[nvptx libgomp plugin] Build only in supported configurations

As recently again discussed in <https://gcc.gnu.org/PR97436> "[nvptx] -m32
support", nvptx offloading other than for 64-bit host has never been
implemented, tested, supported.  So we simply should buildn't the nvptx libgomp
plugin in this case.

This avoids build problems if, for example, in a (standard) bi-arch
x86_64-pc-linux-gnu '-m64'/'-m32' build, libcuda is available only in a 64-bit
variant but not in a 32-bit one, which, for example, is the case if you build
GCC against the CUDA toolkit's 'stubs/libcuda.so' (see
<https://stackoverflow.com/a/52784819>).

This amends PR65099 commit a92defdab79a1268f4b9dcf42b937e4002a4cf15 (r225560)
"[nvptx offloading] Only 64-bit configurations are currently supported" to
match the way we're doing this for the HSA/GCN plugins.

	libgomp/
	PR libgomp/65099
	* plugin/configfrag.ac (PLUGIN_NVPTX): Restrict to supported
	configurations.
	* configure: Regenerate.
	* plugin/plugin-nvptx.c (nvptx_get_num_devices): Remove 64-bit
	check.

3 files changed, 105 insertions, 82 deletions

diff --git a/libgomp/configure b/libgomp/configure
index 89c17c5..48bf8e4 100755
--- a/libgomp/configure
+++ b/libgomp/configure
@@ -15272,21 +15272,30 @@ if test x"$enable_offload_targets" != x; then
 	tgt_plugin=intelmic
 	;;
       nvptx*)
-	tgt_plugin=nvptx
-	PLUGIN_NVPTX=$tgt
-	if test "x$CUDA_DRIVER_LIB" != xno \
-	   && test "x$CUDA_DRIVER_LIB" != xno; then
-	  PLUGIN_NVPTX_CPPFLAGS=$CUDA_DRIVER_CPPFLAGS
-	  PLUGIN_NVPTX_LDFLAGS=$CUDA_DRIVER_LDFLAGS
-	  PLUGIN_NVPTX_LIBS='-lcuda'
-
-	  PLUGIN_NVPTX_save_CPPFLAGS=$CPPFLAGS
-	  CPPFLAGS="$PLUGIN_NVPTX_CPPFLAGS $CPPFLAGS"
-	  PLUGIN_NVPTX_save_LDFLAGS=$LDFLAGS
-	  LDFLAGS="$PLUGIN_NVPTX_LDFLAGS $LDFLAGS"
-	  PLUGIN_NVPTX_save_LIBS=$LIBS
-	  LIBS="$PLUGIN_NVPTX_LIBS $LIBS"
-	  cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+	case "${target}" in
+	  aarch64*-*-* | powerpc64le-*-* | x86_64-*-*)
+	    case " ${CC} ${CFLAGS} " in
+	      *" -m32 "* | *" -mx32 "*)
+		# PR libgomp/65099: Currently, we only support offloading in
+		# 64-bit configurations.
+		PLUGIN_NVPTX=0
+		;;
+	      *)
+		tgt_plugin=nvptx
+		PLUGIN_NVPTX=$tgt
+		if test "x$CUDA_DRIVER_LIB" != xno \
+		   && test "x$CUDA_DRIVER_LIB" != xno; then
+		  PLUGIN_NVPTX_CPPFLAGS=$CUDA_DRIVER_CPPFLAGS
+		  PLUGIN_NVPTX_LDFLAGS=$CUDA_DRIVER_LDFLAGS
+		  PLUGIN_NVPTX_LIBS='-lcuda'
+
+		  PLUGIN_NVPTX_save_CPPFLAGS=$CPPFLAGS
+		  CPPFLAGS="$PLUGIN_NVPTX_CPPFLAGS $CPPFLAGS"
+		  PLUGIN_NVPTX_save_LDFLAGS=$LDFLAGS
+		  LDFLAGS="$PLUGIN_NVPTX_LDFLAGS $LDFLAGS"
+		  PLUGIN_NVPTX_save_LIBS=$LIBS
+		  LIBS="$PLUGIN_NVPTX_LIBS $LIBS"
+		  cat confdefs.h - <<_ACEOF >conftest.$ac_ext
 /* end confdefs.h.  */
 #include "cuda.h"
 int
@@ -15302,28 +15311,35 @@ if ac_fn_c_try_link "$LINENO"; then :
 fi
 rm -f core conftest.err conftest.$ac_objext \
     conftest$ac_exeext conftest.$ac_ext
-	  CPPFLAGS=$PLUGIN_NVPTX_save_CPPFLAGS
-	  LDFLAGS=$PLUGIN_NVPTX_save_LDFLAGS
-	  LIBS=$PLUGIN_NVPTX_save_LIBS
-	fi
-	case $PLUGIN_NVPTX in
-	  nvptx*)
-	    if (test "x$CUDA_DRIVER_INCLUDE" = x \
-		|| test "x$CUDA_DRIVER_INCLUDE" = xno) \
-	       && (test "x$CUDA_DRIVER_LIB" = x \
-		   || test "x$CUDA_DRIVER_LIB" = xno); then
-	      PLUGIN_NVPTX=1
-	      PLUGIN_NVPTX_CPPFLAGS='-I$(srcdir)/plugin/cuda'
-	      PLUGIN_NVPTX_LIBS='-ldl'
-	      PLUGIN_NVPTX_DYNAMIC=1
-	    else
-	      PLUGIN_NVPTX=0
-	      as_fn_error $? "CUDA driver package required for nvptx support" "$LINENO" 5
-	    fi
-	  ;;
+		  CPPFLAGS=$PLUGIN_NVPTX_save_CPPFLAGS
+		  LDFLAGS=$PLUGIN_NVPTX_save_LDFLAGS
+		  LIBS=$PLUGIN_NVPTX_save_LIBS
+		fi
+		case $PLUGIN_NVPTX in
+		  nvptx*)
+		    if (test "x$CUDA_DRIVER_INCLUDE" = x \
+			|| test "x$CUDA_DRIVER_INCLUDE" = xno) \
+		       && (test "x$CUDA_DRIVER_LIB" = x \
+			   || test "x$CUDA_DRIVER_LIB" = xno); then
+		      PLUGIN_NVPTX=1
+		      PLUGIN_NVPTX_CPPFLAGS='-I$(srcdir)/plugin/cuda'
+		      PLUGIN_NVPTX_LIBS='-ldl'
+		      PLUGIN_NVPTX_DYNAMIC=1
+		    else
+		      PLUGIN_NVPTX=0
+		      as_fn_error $? "CUDA driver package required for nvptx support" "$LINENO" 5
+		    fi
+		    ;;
+		esac
+		;;
+	    esac
+	    ;;
+	  *-*-*)
+	    # Target architecture not supported.
+	    PLUGIN_NVPTX=0
+	    ;;
 	esac
 	;;
-
       amdgcn*)
 	case "${target}" in
 	  x86_64-*-*)
diff --git a/libgomp/plugin/configfrag.ac b/libgomp/plugin/configfrag.ac
index 2e086c0..8855098 100644
--- a/libgomp/plugin/configfrag.ac
+++ b/libgomp/plugin/configfrag.ac
@@ -158,47 +158,63 @@ if test x"$enable_offload_targets" != x; then
 	tgt_plugin=intelmic
 	;;
       nvptx*)
-	tgt_plugin=nvptx
-	PLUGIN_NVPTX=$tgt
-	if test "x$CUDA_DRIVER_LIB" != xno \
-	   && test "x$CUDA_DRIVER_LIB" != xno; then
-	  PLUGIN_NVPTX_CPPFLAGS=$CUDA_DRIVER_CPPFLAGS
-	  PLUGIN_NVPTX_LDFLAGS=$CUDA_DRIVER_LDFLAGS
-	  PLUGIN_NVPTX_LIBS='-lcuda'
+	case "${target}" in
+	  aarch64*-*-* | powerpc64le-*-* | x86_64-*-*)
+	    case " ${CC} ${CFLAGS} " in
+	      *" -m32 "* | *" -mx32 "*)
+		# PR libgomp/65099: Currently, we only support offloading in
+		# 64-bit configurations.
+		PLUGIN_NVPTX=0
+		;;
+	      *)
+		tgt_plugin=nvptx
+		PLUGIN_NVPTX=$tgt
+		if test "x$CUDA_DRIVER_LIB" != xno \
+		   && test "x$CUDA_DRIVER_LIB" != xno; then
+		  PLUGIN_NVPTX_CPPFLAGS=$CUDA_DRIVER_CPPFLAGS
+		  PLUGIN_NVPTX_LDFLAGS=$CUDA_DRIVER_LDFLAGS
+		  PLUGIN_NVPTX_LIBS='-lcuda'
 
-	  PLUGIN_NVPTX_save_CPPFLAGS=$CPPFLAGS
-	  CPPFLAGS="$PLUGIN_NVPTX_CPPFLAGS $CPPFLAGS"
-	  PLUGIN_NVPTX_save_LDFLAGS=$LDFLAGS
-	  LDFLAGS="$PLUGIN_NVPTX_LDFLAGS $LDFLAGS"
-	  PLUGIN_NVPTX_save_LIBS=$LIBS
-	  LIBS="$PLUGIN_NVPTX_LIBS $LIBS"
-	  AC_LINK_IFELSE(
-	    [AC_LANG_PROGRAM(
-	      [#include "cuda.h"],
-		[CUresult r = cuCtxPushCurrent (NULL);])],
-	    [PLUGIN_NVPTX=1])
-	  CPPFLAGS=$PLUGIN_NVPTX_save_CPPFLAGS
-	  LDFLAGS=$PLUGIN_NVPTX_save_LDFLAGS
-	  LIBS=$PLUGIN_NVPTX_save_LIBS
-	fi
-	case $PLUGIN_NVPTX in
-	  nvptx*)
-	    if (test "x$CUDA_DRIVER_INCLUDE" = x \
-		|| test "x$CUDA_DRIVER_INCLUDE" = xno) \
-	       && (test "x$CUDA_DRIVER_LIB" = x \
-		   || test "x$CUDA_DRIVER_LIB" = xno); then
-	      PLUGIN_NVPTX=1
-	      PLUGIN_NVPTX_CPPFLAGS='-I$(srcdir)/plugin/cuda'
-	      PLUGIN_NVPTX_LIBS='-ldl'
-	      PLUGIN_NVPTX_DYNAMIC=1
-	    else
-	      PLUGIN_NVPTX=0
-	      AC_MSG_ERROR([CUDA driver package required for nvptx support])
-	    fi
-	  ;;
+		  PLUGIN_NVPTX_save_CPPFLAGS=$CPPFLAGS
+		  CPPFLAGS="$PLUGIN_NVPTX_CPPFLAGS $CPPFLAGS"
+		  PLUGIN_NVPTX_save_LDFLAGS=$LDFLAGS
+		  LDFLAGS="$PLUGIN_NVPTX_LDFLAGS $LDFLAGS"
+		  PLUGIN_NVPTX_save_LIBS=$LIBS
+		  LIBS="$PLUGIN_NVPTX_LIBS $LIBS"
+		  AC_LINK_IFELSE(
+		    [AC_LANG_PROGRAM(
+		      [#include "cuda.h"],
+			[CUresult r = cuCtxPushCurrent (NULL);])],
+		    [PLUGIN_NVPTX=1])
+		  CPPFLAGS=$PLUGIN_NVPTX_save_CPPFLAGS
+		  LDFLAGS=$PLUGIN_NVPTX_save_LDFLAGS
+		  LIBS=$PLUGIN_NVPTX_save_LIBS
+		fi
+		case $PLUGIN_NVPTX in
+		  nvptx*)
+		    if (test "x$CUDA_DRIVER_INCLUDE" = x \
+			|| test "x$CUDA_DRIVER_INCLUDE" = xno) \
+		       && (test "x$CUDA_DRIVER_LIB" = x \
+			   || test "x$CUDA_DRIVER_LIB" = xno); then
+		      PLUGIN_NVPTX=1
+		      PLUGIN_NVPTX_CPPFLAGS='-I$(srcdir)/plugin/cuda'
+		      PLUGIN_NVPTX_LIBS='-ldl'
+		      PLUGIN_NVPTX_DYNAMIC=1
+		    else
+		      PLUGIN_NVPTX=0
+		      AC_MSG_ERROR([CUDA driver package required for nvptx support])
+		    fi
+		    ;;
+		esac
+		;;
+	    esac
+	    ;;
+	  *-*-*)
+	    # Target architecture not supported.
+	    PLUGIN_NVPTX=0
+	    ;;
 	esac
 	;;
-
       amdgcn*)
 	case "${target}" in
 	  x86_64-*-*)
diff --git a/libgomp/plugin/plugin-nvptx.c b/libgomp/plugin/plugin-nvptx.c
index 681c344..1215212 100644
--- a/libgomp/plugin/plugin-nvptx.c
+++ b/libgomp/plugin/plugin-nvptx.c
@@ -572,15 +572,6 @@ nvptx_get_num_devices (void)
 {
   int n;
 
-  /* PR libgomp/65099: Currently, we only support offloading in 64-bit
-     configurations.  */
-  if (sizeof (void *) != 8)
-    {
-      GOMP_PLUGIN_debug (0, "Disabling nvptx offloading;"
-			 " only 64-bit configurations are supported\n");
-      return 0;
-    }
-
   /* This function will be called before the plugin has been initialized in
      order to enumerate available devices, but CUDA API routines can't be used
      until cuInit has been called.  Just call it now (but don't yet do any