https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65419
--- Comment #4 from vries at gcc dot gnu.org --- When removing the fn spec from GOACC_data_start, we run into the problem that this example doesn't get parallelized anymore: ... #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 *)malloc (N * sizeof (unsigned int)); b = (unsigned int *)malloc (N * sizeof (unsigned int)); c = (unsigned int *)malloc (N * sizeof (unsigned int)); for (COUNTERTYPE i = 0; i < N; i++) a[i] = i * 2; for (COUNTERTYPE i = 0; i < N; i++) b[i] = i * 4; #pragma acc data copyin (a[0:N], b[0:N]) copyout (c[0:N]) { #pragma acc kernels present (a[0:N], b[0:N], c[0:N]) { for (COUNTERTYPE ii = 0; ii < N; ii++) c[ii] = a[ii] + b[ii]; } } for (COUNTERTYPE i = 0; i < N; i++) if (c[i] != a[i] + b[i]) abort (); free (a); free (b); free (c); return 0; } ... In this sequence, we take the address of a and pass it to GOACC_data_start: ... .omp_data_arr.18.a = &a; __builtin_GOACC_data_start (-1, 6, &.omp_data_arr.18, &.omp_data_sizes.19, &.omp_data_kinds.20); ... With the fnspec, we need to assume that a could be modified by __builtin_GOACC_data_start. And that inhibits optimization.