__append_2)
@PLUGIN_NVPTX_TRUE@libgomp_plugin_nvptx_la_LDFLAGS = \
@PLUGIN_NVPTX_TRUE@ $(libgomp_plugin_nvptx_version_info) \
@PLUGIN_NVPTX_TRUE@ $(lt_host_flags) $(PLUGIN_NVPTX_LDFLAGS)
-@PLUGIN_NVPTX_TRUE@libgomp_plugin_nvptx_la_LIBADD = libgomp.la $(PLUGIN_NVPTX_LIBS)
+@PLUGIN_NVPTX_TRUE@libgomp_plugin_nvptx_la_LIBADD = libgomp.la \
+@PLUGIN_NVPTX_TRUE@ $(am__append_3) $(am__append_4)
@PLUGIN_NVPTX_TRUE@libgomp_plugin_nvptx_la_LIBTOOLFLAGS = --tag=disable-static
# AMD GCN plugin
@@ -176,10 +176,6 @@
/* Define to 1 if the NVIDIA plugin is built, 0 if not. */
#undef PLUGIN_NVPTX
-/* Define to 1 if the NVIDIA plugin should dlopen libcuda.so.1, 0 if it should
- be linked against it. */
-#undef PLUGIN_NVPTX_DYNAMIC
-
/* Define if all infrastructure, needed for plugins, is supported. */
#undef PLUGIN_SUPPORT
@@ -667,6 +667,8 @@ OPT_LDFLAGS
SECTION_LDFLAGS
PLUGIN_GCN_FALSE
PLUGIN_GCN_TRUE
+PLUGIN_NVPTX_DYNAMIC_FALSE
+PLUGIN_NVPTX_DYNAMIC_TRUE
PLUGIN_NVPTX_FALSE
PLUGIN_NVPTX_TRUE
offload_additional_lib_paths
@@ -11431,7 +11433,7 @@ else
lt_dlunknown=0; lt_dlno_uscore=1; lt_dlneed_uscore=2
lt_status=$lt_dlunknown
cat > conftest.$ac_ext <<_LT_EOF
-#line 11434 "configure"
+#line 11436 "configure"
#include "confdefs.h"
#if HAVE_DLFCN_H
@@ -11537,7 +11539,7 @@ else
lt_dlunknown=0; lt_dlno_uscore=1; lt_dlneed_uscore=2
lt_status=$lt_dlunknown
cat > conftest.$ac_ext <<_LT_EOF
-#line 11540 "configure"
+#line 11542 "configure"
#include "confdefs.h"
#if HAVE_DLFCN_H
@@ -15444,10 +15446,13 @@ cat >>confdefs.h <<_ACEOF
#define PLUGIN_NVPTX $PLUGIN_NVPTX
_ACEOF
-
-cat >>confdefs.h <<_ACEOF
-#define PLUGIN_NVPTX_DYNAMIC $PLUGIN_NVPTX_DYNAMIC
-_ACEOF
+ if test $PLUGIN_NVPTX_DYNAMIC = 1; then
+ PLUGIN_NVPTX_DYNAMIC_TRUE=
+ PLUGIN_NVPTX_DYNAMIC_FALSE='#'
+else
+ PLUGIN_NVPTX_DYNAMIC_TRUE='#'
+ PLUGIN_NVPTX_DYNAMIC_FALSE=
+fi
if test $PLUGIN_GCN = 1; then
PLUGIN_GCN_TRUE=
@@ -17221,6 +17226,10 @@ if test -z "${PLUGIN_NVPTX_TRUE}" && test -z "${PLUGIN_NVPTX_FALSE}"; then
as_fn_error $? "conditional \"PLUGIN_NVPTX\" was never defined.
Usually this means the macro was only invoked conditionally." "$LINENO" 5
fi
+if test -z "${PLUGIN_NVPTX_DYNAMIC_TRUE}" && test -z "${PLUGIN_NVPTX_DYNAMIC_FALSE}"; then
+ as_fn_error $? "conditional \"PLUGIN_NVPTX_DYNAMIC\" was never defined.
+Usually this means the macro was only invoked conditionally." "$LINENO" 5
+fi
if test -z "${PLUGIN_GCN_TRUE}" && test -z "${PLUGIN_GCN_FALSE}"; then
as_fn_error $? "conditional \"PLUGIN_GCN\" was never defined.
Usually this means the macro was only invoked conditionally." "$LINENO" 5
@@ -35,8 +35,22 @@ libgomp_plugin_nvptx_la_CPPFLAGS = $(AM_CPPFLAGS) $(PLUGIN_NVPTX_CPPFLAGS)
libgomp_plugin_nvptx_la_LDFLAGS = $(libgomp_plugin_nvptx_version_info) \
$(lt_host_flags)
libgomp_plugin_nvptx_la_LDFLAGS += $(PLUGIN_NVPTX_LDFLAGS)
-libgomp_plugin_nvptx_la_LIBADD = libgomp.la $(PLUGIN_NVPTX_LIBS)
+libgomp_plugin_nvptx_la_LIBADD = libgomp.la
libgomp_plugin_nvptx_la_LIBTOOLFLAGS = --tag=disable-static
+
+# Including the GCC-shipped 'include/cuda/cuda.h' vs. system <cuda.h>.
+if PLUGIN_NVPTX_DYNAMIC
+else
+libgomp_plugin_nvptx_la_CPPFLAGS += -DPLUGIN_NVPTX_INCLUDE_SYSTEM_CUDA_H
+endif
+
+# 'dlopen'ing the CUDA Driver library vs. linking it.
+if PLUGIN_NVPTX_DYNAMIC
+libgomp_plugin_nvptx_la_LIBADD += $(PLUGIN_NVPTX_LIBS)
+else
+libgomp_plugin_nvptx_la_CPPFLAGS += -DPLUGIN_NVPTX_LINK_LIBCUDA
+libgomp_plugin_nvptx_la_LIBADD += $(PLUGIN_NVPTX_LIBS)
+endif
endif
if PLUGIN_GCN
@@ -266,8 +266,7 @@ AC_DEFINE_UNQUOTED(OFFLOAD_PLUGINS, "$offload_plugins",
AM_CONDITIONAL([PLUGIN_NVPTX], [test $PLUGIN_NVPTX = 1])
AC_DEFINE_UNQUOTED([PLUGIN_NVPTX], [$PLUGIN_NVPTX],
[Define to 1 if the NVIDIA plugin is built, 0 if not.])
-AC_DEFINE_UNQUOTED([PLUGIN_NVPTX_DYNAMIC], [$PLUGIN_NVPTX_DYNAMIC],
- [Define to 1 if the NVIDIA plugin should dlopen libcuda.so.1, 0 if it should be linked against it.])
+AM_CONDITIONAL([PLUGIN_NVPTX_DYNAMIC], [test $PLUGIN_NVPTX_DYNAMIC = 1])
AM_CONDITIONAL([PLUGIN_GCN], [test $PLUGIN_GCN = 1])
AC_DEFINE_UNQUOTED([PLUGIN_GCN], [$PLUGIN_GCN],
[Define to 1 if the GCN plugin is built, 0 if not.])
@@ -41,7 +41,7 @@
#include "oacc-int.h"
#include <pthread.h>
-#if PLUGIN_NVPTX_DYNAMIC
+#ifndef PLUGIN_NVPTX_INCLUDE_SYSTEM_CUDA_H
# include "cuda/cuda.h"
#else
# include <cuda.h>
@@ -85,7 +85,7 @@ CUresult cuOccupancyMaxPotentialBlockSize(int *, int *, CUfunction,
#define DO_PRAGMA(x) _Pragma (#x)
-#if PLUGIN_NVPTX_DYNAMIC
+#ifndef PLUGIN_NVPTX_LINK_LIBCUDA
# include <dlfcn.h>
struct cuda_lib_s {
--
2.25.1