A basic NEON implementation of SSE _mm_movemask_ps

movemask.c

uint32_t _mm_movemask_ps(float32x4_t x) {
  uint32x4_t mmA = vandq_u32(
    vreinterpretq_u32_f32(x), (uint32x4_t) {0x1, 0x2, 0x4, 0x8}); // [0 1 2 3]
  uint32x4_t mmB = vextq_u32(mmA, mmA, 2);                        // [2 3 0 1]
  uint32x4_t mmC = vorrq_u32(mmA, mmB);                           // [0+2 1+3 0+2 1+3]
  uint32x4_t mmD = vextq_u32(mmC, mmC, 3);                        // [1+3 0+2 1+3 0+2]
  uint32x4_t mmE = vorrq_u32(mmC, mmD);                           // [0+1+2+3 ...]
  return vgetq_lane_u32(mmE, 0);
}

Unfortunately a NEON analog to SSE's _mm_movemask_ps does not exist. There are some reimplementations (e.g. here), this one is mine. The input is assumed to be the result of a comparison (e.g. consisting of either 0x0 or ~0x0). This implementation is "reasonably" fast.