maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Fork performance improvements 

Most of this is modifications to check for differences before updating data
fields in team struct. There is also some rearrangement of the team struct.

Patch by Diego Caballero

Differential Revision: http://reviews.llvm.org/D20487

llvm-svn: 270468
This commit is contained in:
Jonathan Peyton 2016-05-23 18:01:19 +00:00
parent 13a0d49813
commit b044e4fa31
3 changed files with 51 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
openmp/CREDITS.txt
View File

@ -51,3 +51,7 @@ D: Making build work for FreeBSD.
N: Cheng Wang
D: Contributor to testsuite from OpenUH
N: Diego Caballero
E: diego.l.caballero@gmail.com
D: Fork performance improvements

14
openmp/runtime/src/kmp.h
View File

@ -1951,6 +1951,9 @@ typedef struct kmp_local {
} kmp_local_t;
#define KMP_CHECK_UPDATE(a, b) if ((a) != (b)) (a) = (b)
#define KMP_CHECK_UPDATE_SYNC(a, b) if ((a) != (b)) TCW_SYNC_PTR((a), (b))
#define get__blocktime( xteam, xtid ) ((xteam)->t.t_threads[(xtid)]->th.th_current_task->td_icvs.blocktime)
#define get__bt_set( xteam, xtid ) ((xteam)->t.t_threads[(xtid)]->th.th_current_task->td_icvs.bt_set)
#define get__bt_intervals( xteam, xtid ) ((xteam)->t.t_threads[(xtid)]->th.th_current_task->td_icvs.bt_intervals)
@ -2196,7 +2199,7 @@ struct kmp_taskdata { /* aligned during dynamic
kmp_uint32 td_taskwait_counter;
kmp_int32 td_taskwait_thread; /* gtid + 1 of thread encountered taskwait */
KMP_ALIGN_CACHE kmp_internal_control_t td_icvs; /* Internal control variables for the task */
volatile kmp_uint32 td_allocated_child_tasks; /* Child tasks (+ current task) not yet deallocated */
KMP_ALIGN_CACHE volatile kmp_uint32 td_allocated_child_tasks; /* Child tasks (+ current task) not yet deallocated */
volatile kmp_uint32 td_incomplete_child_tasks; /* Child tasks not yet complete */
#if OMP_40_ENABLED
kmp_taskgroup_t * td_taskgroup; // Each task keeps pointer to its current taskgroup
@ -2515,12 +2518,14 @@ typedef struct KMP_ALIGN_CACHE kmp_base_team {
void *t_inline_argv[ KMP_INLINE_ARGV_ENTRIES ];
KMP_ALIGN_CACHE kmp_info_t **t_threads;
int t_max_argc;
kmp_taskdata_t *t_implicit_task_taskdata; // Taskdata for the thread's implicit task
int t_level; // nested parallel level
KMP_ALIGN_CACHE int t_max_argc;
int t_max_nproc; // maximum threads this team can handle (dynamicly expandable)
int t_serialized; // levels deep of serialized teams
dispatch_shared_info_t *t_disp_buffer; // buffers for dispatch system
int t_id; // team's id, assigned by debugger.
int t_level; // nested parallel level
int t_active_level; // nested active parallel level
kmp_r_sched_t t_sched; // run-time schedule for the team
#if OMP_40_ENABLED && KMP_AFFINITY_SUPPORTED
@ -2536,8 +2541,7 @@ typedef struct KMP_ALIGN_CACHE kmp_base_team {
// and 'barrier' when CACHE_LINE=64. TODO: investigate more and get rid if this padding.
char dummy_padding[1024];
#endif
KMP_ALIGN_CACHE kmp_taskdata_t *t_implicit_task_taskdata; // Taskdata for the thread's implicit task
kmp_internal_control_t *t_control_stack_top; // internal control stack for additional nested teams.
KMP_ALIGN_CACHE kmp_internal_control_t *t_control_stack_top; // internal control stack for additional nested teams.
// for SERIALIZED teams nested 2 or more levels deep
#if OMP_40_ENABLED
kmp_int32 t_cancel_request; // typed flag to store request state of cancellation

64
openmp/runtime/src/kmp_runtime.c
View File

@ -2003,32 +2003,38 @@ __kmp_fork_call(
KF_TRACE( 10, ( "__kmp_fork_call: after __kmp_allocate_team - team = %p\n", team ) );
/* setup the new team */
team->t.t_master_tid = master_tid;
team->t.t_master_this_cons = master_this_cons;
team->t.t_ident = loc;
team->t.t_parent = parent_team;
TCW_SYNC_PTR(team->t.t_pkfn, microtask);
KMP_CHECK_UPDATE(team->t.t_master_tid, master_tid);
KMP_CHECK_UPDATE(team->t.t_master_this_cons, master_this_cons);
KMP_CHECK_UPDATE(team->t.t_ident, loc);
KMP_CHECK_UPDATE(team->t.t_parent, parent_team);
KMP_CHECK_UPDATE_SYNC(team->t.t_pkfn, microtask);
#if OMPT_SUPPORT
TCW_SYNC_PTR(team->t.ompt_team_info.microtask, unwrapped_task);
KMP_CHECK_UPDATE_SYNC(team->t.ompt_team_info.microtask, unwrapped_task);
#endif
team->t.t_invoke = invoker; /* TODO move this to root, maybe */
KMP_CHECK_UPDATE(team->t.t_invoke, invoker); /* TODO move this to root, maybe */
// TODO: parent_team->t.t_level == INT_MAX ???
#if OMP_40_ENABLED
if ( !master_th->th.th_teams_microtask || level > teams_level ) {
#endif /* OMP_40_ENABLED */
team->t.t_level = parent_team->t.t_level + 1;
team->t.t_active_level = parent_team->t.t_active_level + 1;
int new_level = parent_team->t.t_level + 1;
KMP_CHECK_UPDATE(team->t.t_level, new_level);
new_level = parent_team->t.t_active_level + 1;
KMP_CHECK_UPDATE(team->t.t_active_level, new_level);
#if OMP_40_ENABLED
} else {
// AC: Do not increase parallel level at start of the teams construct
team->t.t_level = parent_team->t.t_level;
team->t.t_active_level = parent_team->t.t_active_level;
int new_level = parent_team->t.t_level;
KMP_CHECK_UPDATE(team->t.t_level, new_level);
new_level = parent_team->t.t_active_level;
KMP_CHECK_UPDATE(team->t.t_active_level, new_level);
}
#endif /* OMP_40_ENABLED */
team->t.t_sched = get__sched_2(parent_team, master_tid); // set master's schedule as new run-time schedule
kmp_r_sched_t new_sched = get__sched_2(parent_team, master_tid);
if (team->t.t_sched.r_sched_type != new_sched.r_sched_type || new_sched.chunk != new_sched.chunk)
team->t.t_sched = new_sched; // set master's schedule as new run-time schedule
#if OMP_40_ENABLED
team->t.t_cancel_request = cancel_noreq;
KMP_CHECK_UPDATE(team->t.t_cancel_request, cancel_noreq);
#endif
// Update the floating point rounding in the team if required.
@ -2095,23 +2101,27 @@ __kmp_fork_call(
#if OMP_40_ENABLED
if ( ap ) {
#endif /* OMP_40_ENABLED */
for ( i=argc-1; i >= 0; --i )
for ( i=argc-1; i >= 0; --i ) {
// TODO: revert workaround for Intel(R) 64 tracker #96
#if (KMP_ARCH_X86_64 || KMP_ARCH_ARM || KMP_ARCH_AARCH64) && KMP_OS_LINUX
*argv++ = va_arg( *ap, void * );
void *new_argv = va_arg(*ap, void *);
#else
*argv++ = va_arg( ap, void * );
void *new_argv = va_arg(ap, void *);
#endif
KMP_CHECK_UPDATE(*argv, new_argv);
argv++;
}
#if OMP_40_ENABLED
} else {
for ( i=0; i < argc; ++i )
for ( i=0; i < argc; ++i ) {
// Get args from parent team for teams construct
argv[i] = team->t.t_parent->t.t_argv[i];
KMP_CHECK_UPDATE(argv[i], team->t.t_parent->t.t_argv[i]);
}
}
#endif /* OMP_40_ENABLED */
/* now actually fork the threads */
team->t.t_master_active = master_active;
KMP_CHECK_UPDATE(team->t.t_master_active, master_active);
if (!root->r.r_active) // Only do assignment if it prevents cache ping-pong
root->r.r_active = TRUE;
@ -4320,9 +4330,9 @@ __kmp_reinitialize_team( kmp_team_t *team, kmp_internal_control_t *new_icvs, ide
team->t.t_threads[0], team ) );
KMP_DEBUG_ASSERT( team && new_icvs);
KMP_DEBUG_ASSERT( ( ! TCR_4(__kmp_init_parallel) ) || new_icvs->nproc );
team->t.t_ident = loc;
KMP_CHECK_UPDATE(team->t.t_ident, loc);
team->t.t_id = KMP_GEN_TEAM_ID();
KMP_CHECK_UPDATE(team->t.t_id, KMP_GEN_TEAM_ID());
// Copy ICVs to the master thread's implicit taskdata
__kmp_init_implicit_task( loc, team->t.t_threads[0], team, 0, FALSE );
@ -4774,11 +4784,13 @@ __kmp_allocate_team( kmp_root_t *root, int new_nproc, int max_nproc,
if ( team->t.t_size_changed == -1 ) {
team->t.t_size_changed = 1;
} else {
team->t.t_size_changed = 0;
KMP_CHECK_UPDATE(team->t.t_size_changed, 0);
}
// TODO???: team->t.t_max_active_levels = new_max_active_levels;
team->t.t_sched = new_icvs->sched;
kmp_r_sched_t new_sched = new_icvs->sched;
if (team->t.t_sched.r_sched_type != new_sched.r_sched_type || new_sched.chunk != new_sched.chunk)
team->t.t_sched = new_sched; // set master's schedule as new run-time schedule
__kmp_reinitialize_team( team, new_icvs, root->r.r_uber_thread->th.th_ident );
@ -4795,7 +4807,7 @@ __kmp_allocate_team( kmp_root_t *root, int new_nproc, int max_nproc,
team->t.t_last_place ) );
}
else {
team->t.t_proc_bind = new_proc_bind;
KMP_CHECK_UPDATE(team->t.t_proc_bind, new_proc_bind);
__kmp_partition_places( team );
}
# else
@ -5016,7 +5028,7 @@ __kmp_allocate_team( kmp_root_t *root, int new_nproc, int max_nproc,
/* reallocate space for arguments if necessary */
__kmp_alloc_argv_entries( argc, team, TRUE );
team->t.t_argc = argc;
KMP_CHECK_UPDATE(team->t.t_argc, argc);
//
// The hot team re-uses the previous task team,
// if untouched during the previous release->gather phase.
@ -5059,7 +5071,7 @@ __kmp_allocate_team( kmp_root_t *root, int new_nproc, int max_nproc,
/* reallocate space for arguments if necessary */
__kmp_alloc_argv_entries( argc, team, TRUE );
team->t.t_argc = argc;
KMP_CHECK_UPDATE(team->t.t_argc, argc);
KA_TRACE( 20, ("__kmp_allocate_team: team %d init arrived: join=%u, plain=%u\n",
team->t.t_id, KMP_INIT_BARRIER_STATE, KMP_INIT_BARRIER_STATE ));