3bc75533d1
With strict: modifier on these clauses, the standard is explicit about how many iterations (and which) each generated task of taskloop directive should contain. For num_tasks it actually matches what we were already implementing, but for grainsize it does not (and even violates the old rule - without strict it requires that the number of iterations (unspecified which exactly) handled by each generated task is >= grainsize argument and < 2 * grainsize argument, with strict: it requires that each generated task handles exactly == grainsize argument iterations, except for the generated task handling the last iteration which can handles <= grainsize iterations). The following patch implements it for C and C++. 2021-08-23 Jakub Jelinek <jakub@redhat.com> gcc/ * tree.h (OMP_CLAUSE_GRAINSIZE_STRICT): Define. (OMP_CLAUSE_NUM_TASKS_STRICT): Define. * tree-pretty-print.c (dump_omp_clause) <case OMP_CLAUSE_GRAINSIZE, case OMP_CLAUSE_NUM_TASKS>: Print strict: modifier. * omp-expand.c (expand_task_call): Use GOMP_TASK_FLAG_STRICT in iflags if either grainsize or num_tasks clause has the strict modifier. gcc/c/ * c-parser.c (c_parser_omp_clause_num_tasks, c_parser_omp_clause_grainsize): Parse the optional strict: modifier. gcc/cp/ * parser.c (cp_parser_omp_clause_num_tasks, cp_parser_omp_clause_grainsize): Parse the optional strict: modifier. include/ * gomp-constants.h (GOMP_TASK_FLAG_STRICT): Define. libgomp/ * taskloop.c (GOMP_taskloop): Handle GOMP_TASK_FLAG_STRICT. * testsuite/libgomp.c-c++-common/taskloop-4.c (main): Fix up comment. * testsuite/libgomp.c-c++-common/taskloop-5.c: New test.
99 lines
2.2 KiB
C
99 lines
2.2 KiB
C
/* { dg-do run } */
|
|
/* { dg-options "-O2" } */
|
|
|
|
int u[64], v;
|
|
|
|
__attribute__((noinline, noclone)) int
|
|
test (int a, int b, int c, int d, void (*fn) (int, int, int, int),
|
|
int *num_tasks, int *min_iters, int *max_iters)
|
|
{
|
|
int i, t = 0;
|
|
__builtin_memset (u, 0, sizeof u);
|
|
v = 0;
|
|
fn (a, b, c, d);
|
|
*min_iters = 0;
|
|
*max_iters = 0;
|
|
*num_tasks = v;
|
|
if (v)
|
|
{
|
|
*min_iters = u[0];
|
|
*max_iters = u[0];
|
|
t = u[0];
|
|
for (i = 1; i < v; i++)
|
|
{
|
|
if (*min_iters > u[i])
|
|
*min_iters = u[i];
|
|
if (*max_iters < u[i])
|
|
*max_iters = u[i];
|
|
t += u[i];
|
|
}
|
|
}
|
|
return t;
|
|
}
|
|
|
|
void
|
|
grainsize (int a, int b, int c, int d)
|
|
{
|
|
int i, j = 0, k = 0;
|
|
#pragma omp taskloop firstprivate (j, k) grainsize(d)
|
|
for (i = a; i < b; i += c)
|
|
{
|
|
if (j == 0)
|
|
{
|
|
#pragma omp atomic capture
|
|
k = v++;
|
|
if (k >= 64)
|
|
__builtin_abort ();
|
|
}
|
|
u[k] = ++j;
|
|
}
|
|
}
|
|
|
|
void
|
|
num_tasks (int a, int b, int c, int d)
|
|
{
|
|
int i, j = 0, k = 0;
|
|
#pragma omp taskloop firstprivate (j, k) num_tasks(d)
|
|
for (i = a; i < b; i += c)
|
|
{
|
|
if (j == 0)
|
|
{
|
|
#pragma omp atomic capture
|
|
k = v++;
|
|
if (k >= 64)
|
|
__builtin_abort ();
|
|
}
|
|
u[k] = ++j;
|
|
}
|
|
}
|
|
|
|
int
|
|
main ()
|
|
{
|
|
#pragma omp parallel
|
|
#pragma omp single
|
|
{
|
|
int min_iters, max_iters, ntasks;
|
|
/* If grainsize is present, # of task loop iters is >= grainsize && < 2 * grainsize,
|
|
unless # of loop iterations is smaller than grainsize. */
|
|
if (test (0, 79, 1, 17, grainsize, &ntasks, &min_iters, &max_iters) != 79
|
|
|| min_iters < 17 || max_iters >= 17 * 2)
|
|
__builtin_abort ();
|
|
if (test (-49, 2541, 7, 28, grainsize, &ntasks, &min_iters, &max_iters) != 370
|
|
|| min_iters < 28 || max_iters >= 28 * 2)
|
|
__builtin_abort ();
|
|
if (test (7, 21, 2, 15, grainsize, &ntasks, &min_iters, &max_iters) != 7
|
|
|| ntasks != 1 || min_iters != 7 || max_iters != 7)
|
|
__builtin_abort ();
|
|
/* If num_tasks is present, # of tasks is min (# of loop iters, num_tasks)
|
|
and each task has at least one iteration. */
|
|
if (test (-51, 2500, 48, 9, num_tasks, &ntasks, &min_iters, &max_iters) != 54
|
|
|| ntasks != 9)
|
|
__builtin_abort ();
|
|
if (test (0, 25, 2, 17, num_tasks, &ntasks, &min_iters, &max_iters) != 13
|
|
|| ntasks != 13)
|
|
__builtin_abort ();
|
|
}
|
|
return 0;
|
|
}
|