typedef struct
{
  double a[MAX_THREADS];
  double b[MAX_THREADS];
} lib_workspace;

double lib_calc_something(double x, lib_workspace * work)
{
  int thread_id = omp_get_thread_num();
  work->a[thread_id] = x - 2.0;
  work->b[thread_id] = x + 1.0;
  return work->a[thread_id] * work->b[thread_id];
}

#pragma omp parallel for
for (x = 0.0; x < 1.0; x += 0.1)
  {
    double y = lib_calc_something(x, work);
    ...
  }

typedef struct
{
  double a;
  double b;
} lib_workspace;

double lib_calc_something(double x, lib_workspace * work)
{
  work->a = x - 2.0;
  work->b = x + 1.0;
  return work->a * work->b;
}

/* allocate MAX_THREADS copies of lib_workspace */
for (i = 0; i < MAX_THREADS; ++i)
  work[i] = lib_alloc();

#pragma omp parallel for
for (x = 0.0; x < 1.0; x += 0.1)
  {
    int thread_id = omp_get_thread_num();
    double y = lib_calc_something(x, work[thread_id]);
    ...
  }