OpenMP offloading to NVPTX: libgomp changes

	* Makefile.am (libgomp_la_SOURCES): Add atomic.c, icv.c, icv-device.c.
	* Makefile.in. Regenerate.
	* configure.ac [nvptx*-*-*] (libgomp_use_pthreads): Set and use it...
	(LIBGOMP_USE_PTHREADS): ...here; new define.
	* configure: Regenerate.
	* config.h.in: Likewise.
	* config/posix/affinity.c: Move to...
	* affinity.c: ...here (new file).  Guard use of Pthreads-specific
	interface by LIBGOMP_USE_PTHREADS. 
	* critical.c: Split out GOMP_atomic_{start,end} into...
	* atomic.c: ...here (new file).
	* env.c: Split out ICV definitions into...
	* icv.c: ...here (new file) and...
	* icv-device.c: ...here. New file.
	* config/linux/lock.c (gomp_init_lock_30): Move to generic lock.c.
	(gomp_destroy_lock_30): Ditto.
	(gomp_set_lock_30): Ditto.
	(gomp_unset_lock_30): Ditto.
	(gomp_test_lock_30): Ditto.
	(gomp_init_nest_lock_30): Ditto.
	(gomp_destroy_nest_lock_30): Ditto.
	(gomp_set_nest_lock_30): Ditto.
	(gomp_unset_nest_lock_30): Ditto.
	(gomp_test_nest_lock_30): Ditto.
	* lock.c: New.
	* config/nvptx/lock.c: New.
	* config/nvptx/bar.c: New.
	* config/nvptx/bar.h: New.
	* config/nvptx/doacross.h: New.
	* config/nvptx/error.c: New.
	* config/nvptx/icv-device.c: New.
	* config/nvptx/mutex.h: New.
	* config/nvptx/pool.h: New.
	* config/nvptx/proc.c: New.
	* config/nvptx/ptrlock.h: New.
	* config/nvptx/sem.h: New.
	* config/nvptx/simple-bar.h: New.
	* config/nvptx/target.c: New.
	* config/nvptx/task.c: New.
	* config/nvptx/team.c: New.
	* config/nvptx/time.c: New.
	* config/posix/simple-bar.h: New.
	* libgomp.h: Guard pthread.h inclusion.  Include simple-bar.h.
	(gomp_num_teams_var): Declare.
	(struct gomp_thread_pool): Change threads_dock member to
	gomp_simple_barrier_t.
	[__nvptx__] (gomp_thread): New implementation.
	(gomp_thread_attr): Guard by LIBGOMP_USE_PTHREADS.
	(gomp_thread_destructor): Ditto.
	(gomp_init_thread_affinity): Ditto.
	* team.c: Guard uses of Pthreads-specific interfaces by
	LIBGOMP_USE_PTHREADS.  Adjust all uses of threads_dock.
	(gomp_free_thread) [__nvptx__]: Do not call 'free'.

	* config/nvptx/alloc.c: Delete.
	* config/nvptx/barrier.c: Ditto.
	* config/nvptx/fortran.c: Ditto.
	* config/nvptx/iter.c: Ditto.
	* config/nvptx/iter_ull.c: Ditto.
	* config/nvptx/loop.c: Ditto.
	* config/nvptx/loop_ull.c: Ditto.
	* config/nvptx/ordered.c: Ditto.
	* config/nvptx/parallel.c: Ditto.
	* config/nvptx/priority_queue.c: Ditto.
	* config/nvptx/sections.c: Ditto.
	* config/nvptx/single.c: Ditto.
	* config/nvptx/splay-tree.c: Ditto.
	* config/nvptx/work.c: Ditto.

	* testsuite/libgomp.fortran/fortran.exp (lang_link_flags): Pass
	-foffload=-lgfortran in addition to -lgfortran.
	* testsuite/libgomp.oacc-fortran/fortran.exp (lang_link_flags): Ditto.

	* plugin/plugin-nvptx.c: Include <limits.h>.
	(struct targ_fn_descriptor): Add new fields.
	(struct ptx_device): Ditto.  Set them...
	(nvptx_open_device): ...here.
	(nvptx_adjust_launch_bounds): New.
	(nvptx_host2dev): Allow NULL 'nvthd'.
	(nvptx_dev2host): Ditto.
	(GOMP_OFFLOAD_get_caps): Add GOMP_OFFLOAD_CAP_OPENMP_400.
	(link_ptx): Adjust log sizes.
	(nvptx_host2dev): Allow NULL 'nvthd'.
	(nvptx_dev2host): Ditto.
	(nvptx_set_clocktick): New.  Use it...
	(GOMP_OFFLOAD_load_image): ...here.  Set new targ_fn_descriptor
	fields.
	(GOMP_OFFLOAD_dev2dev): New.
	(nvptx_adjust_launch_bounds): New.
	(nvptx_stacks_size): New.
	(nvptx_stacks_alloc): New.
	(nvptx_stacks_free): New.
	(GOMP_OFFLOAD_run): New.
	(GOMP_OFFLOAD_async_run): New (stub).

Co-Authored-By: Dmitry Melnik <dm@ispras.ru>
Co-Authored-By: Jakub Jelinek <jakub@redhat.com>

From-SVN: r242789

1 files changed, 19 insertions, 3 deletions

diff --git a/libgomp/libgomp.h b/libgomp/libgomp.h
index 7b2671b..c86ac3d8 100644
--- a/libgomp/libgomp.h
+++ b/libgomp/libgomp.h
@@ -45,7 +45,9 @@
 #include "gstdint.h"
 #include "libgomp-plugin.h"
 
+#ifdef HAVE_PTHREAD_H
 #include <pthread.h>
+#endif
 #include <stdbool.h>
 #include <stdlib.h>
 #include <stdarg.h>
@@ -122,6 +124,7 @@ struct htab;
 #include "sem.h"
 #include "mutex.h"
 #include "bar.h"
+#include "simple-bar.h"
 #include "ptrlock.h"
 
 
@@ -360,6 +363,7 @@ extern char *gomp_bind_var_list;
 extern unsigned long gomp_bind_var_list_len;
 extern void **gomp_places_list;
 extern unsigned long gomp_places_list_len;
+extern unsigned int gomp_num_teams_var;
 extern int gomp_debug_var;
 extern int goacc_device_num;
 extern char *goacc_device_type;
@@ -626,8 +630,8 @@ struct gomp_thread_pool
   /* Number of threads running in this contention group.  */
   unsigned long threads_busy;
 
-  /* This barrier holds and releases threads waiting in threads.  */
-  gomp_barrier_t threads_dock;
+  /* This barrier holds and releases threads waiting in thread pools.  */
+  gomp_simple_barrier_t threads_dock;
 };
 
 enum gomp_cancel_kind
@@ -642,7 +646,15 @@ enum gomp_cancel_kind
 
 /* ... and here is that TLS data.  */
 
-#if defined HAVE_TLS || defined USE_EMUTLS
+#if defined __nvptx__
+extern struct gomp_thread *nvptx_thrs __attribute__((shared));
+static inline struct gomp_thread *gomp_thread (void)
+{
+  int tid;
+  asm ("mov.u32 %0, %%tid.y;" : "=r" (tid));
+  return nvptx_thrs + tid;
+}
+#elif defined HAVE_TLS || defined USE_EMUTLS
 extern __thread struct gomp_thread gomp_tls_data;
 static inline struct gomp_thread *gomp_thread (void)
 {
@@ -671,17 +683,21 @@ static inline struct gomp_task_icv *gomp_icv (bool write)
     return &gomp_global_icv;
 }
 
+#ifdef LIBGOMP_USE_PTHREADS
 /* The attributes to be used during thread creation.  */
 extern pthread_attr_t gomp_thread_attr;
 
 extern pthread_key_t gomp_thread_destructor;
+#endif
 
 /* Function prototypes.  */
 
 /* affinity.c */
 
 extern void gomp_init_affinity (void);
+#ifdef LIBGOMP_USE_PTHREADS
 extern void gomp_init_thread_affinity (pthread_attr_t *, unsigned int);
+#endif
 extern void **gomp_affinity_alloc (unsigned long, bool);
 extern void gomp_affinity_init_place (void *);
 extern bool gomp_affinity_add_cpus (void *, unsigned long, unsigned long,