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

Performance improvement: accessing thread struct as opposed to team struct 

Replaced readings of nproc from team structure with ones from
thread structure to improve performance.

Patch by Andrey Churbanov.

Differential Revision: http://reviews.llvm.org/D21559

llvm-svn: 273293
This commit is contained in:
Jonathan Peyton 2016-06-21 18:30:15 +00:00
parent 2487cb28ce
commit ff5ca8b4cf
1 changed files with 12 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
openmp/runtime/src/kmp_dispatch.cpp
View File

@ -738,7 +738,7 @@ __kmp_dispatch_init(
}
/* guided analytical not safe for too many threads */
if ( team->t.t_nproc > 1<<20 && schedule == kmp_sch_guided_analytical_chunked ) {
if ( schedule == kmp_sch_guided_analytical_chunked && th->th.th_team_nproc > 1<<20 ) {
schedule = kmp_sch_guided_iterative_chunked;
KMP_WARNING( DispatchManyThreads );
}
@ -836,7 +836,7 @@ __kmp_dispatch_init(
#if ( KMP_STATIC_STEAL_ENABLED && KMP_ARCH_X86_64 )
case kmp_sch_static_steal:
{
T nproc = team->t.t_nproc;
T nproc = th->th.th_team_nproc;
T ntc, init;
KD_TRACE(100, ("__kmp_dispatch_init: T#%d kmp_sch_static_steal case\n", gtid ) );
@ -869,7 +869,7 @@ __kmp_dispatch_init(
#endif
case kmp_sch_static_balanced:
{
T nproc = team->t.t_nproc;
T nproc = th->th.th_team_nproc;
T init, limit;
KD_TRACE(100, ("__kmp_dispatch_init: T#%d kmp_sch_static_balanced case\n",
@ -933,7 +933,7 @@ __kmp_dispatch_init(
} // case
case kmp_sch_guided_iterative_chunked :
{
T nproc = team->t.t_nproc;
T nproc = th->th.th_team_nproc;
KD_TRACE(100,("__kmp_dispatch_init: T#%d kmp_sch_guided_iterative_chunked case\n",gtid));
if ( nproc > 1 ) {
@ -956,7 +956,7 @@ __kmp_dispatch_init(
break;
case kmp_sch_guided_analytical_chunked:
{
T nproc = team->t.t_nproc;
T nproc = th->th.th_team_nproc;
KD_TRACE(100, ("__kmp_dispatch_init: T#%d kmp_sch_guided_analytical_chunked case\n", gtid));
if ( nproc > 1 ) {
@ -1074,8 +1074,8 @@ __kmp_dispatch_init(
break;
case kmp_sch_static_greedy:
KD_TRACE(100,("__kmp_dispatch_init: T#%d kmp_sch_static_greedy case\n",gtid));
pr->u.p.parm1 = ( team -> t.t_nproc > 1 ) ?
( tc + team->t.t_nproc - 1 ) / team->t.t_nproc :
pr->u.p.parm1 = ( th->th.th_team_nproc > 1 ) ?
( tc + th->th.th_team_nproc - 1 ) / th->th.th_team_nproc :
tc;
break;
case kmp_sch_static_chunked :
@ -1095,7 +1095,7 @@ __kmp_dispatch_init(
parm1 = chunk;
/* F : size of the first cycle */
parm2 = ( tc / (2 * team->t.t_nproc) );
parm2 = ( tc / (2 * th->th.th_team_nproc) );
if ( parm2 < 1 ) {
parm2 = 1;
@ -1793,7 +1793,7 @@ __kmp_dispatch_next(
if ( p_st != NULL ) *p_st = incr;
pr->u.p.count += team->t.t_nproc;
pr->u.p.count += th->th.th_team_nproc;
if ( incr == 1 ) {
*p_lb = start + init;
@ -1963,8 +1963,8 @@ __kmp_dispatch_next(
trip = pr->u.p.tc;
KMP_DEBUG_ASSERT(team->t.t_nproc > 1);
KMP_DEBUG_ASSERT((2UL * chunkspec + 1) * (UT)team->t.t_nproc < trip);
KMP_DEBUG_ASSERT(th->th.th_team_nproc > 1);
KMP_DEBUG_ASSERT((2UL * chunkspec + 1) * (UT)th->th.th_team_nproc < trip);
while(1) { /* this while loop is a safeguard against unexpected zero chunk sizes */
chunkIdx = test_then_inc_acq< ST >((volatile ST *) & sh->u.s.iteration );
@ -2135,7 +2135,7 @@ __kmp_dispatch_next(
}
#endif
if ( (ST)num_done == team->t.t_nproc-1 ) {
if ( (ST)num_done == th->th.th_team_nproc - 1 ) {
/* NOTE: release this buffer to be reused */
KMP_MB(); /* Flush all pending memory write invalidates. */