This is an automated email from the ASF dual-hosted git repository.
bgawrych pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-mxnet.git.
from a2ad4db [API NEW][LINALG] Add vector_norm, matrix_norm (#20703)
add 1add250 [master][clang-format] Re-format cc. .h. .cu files; cond.
(#20704)
No new revisions were added by this update.
Summary of changes:
.../multi_threaded_inference.cc | 152 +--
cpp-package/example/utils.h | 56 +-
cpp-package/include/mxnet-cpp/base.h | 16 +-
cpp-package/include/mxnet-cpp/contrib.h | 135 +-
cpp-package/include/mxnet-cpp/executor.h | 143 ++-
cpp-package/include/mxnet-cpp/initializer.h | 83 +-
cpp-package/include/mxnet-cpp/io.h | 69 +-
cpp-package/include/mxnet-cpp/kvstore.h | 20 +-
cpp-package/include/mxnet-cpp/lr_scheduler.h | 45 +-
cpp-package/include/mxnet-cpp/metric.h | 41 +-
cpp-package/include/mxnet-cpp/model.h | 19 +-
cpp-package/include/mxnet-cpp/ndarray.h | 683 +++++-----
cpp-package/include/mxnet-cpp/op_map.h | 76 +-
cpp-package/include/mxnet-cpp/op_suppl.h | 122 +-
cpp-package/include/mxnet-cpp/op_util.h | 14 +-
cpp-package/include/mxnet-cpp/operator.h | 186 +--
cpp-package/include/mxnet-cpp/optimizer.h | 80 +-
cpp-package/include/mxnet-cpp/shape.h | 351 +++--
cpp-package/include/mxnet-cpp/symbol.h | 362 +++---
example/extensions/lib_api/libtest.cc | 8 +-
example/extensions/lib_custom_op/gemm_lib.cc | 68 +-
example/extensions/lib_custom_op/relu_lib.cc | 67 +-
example/extensions/lib_custom_op/relu_lib.cu | 59 +-
example/extensions/lib_custom_op/relu_lib.h | 44 +-
.../extensions/lib_custom_op/transposecsr_lib.cc | 101 +-
.../extensions/lib_custom_op/transposerowsp_lib.cc | 98 +-
example/extensions/lib_external_ops/min_ex-inl.h | 19 +-
example/extensions/lib_external_ops/min_ex.cc | 16 +-
example/extensions/lib_external_ops/min_ex.cu | 3 +-
example/extensions/lib_pass/pass_lib.cc | 5 +-
example/extensions/lib_subgraph/subgraph_lib.cc | 181 +--
include/mxnet/base.h | 100 +-
include/mxnet/c_api.h | 1340 ++++++++++----------
include/mxnet/c_api_error.h | 42 +-
include/mxnet/c_api_test.h | 21 +-
include/mxnet/engine.h | 53 +-
include/mxnet/executor.h | 94 +-
include/mxnet/expr_operator.h | 11 +-
include/mxnet/imperative.h | 112 +-
include/mxnet/io.h | 46 +-
include/mxnet/ir/expr.h | 2 +-
include/mxnet/kvstore.h | 50 +-
include/mxnet/lib_api.h | 1286 +++++++++++--------
include/mxnet/libinfo.h | 9 +-
include/mxnet/node/container.h | 66 +-
include/mxnet/node/node.h | 10 +-
include/mxnet/op_attr_types.h | 112 +-
include/mxnet/operator.h | 121 +-
include/mxnet/operator_util.h | 105 +-
include/mxnet/random_generator.h | 77 +-
include/mxnet/resource.h | 74 +-
include/mxnet/rtc.h | 18 +-
include/mxnet/runtime/c_runtime_api.h | 27 +-
include/mxnet/runtime/container.h | 43 +-
include/mxnet/runtime/container_ext.h | 289 +++--
include/mxnet/runtime/data_type.h | 22 +-
include/mxnet/runtime/ffi_helper.h | 40 +-
include/mxnet/runtime/memory.h | 52 +-
include/mxnet/runtime/ndarray.h | 2 +-
include/mxnet/runtime/ndarray_handle.h | 4 +-
include/mxnet/runtime/object.h | 193 +--
include/mxnet/runtime/packed_func.h | 345 +++--
include/mxnet/runtime/py_arg.h | 3 +-
include/mxnet/runtime/registry.h | 47 +-
include/mxnet/storage.h | 20 +-
include/mxnet/tensor_blob.h | 239 ++--
include/mxnet/tuple.h | 241 ++--
plugin/opencv/cv_api.cc | 150 ++-
plugin/opencv/cv_api.h | 37 +-
plugin/sframe/iter_sframe.cc | 98 +-
plugin/torch/torch_base.cc | 8 +-
plugin/torch/torch_base.h | 53 +-
plugin/torch/torch_criterion-inl.h | 85 +-
plugin/torch/torch_criterion.cc | 12 +-
plugin/torch/torch_criterion.cu | 6 +-
plugin/torch/torch_function.cc | 55 +-
plugin/torch/torch_function.h | 136 +-
plugin/torch/torch_module-inl.h | 136 +-
plugin/torch/torch_module.cc | 12 +-
plugin/torch/torch_module.cu | 6 +-
plugin/warpctc/warpctc-inl.h | 151 +--
plugin/warpctc/warpctc.cc | 16 +-
plugin/warpctc/warpctc.cu | 6 +-
src/api/_api_internal/_api_internal.cc | 4 +-
src/api/operator/numpy/np_tri_op.cc | 6 +-
src/c_api/c_api.cc | 6 +-
src/c_api/c_api_ndarray.cc | 3 +-
src/c_api/c_api_symbolic.cc | 6 +-
src/common/cuda/nvtx.h | 19 +-
src/common/cuda/utils.h | 4 +-
src/common/utils.h | 4 +-
src/engine/naive_engine.cc | 4 +-
src/engine/threaded_engine.h | 2 +-
src/engine/threaded_engine_perdevice.cc | 10 +-
src/engine/threaded_engine_pooled.cc | 6 +-
src/imperative/attach_op_resource_pass.cc | 5 +-
src/imperative/exec_pass.h | 2 +-
src/imperative/imperative.cc | 19 +-
src/imperative/imperative_utils.h | 10 +-
src/io/iter_prefetcher.h | 6 +-
src/kvstore/comm.h | 26 +-
src/kvstore/gpu_topology.h | 4 +-
src/kvstore/kvstore_dist.h | 16 +-
src/kvstore/p3store_dist.h | 2 +-
src/ndarray/ndarray.cc | 16 +-
src/nnvm/gradient.cc | 10 +-
src/nnvm/plan_memory.cc | 6 +-
src/operator/contrib/adamw.cu | 2 +
src/operator/contrib/bilinear_resize-inl.h | 16 +-
src/operator/contrib/bounding_box-inl.h | 30 +-
src/operator/contrib/bounding_box.cu | 6 +-
src/operator/contrib/deformable_psroi_pooling.cc | 40 +-
src/operator/contrib/deformable_psroi_pooling.cu | 40 +-
src/operator/contrib/intgemm/prepare_weight_op.cc | 6 +-
src/operator/contrib/multi_lamb.cc | 12 +-
src/operator/contrib/multi_lamb.cu | 12 +-
src/operator/contrib/multi_lans.cc | 8 +-
src/operator/contrib/multi_lans.cu | 12 +-
src/operator/contrib/multi_lars-inl.h | 8 +-
src/operator/control_flow.cc | 6 +-
src/operator/correlation.cc | 12 +-
src/operator/leaky_relu.cc | 12 +-
src/operator/mxnet_op.h | 56 +-
src/operator/nn/batch_norm-inl.h | 10 +-
src/operator/nn/batch_norm.cu | 36 +-
src/operator/nn/concat.cc | 4 +-
src/operator/nn/convolution.cc | 36 +-
src/operator/nn/cudnn/cudnn_batch_norm.cu | 186 ++-
src/operator/nn/cudnn/cudnn_batch_norm.h | 14 +-
src/operator/nn/cudnn/cudnn_convolution-inl.h | 831 ++++++++++++
src/operator/nn/cudnn/cudnn_deconvolution-inl.h | 852 +++++++++++++
src/operator/nn/cudnn/cudnn_pooling-inl.h | 48 +-
src/operator/nn/dnnl/dnnl_base-inl.h | 6 +-
src/operator/nn/dnnl/dnnl_base.cc | 41 +-
src/operator/nn/dnnl/dnnl_convolution.cc | 4 +-
src/operator/nn/dnnl/dnnl_deconvolution-inl.h | 10 +-
src/operator/nn/dnnl/dnnl_fully_connected.cc | 6 +-
src/operator/nn/dnnl/dnnl_rnn.cc | 41 +-
src/operator/nn/pooling-inl.h | 12 +-
src/operator/nn/pooling.cc | 33 +-
src/operator/nn/softmax-inl.h | 32 +-
src/operator/nn/softmax.cc | 6 +-
src/operator/npx_control_flow.cc | 6 +-
src/operator/numpy/linalg/np_lstsq.cc | 6 +-
src/operator/numpy/linalg/np_norm.cc | 4 +-
src/operator/numpy/np_bincount_op.cc | 6 +-
src/operator/numpy/np_boolean_mask_assign.cc | 6 +-
src/operator/numpy/np_broadcast_reduce_op_value.h | 6 +-
src/operator/numpy/np_delete_op-inl.h | 8 +-
src/operator/numpy/np_delete_op.cc | 6 +-
src/operator/numpy/np_einsum_op-inl.h | 4 +-
.../numpy/np_elemwise_broadcast_logic_op.h | 21 +-
src/operator/numpy/np_elemwise_broadcast_op.h | 4 +-
src/operator/numpy/np_elemwise_broadcast_op_add.cc | 37 +-
src/operator/numpy/np_elemwise_broadcast_op_add.cu | 5 +-
src/operator/numpy/np_elemwise_broadcast_op_mod.cc | 37 +-
src/operator/numpy/np_elemwise_broadcast_op_mod.cu | 5 +-
src/operator/numpy/np_elemwise_broadcast_op_mul.cc | 37 +-
src/operator/numpy/np_elemwise_broadcast_op_mul.cu | 4 +-
src/operator/numpy/np_elemwise_broadcast_op_pow.cc | 38 +-
src/operator/numpy/np_elemwise_broadcast_op_pow.cu | 5 +-
.../numpy/np_elemwise_broadcast_op_scalar.cc | 32 +-
.../numpy/np_elemwise_broadcast_op_scalar.cu | 16 +-
src/operator/numpy/np_elemwise_broadcast_op_sub.cc | 37 +-
src/operator/numpy/np_elemwise_broadcast_op_sub.cu | 4 +-
src/operator/numpy/np_insert_op_scalar-inl.h | 6 +-
src/operator/numpy/np_insert_op_slice-inl.h | 6 +-
src/operator/numpy/np_insert_op_tensor-inl.h | 6 +-
src/operator/numpy/np_interp_op.cc | 6 +-
src/operator/numpy/np_moments_op.cc | 6 +-
src/operator/numpy/np_percentile_op.cc | 6 +-
src/operator/numpy/np_true_divide.cc | 6 +-
src/operator/numpy/np_unique_op.cc | 7 +-
src/operator/numpy/random/np_bernoulli_op.cc | 6 +-
src/operator/numpy/random/np_exponential_op.cc | 6 +-
src/operator/numpy/random/np_pareto_op.cc | 6 +-
src/operator/numpy/random/np_power_op.cc | 6 +-
src/operator/numpy/random/np_rayleigh_op.cc | 6 +-
src/operator/numpy/random/np_weibull_op.cc | 6 +-
src/operator/optimizer_op-inl.h | 6 +-
src/operator/optimizer_op.cc | 4 +-
src/operator/optimizer_op.cu | 4 +-
src/operator/random/sampler.h | 8 +-
src/operator/random/shuffle_op.cu | 4 +-
src/operator/sequence_last-inl.h | 12 +-
src/operator/subgraph/build_subgraph.cc | 6 +-
src/operator/subgraph/dnnl/dnnl_conv.cc | 13 +-
src/operator/subgraph/dnnl/dnnl_fc.cc | 4 +-
src/operator/subgraph/tensorrt/nnvm_to_onnx.cc | 2 +-
src/operator/subgraph/tensorrt/onnx_to_tensorrt.h | 12 +-
src/operator/subgraph/tensorrt/tensorrt-inl.h | 2 +-
src/operator/tensor/amp_cast.cc | 12 +-
src/operator/tensor/broadcast_reduce-inl.h | 6 +-
src/operator/tensor/dot-inl.h | 12 +-
src/operator/tensor/elemwise_binary_op-inl.h | 16 +-
src/operator/tensor/elemwise_binary_scalar_op.h | 4 +-
src/operator/tensor/histogram.cc | 6 +-
src/operator/tensor/la_op-inl.h | 20 +-
src/operator/tensor/la_op.h | 12 +-
src/operator/tensor/matrix_op.cu | 10 +-
src/operator/tensor/reduce_rtc.cc | 12 +-
src/operator/tensor/square_sum.cc | 2 +
src/operator/tensor/square_sum.cu | 2 +
src/profiler/aggregate_stats.cc | 12 +-
src/runtime/container.cc | 4 +-
src/serialization/cnpy.cc | 8 +-
src/storage/pooled_storage_manager.h | 2 +-
tests/cpp/engine/engine_shutdown_test.cc | 17 +-
tests/cpp/engine/omp_test.cc | 35 +-
tests/cpp/engine/thread_local_test.cc | 64 +-
tests/cpp/engine/threaded_engine_test.cc | 272 ++--
tests/cpp/include/test_core_op.h | 192 +--
tests/cpp/include/test_legacy_op.h | 245 ++--
tests/cpp/include/test_ndarray_utils.h | 115 +-
tests/cpp/include/test_op.h | 90 +-
tests/cpp/include/test_op_runner.h | 143 +--
tests/cpp/include/test_perf.h | 119 +-
tests/cpp/include/test_tune.h | 122 +-
tests/cpp/include/test_util.h | 249 ++--
tests/cpp/kvstore/gpu_topology_test.cc | 278 ++--
tests/cpp/misc/base.cc | 30 +-
tests/cpp/operator/activation_perf.cc | 69 +-
tests/cpp/operator/batchnorm_test.cc | 872 +++++++------
tests/cpp/operator/coreop_perf.cc | 61 +-
tests/cpp/operator/dnnl_operator_test.cc | 4 +-
tests/cpp/operator/dropout_perf.cc | 58 +-
tests/cpp/operator/fully_conn_perf.cc | 62 +-
tests/cpp/operator/krprod_test.cc | 115 +-
tests/cpp/operator/runner/core_op_runner_test.cc | 196 ++-
tests/cpp/operator/slice_channel_perf.cc | 52 +-
tests/cpp/operator/tune/operator_tune_test.cc | 66 +-
tests/cpp/storage/storage_test.cc | 26 +-
tests/cpp/test_main.cc | 23 +-
tools/im2rec.cc | 275 ++--
234 files changed, 9389 insertions(+), 7384 deletions(-)
mode change 100755 => 100644 include/mxnet/tensor_blob.h
create mode 100644 src/operator/nn/cudnn/cudnn_convolution-inl.h
create mode 100644 src/operator/nn/cudnn/cudnn_deconvolution-inl.h
