e460634820
gcc/ 2015-11-14 Jakub Jelinek <jakub@redhat.com> * omp-low.c (lower_omp_ordered): Add argument to GOMP_SMD_ORDERED_* internal calls - 0 if ordered simd and 1 for ordered threads simd. * tree-vectorizer.c (adjust_simduid_builtins): If GOMP_SIMD_ORDERED_* argument is 1, replace it with GOMP_ordered_* call instead of removing it. gcc/c/ 2015-11-14 Jakub Jelinek <jakub@redhat.com> * c-typeck.c (c_finish_omp_clauses): Don't mark GOMP_MAP_FIRSTPRIVATE_POINTER decls addressable. gcc/cp/ 2015-11-14 Jakub Jelinek <jakub@redhat.com> * semantics.c (finish_omp_clauses): Don't mark GOMP_MAP_FIRSTPRIVATE_POINTER decls addressable. libgomp/ 2015-11-14 Jakub Jelinek <jakub@redhat.com> Aldy Hernandez <aldyh@redhat.com> Ilya Verbin <ilya.verbin@intel.com> * ordered.c (gomp_doacross_init, GOMP_doacross_post, GOMP_doacross_wait, gomp_doacross_ull_init, GOMP_doacross_ull_post, GOMP_doacross_ull_wait): For GFS_GUIDED don't divide number of iterators or IV by chunk size. * parallel.c (gomp_resolve_num_threads): Don't assume that if thr->ts.team is non-NULL, then pool must be non-NULL. * libgomp-plugin.h (GOMP_PLUGIN_target_task_completion): Declare. * libgomp.map (GOMP_PLUGIN_1.1): New symbol version, export GOMP_PLUGIN_target_task_completion. * Makefile.am (libgomp_la_SOURCES): Add priority_queue.c. * Makefile.in: Regenerate. * libgomp.h: Shuffle prototypes and forward definitions around so priority queues can be defined. (enum gomp_task_kind): Add GOMP_TASK_ASYNC_RUNNING. (enum gomp_target_task_state): New enum. (struct gomp_target_task): Add state, tgt, task and team fields. (gomp_create_target_task): Change return type to bool, add state argument. (gomp_target_task_fn): Change return type to bool. (struct gomp_device_descr): Add async_run_func. (struct gomp_task): Remove children, next_child, prev_child, next_queue, prev_queue, next_taskgroup, prev_taskgroup. Add pnode field. (struct gomp_taskgroup): Remove children. Add taskgroup_queue. (struct gomp_team): Change task_queue type to a priority queue. (splay_compare): Define inline. (priority_queue_offset): New. (priority_node_to_task): New. (task_to_priority_node): New. * oacc-mem.c: Do not include splay-tree.h. * priority_queue.c: New file. * priority_queue.h: New file. * splay-tree.c: Do not include splay-tree.h. (splay_tree_foreach_internal): New. (splay_tree_foreach): New. * splay-tree.h: Become re-entrant if splay_tree_prefix is defined. (splay_tree_callback): Define typedef. * target.c (splay_compare): Move to libgomp.h. (GOMP_target): Don't adjust *thr in any way around running offloaded task. (GOMP_target_ext): Likewise. Handle target nowait. (GOMP_target_update_ext, GOMP_target_enter_exit_data): Check return value from gomp_create_target_task, if false, fallthrough as if no dependencies exist. (gomp_target_task_fn): Change return type to bool, return true if the task should have another part scheduled later. Handle target nowait. (gomp_load_plugin_for_device): Initialize async_run. * task.c (gomp_init_task): Initialize children_queue. (gomp_clear_parent_in_list): New. (gomp_clear_parent_in_tree): New. (gomp_clear_parent): Handle priorities. (GOMP_task): Likewise. (priority_queue_move_task_first, gomp_target_task_completion, GOMP_PLUGIN_target_task_completion): New functions. (gomp_create_target_task): Use priority queues. Change return type to bool, add state argument, return false if for async {{enter,exit} data,update} constructs no dependencies need to be waited for, handle target nowait. Set task->fn to NULL instead of gomp_target_task_fn. (verify_children_queue): Remove. (priority_list_upgrade_task): New. (priority_queue_upgrade_task): New. (verify_task_queue): Remove. (priority_list_downgrade_task): New. (priority_queue_downgrade_task): New. (gomp_task_run_pre): Use priority queues. Abstract code out to priority_queue_downgrade_task. (gomp_task_run_post_handle_dependers): Use priority queues. (gomp_task_run_post_remove_parent): Likewise. (gomp_task_run_post_remove_taskgroup): Likewise. (gomp_barrier_handle_tasks): Likewise. Handle target nowait target tasks specially. (GOMP_taskwait): Likewise. (gomp_task_maybe_wait_for_dependencies): Likewise. Abstract code to priority-queue_upgrade_task. (GOMP_taskgroup_start): Use priority queues. (GOMP_taskgroup_end): Likewise. Handle target nowait target tasks specially. If taskgroup is NULL, and thr->ts.level is 0, act as a barrier. * taskloop.c (GOMP_taskloop): Handle priorities. * team.c (gomp_new_team): Call priority_queue_init. (free_team): Call priority_queue_free. (gomp_free_thread): Call gomp_team_end if thr->ts.team is artificial team created for target nowait in implicit parallel region. (gomp_team_start): For nested check, test thr->ts.level instead of thr->ts.team != NULL. * testsuite/libgomp.c/doacross-3.c: New test. * testsuite/libgomp.c/ordered-5.c: New test. * testsuite/libgomp.c/priority.c: New test. * testsuite/libgomp.c/target-31.c: New test. * testsuite/libgomp.c/target-32.c: New test. * testsuite/libgomp.c/target-33.c: New test. * testsuite/libgomp.c/target-34.c: New test. liboffloadmic/ 2015-11-14 Ilya Verbin <ilya.verbin@intel.com> * runtime/offload_host.cpp (task_completion_callback): New variable. (offload_proxy_task_completed_ooo): Call task_completion_callback. (__offload_register_task_callback): New function. * runtime/offload_host.h (__offload_register_task_callback): New declaration. * plugin/libgomp-plugin-intelmic.cpp (offload): Add async_data argument, handle async offloading. (register_main_image): Call register_main_image. (GOMP_OFFLOAD_init_device, get_target_table, GOMP_OFFLOAD_alloc, GOMP_OFFLOAD_free, GOMP_OFFLOAD_host2dev, GOMP_OFFLOAD_dev2host, GOMP_OFFLOAD_dev2dev) Adjust offload callers. (GOMP_OFFLOAD_async_run): New function. (GOMP_OFFLOAD_run): Implement using GOMP_OFFLOAD_async_run. From-SVN: r230381
239 lines
5.9 KiB
C
239 lines
5.9 KiB
C
/* A splay-tree datatype.
|
|
Copyright (C) 1998-2015 Free Software Foundation, Inc.
|
|
Contributed by Mark Mitchell (mark@markmitchell.com).
|
|
|
|
This file is part of the GNU Offloading and Multi Processing Library
|
|
(libgomp).
|
|
|
|
Libgomp 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.
|
|
|
|
Libgomp 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/>. */
|
|
|
|
/* The splay tree code copied from include/splay-tree.h and adjusted,
|
|
so that all the data lives directly in splay_tree_node_s structure
|
|
and no extra allocations are needed. */
|
|
|
|
/* For an easily readable description of splay-trees, see:
|
|
|
|
Lewis, Harry R. and Denenberg, Larry. Data Structures and Their
|
|
Algorithms. Harper-Collins, Inc. 1991.
|
|
|
|
The major feature of splay trees is that all basic tree operations
|
|
are amortized O(log n) time for a tree with n nodes. */
|
|
|
|
#include "libgomp.h"
|
|
|
|
/* Rotate the edge joining the left child N with its parent P. PP is the
|
|
grandparents' pointer to P. */
|
|
|
|
static inline void
|
|
rotate_left (splay_tree_node *pp, splay_tree_node p, splay_tree_node n)
|
|
{
|
|
splay_tree_node tmp;
|
|
tmp = n->right;
|
|
n->right = p;
|
|
p->left = tmp;
|
|
*pp = n;
|
|
}
|
|
|
|
/* Rotate the edge joining the right child N with its parent P. PP is the
|
|
grandparents' pointer to P. */
|
|
|
|
static inline void
|
|
rotate_right (splay_tree_node *pp, splay_tree_node p, splay_tree_node n)
|
|
{
|
|
splay_tree_node tmp;
|
|
tmp = n->left;
|
|
n->left = p;
|
|
p->right = tmp;
|
|
*pp = n;
|
|
}
|
|
|
|
/* Bottom up splay of KEY. */
|
|
|
|
static void
|
|
splay_tree_splay (splay_tree sp, splay_tree_key key)
|
|
{
|
|
if (sp->root == NULL)
|
|
return;
|
|
|
|
do {
|
|
int cmp1, cmp2;
|
|
splay_tree_node n, c;
|
|
|
|
n = sp->root;
|
|
cmp1 = splay_compare (key, &n->key);
|
|
|
|
/* Found. */
|
|
if (cmp1 == 0)
|
|
return;
|
|
|
|
/* Left or right? If no child, then we're done. */
|
|
if (cmp1 < 0)
|
|
c = n->left;
|
|
else
|
|
c = n->right;
|
|
if (!c)
|
|
return;
|
|
|
|
/* Next one left or right? If found or no child, we're done
|
|
after one rotation. */
|
|
cmp2 = splay_compare (key, &c->key);
|
|
if (cmp2 == 0
|
|
|| (cmp2 < 0 && !c->left)
|
|
|| (cmp2 > 0 && !c->right))
|
|
{
|
|
if (cmp1 < 0)
|
|
rotate_left (&sp->root, n, c);
|
|
else
|
|
rotate_right (&sp->root, n, c);
|
|
return;
|
|
}
|
|
|
|
/* Now we have the four cases of double-rotation. */
|
|
if (cmp1 < 0 && cmp2 < 0)
|
|
{
|
|
rotate_left (&n->left, c, c->left);
|
|
rotate_left (&sp->root, n, n->left);
|
|
}
|
|
else if (cmp1 > 0 && cmp2 > 0)
|
|
{
|
|
rotate_right (&n->right, c, c->right);
|
|
rotate_right (&sp->root, n, n->right);
|
|
}
|
|
else if (cmp1 < 0 && cmp2 > 0)
|
|
{
|
|
rotate_right (&n->left, c, c->right);
|
|
rotate_left (&sp->root, n, n->left);
|
|
}
|
|
else if (cmp1 > 0 && cmp2 < 0)
|
|
{
|
|
rotate_left (&n->right, c, c->left);
|
|
rotate_right (&sp->root, n, n->right);
|
|
}
|
|
} while (1);
|
|
}
|
|
|
|
/* Insert a new NODE into SP. The NODE shouldn't exist in the tree. */
|
|
|
|
attribute_hidden void
|
|
splay_tree_insert (splay_tree sp, splay_tree_node node)
|
|
{
|
|
int comparison = 0;
|
|
|
|
splay_tree_splay (sp, &node->key);
|
|
|
|
if (sp->root)
|
|
comparison = splay_compare (&sp->root->key, &node->key);
|
|
|
|
if (sp->root && comparison == 0)
|
|
gomp_fatal ("Duplicate node");
|
|
else
|
|
{
|
|
/* Insert it at the root. */
|
|
if (sp->root == NULL)
|
|
node->left = node->right = NULL;
|
|
else if (comparison < 0)
|
|
{
|
|
node->left = sp->root;
|
|
node->right = node->left->right;
|
|
node->left->right = NULL;
|
|
}
|
|
else
|
|
{
|
|
node->right = sp->root;
|
|
node->left = node->right->left;
|
|
node->right->left = NULL;
|
|
}
|
|
|
|
sp->root = node;
|
|
}
|
|
}
|
|
|
|
/* Remove node with KEY from SP. It is not an error if it did not exist. */
|
|
|
|
attribute_hidden void
|
|
splay_tree_remove (splay_tree sp, splay_tree_key key)
|
|
{
|
|
splay_tree_splay (sp, key);
|
|
|
|
if (sp->root && splay_compare (&sp->root->key, key) == 0)
|
|
{
|
|
splay_tree_node left, right;
|
|
|
|
left = sp->root->left;
|
|
right = sp->root->right;
|
|
|
|
/* One of the children is now the root. Doesn't matter much
|
|
which, so long as we preserve the properties of the tree. */
|
|
if (left)
|
|
{
|
|
sp->root = left;
|
|
|
|
/* If there was a right child as well, hang it off the
|
|
right-most leaf of the left child. */
|
|
if (right)
|
|
{
|
|
while (left->right)
|
|
left = left->right;
|
|
left->right = right;
|
|
}
|
|
}
|
|
else
|
|
sp->root = right;
|
|
}
|
|
}
|
|
|
|
/* Lookup KEY in SP, returning NODE if present, and NULL
|
|
otherwise. */
|
|
|
|
attribute_hidden splay_tree_key
|
|
splay_tree_lookup (splay_tree sp, splay_tree_key key)
|
|
{
|
|
splay_tree_splay (sp, key);
|
|
|
|
if (sp->root && splay_compare (&sp->root->key, key) == 0)
|
|
return &sp->root->key;
|
|
else
|
|
return NULL;
|
|
}
|
|
|
|
/* Helper function for splay_tree_foreach.
|
|
|
|
Run FUNC on every node in KEY. */
|
|
|
|
static void
|
|
splay_tree_foreach_internal (splay_tree_node node, splay_tree_callback func,
|
|
void *data)
|
|
{
|
|
if (!node)
|
|
return;
|
|
func (&node->key, data);
|
|
splay_tree_foreach_internal (node->left, func, data);
|
|
/* Yeah, whatever. GCC can fix my tail recursion. */
|
|
splay_tree_foreach_internal (node->right, func, data);
|
|
}
|
|
|
|
/* Run FUNC on each of the nodes in SP. */
|
|
|
|
attribute_hidden void
|
|
splay_tree_foreach (splay_tree sp, splay_tree_callback func, void *data)
|
|
{
|
|
splay_tree_foreach_internal (sp->root, func, data);
|
|
}
|