fd71a9a24d
gcc/c/ * c-parser.c (OACC_KERNELS_CLAUSE_MASK): Add "PRAGMA_OACC_CLAUSE_NUM_GANGS", "PRAGMA_OACC_CLAUSE_NUM_WORKERS", "VECTOR_LENGTH". gcc/cp/ * parser.c (OACC_KERNELS_CLAUSE_MASK): Add "PRAGMA_OACC_CLAUSE_NUM_GANGS", "PRAGMA_OACC_CLAUSE_NUM_WORKERS", "VECTOR_LENGTH". gcc/fortran/ * openmp.c (OACC_KERNELS_CLAUSES): Add "OMP_CLAUSE_NUM_GANGS", "OMP_CLAUSE_NUM_WORKERS", "OMP_CLAUSE_VECTOR_LENGTH". gcc/ * omp-offload.c (execute_oacc_device_lower): Remove the parallelism dimensions function attributes for unparallelized OpenACC kernels constructs. gcc/testsuite/ * c-c++-common/goacc/parallel-dims-1.c: Update. * c-c++-common/goacc/parallel-dims-2.c: Likewise. * c-c++-common/goacc/routine-1.c: Likewise. * c-c++-common/goacc/uninit-dim-clause.c: Likewise. * g++.dg/goacc/template.C: Likewise. * gfortran.dg/goacc/kernels-tree.f95: Likewise. * gfortran.dg/goacc/routine-3.f90: Likewise. * gfortran.dg/goacc/sie.f95: Likewise. * gfortran.dg/goacc/uninit-dim-clause.f95: Likewise. libgomp/ * testsuite/libgomp.oacc-c-c++-common/kernels-loop-2.c: Update. * testsuite/libgomp.oacc-c-c++-common/parallel-dims.c: Likewise. * testsuite/libgomp.oacc-fortran/kernels-loop-2.f95: Likewise. From-SVN: r248370
58 lines
1.4 KiB
C
58 lines
1.4 KiB
C
#include <stdlib.h>
|
|
|
|
#define N (1024 * 512)
|
|
#define COUNTERTYPE unsigned int
|
|
|
|
int
|
|
main (void)
|
|
{
|
|
unsigned int *__restrict a;
|
|
unsigned int *__restrict b;
|
|
unsigned int *__restrict c;
|
|
|
|
a = (unsigned int *__restrict)malloc (N * sizeof (unsigned int));
|
|
b = (unsigned int *__restrict)malloc (N * sizeof (unsigned int));
|
|
c = (unsigned int *__restrict)malloc (N * sizeof (unsigned int));
|
|
|
|
/* Parallelism dimensions: compiler/runtime decides. */
|
|
#pragma acc kernels copyout (a[0:N])
|
|
{
|
|
for (COUNTERTYPE i = 0; i < N; i++)
|
|
a[i] = i * 2;
|
|
}
|
|
|
|
/* Parallelism dimensions: variable. */
|
|
#pragma acc kernels copyout (b[0:N]) \
|
|
num_gangs (3 + a[3]) num_workers (5 + a[5]) vector_length (7 + a[7])
|
|
/* { dg-prune-output "using vector_length \\(32\\), ignoring runtime setting" } */
|
|
{
|
|
for (COUNTERTYPE i = 0; i < N; i++)
|
|
b[i] = i * 4;
|
|
}
|
|
|
|
/* Parallelism dimensions: literal. */
|
|
#pragma acc kernels copyin (a[0:N], b[0:N]) copyout (c[0:N]) \
|
|
num_gangs (3) num_workers (5) vector_length (7)
|
|
/* { dg-prune-output "using vector_length \\(32\\), ignoring 7" } */
|
|
{
|
|
for (COUNTERTYPE ii = 0; ii < N; ii++)
|
|
c[ii] = a[ii] + b[ii];
|
|
}
|
|
|
|
for (COUNTERTYPE i = 0; i < N; i++)
|
|
{
|
|
if (a[i] != i * 2)
|
|
abort ();
|
|
if (b[i] != i * 4)
|
|
abort ();
|
|
if (c[i] != a[i] + b[i])
|
|
abort ();
|
|
}
|
|
|
|
free (a);
|
|
free (b);
|
|
free (c);
|
|
|
|
return 0;
|
|
}
|