Displaying 1 result from an estimated 1 matches for "rb_s16x4".
2016 Jul 28
0
[PATCH] Optimize silk_LPC_analysis_filter() for ARM NEON
...+= 8) {
+ int16x8_t in_s16x8 = vld1q_s16(in + ix);
+ int32x4_t out32_Q12_0_s32x4 = vshll_n_s16(vget_low_s16 (in_s16x8), 12);
+ int32x4_t out32_Q12_1_s32x4 = vshll_n_s16(vget_high_s16(in_s16x8), 12);
+ for (j = 0; j < d; j += 4) {
+ const int16x4_t rB_s16x4 = vld1_s16(rB + j);
+ in_s16x8 = vld1q_s16(in - d + ix + j + 0);
+ out32_Q12_0_s32x4 = vmlsl_lane_s16(out32_Q12_0_s32x4, vget_low_s16 (in_s16x8), rB_s16x4, 0);
+ out32_Q12_1_s32x4 = vmlsl_lane_s16(out32_Q12_1_s32x4, vget_high_s16(in_s16x8), rB_s16x4, 0);
+...