17   v8i16 in0, in1, in2, in3, in4, in5, in6, in7;  in fdct8x32_1d_column_load_butterfly()  local
24   LD_SH4(input + (28 * src_stride), src_stride, in4, in5, in6, in7);  in fdct8x32_1d_column_load_butterfly()
28   SLLI_4V(in4, in5, in6, in7, 2);  in fdct8x32_1d_column_load_butterfly()
31   BUTTERFLY_8(in0, in1, in2, in3, in4, in5, in6, in7, step0, step1, step2,  in fdct8x32_1d_column_load_butterfly()
32               step3, in4, in5, in6, in7);  in fdct8x32_1d_column_load_butterfly()
36   ST_SH4(in4, in5, in6, in7, temp_buff + (28 * 8), 8);  in fdct8x32_1d_column_load_butterfly()
42   LD_SH4(input + (20 * src_stride), src_stride, in4, in5, in6, in7);  in fdct8x32_1d_column_load_butterfly()
46   SLLI_4V(in4, in5, in6, in7, 2);  in fdct8x32_1d_column_load_butterfly()
49   BUTTERFLY_8(in0, in1, in2, in3, in4, in5, in6, in7, step0, step1, step2,  in fdct8x32_1d_column_load_butterfly()
50               step3, in4, in5, in6, in7);  in fdct8x32_1d_column_load_butterfly()
54   ST_SH4(in4, in5, in6, in7, temp_buff + (20 * 8), 8);  in fdct8x32_1d_column_load_butterfly()
60   v8i16 in0, in1, in2, in3, in4, in5, in6, in7;  in fdct8x32_1d_column_even_store()  local
70   LD_SH4(input + 32, 8, in4, in5, in6, in7);  in fdct8x32_1d_column_even_store()
72   BUTTERFLY_8(in4, in5, in6, in7, in8, in9, in10, in11, vec4, vec5, vec6, vec7,  in fdct8x32_1d_column_even_store()
256   v8i16 in0, in1, in2, in3, in4, in5, in6, in7;  in fdct8x32_1d_row_load_butterfly()  local
260   LD_SH8(temp_buff, 32, in0, in1, in2, in3, in4, in5, in6, in7);  in fdct8x32_1d_row_load_butterfly()
262   TRANSPOSE8x8_SH_SH(in0, in1, in2, in3, in4, in5, in6, in7, in0, in1, in2, in3,  in fdct8x32_1d_row_load_butterfly()
263                      in4, in5, in6, in7);  in fdct8x32_1d_row_load_butterfly()
266   BUTTERFLY_16(in0, in1, in2, in3, in4, in5, in6, in7, in8, in9, in10, in11,  in fdct8x32_1d_row_load_butterfly()
273   LD_SH8(temp_buff + 8, 32, in0, in1, in2, in3, in4, in5, in6, in7);  in fdct8x32_1d_row_load_butterfly()
275   TRANSPOSE8x8_SH_SH(in0, in1, in2, in3, in4, in5, in6, in7, in0, in1, in2, in3,  in fdct8x32_1d_row_load_butterfly()
276                      in4, in5, in6, in7);  in fdct8x32_1d_row_load_butterfly()
279   BUTTERFLY_16(in0, in1, in2, in3, in4, in5, in6, in7, in8, in9, in10, in11,  in fdct8x32_1d_row_load_butterfly()
289   v8i16 in0, in1, in2, in3, in4, in5, in6, in7;  in fdct8x32_1d_row_even_4x()  local
298   LD_SH8(input, 8, in0, in1, in2, in3, in4, in5, in6, in7);  in fdct8x32_1d_row_even_4x()
301   BUTTERFLY_16(in0, in1, in2, in3, in4, in5, in6, in7, in8, in9, in10, in11,  in fdct8x32_1d_row_even_4x()
393   v8i16 in0, in1, in2, in3, in4, in5, in6, in7;  in fdct8x32_1d_row_even()  local
399   LD_SH8(temp, 8, in0, in1, in2, in3, in4, in5, in6, in7);  in fdct8x32_1d_row_even()
402   BUTTERFLY_16(in0, in1, in2, in3, in4, in5, in6, in7, in8, in9, in10, in11,  in fdct8x32_1d_row_even()
597   v8i16 in0, in1, in2, in3, in4, in5, in6, in7;  in fdct8x32_1d_row_transpose_store()  local
604   in6 = LD_SH(temp + 96);  in fdct8x32_1d_row_transpose_store()
610   TRANSPOSE8x8_SH_SH(in0, in1, in2, in3, in4, in5, in6, in7, in0, in1, in2, in3,  in fdct8x32_1d_row_transpose_store()
611                      in4, in5, in6, in7);  in fdct8x32_1d_row_transpose_store()
623   ST_SH8(in0, in1, in2, in3, in4, in5, in6, in7, output, 32);  in fdct8x32_1d_row_transpose_store()
634   in6 = LD_SH(temp + 104);  in fdct8x32_1d_row_transpose_store()
639   TRANSPOSE8x8_SH_SH(in0, in1, in2, in3, in4, in5, in6, in7, in0, in1, in2, in3,  in fdct8x32_1d_row_transpose_store()
640                      in4, in5, in6, in7);  in fdct8x32_1d_row_transpose_store()
641   ST_SH8(in0, in1, in2, in3, in4, in5, in6, in7, output + 16, 32);  in fdct8x32_1d_row_transpose_store()
696   v8i16 in0, in1, in2, in3, in4, in5, in6, in7;  in fdct8x32_1d_row_even_rd()  local
702   LD_SH8(temp, 8, in0, in1, in2, in3, in4, in5, in6, in7);  in fdct8x32_1d_row_even_rd()
705   BUTTERFLY_16(in0, in1, in2, in3, in4, in5, in6, in7, in8, in9, in10, in11,  in fdct8x32_1d_row_even_rd()
932   v8i16 in0, in1, in2, in3, in4, in5, in6, in7;  in vpx_fdct32x32_1_msa()  local
938     LD_SH4(input, 8, in4, in5, in6, in7);  in vpx_fdct32x32_1_msa()
940     ADD4(in0, in1, in2, in3, in4, in5, in6, in7, in0, in2, in4, in6);  in vpx_fdct32x32_1_msa()
941     ADD2(in0, in2, in4, in6, in0, in4);  in vpx_fdct32x32_1_msa()