[submodule] Remove soon to be obsolete dnnl nomenclature from mxnet

.licenserc.yaml

@@ -35,7 +35,7 @@ header:
     - 'src/operator/contrib/multi_proposal.cu'
     - 'src/operator/contrib/psroi_pooling.cc'
     - 'src/operator/contrib/psroi_pooling.cu'
-    - 'src/operator/nn/mkldnn/mkldnn_base-inl.h'
+    - 'src/operator/nn/dnnl/dnnl_base-inl.h'
     # files licensed under boost license
     - 'cmake/Modules/FindJeMalloc.cmake'
     # files licensed under bsd 3-clause
@@ -64,7 +64,7 @@ header:
     - 'include/mshadow' # symlink to 3rdparty/mshadow/mshadow
     - 'include/onednn' # symlinks to 3rdparty/onednn
     # test/build data
-    - 'tests/python/mkl/data/test_mkldnn_test_mkldnn_model_model1.json'
+    - 'tests/python/dnnl/data/test_dnnl_test_dnnl_model_model1.json'
 
 
   comment: on-failure

CMakeLists.txt

@@ -273,16 +273,16 @@ if(USE_ONEDNN)
   endif()
 
   function(load_onednn)
-    set(MKLDNN_BUILD_TESTS OFF CACHE INTERNAL "" FORCE)
-    set(MKLDNN_BUILD_EXAMPLES OFF CACHE INTERNAL "" FORCE)
-    set(MKLDNN_ARCH_OPT_FLAGS "" CACHE INTERNAL "" FORCE)
-    set(MKLDNN_ENABLE_JIT_PROFILING OFF CACHE INTERNAL "" FORCE)
-    set(MKLDNN_LIBRARY_TYPE STATIC CACHE INTERNAL "" FORCE)
+    set(DNNL_BUILD_TESTS OFF CACHE INTERNAL "" FORCE)
+    set(DNNL_BUILD_EXAMPLES OFF CACHE INTERNAL "" FORCE)
+    set(DNNL_ARCH_OPT_FLAGS "" CACHE INTERNAL "" FORCE)
+    set(DNNL_ENABLE_JIT_PROFILING OFF CACHE INTERNAL "" FORCE)
+    set(DNNL_LIBRARY_TYPE STATIC CACHE INTERNAL "" FORCE)
     set(DNNL_ENABLE_CONCURRENT_EXEC ON CACHE INTERNAL "" FORCE)
     set(DNNL_ENABLE_PRIMITIVE_CACHE ON CACHE INTERNAL "" FORCE)
 
     if(NOT USE_OPENMP)
-      set(MKLDNN_CPU_RUNTIME SEQ CACHE INTERNAL "" FORCE)
+      set(DNNL_CPU_RUNTIME SEQ CACHE INTERNAL "" FORCE)
     endif()
 
     set(CMAKE_INSTALL_INCLUDEDIR "${CMAKE_INSTALL_INCLUDEDIR}/onednn")

CONTRIBUTORS.md

@@ -104,7 +104,7 @@ healthy project. The PPMC actively seeks to appoint new committers from the list
 * [Aaron Markham](https://github.com/aaronmarkham)
 * [Alex Zai](https://github.com/azai91)
 * [Anirudh Acharya](https://github.com/anirudhacharya)
-* [Anna Karbownik]((https://github.com/akarbown)
+* [Anna Karbownik](https://github.com/akarbown)
 * [Aston Zhang](https://github.com/astonzhang)
 * [Chaitanya Bapat](https://github.com/ChaiBapchya)
 * [Ciyong Chen](https://github.com/ciyongch)

MKLDNN_README.md → DNNL_README.md

@@ -18,4 +18,4 @@
   ~
 -->
 
-File is moved to [docs/tutorials/mkldnn/MKLDNN_README.md](docs/python_docs/python/tutorials/performance/backend/mkldnn/mkldnn_readme.md).
+File is moved to [docs/python_docs/python/tutorials/performance/backend/dnnl/dnnl_readme.md](docs/python_docs/python/tutorials/performance/backend/dnnl/dnnl_readme.md).

LICENSE

@@ -252,7 +252,7 @@
     src/operator/contrib/multi_proposal.cu
     src/operator/contrib/psroi_pooling.cc
     src/operator/contrib/psroi_pooling.cu
-    src/operator/nn/mkldnn/mkldnn_base-inl.h
+    src/operator/nn/dnnl/dnnl_base-inl.h
 
     =======================================================================================
     MIT license

README.md

@@ -91,7 +91,7 @@ What's New
 
 ### Ecosystem News
 
-* [ONEDNN for Faster CPU Performance](docs/python_docs/python/tutorials/performance/backend/mkldnn/mkldnn_readme.md)
+* [oneDNN for Faster CPU Performance](docs/python_docs/python/tutorials/performance/backend/dnnl/dnnl_readme.md)
 * [MXNet Memory Monger, Training Deeper Nets with Sublinear Memory Cost](https://github.com/dmlc/mxnet-memonger)
 * [Tutorial for NVidia GTC 2016](https://github.com/dmlc/mxnet-gtc-tutorial)
 * [MXNet.js: Javascript Package for Deep Learning in Browser (without server)](https://github.com/dmlc/mxnet.js/)

cd/python/docker/test_python_image.sh

@@ -33,7 +33,7 @@ fi
 
 # Execute tests
 if [[ $mxnet_variant != native ]]; then
-    python3 tests/python/mkl/test_mkldnn.py
+    python3 tests/python/dnnl/test_dnnl.py
 fi
 
 # TODO: Add more tests (18549)

cd/python/pypi/pypi_package.sh

@@ -22,11 +22,10 @@ set -ex
 export mxnet_variant=${1:?"Please specify the mxnet variant"}
 
 # Due to this PR: https://github.com/apache/incubator-mxnet/pull/14899
-# The setup.py expects that mkldnn_version.h be present in
+# The setup.py expects that dnnl_version.h be present in
 # mxnet-build/3rdparty/onednn/build/install/include
 # The artifact repository stores this file in the dependencies
 # and CD unpacks it to a directory called cd_misc
-# Nov. 2019 Update: With v1.1, MKL-DNN is renaming to DNNL. Hence changing the prefix of file name.
 if [ -f "cd_misc/dnnl_version.h" ]; then
   mkdir -p 3rdparty/onednn/include/oneapi/dnnl
   cp cd_misc/dnnl_version.h 3rdparty/onednn/include/oneapi/dnnl/.

ci/docker/runtime_functions.sh

@@ -801,7 +801,7 @@ cd_unittest_ubuntu() {
     fi
 
     if [[ ${mxnet_variant} = *mkl ]]; then
-        OMP_NUM_THREADS=$(expr $(nproc) / 4) pytest -n 4 --durations=50 --verbose tests/python/mkl
+        OMP_NUM_THREADS=$(expr $(nproc) / 4) pytest -n 4 --durations=50 --verbose tests/python/dnnl
     fi
 }
 
@@ -841,7 +841,7 @@ unittest_ubuntu_python3_cpu_onednn() {
     MXNET_ENGINE_TYPE=NaiveEngine \
                      OMP_NUM_THREADS=$(expr $(nproc) / 4) pytest -m 'not serial' -k 'test_operator' -n 4 --durations=50 --cov-report xml:tests_unittest.xml --cov-append --verbose tests/python/unittest
     pytest -m 'serial' --durations=50 --cov-report xml:tests_unittest.xml --cov-append --verbose tests/python/unittest
-    pytest --durations=50 --cov-report xml:tests_mkl.xml --verbose tests/python/mkl
+    pytest --durations=50 --cov-report xml:tests_mkl.xml --verbose tests/python/dnnl
 }
 
 unittest_array_api_standardization() {

cpp-package/example/inference/README.md

@@ -30,7 +30,7 @@ This directory contains following examples. In order to run the examples, ensure
 
 ## [imagenet_inference.cpp](<https://github.com/apache/incubator-mxnet/blob/master/cpp-package/example/inference/imagenet_inference.cpp>)
 
-This example demonstrates image classification workflow with pre-trained models using MXNet C++ API. Now this script also supports inference with quantized CNN models generated by Intel® MKL-DNN (see this [quantization flow](https://github.com/apache/incubator-mxnet/blob/master/example/quantization/README.md)). By using C++ API, the latency of most models will be reduced to some extent compared with current Python implementation.
+This example demonstrates image classification workflow with pre-trained models using MXNet C++ API. Now this script also supports inference with quantized CNN models generated by oneDNN (see this [quantization flow](https://github.com/apache/incubator-mxnet/blob/master/example/quantization/README.md)). By using C++ API, the latency of most models will be reduced to some extent compared with current Python implementation.
 
 Most of CNN models have been tested on Linux systems. And 50000 images are used to collect accuracy numbers. Please refer to this [README](https://github.com/apache/incubator-mxnet/blob/master/example/quantization/README.md) for  more details about accuracy.
 

docs/python_docs/python/tutorials/index.rst

@@ -84,10 +84,10 @@ Performance
       How to use int8 in your model to boost training speed.
 
    .. card::
-      :title: MKL-DNN
+      :title: oneDNN
       :link: performance/backend/mkldnn/index.html
 
-      How to get the most from your CPU by using Intel's MKL-DNN.
+      How to get the most from your CPU by using oneDNN.
 
    .. card::
       :title: TVM

docs/python_docs/python/tutorials/performance/backend/mkldnn/mkldnn_readme.md → docs/python_docs/python/tutorials/performance/backend/dnnl/dnnl_readme.md

@@ -208,11 +208,11 @@ o = exe.outputs[0]
 t = o.asnumpy()
 ```
 
-More detailed debugging and profiling information can be logged by setting the environment variable 'MKLDNN_VERBOSE':
+More detailed debugging and profiling information can be logged by setting the environment variable 'DNNL_VERBOSE':
 ```
-export MKLDNN_VERBOSE=1
+export DNNL_VERBOSE=1
 ```
-For example, by running above code snippet, the following debugging logs providing more insights on ONEDNN primitives `convolution` and `reorder`. That includes: Memory layout, infer shape and the time cost of primitive execution.
+For example, by running above code snippet, the following debugging logs providing more insights on oneDNN primitives `convolution` and `reorder`. That includes: Memory layout, infer shape and the time cost of primitive execution.
 ```
 dnnl_verbose,info,DNNL v1.1.2 (commit cb2cc7ac17ff4e2ef50805c7048d33256d82be4d)
 dnnl_verbose,info,Detected ISA is Intel AVX-512 with Intel DL Boost
@@ -281,7 +281,7 @@ MKL_VERBOSE SGEMM(T,N,12,10,8,0x7f7f927b1378,0x1bc2140,8,0x1ba8040,8,0x7f7f927b1
 Graph optimization with subgraph is available and enabled by default in master branch. For MXNet release v1.5, you can manually enable it by:
 
 ```
-export MXNET_SUBGRAPH_BACKEND=MKLDNN
+export MXNET_SUBGRAPH_BACKEND=ONEDNN
 ```
 
 This limitations of this experimental feature are:
@@ -293,7 +293,7 @@ This limitations of this experimental feature are:
 
 <h2 id="7">Quantization and Inference with INT8</h2>
 
-Benefiting from Intel ONEDNN, MXNet built with Intel ONEDNN brings outstanding performance improvement on quantization and inference with INT8 Intel CPU Platform on Intel Xeon Scalable Platform.
+Benefiting from oneDNN, MXNet built with oneDNN brings outstanding performance improvement on quantization and inference with INT8 Intel CPU Platform on Intel Xeon Scalable Platform.
 
 - [CNN Quantization Examples](https://github.com/apache/incubator-mxnet/tree/master/example/quantization).
 
@@ -303,6 +303,6 @@ Benefiting from Intel ONEDNN, MXNet built with Intel ONEDNN brings outstanding p
 
 - For questions or support specific to MKL, visit the [Intel MKL](https://software.intel.com/en-us/mkl) website.
 
-- For questions or support specific to ONEDNN, visit the [Intel ONEDNN](https://github.com/oneapi-src/oneDNN) website.
+- For questions or support specific to oneDNN, visit the [oneDNN](https://github.com/oneapi-src/oneDNN) website.
 
-- If you find bugs, please open an issue on GitHub for [MXNet with MKL](https://github.com/apache/incubator-mxnet/labels/MKL) or [MXNet with ONEDNN](https://github.com/apache/incubator-mxnet/labels/MKLDNN).
+- If you find bugs, please open an issue on GitHub for [MXNet with MKL](https://github.com/apache/incubator-mxnet/labels/MKL) or [MXNet with oneDNN](https://github.com/apache/incubator-mxnet/labels/MKLDNN).

docs/python_docs/python/tutorials/performance/backend/mkldnn/index.rst → docs/python_docs/python/tutorials/performance/backend/dnnl/index.rst

@@ -15,22 +15,22 @@
    specific language governing permissions and limitations
    under the License.
 
-Intel MKL-DNN
+oneDNN
 =============
 
 .. container:: cards
 
    .. card::
-      :title: MKL-DNN Installation and Verification
-      :link: mkldnn_readme
+      :title: oneDNN Installation and Verification
+      :link: dnnl_readme
 
-      A guide on using MKL-DNN with MXNet.
+      A guide on using oneDNN with MXNet.
 
    .. card::
-      :title: MKL-DNN Quantization
-      :link: mkldnn_quantization
+      :title: oneDNN Quantization
+      :link: dnnl_quantization
 
-      How to perform quantization with MKLDNN
+      How to perform quantization with oneDNN
 
 .. toctree::
    :hidden:

docs/python_docs/python/tutorials/performance/backend/index.rst

@@ -22,10 +22,10 @@ The following tutorials will help you learn how to use backend tools to boost pe
 .. container:: cards
 
   .. card::
-     :title: MKL-DNN
-     :link: mkldnn/index.html
+     :title: oneDNN
+     :link: dnnl/index.html
 
-     How to get the most from your CPU by using Intel's MKL-DNN.
+     How to get the most from your CPU by using oneDNN.
 
   .. card::
      :title: TVM
@@ -50,7 +50,7 @@ The following tutorials will help you learn how to use backend tools to boost pe
    :hidden:
    :maxdepth: 1
 
-   mkldnn/index
+   dnnl/index
    tvm
    profiler
    amp

docs/python_docs/python/tutorials/performance/backend/profiler.md

@@ -211,11 +211,11 @@ Let's zoom in to check the time taken by operators
 The above picture visualizes the sequence in which the operators were executed and the time taken by each operator.
 
 ### Profiling ONEDNN Operators
-Reagrding ONEDNN operators, the library has already provided the internal profiling tool. Firstly, you need set `MKLDNN_VERBOSE=1` to enable internal profiler.
+Reagrding ONEDNN operators, the library has already provided the internal profiling tool. Firstly, you need set `DNNL_VERBOSE=1` to enable internal profiler.
 
-`$ MKLDNN_VERBOSE=1 python my_script.py > mkldnn_verbose.log`
+`$ DNNL_VERBOSE=1 python my_script.py > dnnl_verbose.log`
 
-Now, the detailed profiling insights of each ONEDNN prmitive are saved into `mkldnn_verbose.log` (like below).
+Now, the detailed profiling insights of each oneDNN prmitive are saved into `dnnl_verbose.log` (like below).
 
 ```
 dnnl_verbose,info,DNNL v1.1.2 (commit cb2cc7ac17ff4e2ef50805c7048d33256d82be4d)
@@ -225,13 +225,13 @@ dnnl_verbose,exec,cpu,convolution,jit:avx512_common,forward_inference,src_f32::b
 
 For example, if you want to calculate the total executing time of `convolution` primitive, you can just run:
 
-`$ cat mkldnn_verbose.log | grep "exec,cpu,convolution" | awk 'BEGIN{FS=","} {SUM+=$11} END {print SUM}'`
+`$ cat dnnl_verbose.log | grep "exec,cpu,convolution" | awk 'BEGIN{FS=","} {SUM+=$11} END {print SUM}'`
 
-Moreover, you can set `MKLDNN_VERBOSE=2` to collect both creating and executing time of each primitive.
+Moreover, you can set `DNNL_VERBOSE=2` to collect both creating and executing time of each primitive.
 
-`$ cat mkldnn_verbose.log | grep "create,cpu,convolution" | awk 'BEGIN{FS=","} {SUM+=$11} END {print SUM}'`
+`$ cat dnnl_verbose.log | grep "create,cpu,convolution" | awk 'BEGIN{FS=","} {SUM+=$11} END {print SUM}'`
 
-`$ cat mkldnn_verbose.log | grep "exec,cpu,convolution" | awk 'BEGIN{FS=","} {SUM+=$11} END {print SUM}'`
+`$ cat dnnl_verbose.log | grep "exec,cpu,convolution" | awk 'BEGIN{FS=","} {SUM+=$11} END {print SUM}'`
 
 
 ### Profiling Custom Operators

docs/python_docs/python/tutorials/performance/index.rst

@@ -76,10 +76,10 @@ Accelerated Backend
    ..
       TBD Content
       .. card::
-         :title: MKL-DNN
-         :link: backend/mkldnn/mkldnn_readme
+         :title: oneDNN
+         :link: backend/dnnl/dnnl_readme
 
-         How to get the most from your CPU by using Intel's MKL-DNN.
+         How to get the most from your CPU by using oneDNN.
 
       .. card::
          :title: TVM

docs/static_site/src/pages/api/faq/env_var.md

@@ -375,9 +375,9 @@ If ctypes is used, it must be `mxnet._ctypes.ndarray.NDArrayBase`.
   - This variable controls how many CuDNN dropout state resources to create for each GPU context for use in operator.
 
 * MXNET_SUBGRAPH_BACKEND
-  - Values: String ```(default="MKLDNN")``` if ONEDNN is avaliable, otherwise ```(default="")```
+  - Values: String ```(default="ONEDNN")``` if oneDNN is available, otherwise ```(default="")```
   - This variable controls the subgraph partitioning in MXNet.
-  - This variable is used to perform ONEDNN FP32 operator fusion and quantization. Please refer to the [ONEDNN operator list](https://github.com/apache/incubator-mxnet/blob/v1.5.x/docs/tutorials/mkldnn/operator_list.md) for how this variable is used and the list of fusion passes.
+  - This variable is used to perform oneDNN FP32 operator fusion and quantization. Please refer to the [oneDNN operator list](https://github.com/apache/incubator-mxnet/blob/v1.5.x/docs/tutorials/mkldnn/operator_list.md) for how this variable is used and the list of fusion passes.
   - Set ```MXNET_SUBGRAPH_BACKEND=NONE``` to disable subgraph backend.
 
 * MXNET_SAFE_ACCUMULATION

docs/static_site/src/pages/api/faq/perf.md

@@ -58,7 +58,7 @@ We also find that setting the following environment variables can help:
 | :-------- | :---------- |
 | `OMP_NUM_THREADS`            | Suggested value: `vCPUs / 2` in which `vCPUs` is the number of virtual CPUs. For more information, please see the guide for [setting the number of threads using an OpenMP environment variable](https://software.intel.com/en-us/mkl-windows-developer-guide-setting-the-number-of-threads-using-an-openmp-environment-variable) |
 | `KMP_AFFINITY`               | Suggested value: `granularity=fine,compact,1,0`.  For more information, please see the guide for [Thread Affinity Interface (Linux* and Windows*)](https://software.intel.com/en-us/node/522691). |
-| `MXNET_SUBGRAPH_BACKEND` | Set to ONEDNN to enable the [subgraph feature](https://cwiki.apache.org/confluence/display/MXNET/MXNet+Graph+Optimization+and+Quantization+based+on+subgraph+and+MKL-DNN) for better performance. For more information please see [Build/Install MXNet with ONEDNN](https://mxnet.apache.org/api/python/docs/tutorials/performance/backend/mkldnn/mkldnn_readme.html)|
+| `MXNET_SUBGRAPH_BACKEND` | Set to ONEDNN to enable the [subgraph feature](https://cwiki.apache.org/confluence/display/MXNET/MXNet+Graph+Optimization+and+Quantization+based+on+subgraph+and+MKL-DNN) for better performance. For more information please see [Build/Install MXNet with oneDNN](https://mxnet.apache.org/api/python/docs/tutorials/performance/backend/dnnl/dnnl_readme.html)|
 
 Note that _MXNet_ treats all CPUs on a single machine as a single device.
 So whether you specify `cpu(0)` or `cpu()`, _MXNet_ will use all CPU cores on the machine.

include/mxnet/base.h

@@ -541,7 +541,7 @@ inline std::ostream& operator<<(std::ostream &out, const Context &ctx) {
 
 
 #if MXNET_USE_ONEDNN == 1 || MXNET_USE_INTGEMM == 1
-constexpr size_t kMKLDNNAlign = 64;
+constexpr size_t kDNNLAlign = 64;
 #endif
 
 }  // namespace mxnet