Home
last modified time | relevance | path

Searched refs:GPU_1D_KERNEL_LOOP (Results 1 – 25 of 47) sorted by relevance

12

/external/tensorflow/tensorflow/core/kernels/
Dpopulation_count_op_gpu.cu.cc39 GPU_1D_KERNEL_LOOP(i, size) { output[i] = __popc(ldg(input + i)); } in PopulationCountKernel()
47 GPU_1D_KERNEL_LOOP(i, size) { in PopulationCountKernel()
57 GPU_1D_KERNEL_LOOP(i, size) { in PopulationCountKernel()
66 GPU_1D_KERNEL_LOOP(i, size) { output[i] = __popcll(ldg(input + i)); } in PopulationCountKernel()
Dcompare_and_bitpack_op_gpu.cu.cc46 GPU_1D_KERNEL_LOOP(i, size) { in CompareAndBitpackKernel()
65 GPU_1D_KERNEL_LOOP(i, size) { in CompareAndBitpackKernel()
84 GPU_1D_KERNEL_LOOP(i, size) { in CompareAndBitpackKernel()
100 GPU_1D_KERNEL_LOOP(i, size) { in CompareAndBitpackKernel()
Dmaxpooling_op_gpu.cu.cc74 GPU_1D_KERNEL_LOOP(index, nthreads) { in MaxPoolForwardNCHW()
119 GPU_1D_KERNEL_LOOP(index, nthreads) { in MaxPoolForwardNoMaskKernel_NCHW_VECT_C()
151 GPU_1D_KERNEL_LOOP(index, nthreads) { in MaxPoolForwardNHWC()
209 GPU_1D_KERNEL_LOOP(index, nthreads) { in MaxPoolBackward()
237 GPU_1D_KERNEL_LOOP(index, nthreads) { in MaxPoolGradBackwardNoMaskNCHW()
278 GPU_1D_KERNEL_LOOP(index, nthreads) { in MaxPoolGradBackwardNoMaskNHWC()
339 GPU_1D_KERNEL_LOOP(index, nthreads) { in MaxPoolGradBackward()
346 #undef GPU_1D_KERNEL_LOOP
Dcwise_op_clip_gpu.cu.cc32 GPU_1D_KERNEL_LOOP(i, size_in) { in UnaryClipCustomKernel()
44 GPU_1D_KERNEL_LOOP(i, size_in) { in BinaryRightClipCustomKernel()
56 GPU_1D_KERNEL_LOOP(i, size_in) { in BinaryLeftClipCustomKernel()
Ddiag_op_gpu.cu.cc34 GPU_1D_KERNEL_LOOP(index, num_threads) { in DiagGpuKernel()
85 GPU_1D_KERNEL_LOOP(index, num_threads) { in DiagPartGpuKernel()
Ddepthtospace_op_gpu.cu.cc40 GPU_1D_KERNEL_LOOP(out_idx, nthreads) { in D2S_NHWC()
69 GPU_1D_KERNEL_LOOP(input_idx, nthreads) { in D2S_NCHW()
107 GPU_1D_KERNEL_LOOP(thread_idx, nthreads) { in D2S_NCHW_LOOP()
Dbias_op_gpu.cu.cc57 GPU_1D_KERNEL_LOOP(index, nthreads) { in BiasNHWCKernel()
68 GPU_1D_KERNEL_LOOP(index, nthreads) { in BiasNCHWKernel()
107 GPU_1D_KERNEL_LOOP(index, nthreads) { in BiasGradNHWC_Naive()
119 GPU_1D_KERNEL_LOOP(index, nthreads) { in BiasGradNCHW_Naive()
Dbincount_op_gpu.cu.cc107 GPU_1D_KERNEL_LOOP(index, nthreads) { in BincountReduceKernel()
138 GPU_1D_KERNEL_LOOP(index, nthreads) { in BincountColReduceKernel()
168 GPU_1D_KERNEL_LOOP(index, nthreads) { in BincountColReduceSharedKernel()
Dspacetodepth_op_gpu.cu.cc39 GPU_1D_KERNEL_LOOP(inp_idx, nthreads) { in S2D_NHWC()
69 GPU_1D_KERNEL_LOOP(input_idx, nthreads) { in S2D_NCHW()
108 GPU_1D_KERNEL_LOOP(thread_idx, nthreads) { in S2D_NCHW_LOOP()
Dsearchsorted_op_gpu.cu.cc38 GPU_1D_KERNEL_LOOP(work_unit_id, values_size * batch_size) { in UpperBoundKernel()
51 GPU_1D_KERNEL_LOOP(work_unit_id, values_size * batch_size) { in LowerBoundKernel()
Ddilation_ops_gpu.cu.cc44 GPU_1D_KERNEL_LOOP(out_idx, nthreads) { in DilationKernel()
84 GPU_1D_KERNEL_LOOP(out_idx, nthreads) { in DilationBackpropInputKernel()
134 GPU_1D_KERNEL_LOOP(out_idx, nthreads) { in DilationBackpropFilterKernel()
Dpooling_ops_3d_gpu.cu.cc39 GPU_1D_KERNEL_LOOP(index, nthreads) { in MaxPoolGradBackwardNoMaskNCDHW()
90 GPU_1D_KERNEL_LOOP(index, nthreads) { in MaxPoolGradBackwardNoMaskNDHWC()
Dscatter_functor_gpu.cu.h92 GPU_1D_KERNEL_LOOP(i, updates_size) {
114 GPU_1D_KERNEL_LOOP(i, synthesized_updates_size) {
Ddynamic_stitch_op_gpu.cu.cc39 GPU_1D_KERNEL_LOOP(output_index, output_size) { in DynamicStitchKernel()
Dinplace_ops_functor_gpu.cu.cc34 GPU_1D_KERNEL_LOOP(idx, nthreads) { in DoParallelConcatOpKernel()
88 GPU_1D_KERNEL_LOOP(idx, nthreads) { in DoInplaceOpKernel()
Dsplit_lib_gpu.cu.cc87 GPU_1D_KERNEL_LOOP(offset, size) { in SplitOpKernel()
182 GPU_1D_KERNEL_LOOP(offset, size) { in SplitVOpKernel_fixed()
Dtile_functor_gpu.h39 GPU_1D_KERNEL_LOOP(o_idx, nthreads) { in TileKernel()
/external/tensorflow/tensorflow/core/kernels/image/
Dresize_nearest_neighbor_op_gpu.cu.cc40 GPU_1D_KERNEL_LOOP(index, nthreads) { in ResizeNearestNeighborNHWC()
71 GPU_1D_KERNEL_LOOP(index, nthreads) { in LegacyResizeNearestNeighborNHWC()
100 GPU_1D_KERNEL_LOOP(index, nthreads) { in ResizeNearestNeighborBackwardNHWC()
131 GPU_1D_KERNEL_LOOP(index, nthreads) { in LegacyResizeNearestNeighborBackwardNHWC()
Dresize_bilinear_op_gpu.cu.cc121 GPU_1D_KERNEL_LOOP(out_idx, nthreads) { in ResizeBilinearKernel()
175 GPU_1D_KERNEL_LOOP(in_idx, nthreads) { in ResizeBilinearGradKernel()
239 GPU_1D_KERNEL_LOOP(out_idx, nthreads) { in ResizeBilinearDeterministicGradKernel()
290 GPU_1D_KERNEL_LOOP(out_idx, nthreads) { in LegacyResizeBilinearKernel()
341 GPU_1D_KERNEL_LOOP(in_idx, nthreads) { in LegacyResizeBilinearGradKernel()
Dcrop_and_resize_op_gpu.cu.cc46 GPU_1D_KERNEL_LOOP(out_idx, nthreads) { in CropAndResizeKernel()
139 GPU_1D_KERNEL_LOOP(out_idx, nthreads) { in CropAndResizeBackpropImageKernel()
235 GPU_1D_KERNEL_LOOP(out_idx, nthreads) { in CropAndResizeBackpropBoxesKernel()
/external/tensorflow/tensorflow/core/kernels/sparse/
Dkernels_gpu.cu.cc140 GPU_1D_KERNEL_LOOP(i, size) { in SparseTensorToCOOMatrixKernel()
172 GPU_1D_KERNEL_LOOP(i, size) { in COOMatrixToSparseTensorKernel2D()
205 GPU_1D_KERNEL_LOOP(i, size) { in COOMatrixToSparseTensorKernel3D()
277 GPU_1D_KERNEL_LOOP(i, total_nnz) { in CSRSparseMatrixBatchMulVecKernel3D()
377 GPU_1D_KERNEL_LOOP(row, rows) { in CSRSparseMatrixSoftmaxKernel2D()
407 GPU_1D_KERNEL_LOOP(i, size) { in CSRSparseMatrixSoftmaxKernel3D()
553 GPU_1D_KERNEL_LOOP(row, rows) { in CSRSparseMatrixSoftmaxGradKernel2D()
583 GPU_1D_KERNEL_LOOP(i, size) { in CSRSparseMatrixSoftmaxGradKernel3D()
/external/tensorflow/tensorflow/core/kernels/linalg/
Dmatrix_set_diag_op_gpu.cu.cc51 GPU_1D_KERNEL_LOOP(index, num_threads) { in MatrixSetDiagKernel()
78 GPU_1D_KERNEL_LOOP(index, num_threads) { in MatrixCopyInputAndSetDiagKernel()
Dmatrix_diag_op_gpu.cu.cc51 GPU_1D_KERNEL_LOOP(index, num_threads) { in MatrixDiagKernel()
108 GPU_1D_KERNEL_LOOP(index, num_threads) { in MatrixDiagPartKernel()
Deye_functor_gpu.cu.cc36 GPU_1D_KERNEL_LOOP(index, num_threads) { in EyeKernel()
Dmatrix_band_part_op_gpu.cu.cc38 GPU_1D_KERNEL_LOOP(index, num_threads) { in MatrixBandPartKernel()

12