/aosp_15_r20/external/pytorch/aten/src/ATen/ |
H A D | InferSize.h | 22 NumelType numel, in infer_size_impl() 67 inline std::vector<int64_t> infer_size(IntArrayRef shape, int64_t numel) { in infer_size() 73 inline at::DimVector infer_size_dv(IntArrayRef shape, int64_t numel) { in infer_size_dv() 81 c10::SymInt numel) { in infer_size_dv()
|
/aosp_15_r20/external/pytorch/aten/src/ATen/native/cuda/ |
H A D | KernelUtils.cuh | 48 const index_t numel, in fastSpecializedAtomicAdd() 88 const index_t numel, in fastSpecializedAtomicAdd() 129 const index_t numel, in fastSpecializedAtomicAdd() 138 const index_t numel, in fastAtomicAdd()
|
H A D | ScatterGatherKernel.cu | 24 …constexpr C10_DEVICE void operator() (scalar_t* self_data_start, int64_t index, int64_t numel, con… in operator ()() 34 …constexpr C10_DEVICE void operator() (scalar_t* self_data_start, int64_t index, int64_t numel, con… in operator ()() 43 …constexpr C10_DEVICE void operator() (scalar_t* self_data_start, int64_t index, int64_t numel, con… in operator ()() 52 …constexpr C10_DEVICE void operator() (scalar_t* self_data_start, int64_t index, int64_t numel, con… in operator ()() 62 …constexpr C10_DEVICE void operator() (scalar_t* self_data_start, int64_t index, int64_t numel, con… in operator ()() 72 …constexpr C10_DEVICE void operator() (scalar_t* self_data_start, int64_t index, int64_t numel, con… in operator ()()
|
H A D | EmbeddingBackwardKernel.cu | 48 const int64_t *num_of_segments_ptr, int64_t numel) { in krn_partials_per_segment() 83 const index_t *offset2bag, const index_t *count, ptrdiff_t numel, in compute_grad_weight_bags() 128 ptrdiff_t numel, in compute_grad_weight() 225 const ptrdiff_t numel = sorted_indices.numel(); in embedding_backward_cuda_kernel() local
|
H A D | DistributionTemplates.h | 50 const uint64_t numel = static_cast<uint64_t>(total_elements); in calc_execution_policy() local 121 int64_t numel = iter.numel(); in distribution_nullary_kernel() local 180 int numel, in distribution_binary_elementwise_kernel() 250 int64_t numel = iter.numel(); in distribution_binary_kernel() local
|
H A D | SortStable.cu | 143 const auto numel = nsort * nsegments; in segmented_sort_pairs_by_full_sort() local 191 const auto numel = nsort * nsegments; in segmented_sort_pairs() local 224 const auto numel = self.numel(); in launch_stable_sort_kernel() local
|
H A D | Indexing.cu | 52 int64_t numel, int64_t stride, int64_t stride_before, int64_t outer_dim, bool accumulate) { in indexing_backward_kernel() 130 int64_t numel, int64_t stride, int64_t stride_before, int64_t outer_dim, bool accumulate) { in indexing_backward_kernel_stride_1() 186 int64_t numel, int64_t stride, int64_t stride_before, int64_t outer_dim, bool accumulate) { in indexing_backward_kernel_small_stride() 230 int64_t numel, int64_t stride, int64_t stride_before, int64_t outer_dim, in indexing_backward_kernel_quantized() 297 …constexpr C10_DEVICE void operator() (scalar_t* self_data_start, int64_t index, int64_t numel, con… in operator ()() 307 …constexpr C10_DEVICE void operator() (scalar_t* self_data_start, int64_t index, int64_t numel, con… in operator ()() 316 …constexpr C10_DEVICE void operator() (scalar_t* self_data_start, int64_t index, int64_t numel, con… in operator ()() 326 …constexpr C10_DEVICE void operator() (scalar_t* self_data_start, int64_t index, int64_t numel, con… in operator ()()
|
H A D | MultiTensorApply.cuh | 160 const auto numel = tensor_lists[0][t].numel(); in multi_tensor_apply() local 245 const auto numel = tensor_lists[0][t].numel(); in multi_tensor_apply() local 327 const auto numel = tensor_lists[0][tensor_index].numel(); in multi_tensor_apply_for_fused_optimizer() local
|
H A D | RNN.cu | 57 void getLaunchConfig(dim3* block, dim3* grid, int64_t numel) { in getLaunchConfig() 377 int64_t numel = cx.numel(); in lstm_forward_impl() local 414 int64_t numel = cx.numel(); in lstm_backward_impl() local 450 int64_t numel = hx.numel(); in gru_forward_impl() local 484 int64_t numel = grad_hy.numel(); in gru_backward_impl() local
|
/aosp_15_r20/external/pytorch/c10/xpu/test/impl/ |
H A D | XPUTest.h | 5 static inline void initHostData(int* hostData, int numel) { in initHostData() 11 static inline void clearHostData(int* hostData, int numel) { in clearHostData() 17 static inline void validateHostData(int* hostData, int numel) { in validateHostData()
|
/aosp_15_r20/external/pytorch/aten/src/ATen/test/ |
H A D | quantized_test.cpp | 107 int numel = 10; in TEST() local 125 int numel = 10; in TEST() local 218 auto numel = c10::multiply_integers(shape); in TEST() local 261 auto numel = c10::multiply_integers(shape); in TEST() local 295 const int numel = 132; in TEST() local
|
/aosp_15_r20/external/executorch/runtime/core/exec_aten/testing_util/ |
H A D | tensor_util.cpp | 41 size_t numel, in data_is_close() 242 std::ostream& print_data(std::ostream& os, const T* data, size_t numel) { in print_data() 262 std::ostream& print_data(std::ostream& os, const uint8_t* data, size_t numel) { in print_data()
|
/aosp_15_r20/external/pytorch/torch/_inductor/codegen/ |
H A D | simd.py | 1065 def generate_node_schedule(self, nodes, numel, rnumel): argument 1206 def select_index_dtype(cls, node_schedule, numel, reduction_numel): argument 1235 def has_non_contiguous_pw_in_reduction_kernel(self, node_schedule, numel, rnumel): argument 1258 def get_kernel_args(self, node_schedule, numel, reduction_numel): argument 1296 self, node_schedule, buf_accesses, numel, reduction_numel argument 1675 def select_tiling(cls, node_schedule, numel, reduction_numel=sympy.Integer(1)): argument
|
/aosp_15_r20/external/pytorch/torch/csrc/distributed/c10d/ |
H A D | CUDASymmetricMemoryOps.cu | 52 size_t numel, in init_elementwise_launch_config() 80 size_t numel, in multimem_all_reduce_kernel() 173 size_t numel, in multimem_one_shot_all_reduce_kernel()
|
/aosp_15_r20/external/pytorch/aten/src/ATen/native/ |
H A D | Unique.cpp | 42 int64_t numel = input.numel(); in unique_cpu_bool_template() local 165 int64_t numel = input.numel(); in unique_cpu_sorted_template() local 273 int64_t numel = input.numel(); in unique_consecutive_cpu_template() local 391 int64_t numel = input_flat.size(1); in _unique_dim_cpu_template() local
|
H A D | EmbeddingBag.cpp | 129 auto numel = add_indices.numel(); in index_select_add() local 321 auto numel = add_indices.numel(); in index_select_add() local 466 auto numel = add_indices.numel(); in index_select_add() local 517 auto numel = add_indices.numel(); in index_select_scale_add() local 705 auto numel = add_indices.numel(); in index_select_scale_add() local 842 auto numel = add_indices.numel(); in index_select_scale_add() local 1534 int64_t numel = indices.numel(); in _embedding_bag_dense_backward_cpu_sum_mean() local
|
/aosp_15_r20/external/executorch/extension/android/src/main/java/org/pytorch/executorch/ |
H A D | Tensor.java | 351 public long numel() { in numel() method in Tensor 356 public static long numel(long[] shape) { in numel() method in Tensor 648 final long numel = numel(shape); in checkShapeAndDataCapacityConsistency() local 759 long numel = 1; in fromByteArray() local
|
/aosp_15_r20/external/executorch/backends/vulkan/runtime/api/containers/ |
H A D | StagingBuffer.h | 36 const size_t numel) in StagingBuffer() 70 inline size_t numel() { in numel() function
|
/aosp_15_r20/external/executorch/kernels/optimized/cpu/ |
H A D | op_exp.cpp | 35 const size_t numel, in exp_data() 57 const size_t numel, in exp_data()
|
H A D | op_sigmoid.cpp | 34 const size_t numel, in sigmoid_data() 56 const size_t numel, in sigmoid_data()
|
/aosp_15_r20/external/pytorch/aten/src/ATen/native/cpu/ |
H A D | PixelShuffleKernel.cpp | 28 int64_t numel = input.numel(); in cpu_pixel_shuffle() local 126 int64_t numel = input.numel(); in cpu_pixel_unshuffle() local 169 int64_t numel = input.numel(); in cpu_pixel_unshuffle_channels_last() local
|
/aosp_15_r20/external/pytorch/torch/_inductor/codegen/aoti_runtime/ |
H A D | implementation.cpp | 39 int64_t numel; in convert_handle_to_arrayref_tensor() local 79 void assert_numel(const ArrayRefTensor<T>& tensor, uint64_t numel) { in assert_numel()
|
/aosp_15_r20/external/executorch/backends/vulkan/runtime/graph/ops/ |
H A D | PrepackNode.cpp | 54 size_t numel = utils::multiply_integers(packed->sizes()); in create_staging_buffer() local 61 size_t numel = utils::multiply_integers(tref->sizes); in create_staging_buffer() local
|
/aosp_15_r20/external/pytorch/aten/src/ATen/native/sparse/cuda/ |
H A D | SparseCsrTensorMath.cu | 53 …_cuda_kernel(output_t* data_out, const input_t* data_in, const int64_t size, const int64_t numel) { in convert_indices_from_coo_to_csr_cuda_kernel() 69 int64_t numel = input.numel(); in convert_indices_from_coo_to_csr_cuda() local 572 auto numel = values.numel(); in reduce_sparse_csr_dim1_cuda_template() local 631 auto numel = values.numel(); in reduce_sparse_csr_dim01_cuda_template() local
|
/aosp_15_r20/external/executorch/backends/vulkan/runtime/graph/ |
H A D | ComputeGraph.cpp | 347 const size_t numel) { in add_staging() 536 const size_t numel) { in copy_into_staging() 545 const size_t numel) { in copy_from_staging()
|