27 v16u8 in0, in1, in2, in3, in4, in5, in6, in7;
28 v16u8 in8, in9, in10, in11, in12, in13, in14, in15;
30 LD_UB8(src, stride, in0, in1, in2, in3, in4, in5, in6, in7);
32 LD_UB8(src, stride, in8, in9, in10, in11, in12, in13, in14, in15);
34 HADD_UB4_UB(in0, in1, in2, in3, in0, in1, in2, in3);
35 HADD_UB4_UB(in4, in5, in6, in7, in4, in5, in6, in7);
36 HADD_UB4_UB(in8, in9, in10, in11, in8, in9, in10, in11);
37 HADD_UB4_UB(in12, in13, in14, in15, in12, in13, in14, in15);
static int32_t sum_u8src_16width_msa(uint8_t *src, int32_t stride)
int ff_pix_sum_msa(uint8_t *pix, int line_size)