diff options
| -rwxr-xr-x | libgomp/configure | 86 | ||||
| -rw-r--r-- | libgomp/plugin/configfrag.ac | 92 | ||||
| -rw-r--r-- | libgomp/plugin/plugin-nvptx.c | 9 |
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 |