/external/tensorflow/tensorflow/core/kernels/ |
population_count_op_gpu.cu.cc | 39 CUDA_1D_KERNEL_LOOP(i, size) { output[i] = __popc(ldg(input + i)); } 46 CUDA_1D_KERNEL_LOOP(i, size) { 55 CUDA_1D_KERNEL_LOOP(i, size) { 63 CUDA_1D_KERNEL_LOOP(i, size) { output[i] = __popcll(ldg(input + i)); }
|
compare_and_bitpack_op_gpu.cu.cc | 45 CUDA_1D_KERNEL_LOOP(i, size) { 65 CUDA_1D_KERNEL_LOOP(i, size) { 85 CUDA_1D_KERNEL_LOOP(i, size) { 102 CUDA_1D_KERNEL_LOOP(i, size) {
|
fused_batch_norm_op.cu.cc | 31 CUDA_1D_KERNEL_LOOP(index, nthreads) { 49 CUDA_1D_KERNEL_LOOP(index, nthreads) {
|
diag_op_gpu.cu.cc | 33 CUDA_1D_KERNEL_LOOP(index, num_threads) { 87 CUDA_1D_KERNEL_LOOP(index, num_threads) {
|
matrix_set_diag_op_gpu.cu.cc | 34 CUDA_1D_KERNEL_LOOP(index, num_threads) { 46 CUDA_1D_KERNEL_LOOP(index, num_threads) {
|
dynamic_stitch_op_gpu.cu.cc | 39 CUDA_1D_KERNEL_LOOP(output_index, output_size) {
|
eye_functor_gpu.cu.cc | 36 CUDA_1D_KERNEL_LOOP(index, num_threads) {
|
matrix_band_part_op_gpu.cu.cc | 38 CUDA_1D_KERNEL_LOOP(index, num_threads) {
|
maxpooling_op_gpu.cu.cc | 72 CUDA_1D_KERNEL_LOOP(index, nthreads) { 116 CUDA_1D_KERNEL_LOOP(index, nthreads) { 146 CUDA_1D_KERNEL_LOOP(index, nthreads) { 185 CUDA_1D_KERNEL_LOOP(index, nthreads) { 244 CUDA_1D_KERNEL_LOOP(index, nthreads) { 272 CUDA_1D_KERNEL_LOOP(index, nthreads) { 312 CUDA_1D_KERNEL_LOOP(index, nthreads) { 371 CUDA_1D_KERNEL_LOOP(index, nthreads) { 378 #undef CUDA_1D_KERNEL_LOOP
|
searchsorted_op_gpu.cu.cc | 38 CUDA_1D_KERNEL_LOOP(work_unit_id, values_size * batch_size) { 50 CUDA_1D_KERNEL_LOOP(work_unit_id, values_size * batch_size) {
|
bias_op_gpu.cu.cc | 58 CUDA_1D_KERNEL_LOOP(index, nthreads) { 67 CUDA_1D_KERNEL_LOOP(index, nthreads) { 104 CUDA_1D_KERNEL_LOOP(index, nthreads) { 115 CUDA_1D_KERNEL_LOOP(index, nthreads) {
|
resize_nearest_neighbor_op_gpu.cu.cc | 41 CUDA_1D_KERNEL_LOOP(index, nthreads) { 72 CUDA_1D_KERNEL_LOOP(index, nthreads) { 101 CUDA_1D_KERNEL_LOOP(index, nthreads) { 132 CUDA_1D_KERNEL_LOOP(index, nthreads) {
|
cwise_op_clip_gpu.cu.cc | 29 CUDA_1D_KERNEL_LOOP(i, size_in) { 39 CUDA_1D_KERNEL_LOOP(i, size_in) { 48 CUDA_1D_KERNEL_LOOP(i, size_in) {
|
depthtospace_op_gpu.cu.cc | 41 CUDA_1D_KERNEL_LOOP(out_idx, nthreads) { 70 CUDA_1D_KERNEL_LOOP(input_idx, nthreads) { 108 CUDA_1D_KERNEL_LOOP(thread_idx, nthreads) {
|
spacetodepth_op_gpu.cu.cc | 39 CUDA_1D_KERNEL_LOOP(inp_idx, nthreads) { 69 CUDA_1D_KERNEL_LOOP(input_idx, nthreads) { 108 CUDA_1D_KERNEL_LOOP(thread_idx, nthreads) {
|
bucketize_op_gpu.cu.cc | 58 CUDA_1D_KERNEL_LOOP(i, size_in) {
|
gather_functor_gpu.cu.h | 36 CUDA_1D_KERNEL_LOOP(i, out_size) {
|
resize_bilinear_op_gpu.cu.cc | 41 CUDA_1D_KERNEL_LOOP(out_idx, nthreads) { 92 CUDA_1D_KERNEL_LOOP(in_idx, nthreads) { 156 CUDA_1D_KERNEL_LOOP(out_idx, nthreads) { 206 CUDA_1D_KERNEL_LOOP(in_idx, nthreads) {
|
sparse_tensor_dense_matmul_op_gpu.cu.cc | 39 CUDA_1D_KERNEL_LOOP(index, nnz * p) {
|
tile_functor_gpu.h | 39 CUDA_1D_KERNEL_LOOP(o_idx, nthreads) {
|
inplace_ops_functor_gpu.cu.cc | 33 CUDA_1D_KERNEL_LOOP(idx, nthreads) { 85 CUDA_1D_KERNEL_LOOP(idx, nthreads) {
|
pooling_ops_3d_gpu.cu.cc | 38 CUDA_1D_KERNEL_LOOP(index, nthreads) { 88 CUDA_1D_KERNEL_LOOP(index, nthreads) {
|
scatter_functor_gpu.cu.h | 79 CUDA_1D_KERNEL_LOOP(i, updates_size) { 100 CUDA_1D_KERNEL_LOOP(i, synthesized_updates_size) {
|
dilation_ops_gpu.cu.cc | 46 CUDA_1D_KERNEL_LOOP(out_idx, nthreads) { 85 CUDA_1D_KERNEL_LOOP(out_idx, nthreads) { 134 CUDA_1D_KERNEL_LOOP(out_idx, nthreads) {
|
/external/tensorflow/tensorflow/contrib/seq2seq/kernels/ |
beam_search_ops_gpu.cu.cc | 34 CUDA_1D_KERNEL_LOOP(i, batch_size * beam_width) {
|