Lines Matching refs:v_b1
910 __m128 v_b0 = _mm_set1_ps(beta[0]), v_b1 = _mm_set1_ps(beta[1]),
918 v_dst0 = _mm_add_ps(v_dst0, _mm_mul_ps(v_b1, _mm_loadu_ps(S1 + x)));
927 v_dst1 = _mm_add_ps(v_dst1, _mm_mul_ps(v_b1, _mm_loadu_ps(S1 + x + 4)));
961 __m128 v_b0 = _mm_set1_ps(beta[0]), v_b1 = _mm_set1_ps(beta[1]),
969 v_dst0 = _mm_add_ps(v_dst0, _mm_mul_ps(v_b1, _mm_loadu_ps(S1 + x)));
978 v_dst1 = _mm_add_ps(v_dst1, _mm_mul_ps(v_b1, _mm_loadu_ps(S1 + x + 4)));
1008 __m128 v_b0 = _mm_set1_ps(beta[0]), v_b1 = _mm_set1_ps(beta[1]),
1016 v_dst = _mm_add_ps(v_dst, _mm_mul_ps(v_b1, _mm_loadu_ps(S1 + x)));
1041 int16x8_t v_b0 = vdupq_n_s16(beta[0]), v_b1 = vdupq_n_s16(beta[1]), v_delta = vdupq_n_s16(2);
1052 vshrq_n_s16(vqdmulhq_s16(v_src1, v_b1), 1));
1064 vshrq_n_s16(vqdmulhq_s16(v_src1, v_b1), 1));
1084 float32x4_t v_b0 = vdupq_n_f32(beta[0]), v_b1 = vdupq_n_f32(beta[1]);
1091 float32x4_t v_dst0 = vmlaq_f32(vmulq_f32(v_src00, v_b0), v_src10, v_b1);
1092 float32x4_t v_dst1 = vmlaq_f32(vmulq_f32(v_src01, v_b0), v_src11, v_b1);
1112 float32x4_t v_b0 = vdupq_n_f32(beta[0]), v_b1 = vdupq_n_f32(beta[1]);
1119 float32x4_t v_dst0 = vmlaq_f32(vmulq_f32(v_src00, v_b0), v_src10, v_b1);
1120 float32x4_t v_dst1 = vmlaq_f32(vmulq_f32(v_src01, v_b0), v_src11, v_b1);
1140 float32x4_t v_b0 = vdupq_n_f32(beta[0]), v_b1 = vdupq_n_f32(beta[1]);
1147 vst1q_f32(dst + x, vmlaq_f32(vmulq_f32(v_src00, v_b0), v_src10, v_b1));
1148 vst1q_f32(dst + x + 4, vmlaq_f32(vmulq_f32(v_src01, v_b0), v_src11, v_b1));
1166 float32x4_t v_b0 = vdupq_n_f32(beta[0]), v_b1 = vdupq_n_f32(beta[1]),
1172 v_b1, vld1q_f32(S1 + x)),
1176 v_b1, vld1q_f32(S1 + x + 4)),
1197 float32x4_t v_b0 = vdupq_n_f32(beta[0]), v_b1 = vdupq_n_f32(beta[1]),
1203 v_b1, vld1q_f32(S1 + x)),
1207 v_b1, vld1q_f32(S1 + x + 4)),
1228 float32x4_t v_b0 = vdupq_n_f32(beta[0]), v_b1 = vdupq_n_f32(beta[1]),
1234 v_b1, vld1q_f32(S1 + x)),
1238 v_b1, vld1q_f32(S1 + x + 4)),
1257 float32x4_t v_b0 = vdupq_n_f32(beta[0]), v_b1 = vdupq_n_f32(beta[1]),
1265 v_b1, vld1q_f32(S1 + x)),
1275 v_b1, vld1q_f32(S1 + x + 4)),
1302 float32x4_t v_b0 = vdupq_n_f32(beta[0]), v_b1 = vdupq_n_f32(beta[1]),
1310 v_b1, vld1q_f32(S1 + x)),
1320 v_b1, vld1q_f32(S1 + x + 4)),
1347 float32x4_t v_b0 = vdupq_n_f32(beta[0]), v_b1 = vdupq_n_f32(beta[1]),
1355 v_b1, vld1q_f32(S1 + x)),
