Searched defs:k_offset (Results 1 – 7 of 7) sorted by relevance
| /aosp_15_r20/external/ComputeLibrary/src/cpu/kernels/ |
| H A D | CpuGemmLowpOffsetContributionOutputStageKernel.cpp | 145 inline int32x4x4_t get_k_offset(int32_t k_offset) in get_k_offset()
311 … int32_t a_offset, int32_t b_offset, int32_t k_offset, in run_offset_contribution_output_stage_window()
478 … int32_t a_offset, int32_t b_offset, int32_t k_offset, bool is_vector_sum_col_batched, in run_offset_contribution_output_stage()
682 … int32_t a_offset, int32_t b_offset, int32_t k_offset, bool is_vector_sum_col_batched, in run_offset_contribution_output_stage_symm()
|
| H A D | CpuGemmLowpOffsetContributionKernel.cpp | 99 … int32_t a_offset, int32_t b_offset, int32_t k_offset, bool slide_vector_sum_col, bool is_gemm3d) in run_offset_contribution()
|
| /aosp_15_r20/external/pytorch/aten/src/ATen/native/transformers/cuda/flash_attn/ |
| H A D | block_info.h | 32 …__forceinline__ __device__ index_t k_offset(const index_t batch_stride, const index_t row_stride, … in k_offset() function
|
| /aosp_15_r20/external/ComputeLibrary/src/cpu/kernels/depthwiseconv2d/generic/neon/ |
| H A D | impl.cpp | 347 …const int32_t k_offset = run_info.weights_width * run_info.weights_height * input_qoffset *… in depthwise_loop_multiplier1_quantized() local
518 …const int32_t k_offset = run_info.weights_width * run_info.weights_height * input_qoffset *… in depthwise_loop_generic_quantized() local
|
| /aosp_15_r20/external/ComputeLibrary/src/core/NEON/kernels/arm_gemm/ |
| H A D | gemm_hybrid_indirect.hpp | 671 unsigned int k_offset = kpos - (k_section_base * rounded_section_size); in pretranspose_B_array() local
|
| H A D | gemm_interleaved.hpp | 1088 unsigned int k_offset = kpos - (k_section_base * rounded_section_size); in pretranspose_B_array() local
|
| /aosp_15_r20/external/tensorflow/tensorflow/core/kernels/ |
| H A D | sparse_matmul_op.cc | 622 int k_offset = 0; in GEPP() local
|