configfrag.ac: For --without-cuda-driver don't initialize CUDA_DRIVER_INCLUDE nor CUDA_DRIVER_LIB.

	* plugin/configfrag.ac: For --without-cuda-driver don't initialize
	CUDA_DRIVER_INCLUDE nor CUDA_DRIVER_LIB.  If both
	CUDA_DRIVER_INCLUDE and CUDA_DRIVER_LIB are empty and linking small
	cuda program fails, define PLUGIN_NVPTX_DYNAMIC to 1 and use
	plugin/include/cuda as include dir and -ldl instead of -lcuda as
	library to link ptx plugin against.
	* plugin/plugin-nvptx.c: Include dlfcn.h if PLUGIN_NVPTX_DYNAMIC.
	(CUDA_CALLS): Define.
	(cuda_lib, cuda_lib_inited): New variables.
	(init_cuda_lib): New function.
	(CUDA_CALL_PREFIX): Define.
	(CUDA_CALL_ERET, CUDA_CALL_ASSERT): Use CUDA_CALL_PREFIX.
	(CUDA_CALL): Use FN instead of (FN).
	(CUDA_CALL_NOCHECK): Define.
	(cuda_error, fini_streams_for_device, select_stream_for_async,
	nvptx_attach_host_thread_to_device, nvptx_open_device, link_ptx,
	event_gc, nvptx_exec, nvptx_async_test, nvptx_async_test_all,
	nvptx_wait_all, nvptx_set_clocktick, GOMP_OFFLOAD_unload_image,
	nvptx_stacks_alloc, nvptx_stacks_free, GOMP_OFFLOAD_run): Use
	CUDA_CALL_NOCHECK.
	(nvptx_init): Call init_cuda_lib, if it fails, return false.  Use
	CUDA_CALL_NOCHECK.
	(nvptx_get_num_devices): Call init_cuda_lib, if it fails, return 0.
	Use CUDA_CALL_NOCHECK.
	* plugin/cuda/cuda.h: New file.
	* config.h.in: Regenerated.
	* configure: Regenerated.

From-SVN: r244522

libgomp/ChangeLog

 2017-01-17  Jakub Jelinek  <jakub@redhat.com>
 
+	* plugin/configfrag.ac: For --without-cuda-driver don't initialize
+	CUDA_DRIVER_INCLUDE nor CUDA_DRIVER_LIB.  If both
+	CUDA_DRIVER_INCLUDE and CUDA_DRIVER_LIB are empty and linking small
+	cuda program fails, define PLUGIN_NVPTX_DYNAMIC to 1 and use
+	plugin/include/cuda as include dir and -ldl instead of -lcuda as
+	library to link ptx plugin against.
+	* plugin/plugin-nvptx.c: Include dlfcn.h if PLUGIN_NVPTX_DYNAMIC.
+	(CUDA_CALLS): Define.
+	(cuda_lib, cuda_lib_inited): New variables.
+	(init_cuda_lib): New function.
+	(CUDA_CALL_PREFIX): Define.
+	(CUDA_CALL_ERET, CUDA_CALL_ASSERT): Use CUDA_CALL_PREFIX.
+	(CUDA_CALL): Use FN instead of (FN).
+	(CUDA_CALL_NOCHECK): Define.
+	(cuda_error, fini_streams_for_device, select_stream_for_async,
+	nvptx_attach_host_thread_to_device, nvptx_open_device, link_ptx,
+	event_gc, nvptx_exec, nvptx_async_test, nvptx_async_test_all,
+	nvptx_wait_all, nvptx_set_clocktick, GOMP_OFFLOAD_unload_image,
+	nvptx_stacks_alloc, nvptx_stacks_free, GOMP_OFFLOAD_run): Use
+	CUDA_CALL_NOCHECK.
+	(nvptx_init): Call init_cuda_lib, if it fails, return false.  Use
+	CUDA_CALL_NOCHECK.
+	(nvptx_get_num_devices): Call init_cuda_lib, if it fails, return 0.
+	Use CUDA_CALL_NOCHECK.
+	* plugin/cuda/cuda.h: New file.
+	* config.h.in: Regenerated.
+	* configure: Regenerated.
+
 	PR other/79046
 	* configure.ac: Add GCC_BASE_VER.
 	* Makefile.am (gcc_version): Use @get_gcc_base_ver@ instead of cat to

libgomp/config.h.in

@@ -155,6 +155,10 @@
 /* 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
 

libgomp/configure

@@ -15299,10 +15299,12 @@ if test "${with_cuda_driver_lib+set}" = set; then :
   withval=$with_cuda_driver_lib;
 fi
 
-if test "x$with_cuda_driver" != x; then
-  CUDA_DRIVER_INCLUDE=$with_cuda_driver/include
-  CUDA_DRIVER_LIB=$with_cuda_driver/lib
-fi
+case "x$with_cuda_driver" in
+  x | xno) ;;
+  *) CUDA_DRIVER_INCLUDE=$with_cuda_driver/include
+     CUDA_DRIVER_LIB=$with_cuda_driver/lib
+     ;;
+esac
 if test "x$with_cuda_driver_include" != x; then
   CUDA_DRIVER_INCLUDE=$with_cuda_driver_include
 fi
@@ -15320,6 +15322,7 @@ PLUGIN_NVPTX=0
 PLUGIN_NVPTX_CPPFLAGS=
 PLUGIN_NVPTX_LDFLAGS=
 PLUGIN_NVPTX_LIBS=
+PLUGIN_NVPTX_DYNAMIC=0
 
 
 
@@ -15426,9 +15429,17 @@ rm -f core conftest.err conftest.$ac_objext \
 	LIBS=$PLUGIN_NVPTX_save_LIBS
 	case $PLUGIN_NVPTX in
 	  nvptx*)
-	    PLUGIN_NVPTX=0
-	    as_fn_error "CUDA driver package required for nvptx support" "$LINENO" 5
-	    ;;
+	    if test "x$CUDA_DRIVER_INCLUDE" = x \
+	       && test "x$CUDA_DRIVER_LIB" = x; 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
 	;;
       hsa*)
@@ -15513,6 +15524,11 @@ 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_HSA = 1; then
   PLUGIN_HSA_TRUE=
   PLUGIN_HSA_FALSE='#'

libgomp/plugin/configfrag.ac

@@ -58,10 +58,12 @@ AC_ARG_WITH(cuda-driver-include,
 AC_ARG_WITH(cuda-driver-lib,
 	[AS_HELP_STRING([--with-cuda-driver-lib=PATH],
 		[specify directory for the installed CUDA driver library])])
-if test "x$with_cuda_driver" != x; then
-  CUDA_DRIVER_INCLUDE=$with_cuda_driver/include
-  CUDA_DRIVER_LIB=$with_cuda_driver/lib
-fi
+case "x$with_cuda_driver" in
+  x | xno) ;;
+  *) CUDA_DRIVER_INCLUDE=$with_cuda_driver/include
+     CUDA_DRIVER_LIB=$with_cuda_driver/lib
+     ;;
+esac
 if test "x$with_cuda_driver_include" != x; then
   CUDA_DRIVER_INCLUDE=$with_cuda_driver_include
 fi
@@ -79,6 +81,7 @@ PLUGIN_NVPTX=0
 PLUGIN_NVPTX_CPPFLAGS=
 PLUGIN_NVPTX_LDFLAGS=
 PLUGIN_NVPTX_LIBS=
+PLUGIN_NVPTX_DYNAMIC=0
 AC_SUBST(PLUGIN_NVPTX)
 AC_SUBST(PLUGIN_NVPTX_CPPFLAGS)
 AC_SUBST(PLUGIN_NVPTX_LDFLAGS)
@@ -167,9 +170,17 @@ if test x"$enable_offload_targets" != x; then
 	LIBS=$PLUGIN_NVPTX_save_LIBS
 	case $PLUGIN_NVPTX in
 	  nvptx*)
-	    PLUGIN_NVPTX=0
-	    AC_MSG_ERROR([CUDA driver package required for nvptx support])
-	    ;;
+	    if test "x$CUDA_DRIVER_INCLUDE" = x \
+	       && test "x$CUDA_DRIVER_LIB" = x; then
+	      PLUGIN_NVPTX=1
+	      PLUGIN_NVPTX_CPPFLAGS='-I$(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
 	;;
       hsa*)
@@ -241,6 +252,8 @@ AC_DEFINE_UNQUOTED(OFFLOAD_TARGETS, "$offload_targets",
 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_HSA], [test $PLUGIN_HSA = 1])
 AC_DEFINE_UNQUOTED([PLUGIN_HSA], [$PLUGIN_HSA],
   [Define to 1 if the HSA plugin is built, 0 if not.])

libgomp/plugin/cuda/cuda.h

+/* CUDA API description.
+   Copyright (C) 2017 Free Software Foundation, Inc.
+
+This file is part of GCC.
+
+GCC is free software; you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation; either version 3, or (at your option)
+any later version.
+
+GCC is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+Under Section 7 of GPL version 3, you are granted additional
+permissions described in the GCC Runtime Library Exception, version
+3.1, as published by the Free Software Foundation.
+
+You should have received a copy of the GNU General Public License and
+a copy of the GCC Runtime Library Exception along with this program;
+see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
+<http://www.gnu.org/licenses/>.
+
+This header provides the minimum amount of typedefs, enums and function
+declarations to be able to compile plugin-nvptx.c if cuda.h and
+libcuda.so.1 are not available.  */
+
+#ifndef GCC_CUDA_H
+#define GCC_CUDA_H
+
+#include <stdlib.h>
+
+#define CUDA_VERSION 8000
+
+typedef void *CUcontext;
+typedef int CUdevice;
+#ifdef __LP64__
+typedef unsigned long long CUdeviceptr;
+#else
+typedef unsigned CUdeviceptr;
+#endif
+typedef void *CUevent;
+typedef void *CUfunction;
+typedef void *CUlinkState;
+typedef void *CUmodule;
+typedef void *CUstream;
+
+typedef enum {
+  CUDA_SUCCESS = 0,
+  CUDA_ERROR_INVALID_VALUE = 1,
+  CUDA_ERROR_OUT_OF_MEMORY = 2,
+  CUDA_ERROR_INVALID_CONTEXT = 201,
+  CUDA_ERROR_NOT_FOUND = 500,
+  CUDA_ERROR_NOT_READY = 600,
+  CUDA_ERROR_LAUNCH_FAILED = 719
+} CUresult;
+
+typedef enum {
+  CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK = 1,
+  CU_DEVICE_ATTRIBUTE_WARP_SIZE = 10,
+  CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK = 12,
+  CU_DEVICE_ATTRIBUTE_CLOCK_RATE = 13,
+  CU_DEVICE_ATTRIBUTE_GPU_OVERLAP = 15,
+  CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT = 16,
+  CU_DEVICE_ATTRIBUTE_INTEGRATED = 18,
+  CU_DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY = 19,
+  CU_DEVICE_ATTRIBUTE_COMPUTE_MODE = 20,
+  CU_DEVICE_ATTRIBUTE_CONCURRENT_KERNELS = 31,
+  CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR = 39,
+  CU_DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT = 40,
+  CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR = 82
+} CUdevice_attribute;
+
+enum {
+  CU_EVENT_DEFAULT = 0,
+  CU_EVENT_DISABLE_TIMING = 2
+};
+
+typedef enum {
+  CU_FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK = 0,
+  CU_FUNC_ATTRIBUTE_NUM_REGS = 4
+} CUfunction_attribute;
+
+typedef enum {
+  CU_JIT_WALL_TIME = 2,
+  CU_JIT_INFO_LOG_BUFFER = 3,
+  CU_JIT_INFO_LOG_BUFFER_SIZE_BYTES = 4,
+  CU_JIT_ERROR_LOG_BUFFER = 5,
+  CU_JIT_ERROR_LOG_BUFFER_SIZE_BYTES = 6,
+  CU_JIT_LOG_VERBOSE = 12
+} CUjit_option;
+
+typedef enum {
+  CU_JIT_INPUT_PTX = 1
+} CUjitInputType;
+
+enum {
+  CU_CTX_SCHED_AUTO = 0
+};
+
+#define CU_LAUNCH_PARAM_END ((void *) 0)
+#define CU_LAUNCH_PARAM_BUFFER_POINTER ((void *) 1)
+#define CU_LAUNCH_PARAM_BUFFER_SIZE ((void *) 2)
+
+enum {
+  CU_STREAM_DEFAULT = 0,
+  CU_STREAM_NON_BLOCKING = 1
+};
+
+#define cuCtxCreate cuCtxCreate_v2
+CUresult cuCtxCreate (CUcontext *, unsigned, CUdevice);
+#define cuCtxDestroy cuCtxDestroy_v2
+CUresult cuCtxDestroy (CUcontext);
+CUresult cuCtxGetCurrent (CUcontext *);
+CUresult cuCtxGetDevice (CUdevice *);
+#define cuCtxPopCurrent cuCtxPopCurrent_v2
+CUresult cuCtxPopCurrent (CUcontext *);
+#define cuCtxPushCurrent cuCtxPushCurrent_v2
+CUresult cuCtxPushCurrent (CUcontext);
+CUresult cuCtxSynchronize (void);
+CUresult cuDeviceGet (CUdevice *, int);
+CUresult cuDeviceGetAttribute (int *, CUdevice_attribute, CUdevice);
+CUresult cuDeviceGetCount (int *);
+CUresult cuEventCreate (CUevent *, unsigned);
+#define cuEventDestroy cuEventDestroy_v2
+CUresult cuEventDestroy (CUevent);
+CUresult cuEventElapsedTime (float *, CUevent, CUevent);
+CUresult cuEventQuery (CUevent);
+CUresult cuEventRecord (CUevent, CUstream);
+CUresult cuEventSynchronize (CUevent);
+CUresult cuFuncGetAttribute (int *, CUfunction_attribute, CUfunction);
+CUresult cuGetErrorString (CUresult, const char **);
+CUresult cuInit (unsigned);
+CUresult cuLaunchKernel (CUfunction, unsigned, unsigned, unsigned, unsigned,
+			 unsigned, unsigned, unsigned, CUstream, void **, void **);
+#define cuLinkAddData cuLinkAddData_v2
+CUresult cuLinkAddData (CUlinkState, CUjitInputType, void *, size_t, const char *,
+			unsigned, CUjit_option *, void **);
+CUresult cuLinkComplete (CUlinkState, void **, size_t *);
+#define cuLinkCreate cuLinkCreate_v2
+CUresult cuLinkCreate (unsigned, CUjit_option *, void **, CUlinkState *);
+CUresult cuLinkDestroy (CUlinkState);
+#define cuMemAlloc cuMemAlloc_v2
+CUresult cuMemAlloc (CUdeviceptr *, size_t);
+#define cuMemAllocHost cuMemAllocHost_v2
+CUresult cuMemAllocHost (void **, size_t);
+CUresult cuMemcpy (CUdeviceptr, CUdeviceptr, size_t);
+#define cuMemcpyDtoDAsync cuMemcpyDtoDAsync_v2
+CUresult cuMemcpyDtoDAsync (CUdeviceptr, CUdeviceptr, size_t, CUstream);
+#define cuMemcpyDtoH cuMemcpyDtoH_v2
+CUresult cuMemcpyDtoH (void *, CUdeviceptr, size_t);
+#define cuMemcpyDtoHAsync cuMemcpyDtoHAsync_v2
+CUresult cuMemcpyDtoHAsync (void *, CUdeviceptr, size_t, CUstream);
+#define cuMemcpyHtoD cuMemcpyHtoD_v2
+CUresult cuMemcpyHtoD (CUdeviceptr, const void *, size_t);
+#define cuMemcpyHtoDAsync cuMemcpyHtoDAsync_v2
+CUresult cuMemcpyHtoDAsync (CUdeviceptr, const void *, size_t, CUstream);
+#define cuMemFree cuMemFree_v2
+CUresult cuMemFree (CUdeviceptr);
+CUresult cuMemFreeHost (void *);
+#define cuMemGetAddressRange cuMemGetAddressRange_v2
+CUresult cuMemGetAddressRange (CUdeviceptr *, size_t *, CUdeviceptr);
+#define cuMemHostGetDevicePointer cuMemHostGetDevicePointer_v2
+CUresult cuMemHostGetDevicePointer (CUdeviceptr *, void *, unsigned);
+CUresult cuModuleGetFunction (CUfunction *, CUmodule, const char *);
+#define cuModuleGetGlobal cuModuleGetGlobal_v2
+CUresult cuModuleGetGlobal (CUdeviceptr *, size_t *, CUmodule, const char *);
+CUresult cuModuleLoad (CUmodule *, const char *);
+CUresult cuModuleLoadData (CUmodule *, const void *);
+CUresult cuModuleUnload (CUmodule);
+CUresult cuStreamCreate (CUstream *, unsigned);
+#define cuStreamDestroy cuStreamDestroy_v2
+CUresult cuStreamDestroy (CUstream);
+CUresult cuStreamQuery (CUstream);
+CUresult cuStreamSynchronize (CUstream);
+CUresult cuStreamWaitEvent (CUstream, CUevent, unsigned);
+
+#endif /* GCC_CUDA_H */