void
__kmp_str_fname_init(
kmp_str_fname_t * fname,
char const * path
) {
fname->path = NULL;
fname->dir = NULL;
fname->base = NULL;
if ( path != NULL ) {
char * slash = NULL; // Pointer to the last character of dir.
char * base = NULL; // Pointer to the beginning of basename.
fname->path = __kmp_str_format( "%s", path );
// Original code used strdup() function to copy a string, but on Windows* OS Intel(R) 64 it
// causes assertioon id debug heap, so I had to replace strdup with __kmp_str_format().
if ( KMP_OS_WINDOWS ) {
__kmp_str_replace( fname->path, '\\', '/' );
}; // if
fname->dir = __kmp_str_format( "%s", fname->path );
slash = strrchr( fname->dir, '/' );
if ( KMP_OS_WINDOWS && slash == NULL ) { // On Windows* OS, if slash not found,
char first = TOLOWER( fname->dir[ 0 ] ); // look for drive.
if ( 'a' <= first && first <= 'z' && fname->dir[ 1 ] == ':' ) {
slash = & fname->dir[ 1 ];
}; // if
}; // if
base = ( slash == NULL ? fname->dir : slash + 1 );
fname->base = __kmp_str_format( "%s", base ); // Copy basename
* base = 0; // and truncate dir.
}; // if
} // kmp_str_fname_init
static
void
___kmp_env_blk_parse_string(
kmp_env_blk_t * block, // M: Env block to fill.
char const * env // I: String to parse.
) {
char const chr_delimiter = '|';
char const str_delimiter[] = { chr_delimiter, 0 };
char * bulk = NULL;
kmp_env_var_t * vars = NULL;
int count = 0; // Number of used elements in vars array.
int delimiters = 0; // Number of delimiters in input string.
// Copy original string, we will modify the copy.
bulk = __kmp_str_format( "%s", env );
// Loop thru all the vars in environment block. Count delimiters (maximum number of variables
// is number of delimiters plus one).
{
char const * ptr = bulk;
for ( ; ; ) {
ptr = strchr( ptr, chr_delimiter );
if ( ptr == NULL ) {
break;
}; // if
++ delimiters;
ptr += 1;
}; // forever
}
// Allocate vars array.
vars = (kmp_env_var_t *) allocate( ( delimiters + 1 ) * sizeof( kmp_env_var_t ) );
// Loop thru all the variables.
{
char * var; // Pointer to variable (both name and value).
char * name; // Pointer to name of variable.
char * value; // Pointer to value.
char * buf; // Buffer for __kmp_str_token() function.
var = __kmp_str_token( bulk, str_delimiter, & buf ); // Get the first var.
while ( var != NULL ) {
// Save found variable in vars array.
__kmp_str_split( var, '=', & name, & value );
KMP_DEBUG_ASSERT( count < delimiters + 1 );
vars[ count ].name = name;
vars[ count ].value = value;
++ count;
// Get the next var.
var = __kmp_str_token( NULL, str_delimiter, & buf );
}; // while
}
// Fill out result.
block->bulk = bulk;
block->vars = vars;
block->count = count;
}; // ___kmp_env_blk_parse_string
kmp_str_loc_t
__kmp_str_loc_init(
char const * psource,
int init_fname
) {
kmp_str_loc_t loc;
loc._bulk = NULL;
loc.file = NULL;
loc.func = NULL;
loc.line = 0;
loc.col = 0;
if ( psource != NULL ) {
char * str = NULL;
char * dummy = NULL;
char * line = NULL;
char * col = NULL;
// Copy psource to keep it intact.
loc._bulk = __kmp_str_format( "%s", psource );
// Parse psource string: ";file;func;line;col;;"
str = loc._bulk;
__kmp_str_split( str, ';', & dummy, & str );
__kmp_str_split( str, ';', & loc.file, & str );
__kmp_str_split( str, ';', & loc.func, & str );
__kmp_str_split( str, ';', & line, & str );
__kmp_str_split( str, ';', & col, & str );
// Convert line and col into numberic values.
if ( line != NULL ) {
loc.line = atoi( line );
if ( loc.line < 0 ) {
loc.line = 0;
}; // if
}; // if
if ( col != NULL ) {
loc.col = atoi( col );
if ( loc.col < 0 ) {
loc.col = 0;
}; // if
}; // if
}; // if
__kmp_str_fname_init( & loc.fname, init_fname ? loc.file : NULL );
return loc;
} // kmp_str_loc_init
kmp_msg_t
__kmp_msg_error_mesg(
char const * mesg
) {
kmp_msg_t msg;
msg.type = kmp_mt_syserr;
msg.num = 0;
msg.str = __kmp_str_format( "%s", mesg );
msg.len = KMP_STRLEN( msg.str );
return msg;
} // __kmp_msg_error_mesg
static void
__kmp_for_static_init(
ident_t *loc,
kmp_int32 global_tid,
kmp_int32 schedtype,
kmp_int32 *plastiter,
T *plower,
T *pupper,
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_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.. */
register kmp_int32 gtid = global_tid;
register kmp_uint32 tid;
register kmp_uint32 nth;
register UT trip_count;
register kmp_team_t *team;
register kmp_info_t *th = __kmp_threads[ gtid ];
#if OMPT_SUPPORT && OMPT_TRACE
ompt_team_info_t *team_info = __ompt_get_teaminfo(0, NULL);
ompt_task_info_t *task_info = __ompt_get_taskinfo(0);
#endif
KMP_DEBUG_ASSERT( plastiter && plower && pupper && pstride );
KE_TRACE( 10, ("__kmpc_for_static_init called (%d)\n", global_tid));
#ifdef KMP_DEBUG
{
const char * buff;
// create format specifiers before the debug output
buff = __kmp_str_format(
"__kmpc_for_static_init: T#%%d sched=%%d liter=%%d iter=(%%%s," \
" %%%s, %%%s) incr=%%%s chunk=%%%s signed?<%s>\n",
traits_t< T >::spec, traits_t< T >::spec, traits_t< ST >::spec,
traits_t< ST >::spec, traits_t< ST >::spec, traits_t< T >::spec );
KD_TRACE(100, ( buff, global_tid, schedtype, *plastiter,
*plower, *pupper, *pstride, incr, chunk ) );
__kmp_str_free( &buff );
}
#endif
if ( __kmp_env_consistency_check ) {
__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) ) {
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,\
upper=0,stride=1) - JPH June 23, 2009.
#ifdef KMP_DEBUG
{
const char * buff;
// create format specifiers before the debug output
buff = __kmp_str_format(
"__kmpc_for_static_init:(ZERO TRIP) liter=%%d lower=%%%s upper=%%%s stride = %%%s signed?<%s>, loc = %%s\n",
traits_t< T >::spec, traits_t< T >::spec, traits_t< ST >::spec, traits_t< T >::spec );
KD_TRACE(100, ( buff, *plastiter, *plower, *pupper, *pstride, loc->psource ) );
__kmp_str_free( &buff );
}
#endif
KE_TRACE( 10, ("__kmpc_for_static_init: T#%d return\n", global_tid ) );
#if OMPT_SUPPORT && OMPT_TRACE
if ((ompt_status == ompt_status_track_callback) &&
ompt_callbacks.ompt_callback(ompt_event_loop_begin)) {
ompt_callbacks.ompt_callback(ompt_event_loop_begin)(
team_info->parallel_id, task_info->task_id,
team_info->microtask);
}
#endif
return;
}
#if OMP_40_ENABLED
if ( schedtype > kmp_ord_upper ) {
// we are in DISTRIBUTE construct
schedtype += kmp_sch_static - kmp_distribute_static; // AC: convert to usual schedule type
tid = th->th.th_team->t.t_master_tid;
team = th->th.th_team->t.t_parent;
} else
#endif
{
tid = __kmp_tid_from_gtid( global_tid );
team = th->th.th_team;
}
/* determine if "for" loop is an active worksharing construct */
if ( team -> t.t_serialized ) {
/* serialized parallel, each thread executes whole iteration space */
if( plastiter != NULL )
*plastiter = TRUE;
/* leave pupper and plower set to entire iteration space */
*pstride = (incr > 0) ? (*pupper - *plower + 1) : (-(*plower - *pupper + 1));
#ifdef KMP_DEBUG
{
const char * buff;
// create format specifiers before the debug output
buff = __kmp_str_format(
"__kmpc_for_static_init: (serial) liter=%%d lower=%%%s upper=%%%s stride = %%%s\n",
traits_t< T >::spec, traits_t< T >::spec, traits_t< ST >::spec );
KD_TRACE(100, ( buff, *plastiter, *plower, *pupper, *pstride ) );
__kmp_str_free( &buff );
}
#endif
KE_TRACE( 10, ("__kmpc_for_static_init: T#%d return\n", global_tid ) );
#if OMPT_SUPPORT && OMPT_TRACE
if ((ompt_status == ompt_status_track_callback) &&
ompt_callbacks.ompt_callback(ompt_event_loop_begin)) {
ompt_callbacks.ompt_callback(ompt_event_loop_begin)(
team_info->parallel_id, task_info->task_id,
team_info->microtask);
}
#endif
return;
}
nth = team->t.t_nproc;
if ( nth == 1 ) {
if( plastiter != NULL )
*plastiter = TRUE;
*pstride = (incr > 0) ? (*pupper - *plower + 1) : (-(*plower - *pupper + 1));
#ifdef KMP_DEBUG
{
const char * buff;
// create format specifiers before the debug output
buff = __kmp_str_format(
"__kmpc_for_static_init: (serial) liter=%%d lower=%%%s upper=%%%s stride = %%%s\n",
traits_t< T >::spec, traits_t< T >::spec, traits_t< ST >::spec );
KD_TRACE(100, ( buff, *plastiter, *plower, *pupper, *pstride ) );
__kmp_str_free( &buff );
}
#endif
KE_TRACE( 10, ("__kmpc_for_static_init: T#%d return\n", global_tid ) );
#if OMPT_SUPPORT && OMPT_TRACE
if ((ompt_status == ompt_status_track_callback) &&
ompt_callbacks.ompt_callback(ompt_event_loop_begin)) {
ompt_callbacks.ompt_callback(ompt_event_loop_begin)(
team_info->parallel_id, task_info->task_id,
team_info->microtask);
}
#endif
return;
}
/* compute trip count */
if ( incr == 1 ) {
trip_count = *pupper - *plower + 1;
} else if (incr == -1) {
trip_count = *plower - *pupper + 1;
} else {
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 ) {
__kmp_error_construct( kmp_i18n_msg_CnsIterationRangeTooLarge, ct_pdo, loc );
}
}
/* compute remaining parameters */
switch ( schedtype ) {
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;
}
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 );
if( plastiter != NULL )
*plastiter = ( tid == nth - 1 );
} else {
register T big_chunk_inc_count = ( trip_count/nth +
( ( trip_count % nth ) ? 1 : 0) ) * incr;
register T old_upper = *pupper;
KMP_DEBUG_ASSERT( __kmp_static == kmp_sch_static_greedy );
// Unknown static scheduling type.
*plower += tid * big_chunk_inc_count;
*pupper = *plower + big_chunk_inc_count - incr;
if ( incr > 0 ) {
if( *pupper < *plower )
*pupper = i_maxmin< T >::mx;
if( plastiter != NULL )
*plastiter = *plower <= old_upper && *pupper > old_upper - incr;
if ( *pupper > old_upper ) *pupper = old_upper; // tracker C73258
} else {
if( *pupper > *plower )
*pupper = i_maxmin< T >::mn;
if( plastiter != NULL )
*plastiter = *plower >= old_upper && *pupper < old_upper - incr;
if ( *pupper < old_upper ) *pupper = old_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 )
*plastiter = (tid == ((trip_count - 1)/( UT )chunk) % nth);
break;
}
default:
KMP_ASSERT2( 0, "__kmpc_for_static_init: unknown scheduling type" );
break;
}
#if USE_ITT_BUILD
// Report loop metadata
if ( KMP_MASTER_TID(tid) && __itt_metadata_add_ptr && __kmp_forkjoin_frames_mode == 3 &&
#if OMP_40_ENABLED
th->th.th_teams_microtask == NULL &&
#endif
team->t.t_active_level == 1 )
{
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;
// create format specifiers before the debug output
buff = __kmp_str_format(
"__kmpc_for_static_init: liter=%%d lower=%%%s upper=%%%s stride = %%%s signed?<%s>\n",
traits_t< T >::spec, traits_t< T >::spec, traits_t< ST >::spec, traits_t< T >::spec );
KD_TRACE(100, ( buff, *plastiter, *plower, *pupper, *pstride ) );
__kmp_str_free( &buff );
}
#endif
KE_TRACE( 10, ("__kmpc_for_static_init: T#%d return\n", global_tid ) );
#if OMPT_SUPPORT && OMPT_TRACE
if ((ompt_status == ompt_status_track_callback) &&
ompt_callbacks.ompt_callback(ompt_event_loop_begin)) {
ompt_callbacks.ompt_callback(ompt_event_loop_begin)(
team_info->parallel_id, task_info->task_id, team_info->microtask);
}
#endif
return;
}
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
}
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;
}
static
char *
sys_error(
int err
) {
char * message = NULL;
#if KMP_OS_WINDOWS
LPVOID buffer = NULL;
int len;
DWORD rc;
rc =
FormatMessage(
FORMAT_MESSAGE_ALLOCATE_BUFFER | FORMAT_MESSAGE_FROM_SYSTEM,
NULL,
err,
MAKELANGID( LANG_NEUTRAL, SUBLANG_DEFAULT ), // Default language.
(LPTSTR) & buffer,
0,
NULL
);
if ( rc > 0 ) {
// Message formatted. Copy it (so we can free it later with normal free().
message = __kmp_str_format( "%s", (char *) buffer );
len = ___strip_crs( message ); // Delete carriage returns if any.
// Strip trailing newlines.
while ( len > 0 && message[ len - 1 ] == '\n' ) {
-- len;
}; // while
message[ len ] = 0;
} else {
// FormatMessage() failed to format system error message. GetLastError() would give us
// error code, which we would convert to message... this it dangerous recursion, which
// cannot clarify original error, so we will not even start it.
}; // if
if ( buffer != NULL ) {
LocalFree( buffer );
}; // if
#else // Non-Windows* OS: Linux* OS or OS X*
/*
There are 2 incompatible versions of strerror_r:
char * strerror_r( int, char *, size_t ); // GNU version
int strerror_r( int, char *, size_t ); // XSI version
*/
#if defined(__GLIBC__) && defined(_GNU_SOURCE)
// GNU version of strerror_r.
char buffer[ 2048 ];
char * const err_msg = strerror_r( err, buffer, sizeof( buffer ) );
// Do not eliminate this assignment to temporary variable, otherwise compiler would
// not issue warning if strerror_r() returns `int' instead of expected `char *'.
message = __kmp_str_format( "%s", err_msg );
#else // OS X*, FreeBSD* etc.
// XSI version of strerror_r.
int size = 2048;
// TODO: Add checking result of malloc().
char * buffer = (char *) KMP_INTERNAL_MALLOC( size );
int rc;
if (buffer == NULL) {
KMP_FATAL(MemoryAllocFailed);
}
rc = strerror_r( err, buffer, size );
if ( rc == -1 ) {
rc = errno; // XSI version sets errno.
}; // if
while ( rc == ERANGE ) { // ERANGE means the buffer is too small.
KMP_INTERNAL_FREE( buffer );
size *= 2;
buffer = (char *) KMP_INTERNAL_MALLOC( size );
if (buffer == NULL) {
KMP_FATAL(MemoryAllocFailed);
}
rc = strerror_r( err, buffer, size );
if ( rc == -1 ) {
rc = errno; // XSI version sets errno.
}; // if
}; // while
if ( rc == 0 ) {
message = buffer;
} else {
// Buffer is unused. Free it.
KMP_INTERNAL_FREE( buffer );
}; // if
#endif
#endif /* KMP_OS_WINDOWS */
if ( message == NULL ) {
// TODO: I18n this message.
message = __kmp_str_format( "%s", "(No system error message available)" );
}; // if
return message;
} // sys_error
static void
__kmp_for_static_init(
ident_t *loc,
kmp_int32 global_tid,
kmp_int32 schedtype,
kmp_int32 *plastiter,
T *plower,
T *pupper,
typename traits_t< T >::signed_t *pstride,
typename traits_t< T >::signed_t incr,
typename traits_t< T >::signed_t chunk
) {
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.. */
register kmp_int32 gtid = global_tid;
register kmp_uint32 tid;
register kmp_uint32 nth;
register UT trip_count;
register kmp_team_t *team;
KE_TRACE( 10, ("__kmpc_for_static_init called (%d)\n", global_tid));
#ifdef KMP_DEBUG
{
const char * buff;
// create format specifiers before the debug output
buff = __kmp_str_format(
"__kmpc_for_static_init: T#%%d sched=%%d liter=%%d iter=(%%%s," \
" %%%s, %%%s) incr=%%%s chunk=%%%s signed?<%s>\n",
traits_t< T >::spec, traits_t< T >::spec, traits_t< ST >::spec,
traits_t< ST >::spec, traits_t< ST >::spec, traits_t< T >::spec );
KD_TRACE(100, ( buff, global_tid, schedtype, *plastiter,
*plower, *pupper, *pstride, incr, chunk ) );
__kmp_str_free( &buff );
}
#endif
if ( __kmp_env_consistency_check ) {
__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;
/* 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,\
upper=0,stride=1) - JPH June 23, 2009.
#ifdef KMP_DEBUG
{
const char * buff;
// create format specifiers before the debug output
buff = __kmp_str_format(
"__kmpc_for_static_init:(ZERO TRIP) liter=%%d lower=%%%s upper=%%%s stride = %%%s signed?<%s>, loc = %%s\n",
traits_t< T >::spec, traits_t< T >::spec, traits_t< ST >::spec, traits_t< T >::spec );
KD_TRACE(100, ( buff, *plastiter, *plower, *pupper, *pstride, loc->psource ) );
__kmp_str_free( &buff );
}
#endif
KE_TRACE( 10, ("__kmpc_for_static_init: T#%d return\n", global_tid ) );
return;
}
static void __kmp_for_static_init(ident_t *loc, kmp_int32 global_tid,
kmp_int32 schedtype, kmp_int32 *plastiter,
T *plower, T *pupper,
typename traits_t<T>::signed_t *pstride,
typename traits_t<T>::signed_t incr,
typename traits_t<T>::signed_t chunk
#if OMPT_SUPPORT && OMPT_OPTIONAL
,
void *codeptr
#endif
) {
KMP_COUNT_BLOCK(OMP_FOR_static);
KMP_TIME_PARTITIONED_BLOCK(FOR_static_scheduling);
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.. */
kmp_int32 gtid = global_tid;
kmp_uint32 tid;
kmp_uint32 nth;
UT trip_count;
kmp_team_t *team;
kmp_info_t *th = __kmp_threads[gtid];
#if OMPT_SUPPORT && OMPT_OPTIONAL
ompt_team_info_t *team_info = NULL;
ompt_task_info_t *task_info = NULL;
ompt_work_type_t ompt_work_type = ompt_work_loop;
static kmp_int8 warn = 0;
if (ompt_enabled.ompt_callback_work) {
// Only fully initialize variables needed by OMPT if OMPT is enabled.
team_info = __ompt_get_teaminfo(0, NULL);
task_info = __ompt_get_task_info_object(0);
// Determine workshare type
if (loc != NULL) {
if ((loc->flags & KMP_IDENT_WORK_LOOP) != 0) {
ompt_work_type = ompt_work_loop;
} else if ((loc->flags & KMP_IDENT_WORK_SECTIONS) != 0) {
ompt_work_type = ompt_work_sections;
} else if ((loc->flags & KMP_IDENT_WORK_DISTRIBUTE) != 0) {
ompt_work_type = ompt_work_distribute;
} else {
kmp_int8 bool_res =
KMP_COMPARE_AND_STORE_ACQ8(&warn, (kmp_int8)0, (kmp_int8)1);
if (bool_res)
KMP_WARNING(OmptOutdatedWorkshare);
}
KMP_DEBUG_ASSERT(ompt_work_type);
}
}
#endif
KMP_DEBUG_ASSERT(plastiter && plower && pupper && pstride);
KE_TRACE(10, ("__kmpc_for_static_init called (%d)\n", global_tid));
#ifdef KMP_DEBUG
{
char *buff;
// create format specifiers before the debug output
buff = __kmp_str_format(
"__kmpc_for_static_init: T#%%d sched=%%d liter=%%d iter=(%%%s,"
" %%%s, %%%s) incr=%%%s chunk=%%%s signed?<%s>\n",
traits_t<T>::spec, traits_t<T>::spec, traits_t<ST>::spec,
traits_t<ST>::spec, traits_t<ST>::spec, traits_t<T>::spec);
KD_TRACE(100, (buff, global_tid, schedtype, *plastiter, *plower, *pupper,
*pstride, incr, chunk));
__kmp_str_free(&buff);
}
#endif
if (__kmp_env_consistency_check) {
__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)) {
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--))
// THE LINE COMMENTED ABOVE CAUSED shape2F/h_tests_1.f TO HAVE A FAILURE
// ON A ZERO-TRIP LOOP (lower=1, upper=0,stride=1) - JPH June 23, 2009.
#ifdef KMP_DEBUG
{
char *buff;
// create format specifiers before the debug output
buff = __kmp_str_format("__kmpc_for_static_init:(ZERO TRIP) liter=%%d "
"lower=%%%s upper=%%%s stride = %%%s "
"signed?<%s>, loc = %%s\n",
traits_t<T>::spec, traits_t<T>::spec,
traits_t<ST>::spec, traits_t<T>::spec);
KD_TRACE(100,
(buff, *plastiter, *plower, *pupper, *pstride, loc->psource));
__kmp_str_free(&buff);
}
#endif
KE_TRACE(10, ("__kmpc_for_static_init: T#%d return\n", global_tid));
#if OMPT_SUPPORT && OMPT_OPTIONAL
if (ompt_enabled.ompt_callback_work) {
ompt_callbacks.ompt_callback(ompt_callback_work)(
ompt_work_type, ompt_scope_begin, &(team_info->parallel_data),
&(task_info->task_data), 0, codeptr);
}
#endif
KMP_COUNT_VALUE(FOR_static_iterations, 0);
return;
}
#if OMP_40_ENABLED
// Although there are schedule enumerations above kmp_ord_upper which are not
// schedules for "distribute", the only ones which are useful are dynamic, so
// cannot be seen here, since this codepath is only executed for static
// schedules.
if (schedtype > kmp_ord_upper) {
// we are in DISTRIBUTE construct
schedtype += kmp_sch_static -
kmp_distribute_static; // AC: convert to usual schedule type
tid = th->th.th_team->t.t_master_tid;
team = th->th.th_team->t.t_parent;
} else
#endif
{
tid = __kmp_tid_from_gtid(global_tid);
team = th->th.th_team;
}
/* determine if "for" loop is an active worksharing construct */
if (team->t.t_serialized) {
/* serialized parallel, each thread executes whole iteration space */
if (plastiter != NULL)
*plastiter = TRUE;
/* leave pupper and plower set to entire iteration space */
*pstride =
(incr > 0) ? (*pupper - *plower + 1) : (-(*plower - *pupper + 1));
#ifdef KMP_DEBUG
{
char *buff;
// create format specifiers before the debug output
buff = __kmp_str_format("__kmpc_for_static_init: (serial) liter=%%d "
"lower=%%%s upper=%%%s stride = %%%s\n",
traits_t<T>::spec, traits_t<T>::spec,
traits_t<ST>::spec);
KD_TRACE(100, (buff, *plastiter, *plower, *pupper, *pstride));
__kmp_str_free(&buff);
}
#endif
KE_TRACE(10, ("__kmpc_for_static_init: T#%d return\n", global_tid));
#if OMPT_SUPPORT && OMPT_OPTIONAL
if (ompt_enabled.ompt_callback_work) {
ompt_callbacks.ompt_callback(ompt_callback_work)(
ompt_work_type, ompt_scope_begin, &(team_info->parallel_data),
&(task_info->task_data), *pstride, codeptr);
}
#endif
return;
}
nth = team->t.t_nproc;
if (nth == 1) {
if (plastiter != NULL)
*plastiter = TRUE;
*pstride =
(incr > 0) ? (*pupper - *plower + 1) : (-(*plower - *pupper + 1));
#ifdef KMP_DEBUG
{
char *buff;
// create format specifiers before the debug output
buff = __kmp_str_format("__kmpc_for_static_init: (serial) liter=%%d "
"lower=%%%s upper=%%%s stride = %%%s\n",
traits_t<T>::spec, traits_t<T>::spec,
traits_t<ST>::spec);
KD_TRACE(100, (buff, *plastiter, *plower, *pupper, *pstride));
__kmp_str_free(&buff);
}
#endif
KE_TRACE(10, ("__kmpc_for_static_init: T#%d return\n", global_tid));
#if OMPT_SUPPORT && OMPT_OPTIONAL
if (ompt_enabled.ompt_callback_work) {
ompt_callbacks.ompt_callback(ompt_callback_work)(
ompt_work_type, ompt_scope_begin, &(team_info->parallel_data),
&(task_info->task_data), *pstride, codeptr);
}
#endif
return;
}
/* compute trip count */
if (incr == 1) {
trip_count = *pupper - *plower + 1;
} else if (incr == -1) {
trip_count = *plower - *pupper + 1;
} else if (incr > 0) {
// upper-lower can exceed the limit of signed type
trip_count = (UT)(*pupper - *plower) / incr + 1;
} else {
trip_count = (UT)(*plower - *pupper) / (-incr) + 1;
}
if (__kmp_env_consistency_check) {
/* tripcount overflow? */
if (trip_count == 0 && *pupper != *plower) {
__kmp_error_construct(kmp_i18n_msg_CnsIterationRangeTooLarge, ct_pdo,
loc);
}
}
KMP_COUNT_VALUE(FOR_static_iterations, trip_count);
/* compute remaining parameters */
switch (schedtype) {
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;
}
if (plastiter != NULL)
*plastiter = (tid == trip_count - 1);
} else {
if (__kmp_static == kmp_sch_static_balanced) {
UT small_chunk = trip_count / nth;
UT extras = trip_count % nth;
*plower += incr * (tid * small_chunk + (tid < extras ? tid : extras));
*pupper = *plower + small_chunk * incr - (tid < extras ? 0 : incr);
if (plastiter != NULL)
*plastiter = (tid == nth - 1);
} else {
T big_chunk_inc_count =
(trip_count / nth + ((trip_count % nth) ? 1 : 0)) * incr;
T old_upper = *pupper;
KMP_DEBUG_ASSERT(__kmp_static == kmp_sch_static_greedy);
// Unknown static scheduling type.
*plower += tid * big_chunk_inc_count;
*pupper = *plower + big_chunk_inc_count - incr;
if (incr > 0) {
if (*pupper < *plower)
*pupper = traits_t<T>::max_value;
if (plastiter != NULL)
*plastiter = *plower <= old_upper && *pupper > old_upper - incr;
if (*pupper > old_upper)
*pupper = old_upper; // tracker C73258
} else {
if (*pupper > *plower)
*pupper = traits_t<T>::min_value;
if (plastiter != NULL)
*plastiter = *plower >= old_upper && *pupper < old_upper - incr;
if (*pupper < old_upper)
*pupper = old_upper; // tracker C73258
}
}
}
*pstride = trip_count;
break;
}
case kmp_sch_static_chunked: {
ST span;
if (chunk < 1) {
chunk = 1;
}
span = chunk * incr;
*pstride = span * nth;
*plower = *plower + (span * tid);
*pupper = *plower + span - incr;
if (plastiter != NULL)
*plastiter = (tid == ((trip_count - 1) / (UT)chunk) % nth);
break;
}
#if OMP_45_ENABLED
case kmp_sch_static_balanced_chunked: {
T old_upper = *pupper;
// round up to make sure the chunk is enough to cover all iterations
UT span = (trip_count + nth - 1) / nth;
// perform chunk adjustment
chunk = (span + chunk - 1) & ~(chunk - 1);
span = chunk * incr;
*plower = *plower + (span * tid);
*pupper = *plower + span - incr;
if (incr > 0) {
if (*pupper > old_upper)
*pupper = old_upper;
} else if (*pupper < old_upper)
*pupper = old_upper;
if (plastiter != NULL)
*plastiter = (tid == ((trip_count - 1) / (UT)chunk));
break;
}
#endif
default:
KMP_ASSERT2(0, "__kmpc_for_static_init: unknown scheduling type");
break;
}
#if USE_ITT_BUILD
// Report loop metadata
if (KMP_MASTER_TID(tid) && __itt_metadata_add_ptr &&
__kmp_forkjoin_frames_mode == 3 &&
#if OMP_40_ENABLED
th->th.th_teams_microtask == NULL &&
#endif
team->t.t_active_level == 1) {
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
{
char *buff;
// create format specifiers before the debug output
buff = __kmp_str_format("__kmpc_for_static_init: liter=%%d lower=%%%s "
"upper=%%%s stride = %%%s signed?<%s>\n",
traits_t<T>::spec, traits_t<T>::spec,
traits_t<ST>::spec, traits_t<T>::spec);
KD_TRACE(100, (buff, *plastiter, *plower, *pupper, *pstride));
__kmp_str_free(&buff);
}
#endif
KE_TRACE(10, ("__kmpc_for_static_init: T#%d return\n", global_tid));
#if OMPT_SUPPORT && OMPT_OPTIONAL
if (ompt_enabled.ompt_callback_work) {
ompt_callbacks.ompt_callback(ompt_callback_work)(
ompt_work_type, ompt_scope_begin, &(team_info->parallel_data),
&(task_info->task_data), trip_count, codeptr);
}
#endif
return;
}
static ompt_start_tool_result_t *
ompt_try_start_tool(unsigned int omp_version, const char *runtime_version) {
ompt_start_tool_result_t *ret = NULL;
ompt_start_tool_t start_tool = NULL;
#if KMP_OS_WINDOWS
// Cannot use colon to describe a list of absolute paths on Windows
const char *sep = ";";
#else
const char *sep = ":";
#endif
#if KMP_OS_DARWIN
// Try in the current address space
ret = ompt_tool_darwin(omp_version, runtime_version);
#elif OMPT_HAVE_WEAK_ATTRIBUTE
ret = ompt_start_tool(omp_version, runtime_version);
#elif OMPT_HAVE_PSAPI
ret = ompt_tool_windows(omp_version, runtime_version);
#else
#error Activation of OMPT is not supported on this platform.
#endif
if (ret)
return ret;
// Try tool-libraries-var ICV
const char *tool_libs = getenv("OMP_TOOL_LIBRARIES");
if (tool_libs) {
char *libs = __kmp_str_format("%s", tool_libs);
char *buf;
char *fname = __kmp_str_token(libs, sep, &buf);
while (fname) {
#if KMP_OS_UNIX
void *h = dlopen(fname, RTLD_LAZY);
if (h) {
start_tool = (ompt_start_tool_t)dlsym(h, "ompt_start_tool");
#elif KMP_OS_WINDOWS
HMODULE h = LoadLibrary(fname);
if (h) {
start_tool = (ompt_start_tool_t)GetProcAddress(h, "ompt_start_tool");
#else
#error Activation of OMPT is not supported on this platform.
#endif
if (start_tool && (ret = (*start_tool)(omp_version, runtime_version)))
break;
}
fname = __kmp_str_token(NULL, sep, &buf);
}
__kmp_str_free(&libs);
}
return ret;
}
void ompt_pre_init() {
//--------------------------------------------------
// Execute the pre-initialization logic only once.
//--------------------------------------------------
static int ompt_pre_initialized = 0;
if (ompt_pre_initialized)
return;
ompt_pre_initialized = 1;
//--------------------------------------------------
// Use a tool iff a tool is enabled and available.
//--------------------------------------------------
const char *ompt_env_var = getenv("OMP_TOOL");
tool_setting_e tool_setting = omp_tool_error;
if (!ompt_env_var || !strcmp(ompt_env_var, ""))
tool_setting = omp_tool_unset;
else if (OMPT_STR_MATCH(ompt_env_var, "disabled"))
tool_setting = omp_tool_disabled;
else if (OMPT_STR_MATCH(ompt_env_var, "enabled"))
tool_setting = omp_tool_enabled;
#if OMPT_DEBUG
printf("ompt_pre_init(): tool_setting = %d\n", tool_setting);
#endif
switch (tool_setting) {
case omp_tool_disabled:
break;
case omp_tool_unset:
case omp_tool_enabled:
//--------------------------------------------------
// Load tool iff specified in environment variable
//--------------------------------------------------
ompt_start_tool_result =
ompt_try_start_tool(__kmp_openmp_version, ompt_get_runtime_version());
memset(&ompt_enabled, 0, sizeof(ompt_enabled));
break;
case omp_tool_error:
fprintf(stderr, "Warning: OMP_TOOL has invalid value \"%s\".\n"
" legal values are (NULL,\"\",\"disabled\","
"\"enabled\").\n",
ompt_env_var);
break;
}
#if OMPT_DEBUG
printf("ompt_pre_init(): ompt_enabled = %d\n", ompt_enabled);
#endif
}
void ompt_post_init() {
//--------------------------------------------------
// Execute the post-initialization logic only once.
//--------------------------------------------------
static int ompt_post_initialized = 0;
if (ompt_post_initialized)
return;
ompt_post_initialized = 1;
//--------------------------------------------------
// Initialize the tool if so indicated.
//--------------------------------------------------
if (ompt_start_tool_result) {
ompt_enabled.enabled = !!ompt_start_tool_result->initialize(
ompt_fn_lookup, &(ompt_start_tool_result->tool_data));
if (!ompt_enabled.enabled) {
// tool not enabled, zero out the bitmap, and done
memset(&ompt_enabled, 0, sizeof(ompt_enabled));
return;
}
ompt_thread_t *root_thread = ompt_get_thread();
ompt_set_thread_state(root_thread, omp_state_overhead);
if (ompt_enabled.ompt_callback_thread_begin) {
ompt_callbacks.ompt_callback(ompt_callback_thread_begin)(
ompt_thread_initial, __ompt_get_thread_data_internal());
}
ompt_data_t *task_data;
__ompt_get_task_info_internal(0, NULL, &task_data, NULL, NULL, NULL);
if (ompt_enabled.ompt_callback_task_create) {
ompt_callbacks.ompt_callback(ompt_callback_task_create)(
NULL, NULL, task_data, ompt_task_initial, 0, NULL);
}
ompt_set_thread_state(root_thread, omp_state_work_serial);
}
}
void ompt_fini() {
if (ompt_enabled.enabled) {
ompt_start_tool_result->finalize(&(ompt_start_tool_result->tool_data));
}
memset(&ompt_enabled, 0, sizeof(ompt_enabled));
}
/*****************************************************************************
* interface operations
****************************************************************************/
/*****************************************************************************
* state
****************************************************************************/
OMPT_API_ROUTINE int ompt_enumerate_states(int current_state, int *next_state,
const char **next_state_name) {
const static int len = sizeof(omp_state_info) / sizeof(omp_state_info_t);
int i = 0;
for (i = 0; i < len - 1; i++) {
if (omp_state_info[i].state_id == current_state) {
*next_state = omp_state_info[i + 1].state_id;
*next_state_name = omp_state_info[i + 1].state_name;
return 1;
}
}
return 0;
}
OMPT_API_ROUTINE int ompt_enumerate_mutex_impls(int current_impl,
int *next_impl,
const char **next_impl_name) {
const static int len =
sizeof(kmp_mutex_impl_info) / sizeof(kmp_mutex_impl_info_t);
int i = 0;
for (i = 0; i < len - 1; i++) {
if (kmp_mutex_impl_info[i].id != current_impl)
continue;
*next_impl = kmp_mutex_impl_info[i + 1].id;
*next_impl_name = kmp_mutex_impl_info[i + 1].name;
return 1;
}
return 0;
}
/*****************************************************************************
* callbacks
****************************************************************************/
OMPT_API_ROUTINE int ompt_set_callback(ompt_callbacks_t which,
ompt_callback_t callback) {
switch (which) {
#define ompt_event_macro(event_name, callback_type, event_id) \
case event_name: \
if (ompt_event_implementation_status(event_name)) { \
ompt_callbacks.ompt_callback(event_name) = (callback_type)callback; \
ompt_enabled.event_name = (callback != 0); \
} \
if (callback) \
return ompt_event_implementation_status(event_name); \
else \
return ompt_set_always;
FOREACH_OMPT_EVENT(ompt_event_macro)
#undef ompt_event_macro
default:
return ompt_set_error;
}
}
OMPT_API_ROUTINE int ompt_get_callback(ompt_callbacks_t which,
ompt_callback_t *callback) {
switch (which) {
#define ompt_event_macro(event_name, callback_type, event_id) \
case event_name: \
if (ompt_event_implementation_status(event_name)) { \
ompt_callback_t mycb = \
(ompt_callback_t)ompt_callbacks.ompt_callback(event_name); \
if (mycb) { \
*callback = mycb; \
return ompt_get_callback_success; \
} \
} \
return ompt_get_callback_failure;
FOREACH_OMPT_EVENT(ompt_event_macro)
#undef ompt_event_macro
default:
return ompt_get_callback_failure;
}
}
/*****************************************************************************
* parallel regions
****************************************************************************/
OMPT_API_ROUTINE int ompt_get_parallel_info(int ancestor_level,
ompt_data_t **parallel_data,
int *team_size) {
return __ompt_get_parallel_info_internal(ancestor_level, parallel_data,
team_size);
}
OMPT_API_ROUTINE omp_state_t ompt_get_state(omp_wait_id_t *wait_id) {
omp_state_t thread_state = __ompt_get_state_internal(wait_id);
if (thread_state == omp_state_undefined) {
thread_state = omp_state_work_serial;
}
return thread_state;
}
