/external/libgav1/libgav1/src/dsp/arm/ |
D | super_res_neon.cc | 206 res_lo = vmlal_u16(res_lo, vget_low_u16(src[3]), vget_low_u16(f[3])); in SuperRes() 207 res_lo = vmlal_u16(res_lo, vget_low_u16(src[4]), vget_low_u16(f[4])); in SuperRes() 208 res_lo = vmlal_u16(res_lo, vget_low_u16(src[6]), vget_low_u16(f[6])); in SuperRes() 211 temp_lo = vmlal_u16(temp_lo, vget_low_u16(src[2]), vget_low_u16(f[2])); in SuperRes() 212 temp_lo = vmlal_u16(temp_lo, vget_low_u16(src[5]), vget_low_u16(f[5])); in SuperRes() 213 temp_lo = vmlal_u16(temp_lo, vget_low_u16(src[7]), vget_low_u16(f[7])); in SuperRes() 218 res_hi = vmlal_u16(res_hi, vget_high_u16(src[3]), vget_high_u16(f[3])); in SuperRes() 219 res_hi = vmlal_u16(res_hi, vget_high_u16(src[4]), vget_high_u16(f[4])); in SuperRes() 220 res_hi = vmlal_u16(res_hi, vget_high_u16(src[6]), vget_high_u16(f[6])); in SuperRes() 223 temp_hi = vmlal_u16(temp_hi, vget_high_u16(src[2]), vget_high_u16(f[2])); in SuperRes() [all …]
|
D | distance_weighted_blend_neon.cc | 202 const uint32x4_t blended_lo = vmlal_u16(wpred0_lo, weights[1], pred1.val[0]); in ComputeWeightedAverage8() 203 const uint32x4_t blended_hi = vmlal_u16(wpred0_hi, weights[1], pred1.val[1]); in ComputeWeightedAverage8() 223 const uint32x4_t blended0 = vmlal_u16(wpred0, weights[1], pred1.val[0]); in ComputeWeightedAverage8() 224 const uint32x4_t blended1 = vmlal_u16(wpred1, weights[1], pred1.val[1]); in ComputeWeightedAverage8() 229 const uint32x4_t blended2 = vmlal_u16(wpred2, weights[1], pred1.val[2]); in ComputeWeightedAverage8() 230 const uint32x4_t blended3 = vmlal_u16(wpred3, weights[1], pred1.val[3]); in ComputeWeightedAverage8()
|
D | cdef_neon.cc | 320 return vmlal_u16(a, b, b); in SquareAccumulate()
|
/external/zlib/ |
D | adler32_simd.c | 289 v_s2 = vmlal_u16(v_s2, vget_low_u16 (v_column_sum_1), in adler32_simd_() 291 v_s2 = vmlal_u16(v_s2, vget_high_u16(v_column_sum_1), in adler32_simd_() 293 v_s2 = vmlal_u16(v_s2, vget_low_u16 (v_column_sum_2), in adler32_simd_() 295 v_s2 = vmlal_u16(v_s2, vget_high_u16(v_column_sum_2), in adler32_simd_() 297 v_s2 = vmlal_u16(v_s2, vget_low_u16 (v_column_sum_3), in adler32_simd_() 299 v_s2 = vmlal_u16(v_s2, vget_high_u16(v_column_sum_3), in adler32_simd_() 301 v_s2 = vmlal_u16(v_s2, vget_low_u16 (v_column_sum_4), in adler32_simd_() 303 v_s2 = vmlal_u16(v_s2, vget_high_u16(v_column_sum_4), in adler32_simd_()
|
/external/tensorflow/tensorflow/core/kernels/ |
D | quantized_instance_norm.cc | 84 sub_sq_sum[0] = vmlal_u16(sub_sq_sum[0], v_high_high, v_high_high); in ColMeanAndVariance() 85 sub_sq_sum[1] = vmlal_u16(sub_sq_sum[1], v_high_low, v_high_low); in ColMeanAndVariance() 86 sub_sq_sum[2] = vmlal_u16(sub_sq_sum[2], v_low_high, v_low_high); in ColMeanAndVariance() 87 sub_sq_sum[3] = vmlal_u16(sub_sq_sum[3], v_low_low, v_low_low); in ColMeanAndVariance()
|
/external/webrtc/modules/audio_processing/aecm/ |
D | aecm_core_neon.cc | 86 vmlal_u16(echo_adapt_v, vreinterpret_u16_s16(vget_low_s16(adapt_v)), in WebRtcAecm_CalcLinearEnergiesNeon() 89 vmlal_u16(echo_adapt_v, vreinterpret_u16_s16(vget_high_s16(adapt_v)), in WebRtcAecm_CalcLinearEnergiesNeon()
|
/external/libaom/libaom/aom_dsp/arm/ |
D | sse_neon.c | 235 uint32x4_t q6 = vmlal_u16(q1, d0, d0); in highbd_sse_W8x1_neon() 236 uint32x4_t q7 = vmlal_u16(q1, d1, d1); in highbd_sse_W8x1_neon()
|
/external/neon_2_sse/ |
D | NEON_2_SSE.h | 583 _NEON2SSESTORAGE uint32x4_t vmlal_u16(uint32x4_t a, uint16x4_t b, uint16x4_t c); // VMLAL.U16 q0,d0… 3992 _NEON2SSESTORAGE uint32x4_t vmlal_u16(uint32x4_t a, uint16x4_t b, uint16x4_t c); // VMLAL.s16 q0,d0… 3993 _NEON2SSE_INLINE uint32x4_t vmlal_u16(uint32x4_t a, uint16x4_t b, uint16x4_t c) // VMLAL.s16 q0,d0,… in vmlal_u16() function 13399 return vmlal_u16(a, b, c); 14109 return vmlal_u16(a, b, vc); in vmlal_n_u16()
|
/external/llvm-project/clang/test/CodeGen/ |
D | aarch64-neon-intrinsics.c | 8016 return vmlal_u16(a, b, c); in test_vmlal_u16()
|
D | arm_neon_intrinsics.c | 7098 return vmlal_u16(a, b, c); in test_vmlal_u16()
|
/external/clang/test/CodeGen/ |
D | aarch64-neon-intrinsics.c | 8875 return vmlal_u16(a, b, c); in test_vmlal_u16()
|
D | arm_neon_intrinsics.c | 8970 return vmlal_u16(a, b, c); in test_vmlal_u16()
|