Hi! Another ping -- Jakub maybe? This is a simple refactor; no change in behavior. I'll soon post further patches depending on this.
Grüße Thomas On 2022-05-05T21:18:47+0200, I wrote: > Hi! > > Ping. > > > Grüße > Thomas > > > On 2022-04-28T15:45:20+0200, I wrote: >> Hi Tom! >> >> On 2022-04-08T09:35:44+0200, Tom de Vries <tdevr...@suse.de> wrote: >>> On 4/8/22 00:27, Thomas Schwinge wrote: >>>> On 2017-01-13T19:11:23+0100, Jakub Jelinek <ja...@redhat.com> 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 12:07:56.000000000 +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'"? >> >>> we discussed dropping --with-cuda, so do I understand it correctly that >>> you now propose to drop --with-cuda and --with-cuda-driver-lib but >>> intend to keep --with-cuda-driver-include ? >> >> No, I think you're reading too much into this first patch. ;-) >> >> The goal with this patch is just to help disentangle two orthogonal >> concepts (as described in the commit log), and then... >> >>> Can you explain what user or maintainer scenario is served by this? >> >> ... in a next step, we may indeed remove the current user-visible >> '--with-cuda-driver' etc., but keep the underlying functionality >> available for the developers. That's to address the point you'd made in >> the "Proposal to remove '--with-cuda-driver'" thread: that it still >> "could be useful for debugging / comparison purposes" -- and especially >> for development purposes, in my opinion: if you develop CUDA API-level >> changes in the libgomp nvptx plugin, it's likely to be easier to just use >> the full CUDA toolkit 'cuda.h' and directly link against libcuda (so that >> you've got all symbols etc. available), and only once you know what >> exactly you need, update GCC's 'include/cuda/cuda.h' and >> 'libgomp/plugin/cuda-lib.def'. >> >> With that hopefully clarified, OK to push the re-attached >> "libgomp nvptx plugin: Split 'PLUGIN_NVPTX_DYNAMIC' into >> 'PLUGIN_NVPTX_INCLUDE_SYSTEM_CUDA_H' and 'PLUGIN_NVPTX_LINK_LIBCUDA'"? >> >>> Is >>> there a problem with using gcc's cuda.h? >> >> No, all good. >> >> >> 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 72e5a2271348fe167713dd3b2afbcd988274bf7c Mon Sep 17 00:00:00 2001 From: Thomas Schwinge <tho...@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(-) diff --git a/libgomp/Makefile.in b/libgomp/Makefile.in index 1d55f4b65e2..51252b89462 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 <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 = \ @@ -527,7 +537,7 @@ 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. @@ -553,16 +563,18 @@ 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) $(am__append_4) @PLUGIN_NVPTX_TRUE@libgomp_plugin_nvptx_la_LIBTOOLFLAGS = --tag=disable-static # AMD GCN plugin diff --git a/libgomp/config.h.in b/libgomp/config.h.in index 5611ed925ad..d971ea38c46 100644 --- a/libgomp/config.h.in +++ b/libgomp/config.h.in @@ -170,10 +170,6 @@ /* Define to the version of this package. */ #undef PACKAGE_VERSION -/* Define to 1 if the NVIDIA plugin should dlopen libcuda.so.1, 0 if it should - be linked against it. */ -#undef PLUGIN_NVPTX_DYNAMIC - /* Define if all infrastructure, needed for plugins, is supported. */ #undef PLUGIN_SUPPORT diff --git a/libgomp/configure b/libgomp/configure index be675a6b8ab..0df47cf96e3 100755 --- a/libgomp/configure +++ b/libgomp/configure @@ -667,6 +667,8 @@ OPT_LDFLAGS SECTION_LDFLAGS PLUGIN_GCN_FALSE PLUGIN_GCN_TRUE +PLUGIN_NVPTX_DYNAMIC_FALSE +PLUGIN_NVPTX_DYNAMIC_TRUE PLUGIN_NVPTX_FALSE PLUGIN_NVPTX_TRUE offload_additional_lib_paths @@ -11412,7 +11414,7 @@ else lt_dlunknown=0; lt_dlno_uscore=1; lt_dlneed_uscore=2 lt_status=$lt_dlunknown cat > conftest.$ac_ext <<_LT_EOF -#line 11415 "configure" +#line 11417 "configure" #include "confdefs.h" #if HAVE_DLFCN_H @@ -11518,7 +11520,7 @@ else lt_dlunknown=0; lt_dlno_uscore=1; lt_dlneed_uscore=2 lt_status=$lt_dlunknown cat > conftest.$ac_ext <<_LT_EOF -#line 11521 "configure" +#line 11523 "configure" #include "confdefs.h" #if HAVE_DLFCN_H @@ -15368,10 +15370,13 @@ else PLUGIN_NVPTX_FALSE= fi - -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 $PLUGIN_GCN = 1; then PLUGIN_GCN_TRUE= @@ -17140,6 +17145,10 @@ if test -z "${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 diff --git a/libgomp/plugin/Makefrag.am b/libgomp/plugin/Makefrag.am index 11929d4ff29..3eeb3419f9c 100644 --- a/libgomp/plugin/Makefrag.am +++ b/libgomp/plugin/Makefrag.am @@ -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 += $(PLUGIN_NVPTX_LIBS) +endif endif if PLUGIN_GCN diff --git a/libgomp/plugin/configfrag.ac b/libgomp/plugin/configfrag.ac index 1a61db94381..c16224104e3 100644 --- a/libgomp/plugin/configfrag.ac +++ b/libgomp/plugin/configfrag.ac @@ -219,6 +219,5 @@ fi AC_DEFINE_UNQUOTED(OFFLOAD_PLUGINS, "$offload_plugins", [Define to offload plugins, separated by commas.]) AM_CONDITIONAL([PLUGIN_NVPTX], [test $PLUGIN_NVPTX = 1]) -AC_DEFINE_UNQUOTED([PLUGIN_NVPTX_DYNAMIC], [$PLUGIN_NVPTX_DYNAMIC], - [Define to 1 if the NVIDIA plugin should dlopen libcuda.so.1, 0 if it should be linked against it.]) +AM_CONDITIONAL([PLUGIN_NVPTX_DYNAMIC], [test $PLUGIN_NVPTX_DYNAMIC = 1]) AM_CONDITIONAL([PLUGIN_GCN], [test $PLUGIN_GCN = 1]) diff --git a/libgomp/plugin/plugin-nvptx.c b/libgomp/plugin/plugin-nvptx.c index b28dfca00fa..387bcbbc52a 100644 --- a/libgomp/plugin/plugin-nvptx.c +++ b/libgomp/plugin/plugin-nvptx.c @@ -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 { -- 2.35.1