| /external/ComputeLibrary/src/cpu/kernels/meanstddevnorm/generic/neon/ |
| D | qasymm8.cpp | 96 uint32_t sum_sq = vgetq_lane_u32(sum_sq_vec, 0); in neon_qasymm8_meanstddevnorm() local
103 uint32_t sum_sq = vgetq_lane_u32(sum_sq_vec, 0) + in neon_qasymm8_meanstddevnorm() local
|
| D | impl.cpp | 73 auto sum_sq = wrapper::vgetlane(sum_sq_carry_res, 0); in mean_stddev_normalization() local
147 float sum_sq = vgetq_lane_f32(sum_sq_carry_res, 0); in mean_stddev_normalization() local
|
| /external/ComputeLibrary/src/core/NEON/kernels/ |
| D | NEQLSTMLayerNormalizationKernel.cpp | 47 inline std::pair<int64_t, int64_t> compute_mean_variance(int64_t sum, int64_t sum_sq, uint32_t num_… in compute_mean_variance()
186 AccType sum_sq{ 0 }; in sum_qsymm16() local
305 AccType sum_sq{ 0 }; in compute_qsymm16() local
|
| /external/ComputeLibrary/src/runtime/NEON/functions/ |
| D | NEL2NormalizeLayer.cpp | 67 TensorInfo sum_sq; in validate() local
|
| /external/ComputeLibrary/tests/validation/reference/ |
| D | MeanStdDevNormalizationLayer.cpp | 48 T sum_sq = static_cast<T>(0.f); in mean_std_normalization_layer() local
|
| D | QLSTMLayerNormalization.cpp | 63 int64_t sum_sq{}; in qlstm_layer_normalization() local
|
| /external/ComputeLibrary/src/runtime/CL/functions/ |
| D | CLL2NormalizeLayer.cpp | 84 TensorInfo sum_sq; in validate() local
|
| /external/libaom/aom_dsp/x86/ |
| D | masked_variance_intrin_ssse3.c | 397 __m128i *sum, __m128i *sum_sq) { in accumulate_block()
435 __m128i sum = _mm_setzero_si128(), sum_sq = _mm_setzero_si128(); in masked_variance() local
463 __m128i sum = _mm_setzero_si128(), sum_sq = _mm_setzero_si128(); in masked_variance8xh() local
493 __m128i sum = _mm_setzero_si128(), sum_sq = _mm_setzero_si128(); in masked_variance4xh() local
903 __m128i sum = _mm_setzero_si128(), sum_sq = _mm_setzero_si128(); in highbd_masked_variance() local
975 __m128i sum = _mm_setzero_si128(), sum_sq = _mm_setzero_si128(); in highbd_masked_variance4xh() local
|
| /external/armnn/src/backends/reference/workloads/ |
| D | LstmUtils.cpp | 48 float sum_sq = 0.0f; in MeanStddevNormalization() local
|
| /external/libgav1/src/dsp/x86/ |
| D | loop_restoration_10bit_avx2.cc | 1296 inline __m128i CalculateMa(const __m128i sum, const __m128i sum_sq, in CalculateMa()
1327 inline __m256i CalculateMa(const __m256i sum, const __m256i sum_sq, in CalculateMa()
1415 __m128i sum_sq[2]; in CalculateSumAndIndex5() local
1424 __m256i sum_sq[2]; in CalculateSumAndIndex5() local
1433 __m128i sum_sq[2]; in CalculateSumAndIndex3() local
1442 __m256i sum_sq[2]; in CalculateSumAndIndex3() local
|
| D | loop_restoration_avx2.cc | 1372 inline __m128i CalculateMa(const __m128i sum, const __m128i sum_sq, in CalculateMa()
1402 inline __m256i CalculateMa(const __m256i sum, const __m256i sum_sq, in CalculateMa()
1493 __m128i sum_sq[2]; in CalculateSumAndIndex5() local
1502 __m256i sum_sq[2]; in CalculateSumAndIndex5() local
1511 __m128i sum_sq[2]; in CalculateSumAndIndex3() local
1520 __m256i sum_sq[2]; in CalculateSumAndIndex3() local
|
| D | loop_restoration_10bit_sse4.cc | 997 inline __m128i CalculateMa(const __m128i sum, const __m128i sum_sq, in CalculateMa()
1057 __m128i sum_sq[2]; in CalculateSumAndIndex5() local
1066 __m128i sum_sq[2]; in CalculateSumAndIndex3() local
|
| D | loop_restoration_sse4.cc | 1139 inline __m128i CalculateMa(const __m128i sum, const __m128i sum_sq, in CalculateMa()
1200 __m128i sum_sq[2]; in CalculateSumAndIndex5() local
1209 __m128i sum_sq[2]; in CalculateSumAndIndex3() local
|
| /external/tensorflow/tensorflow/lite/kernels/internal/reference/ |
| D | portable_tensor_utils.cc | 455 int64_t sum_sq = 0; in PortableApplyLayerNorm() local
511 float sum_sq = 0.0f; in PortableApplyLayerNormFloat() local
|
| /external/libgav1/src/dsp/arm/ |
| D | loop_restoration_neon.cc | 1063 inline uint16x4_t CalculateMa(const uint16x4_t sum, const uint32x4_t sum_sq, in CalculateMa()
1089 const uint32x4x2_t sum_sq, in CalculateIntermediate()
1159 const uint32x4x2_t sum_sq = Sum5_32(sq5); in CalculateIntermediate5() local
1169 const uint32x4x2_t sum_sq = Sum3_32(sq3); in CalculateIntermediate3() local
|
| D | loop_restoration_10bit_neon.cc | 1044 inline uint16x4_t CalculateMa(const uint16x4_t sum, const uint32x4_t sum_sq, in CalculateMa()
1108 uint32x4_t sum_sq[2]; in CalculateSumAndIndex3() local
1118 uint32x4_t sum_sq[2]; in CalculateSumAndIndex5() local
|
| /external/libvpx/vpx_dsp/mips/ |
| D | deblock_msa.c | 525 int32_t sum_sq; in vpx_mbpost_proc_across_ip_msa() local
|
| /external/webrtc/rtc_base/ |
| D | virtual_socket_unittest.cc | 145 double sum_sq; member
|
| /external/tensorflow/tensorflow/compiler/xla/service/ |
| D | elemental_ir_emitter.cc | 585 auto sum_sq = FAdd(FAdd(FMul(a, a), FMul(two, a)), FMul(b, b)); in EmitComplexUnaryOp() local
|
| /external/tensorflow/tensorflow/lite/kernels/internal/optimized/ |
| D | neon_tensor_utils.cc | 1524 int64_t sum_sq = 0; in NeonApplyLayerNorm() local
|