Hi!
On 2017-01-13T19:11:23+0100, Jakub Jelinek wrote:
> Especially for distributions it is undesirable to need to have proprietary
> CUDA libraries and headers installed when building GCC.
> --- libgomp/plugin/configfrag.ac.jj 2017-01-13 12:07:56.0 +0100
> +++ libgomp/plugin/configfrag.ac 2017-01-13 17:33:26.608240936 +0100
> + PLUGIN_NVPTX_CPPFLAGS='-I$(srcdir)/plugin/cuda'
> + PLUGIN_NVPTX_LIBS='-ldl'
> + PLUGIN_NVPTX_DYNAMIC=1
> +AC_DEFINE_UNQUOTED([PLUGIN_NVPTX_DYNAMIC], [$PLUGIN_NVPTX_DYNAMIC],
> + [Define to 1 if the NVIDIA plugin should dlopen libcuda.so.1, 0 if it
> should be linked against it.])
Actually, the conditionals leading to 'PLUGIN_NVPTX_DYNAMIC=1' here do
control two orthogonal aspects; OK to disentangle that with the attached
"libgomp nvptx plugin: Split 'PLUGIN_NVPTX_DYNAMIC' into
'PLUGIN_NVPTX_INCLUDE_SYSTEM_CUDA_H' and 'PLUGIN_NVPTX_LINK_LIBCUDA'"?
Grüße
Thomas
-
Siemens Electronic Design Automation GmbH; Anschrift: Arnulfstraße 201, 80634
München; Gesellschaft mit beschränkter Haftung; Geschäftsführer: Thomas
Heurung, Frank Thürauf; Sitz der Gesellschaft: München; Registergericht
München, HRB 106955
>From c455522ac5d8ab41e5d11f8997678e042ff48e87 Mon Sep 17 00:00:00 2001
From: Thomas Schwinge
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 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(-)
diff --git a/libgomp/Makefile.in b/libgomp/Makefile.in
index 22cb2136a08..d43c584a32d 100644
--- a/libgomp/Makefile.in
+++ b/libgomp/Makefile.in
@@ -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 .
+@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.
