32   v8i16 in8, in9, in10, in11, in12, in13, in14, in15;  in fdct8x16_1d_column()  local
45           in10, in11, in12, in13, in14, in15);  in fdct8x16_1d_column()
49   SLLI_4V(in12, in13, in14, in15, 2);  in fdct8x16_1d_column()
50   ADD4(in0, in15, in1, in14, in2, in13, in3, in12, tmp0, tmp1, tmp2, tmp3);  in fdct8x16_1d_column()
55   SUB4(in0, in15, in1, in14, in2, in13, in3, in12, in15, in14, in13, in12);  in fdct8x16_1d_column()
61   ILVL_H2_SH(in10, in13, in11, in12, vec2, vec4);  in fdct8x16_1d_column()
62   ILVR_H2_SH(in10, in13, in11, in12, vec3, vec5);  in fdct8x16_1d_column()
121   ADD2(stp34, stp25, stp33, stp22, in13, in10);  in fdct8x16_1d_column()
123   ILVRL_H2_SH(in13, in10, vec1, vec0);  in fdct8x16_1d_column()
151   v8i16 in8, in9, in10, in11, in12, in13, in14, in15;  in fdct16x8_1d_row()  local
154   LD_SH8((input + 8), 16, in8, in9, in10, in11, in12, in13, in14, in15);  in fdct16x8_1d_row()
157   TRANSPOSE8x8_SH_SH(in8, in9, in10, in11, in12, in13, in14, in15, in8, in9,  in fdct16x8_1d_row()
158                      in10, in11, in12, in13, in14, in15);  in fdct16x8_1d_row()
162   ADD4(in12, 1, in13, 1, in14, 1, in15, 1, in12, in13, in14, in15);  in fdct16x8_1d_row()
166   SRA_4V(in12, in13, in14, in15, 2);  in fdct16x8_1d_row()
168                in12, in13, in14, in15, tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6,  in fdct16x8_1d_row()
169                tmp7, in8, in9, in10, in11, in12, in13, in14, in15);  in fdct16x8_1d_row()
170   ST_SH8(in8, in9, in10, in11, in12, in13, in14, in15, input, 16);  in fdct16x8_1d_row()
173   LD_SH8(input, 16, in8, in9, in10, in11, in12, in13, in14, in15);  in fdct16x8_1d_row()
174   FDCT8x16_ODD(in8, in9, in10, in11, in12, in13, in14, in15, in0, in1, in2, in3,  in fdct16x8_1d_row()