diff options
Diffstat (limited to 'openmp/runtime/src/kmp_sched.cpp')
| -rw-r--r-- | openmp/runtime/src/kmp_sched.cpp | 563 |
1 files changed, 540 insertions, 23 deletions
diff --git a/openmp/runtime/src/kmp_sched.cpp b/openmp/runtime/src/kmp_sched.cpp index 18e5a38dc40..14fa62ee85d 100644 --- a/openmp/runtime/src/kmp_sched.cpp +++ b/openmp/runtime/src/kmp_sched.cpp @@ -1,7 +1,7 @@ /* * kmp_sched.c -- static scheduling -- iteration initialization - * $Revision: 42358 $ - * $Date: 2013-05-07 13:43:26 -0500 (Tue, 07 May 2013) $ + * $Revision: 43457 $ + * $Date: 2014-09-17 03:57:22 -0500 (Wed, 17 Sep 2014) $ */ @@ -28,6 +28,8 @@ #include "kmp_i18n.h" #include "kmp_str.h" #include "kmp_error.h" +#include "kmp_stats.h" +#include "kmp_itt.h" // template for type limits template< typename T > @@ -79,6 +81,7 @@ __kmp_for_static_init( typename traits_t< T >::signed_t incr, typename traits_t< T >::signed_t chunk ) { + KMP_COUNT_BLOCK(OMP_FOR_static); typedef typename traits_t< T >::unsigned_t UT; typedef typename traits_t< T >::signed_t ST; /* this all has to be changed back to TID and such.. */ @@ -88,6 +91,7 @@ __kmp_for_static_init( register UT trip_count; register kmp_team_t *team; + KMP_DEBUG_ASSERT( plastiter && plower && pupper && pstride ); KE_TRACE( 10, ("__kmpc_for_static_init called (%d)\n", global_tid)); #ifdef KMP_DEBUG { @@ -108,12 +112,12 @@ __kmp_for_static_init( __kmp_push_workshare( global_tid, ct_pdo, loc ); if ( incr == 0 ) { __kmp_error_construct( kmp_i18n_msg_CnsLoopIncrZeroProhibited, ct_pdo, loc ); - } } /* special handling for zero-trip loops */ if ( incr > 0 ? (*pupper < *plower) : (*plower < *pupper) ) { - *plastiter = FALSE; + if( plastiter != NULL ) + *plastiter = FALSE; /* leave pupper and plower set to entire iteration space */ *pstride = incr; /* value should never be used */ // *plower = *pupper - incr; // let compiler bypass the illegal loop (like for(i=1;i<10;i--)) THIS LINE CAUSED shape2F/h_tests_1.f TO HAVE A FAILURE ON A ZERO-TRIP LOOP (lower=1,\ @@ -149,7 +153,8 @@ __kmp_for_static_init( /* determine if "for" loop is an active worksharing construct */ if ( team -> t.t_serialized ) { /* serialized parallel, each thread executes whole iteration space */ - *plastiter = TRUE; + if( plastiter != NULL ) + *plastiter = TRUE; /* leave pupper and plower set to entire iteration space */ *pstride = (incr > 0) ? (*pupper - *plower + 1) : (-(*plower - *pupper + 1)); @@ -169,8 +174,9 @@ __kmp_for_static_init( } nth = team->t.t_nproc; if ( nth == 1 ) { - *plastiter = TRUE; - + if( plastiter != NULL ) + *plastiter = TRUE; + *pstride = (incr > 0) ? (*pupper - *plower + 1) : (-(*plower - *pupper + 1)); #ifdef KMP_DEBUG { const char * buff; @@ -192,12 +198,13 @@ __kmp_for_static_init( } else if (incr == -1) { trip_count = *plower - *pupper + 1; } else { - if ( incr > 1 ) { + if ( incr > 1 ) { // the check is needed for unsigned division when incr < 0 trip_count = (*pupper - *plower) / incr + 1; } else { trip_count = (*plower - *pupper) / ( -incr ) + 1; } } + if ( __kmp_env_consistency_check ) { /* tripcount overflow? */ if ( trip_count == 0 && *pupper != *plower ) { @@ -219,14 +226,16 @@ __kmp_for_static_init( } else { *plower = *pupper + incr; } - *plastiter = ( tid == trip_count - 1 ); + if( plastiter != NULL ) + *plastiter = ( tid == trip_count - 1 ); } else { if ( __kmp_static == kmp_sch_static_balanced ) { register UT small_chunk = trip_count / nth; register UT extras = trip_count % nth; *plower += incr * ( tid * small_chunk + ( tid < extras ? tid : extras ) ); *pupper = *plower + small_chunk * incr - ( tid < extras ? 0 : incr ); - *plastiter = ( tid == nth - 1 ); + if( plastiter != NULL ) + *plastiter = ( tid == nth - 1 ); } else { register T big_chunk_inc_count = ( trip_count/nth + ( ( trip_count % nth ) ? 1 : 0) ) * incr; @@ -238,16 +247,16 @@ __kmp_for_static_init( *plower += tid * big_chunk_inc_count; *pupper = *plower + big_chunk_inc_count - incr; if ( incr > 0 ) { - if ( *pupper < *plower ) { + if( *pupper < *plower ) *pupper = i_maxmin< T >::mx; - } - *plastiter = *plower <= old_upper && *pupper > old_upper - incr; + if( plastiter != NULL ) + *plastiter = *plower <= old_upper && *pupper > old_upper - incr; if ( *pupper > old_upper ) *pupper = old_upper; // tracker C73258 } else { - if ( *pupper > *plower ) { + if( *pupper > *plower ) *pupper = i_maxmin< T >::mn; - } - *plastiter = *plower >= old_upper && *pupper < old_upper - incr; + if( plastiter != NULL ) + *plastiter = *plower >= old_upper && *pupper < old_upper - incr; if ( *pupper < old_upper ) *pupper = old_upper; // tracker C73258 } } @@ -256,7 +265,7 @@ __kmp_for_static_init( } case kmp_sch_static_chunked: { - register T span; + register ST span; if ( chunk < 1 ) { chunk = 1; } @@ -264,11 +273,8 @@ __kmp_for_static_init( *pstride = span * nth; *plower = *plower + (span * tid); *pupper = *plower + span - incr; - /* TODO: is the following line a bug? Shouldn't it be plastiter instead of *plastiter ? */ - if (*plastiter) { /* only calculate this if it was requested */ - kmp_int32 lasttid = ((trip_count - 1) / ( UT )chunk) % nth; - *plastiter = (tid == lasttid); - } + if( plastiter != NULL ) + *plastiter = (tid == ((trip_count - 1)/( UT )chunk) % nth); break; } default: @@ -276,6 +282,18 @@ __kmp_for_static_init( break; } +#if USE_ITT_BUILD + // Report loop metadata + if ( KMP_MASTER_TID(tid) && __itt_metadata_add_ptr && __kmp_forkjoin_frames_mode == 3 ) { + kmp_uint64 cur_chunk = chunk; + // Calculate chunk in case it was not specified; it is specified for kmp_sch_static_chunked + if ( schedtype == kmp_sch_static ) { + cur_chunk = trip_count / nth + ( ( trip_count % nth ) ? 1 : 0); + } + // 0 - "static" schedule + __kmp_itt_metadata_loop(loc, 0, trip_count, cur_chunk); + } +#endif #ifdef KMP_DEBUG { const char * buff; @@ -291,6 +309,355 @@ __kmp_for_static_init( return; } +template< typename T > +static void +__kmp_dist_for_static_init( + ident_t *loc, + kmp_int32 gtid, + kmp_int32 schedule, + kmp_int32 *plastiter, + T *plower, + T *pupper, + T *pupperDist, + typename traits_t< T >::signed_t *pstride, + typename traits_t< T >::signed_t incr, + typename traits_t< T >::signed_t chunk +) { + KMP_COUNT_BLOCK(OMP_DISTR_FOR_static); + typedef typename traits_t< T >::unsigned_t UT; + typedef typename traits_t< T >::signed_t ST; + register kmp_uint32 tid; + register kmp_uint32 nth; + register kmp_uint32 team_id; + register kmp_uint32 nteams; + register UT trip_count; + register kmp_team_t *team; + kmp_info_t * th; + + KMP_DEBUG_ASSERT( plastiter && plower && pupper && pupperDist && pstride ); + KE_TRACE( 10, ("__kmpc_dist_for_static_init called (%d)\n", gtid)); + #ifdef KMP_DEBUG + { + const char * buff; + // create format specifiers before the debug output + buff = __kmp_str_format( + "__kmpc_dist_for_static_init: T#%%d schedLoop=%%d liter=%%d "\ + "iter=(%%%s, %%%s, %%%s) chunk=%%%s signed?<%s>\n", + traits_t< T >::spec, traits_t< T >::spec, traits_t< ST >::spec, + traits_t< ST >::spec, traits_t< T >::spec ); + KD_TRACE(100, ( buff, gtid, schedule, *plastiter, + *plower, *pupper, incr, chunk ) ); + __kmp_str_free( &buff ); + } + #endif + + if( __kmp_env_consistency_check ) { + __kmp_push_workshare( gtid, ct_pdo, loc ); + if( incr == 0 ) { + __kmp_error_construct( kmp_i18n_msg_CnsLoopIncrZeroProhibited, ct_pdo, loc ); + } + if( incr > 0 ? (*pupper < *plower) : (*plower < *pupper) ) { + // The loop is illegal. + // Some zero-trip loops maintained by compiler, e.g.: + // for(i=10;i<0;++i) // lower >= upper - run-time check + // for(i=0;i>10;--i) // lower <= upper - run-time check + // for(i=0;i>10;++i) // incr > 0 - compile-time check + // for(i=10;i<0;--i) // incr < 0 - compile-time check + // Compiler does not check the following illegal loops: + // for(i=0;i<10;i+=incr) // where incr<0 + // for(i=10;i>0;i-=incr) // where incr<0 + __kmp_error_construct( kmp_i18n_msg_CnsLoopIncrIllegal, ct_pdo, loc ); + } + } + tid = __kmp_tid_from_gtid( gtid ); + th = __kmp_threads[gtid]; + KMP_DEBUG_ASSERT(th->th.th_teams_microtask); // we are in the teams construct + nth = th->th.th_team_nproc; + team = th->th.th_team; + #if OMP_40_ENABLED + nteams = th->th.th_teams_size.nteams; + #endif + team_id = team->t.t_master_tid; + KMP_DEBUG_ASSERT(nteams == team->t.t_parent->t.t_nproc); + + // compute global trip count + if( incr == 1 ) { + trip_count = *pupper - *plower + 1; + } else if(incr == -1) { + trip_count = *plower - *pupper + 1; + } else { + trip_count = (ST)(*pupper - *plower) / incr + 1; // cast to signed to cover incr<0 case + } + *pstride = *pupper - *plower; // just in case (can be unused) + if( trip_count <= nteams ) { + KMP_DEBUG_ASSERT( + __kmp_static == kmp_sch_static_greedy || \ + __kmp_static == kmp_sch_static_balanced + ); // Unknown static scheduling type. + // only masters of some teams get single iteration, other threads get nothing + if( team_id < trip_count && tid == 0 ) { + *pupper = *pupperDist = *plower = *plower + team_id * incr; + } else { + *pupperDist = *pupper; + *plower = *pupper + incr; // compiler should skip loop body + } + if( plastiter != NULL ) + *plastiter = ( tid == 0 && team_id == trip_count - 1 ); + } else { + // Get the team's chunk first (each team gets at most one chunk) + if( __kmp_static == kmp_sch_static_balanced ) { + register UT chunkD = trip_count / nteams; + register UT extras = trip_count % nteams; + *plower += incr * ( team_id * chunkD + ( team_id < extras ? team_id : extras ) ); + *pupperDist = *plower + chunkD * incr - ( team_id < extras ? 0 : incr ); + if( plastiter != NULL ) + *plastiter = ( team_id == nteams - 1 ); + } else { + register T chunk_inc_count = + ( trip_count / nteams + ( ( trip_count % nteams ) ? 1 : 0) ) * incr; + register T upper = *pupper; + KMP_DEBUG_ASSERT( __kmp_static == kmp_sch_static_greedy ); + // Unknown static scheduling type. + *plower += team_id * chunk_inc_count; + *pupperDist = *plower + chunk_inc_count - incr; + // Check/correct bounds if needed + if( incr > 0 ) { + if( *pupperDist < *plower ) + *pupperDist = i_maxmin< T >::mx; + if( plastiter != NULL ) + *plastiter = *plower <= upper && *pupperDist > upper - incr; + if( *pupperDist > upper ) + *pupperDist = upper; // tracker C73258 + if( *plower > *pupperDist ) { + *pupper = *pupperDist; // no iterations available for the team + goto end; + } + } else { + if( *pupperDist > *plower ) + *pupperDist = i_maxmin< T >::mn; + if( plastiter != NULL ) + *plastiter = *plower >= upper && *pupperDist < upper - incr; + if( *pupperDist < upper ) + *pupperDist = upper; // tracker C73258 + if( *plower < *pupperDist ) { + *pupper = *pupperDist; // no iterations available for the team + goto end; + } + } + } + // Get the parallel loop chunk now (for thread) + // compute trip count for team's chunk + if( incr == 1 ) { + trip_count = *pupperDist - *plower + 1; + } else if(incr == -1) { + trip_count = *plower - *pupperDist + 1; + } else { + trip_count = (ST)(*pupperDist - *plower) / incr + 1; + } + KMP_DEBUG_ASSERT( trip_count ); + switch( schedule ) { + case kmp_sch_static: + { + if( trip_count <= nth ) { + KMP_DEBUG_ASSERT( + __kmp_static == kmp_sch_static_greedy || \ + __kmp_static == kmp_sch_static_balanced + ); // Unknown static scheduling type. + if( tid < trip_count ) + *pupper = *plower = *plower + tid * incr; + else + *plower = *pupper + incr; // no iterations available + if( plastiter != NULL ) + if( *plastiter != 0 && !( tid == trip_count - 1 ) ) + *plastiter = 0; + } else { + if( __kmp_static == kmp_sch_static_balanced ) { + register UT chunkL = trip_count / nth; + register UT extras = trip_count % nth; + *plower += incr * (tid * chunkL + (tid < extras ? tid : extras)); + *pupper = *plower + chunkL * incr - (tid < extras ? 0 : incr); + if( plastiter != NULL ) + if( *plastiter != 0 && !( tid == nth - 1 ) ) + *plastiter = 0; + } else { + register T chunk_inc_count = + ( trip_count / nth + ( ( trip_count % nth ) ? 1 : 0) ) * incr; + register T upper = *pupperDist; + KMP_DEBUG_ASSERT( __kmp_static == kmp_sch_static_greedy ); + // Unknown static scheduling type. + *plower += tid * chunk_inc_count; + *pupper = *plower + chunk_inc_count - incr; + if( incr > 0 ) { + if( *pupper < *plower ) + *pupper = i_maxmin< T >::mx; + if( plastiter != NULL ) + if( *plastiter != 0 && !(*plower <= upper && *pupper > upper - incr) ) + *plastiter = 0; + if( *pupper > upper ) + *pupper = upper;//tracker C73258 + } else { + if( *pupper > *plower ) + *pupper = i_maxmin< T >::mn; + if( plastiter != NULL ) + if( *plastiter != 0 && !(*plower >= upper && *pupper < upper - incr) ) + *plastiter = 0; + if( *pupper < upper ) + *pupper = upper;//tracker C73258 + } + } + } + break; + } + case kmp_sch_static_chunked: + { + register ST span; + if( chunk < 1 ) + chunk = 1; + span = chunk * incr; + *pstride = span * nth; + *plower = *plower + (span * tid); + *pupper = *plower + span - incr; + if( plastiter != NULL ) + if( *plastiter != 0 && !(tid == ((trip_count - 1) / ( UT )chunk) % nth) ) + *plastiter = 0; + break; + } + default: + KMP_ASSERT2( 0, "__kmpc_dist_for_static_init: unknown loop scheduling type" ); + break; + } + } + end:; + #ifdef KMP_DEBUG + { + const char * buff; + // create format specifiers before the debug output + buff = __kmp_str_format( + "__kmpc_dist_for_static_init: last=%%d lo=%%%s up=%%%s upDist=%%%s "\ + "stride=%%%s signed?<%s>\n", + traits_t< T >::spec, traits_t< T >::spec, traits_t< T >::spec, + traits_t< ST >::spec, traits_t< T >::spec ); + KD_TRACE(100, ( buff, *plastiter, *plower, *pupper, *pupperDist, *pstride ) ); + __kmp_str_free( &buff ); + } + #endif + KE_TRACE( 10, ("__kmpc_dist_for_static_init: T#%d return\n", gtid ) ); + return; +} + +template< typename T > +static void +__kmp_team_static_init( + ident_t *loc, + kmp_int32 gtid, + kmp_int32 *p_last, + T *p_lb, + T *p_ub, + typename traits_t< T >::signed_t *p_st, + typename traits_t< T >::signed_t incr, + typename traits_t< T >::signed_t chunk +) { + // The routine returns the first chunk distributed to the team and + // stride for next chunks calculation. + // Last iteration flag set for the team that will execute + // the last iteration of the loop. + // The routine is called for dist_schedue(static,chunk) only. + typedef typename traits_t< T >::unsigned_t UT; + typedef typename traits_t< T >::signed_t ST; + kmp_uint32 team_id; + kmp_uint32 nteams; + UT trip_count; + T lower; + T upper; + ST span; + kmp_team_t *team; + kmp_info_t *th; + + KMP_DEBUG_ASSERT( p_last && p_lb && p_ub && p_st ); + KE_TRACE( 10, ("__kmp_team_static_init called (%d)\n", gtid)); + #ifdef KMP_DEBUG + { + const char * buff; + // create format specifiers before the debug output + buff = __kmp_str_format( "__kmp_team_static_init enter: T#%%d liter=%%d "\ + "iter=(%%%s, %%%s, %%%s) chunk %%%s; signed?<%s>\n", + traits_t< T >::spec, traits_t< T >::spec, traits_t< ST >::spec, + traits_t< ST >::spec, traits_t< T >::spec ); + KD_TRACE(100, ( buff, gtid, *p_last, *p_lb, *p_ub, *p_st, chunk ) ); + __kmp_str_free( &buff ); + } + #endif + + lower = *p_lb; + upper = *p_ub; + if( __kmp_env_consistency_check ) { + if( incr == 0 ) { + __kmp_error_construct( kmp_i18n_msg_CnsLoopIncrZeroProhibited, ct_pdo, loc ); + } + if( incr > 0 ? (upper < lower) : (lower < upper) ) { + // The loop is illegal. + // Some zero-trip loops maintained by compiler, e.g.: + // for(i=10;i<0;++i) // lower >= upper - run-time check + // for(i=0;i>10;--i) // lower <= upper - run-time check + // for(i=0;i>10;++i) // incr > 0 - compile-time check + // for(i=10;i<0;--i) // incr < 0 - compile-time check + // Compiler does not check the following illegal loops: + // for(i=0;i<10;i+=incr) // where incr<0 + // for(i=10;i>0;i-=incr) // where incr<0 + __kmp_error_construct( kmp_i18n_msg_CnsLoopIncrIllegal, ct_pdo, loc ); + } + } + th = __kmp_threads[gtid]; + KMP_DEBUG_ASSERT(th->th.th_teams_microtask); // we are in the teams construct + team = th->th.th_team; + #if OMP_40_ENABLED + nteams = th->th.th_teams_size.nteams; + #endif + team_id = team->t.t_master_tid; + KMP_DEBUG_ASSERT(nteams == team->t.t_parent->t.t_nproc); + + // compute trip count + if( incr == 1 ) { + trip_count = upper - lower + 1; + } else if(incr == -1) { + trip_count = lower - upper + 1; + } else { + trip_count = (ST)(upper - lower) / incr + 1; // cast to signed to cover incr<0 case + } + if( chunk < 1 ) + chunk = 1; + span = chunk * incr; + *p_st = span * nteams; + *p_lb = lower + (span * team_id); + *p_ub = *p_lb + span - incr; + if ( p_last != NULL ) + *p_last = (team_id == ((trip_count - 1)/(UT)chunk) % nteams); + // Correct upper bound if needed + if( incr > 0 ) { + if( *p_ub < *p_lb ) // overflow? + *p_ub = i_maxmin< T >::mx; + if( *p_ub > upper ) + *p_ub = upper; // tracker C73258 + } else { // incr < 0 + if( *p_ub > *p_lb ) + *p_ub = i_maxmin< T >::mn; + if( *p_ub < upper ) + *p_ub = upper; // tracker C73258 + } + #ifdef KMP_DEBUG + { + const char * buff; + // create format specifiers before the debug output + buff = __kmp_str_format( "__kmp_team_static_init exit: T#%%d team%%u liter=%%d "\ + "iter=(%%%s, %%%s, %%%s) chunk %%%s\n", + traits_t< T >::spec, traits_t< T >::spec, traits_t< ST >::spec, + traits_t< ST >::spec ); + KD_TRACE(100, ( buff, gtid, team_id, *p_last, *p_lb, *p_ub, *p_st, chunk ) ); + __kmp_str_free( &buff ); + } + #endif +} + //-------------------------------------------------------------------------------------- extern "C" { @@ -310,7 +677,7 @@ Each of the four functions here are identical apart from the argument types. The functions compute the upper and lower bounds and stride to be used for the set of iterations to be executed by the current thread from the statically scheduled loop that is described by the -initial values of the bround, stride, increment and chunk size. +initial values of the bounds, stride, increment and chunk size. @{ */ @@ -362,5 +729,155 @@ __kmpc_for_static_init_8u( ident_t *loc, kmp_int32 gtid, kmp_int32 schedtype, km @} */ +/*! +@ingroup WORK_SHARING +@param loc Source code location +@param gtid Global thread id of this thread +@param scheduleD Scheduling type for the distribute +@param scheduleL Scheduling type for the parallel loop +@param plastiter Pointer to the "last iteration" flag +@param plower Pointer to the lower bound +@param pupper Pointer to the upper bound of loop chunk +@param pupperD Pointer to the upper bound of dist_chunk +@param pstrideD Pointer to the stride for distribute +@param pstrideL Pointer to the stride for parallel loop +@param incr Loop increment +@param chunkD The chunk size for the distribute +@param chunkL The chunk size for the parallel loop + +Each of the four functions here are identical apart from the argument types. + +The functions compute the upper and lower bounds and strides to be used for the set of iterations +to be executed by the current thread from the statically scheduled loop that is described by the +initial values of the bounds, strides, increment and chunks for parallel loop and distribute +constructs. + +@{ +*/ +void +__kmpc_dist_for_static_init_4( + ident_t *loc, kmp_int32 gtid, kmp_int32 schedule, kmp_int32 *plastiter, + kmp_int32 *plower, kmp_int32 *pupper, kmp_int32 *pupperD, + kmp_int32 *pstride, kmp_int32 incr, kmp_int32 chunk ) +{ + __kmp_dist_for_static_init< kmp_int32 >( + loc, gtid, schedule, plastiter, plower, pupper, pupperD, pstride, incr, chunk ); +} + +/*! + See @ref __kmpc_dist_for_static_init_4 + */ +void +__kmpc_dist_for_static_init_4u( + ident_t *loc, kmp_int32 gtid, kmp_int32 schedule, kmp_int32 *plastiter, + kmp_uint32 *plower, kmp_uint32 *pupper, kmp_uint32 *pupperD, + kmp_int32 *pstride, kmp_int32 incr, kmp_int32 chunk ) +{ + __kmp_dist_for_static_init< kmp_uint32 >( + loc, gtid, schedule, plastiter, plower, pupper, pupperD, pstride, incr, chunk ); +} + +/*! + See @ref __kmpc_dist_for_static_init_4 + */ +void +__kmpc_dist_for_static_init_8( + ident_t *loc, kmp_int32 gtid, kmp_int32 schedule, kmp_int32 *plastiter, + kmp_int64 *plower, kmp_int64 *pupper, kmp_int64 *pupperD, + kmp_int64 *pstride, kmp_int64 incr, kmp_int64 chunk ) +{ + __kmp_dist_for_static_init< kmp_int64 >( + loc, gtid, schedule, plastiter, plower, pupper, pupperD, pstride, incr, chunk ); +} + +/*! + See @ref __kmpc_dist_for_static_init_4 + */ +void +__kmpc_dist_for_static_init_8u( + ident_t *loc, kmp_int32 gtid, kmp_int32 schedule, kmp_int32 *plastiter, + kmp_uint64 *plower, kmp_uint64 *pupper, kmp_uint64 *pupperD, + kmp_int64 *pstride, kmp_int64 incr, kmp_int64 chunk ) +{ + __kmp_dist_for_static_init< kmp_uint64 >( + loc, gtid, schedule, plastiter, plower, pupper, pupperD, pstride, incr, chunk ); +} +/*! +@} +*/ + +//----------------------------------------------------------------------------------------- +// Auxiliary routines for Distribute Parallel Loop construct implementation +// Transfer call to template< type T > +// __kmp_team_static_init( ident_t *loc, int gtid, +// int *p_last, T *lb, T *ub, ST *st, ST incr, ST chunk ) + +/*! +@ingroup WORK_SHARING +@{ +@param loc Source location +@param gtid Global thread id +@param p_last pointer to last iteration flag +@param p_lb pointer to Lower bound +@param p_ub pointer to Upper bound +@param p_st Step (or increment if you prefer) +@param incr Loop increment +@param chunk The chunk size to block with + +The functions compute the upper and lower bounds and stride to be used for the set of iterations +to be executed by the current team from the statically scheduled loop that is described by the +initial values of the bounds, stride, increment and chunk for the distribute construct as part of +composite distribute parallel loop construct. +These functions are all identical apart from the types of the arguments. +*/ + +void +__kmpc_team_static_init_4( + ident_t *loc, kmp_int32 gtid, kmp_int32 *p_last, + kmp_int32 *p_lb, kmp_int32 *p_ub, kmp_int32 *p_st, kmp_int32 incr, kmp_int32 chunk ) +{ + KMP_DEBUG_ASSERT( __kmp_init_serial ); + __kmp_team_static_init< kmp_int32 >( loc, gtid, p_last, p_lb, p_ub, p_st, incr, chunk ); +} + +/*! + See @ref __kmpc_team_static_init_4 + */ +void +__kmpc_team_static_init_4u( + ident_t *loc, kmp_int32 gtid, kmp_int32 *p_last, + kmp_uint32 *p_lb, kmp_uint32 *p_ub, kmp_int32 *p_st, kmp_int32 incr, kmp_int32 chunk ) +{ + KMP_DEBUG_ASSERT( __kmp_init_serial ); + __kmp_team_static_init< kmp_uint32 >( loc, gtid, p_last, p_lb, p_ub, p_st, incr, chunk ); +} + +/*! + See @ref __kmpc_team_static_init_4 + */ +void +__kmpc_team_static_init_8( + ident_t *loc, kmp_int32 gtid, kmp_int32 *p_last, + kmp_int64 *p_lb, kmp_int64 *p_ub, kmp_int64 *p_st, kmp_int64 incr, kmp_int64 chunk ) +{ + KMP_DEBUG_ASSERT( __kmp_init_serial ); + __kmp_team_static_init< kmp_int64 >( loc, gtid, p_last, p_lb, p_ub, p_st, incr, chunk ); +} + +/*! + See @ref __kmpc_team_static_init_4 + */ +void +__kmpc_team_static_init_8u( + ident_t *loc, kmp_int32 gtid, kmp_int32 *p_last, + kmp_uint64 *p_lb, kmp_uint64 *p_ub, kmp_int64 *p_st, kmp_int64 incr, kmp_int64 chunk ) +{ + KMP_DEBUG_ASSERT( __kmp_init_serial ); + __kmp_team_static_init< kmp_uint64 >( loc, gtid, p_last, p_lb, p_ub, p_st, incr, chunk ); +} +/*! +@} +*/ + } // extern "C" |
