#include "arm_neon.h"

#define LOAD(DEST, TYPE, X, Y, SRC) \
  (DEST).val = __load_lanes (__array_ref (SRC, X * Y), TYPE##x##Y##_t[X])

#define STORE(DEST, TYPE, X, Y, SRC) \
  __array_ref (DEST, X * Y) = __store_lanes ((SRC).val, TYPE##_t [X * Y])

#define LOAD_LANE(DEST, TYPE, X, Y, SRC, LANE) \
  (DEST).val = __load_lane (__array_ref (SRC, X * Y), (DEST).val, LANE)

#define STORE_LANE(DEST, TYPE, X, Y, SRC, LANE) \
  __array_ref (DEST, X) = __store_lane ((SRC).val, LANE, TYPE##_t[X])

void
foo (uint32_t *a)
{
  uint32x4x2_t x, y;

  LOAD (x, uint32, 2, 4, a);
  LOAD (y, uint32, 2, 4, a + 12);
  x.val[0] = vaddq_u32 (x.val[0], y.val[0]);
  x.val[1] = vaddq_u32 (x.val[1], y.val[1]);
  STORE (a, uint32, 2, 4, x);
}

void
bar (uint32_t *a)
{
  uint32x4x2_t x, y;

  LOAD (x, uint32, 2, 4, a);
  LOAD (y, uint32, 2, 4, a);
  x.val[0] = vaddq_u32 (x.val[0], y.val[0]);
  x.val[1] = vaddq_u32 (x.val[1], y.val[1]);
  STORE (a, uint32, 2, 4, x);
}

void
frob (uint32_t *a)
{
  uint32x4x2_t x, y;

  LOAD (x, uint32, 2, 4, a);
  LOAD (y, uint32, 2, 4, a + 12);
  LOAD_LANE (x, uint32, 2, 4, a + 32, 1);
  LOAD_LANE (y, uint32, 2, 4, a + 36, 2);
  x.val[0] = vaddq_u32 (x.val[0], y.val[0]);
  x.val[1] = vaddq_u32 (x.val[1], y.val[1]);
  STORE_LANE (a, uint32, 2, 4, x, 3);
  STORE_LANE (a + 4, uint32, 2, 4, x, 1);
  STORE_LANE (a + 8, uint32, 2, 4, x, 0);
  STORE_LANE (a + 12, uint32, 2, 4, x, 2);
}