doc: updated name to oneDNN

Author: vpirogov

.github/ISSUE_TEMPLATE/bug_report.md

@@ -11,11 +11,11 @@ Provide a short summary of the issue. Sections below provide guidance on what
 factors are considered important to reproduce an issue.
 
 # Version
-Report DNNL version and githash. Version information is printed to stdout
+Report oneDNN version and githash. Version information is printed to stdout
 in [verbose mode](https://oneapi-src.github.io/oneDNN/dev_guide_verbose.html).
 
 # Environment
-DNNL includes hardware-specific optimizations and may behave
+oneDNN includes hardware-specific optimizations and may behave
 differently on depending on the compiler and build environment. Include
 the following information to help reproduce the issue:
 * CPU make and model (try `lscpu`; if your `lscpu` does not list CPU flags,

CMakeLists.txt

@@ -70,8 +70,8 @@ if("${CMAKE_BUILD_TYPE}" STREQUAL "")
         "Choose the type of build, options are: None Debug Release RelWithDebInfo MinSizeRel ...")
 endif()
 
-set(PROJECT_NAME "DNNL")
-set(PROJECT_FULL_NAME "Deep Neural Network Library (DNNL)")
+set(PROJECT_NAME "oneDNN")
+set(PROJECT_FULL_NAME "oneAPI Deep Neural Network Library (oneDNN)")
 set(PROJECT_VERSION "1.4.0")
 
 set(LIB_NAME dnnl)
@@ -84,7 +84,7 @@ else()
 endif()
 
 if (NOT CMAKE_SIZEOF_VOID_P EQUAL 8)
-    message(FATAL_ERROR "DNNL supports 64 bit platforms only")
+    message(FATAL_ERROR "oneDNN supports 64 bit platforms only")
 endif()
 
 # Set the target architecture.

CONTRIBUTING.md

@@ -1,6 +1,6 @@
 # Contributing guidelines
 
-If you have improvements to the DNNL code, please send us your pull
+If you have improvements to the oneDNN code, please send us your pull
 requests! For getting started, see GitHub
 [howto](https://help.github.com/en/articles/about-pull-requests).
 
@@ -27,7 +27,7 @@ list.
 
 ## Library functionality guidelines
 
-DNNL focuses on functionality that satisfies all of the following
+oneDNN focuses on functionality that satisfies all of the following
 criteria:
 
 1. *Performance*: the functionality has material impact on a workload level.
@@ -53,28 +53,28 @@ primitives. In the RFC, please provide the following details:
   significant percentage of the total time and thus is a good optimization
   candidate.
 
-* The definition of the operation as an DNNL primitive including interface
+* The definition of the operation as a oneDNN primitive including interface
   and semantics. It is OK to have sketches for the interface, but the
   semantics should be fairly well defined.
 
 * If possible, provide information about similar compute operations. Sometimes
-  DNNL primitives are super-sets of operations available in the
+  oneDNN primitives are super-sets of operations available in the
   deep learning applications for the sake of greater portability across them.
 
 ## Code contribution guidelines
 
 The code must be:
 
-* *Tested*: DNNL uses gtests for lightweight functional testing and
+* *Tested*: oneDNN uses gtests for lightweight functional testing and
   benchdnn for functionality that requires both performance and functional
   testing.
 
-* *Documented*: DNNL uses Doxygen for inline comments in public header
+* *Documented*: oneDNN uses Doxygen for inline comments in public header
   files that is used to build reference manual and markdown (also processed by
   Doxygen) for user guide.
 
-* *Portable*: DNNL supports different operating systems, CPU and GPU
-  architectures, compilers, and run-times. The new code should be complaint
+* *Portable*: oneDNN supports different operating systems, CPU and GPU
+  architectures, compilers, and run-times. The new code should be compliant
   with the [System Requirements](README.md#system-requirements).
 
 ## Coding style
@@ -96,14 +96,14 @@ If in doubt, use the `clang-format`:
 ```sh
 clang-format -style=file -i foo.cpp
 ```
-This will format code using the `_clang_format` file found in the Intel
-DNNL top level directory.
+This will format code using the `_clang_format` file found in the oneDNN
+top level directory.
 
 Coding style is secondary to the general code design.
 
 ## Unit tests
 
-DNNL uses gtests for lightweight functional testing and benchdnn for
+oneDNN uses gtests for lightweight functional testing and benchdnn for
 performance and functional testing.
 
 Be sure to extend the existing tests when fixing an issue.

README.binary.in

@@ -1,15 +1,15 @@
-Deep Neural Network Library (DNNL)
-==================================
+oneAPI Deep Neural Network Library (oneDNN)
+===========================================
 
-Deep Neural Network Library (DNNL) is an
+oneAPI Deep Neural Network Library (oneDNN) is an
 open-source performance library for deep learning applications. The library
 includes basic building blocks for neural networks optimized
 for Intel Architecture Processors and Intel Processor Graphics.
 
-This package contains DNNL v@PROJECT_VERSION@ (@DNNL_VERSION_HASH@).
+This package contains oneDNN v@PROJECT_VERSION@ (@DNNL_VERSION_HASH@).
 
 You can find information about the latest version and release notes
-at DNNL Github (https://github.com/oneapi-src/oneDNN/releases).
+at oneDNN Github (https://github.com/oneapi-src/oneDNN/releases).
 
 Documentation
 -------------
@@ -23,7 +23,7 @@ provides comprehensive reference of the library API.
 System Requirements
 -------------------
 
-DNNL supports systems based on Intel 64 or AMD64 architecture.
+oneDNN supports systems based on Intel 64 or AMD64 architecture.
 
 The library is optimized for the following CPUs:
 * Intel Atom processor with Intel SSE4.1 support
@@ -34,7 +34,7 @@ The library is optimized for the following CPUs:
 * Intel Xeon Scalable processor (formerly Skylake and Cascade Lake)
 * future Intel Xeon Scalable processor (code name Cooper Lake)
 
-DNNL detects instruction set architecture (ISA) in the runtime and uses
+oneDNN detects instruction set architecture (ISA) in the runtime and uses
 just-in-time (JIT) code generation to deploy the code optimized
 for the latest supported ISA.
 
@@ -98,7 +98,7 @@ prior notification in future releases:
 License
 -------
 
-DNNL is licensed under Apache License Version 2.0. Refer to the "LICENSE"
+oneDNN is licensed under Apache License Version 2.0. Refer to the "LICENSE"
 file for the full license text and copyright notice.
 
 This distribution includes third party software governed by separate license

README.md

@@ -1,5 +1,5 @@
-Deep Neural Network Library (DNNL)
-==================================
+oneAPI Deep Neural Network Library (oneDNN)
+===========================================
 
 > **Note**
 >
@@ -11,15 +11,15 @@ Deep Neural Network Library (DNNL)
 > Version 1.0 brings incompatible changes to the 0.20 version. Please read
 > [Version 1.0 Transition Guide](https://oneapi-src.github.io/oneDNN/dev_guide_transition_to_v1.html).
 
-Deep Neural Network Library (DNNL) is an
+oneAPI Deep Neural Network Library (oneDNN) is an
 open-source performance library for deep learning applications. The library
 includes basic building blocks for neural networks optimized
 for Intel Architecture Processors and Intel Processor Graphics.
 
-DNNL is intended for deep learning applications and framework
+oneDNN is intended for deep learning applications and framework
 developers interested in improving application performance
 on Intel CPUs and GPUs. Deep learning practitioners should use one of the
-applications enabled with DNNL:
+applications enabled with oneDNN:
 * [Apache\* MXNet](https://mxnet.apache.org)
 * [BigDL](https://github.com/intel-analytics/BigDL)
 * [Caffe\* Optimized for Intel Architecture](https://github.com/intel/caffe)
@@ -77,7 +77,7 @@ If the configuration you need is not available, you can
 
 # System Requirements
 
-DNNL supports systems based on
+oneDNN supports systems based on
 [Intel 64 or AMD64 architecture](https://en.wikipedia.org/wiki/X86-64).
 
 The library is optimized for the following CPUs:
@@ -89,13 +89,13 @@ The library is optimized for the following CPUs:
 * Intel Xeon Scalable processor (formerly Skylake and Cascade Lake)
 * future Intel Xeon Scalable processor (code name Cooper Lake)
 
-DNNL detects instruction set architecture (ISA) in the runtime and uses
+oneDNN detects instruction set architecture (ISA) at runtime and uses
 just-in-time (JIT) code generation to deploy the code optimized
 for the latest supported ISA.
 
 > **WARNING**
 >
-> On macOS, applications that use DNNL may need to request special
+> On macOS, applications that use oneDNN may need to request special
 > entitlements if they use the hardened runtime. See the
 > [linking guide](https://oneapi-src.github.io/oneDNN/dev_guide_link.html)
 > for more details.
@@ -107,7 +107,7 @@ The library is optimized for the following GPUs:
 
 ## Requirements for Building from Source
 
-DNNL supports systems meeting the following requirements:
+oneDNN supports systems meeting the following requirements:
 * Operating system with Intel 64 architecture support
 * C++ compiler with C++11 standard support
 * [CMake](https://cmake.org/download/) 2.8.11 or later
@@ -120,7 +120,7 @@ dependencies.
 ### CPU Engine
 
 Intel Architecture Processors and compatible devices are supported by the
-DNNL CPU engine. The CPU engine is built by default and cannot
+oneDNN CPU engine. The CPU engine is built by default and cannot
 be disabled at build time. The engine can be configured to use the OpenMP or
 TBB threading runtime. The following additional requirements apply:
 * OpenMP runtime requires C++ compiler with OpenMP 2.0 or later standard support
@@ -133,7 +133,7 @@ the Intel C++ Compiler for the best performance results.
 
 ### GPU Engine
 
-Intel Processor Graphics is supported by the DNNL GPU engine. The GPU
+Intel Processor Graphics is supported by the oneDNN GPU engine. The GPU
 engine is disabled in the default build configuration. The following
 additional requirements apply when GPU engine is enabled:
 * OpenCL\* runtime library (OpenCL version 1.2 or later)
@@ -142,7 +142,7 @@ additional requirements apply when GPU engine is enabled:
 
 ### Runtime Dependencies
 
-When DNNL is built from source, the library runtime dependencies
+When oneDNN is built from source, the library runtime dependencies
 and specific versions are defined by the build environment.
 
 #### Linux
@@ -241,7 +241,7 @@ You may reach out to project maintainers privately at dnnl.maintainers@intel.com
 
 # Contributing
 
-We welcome community contributions to DNNL. If you have an idea on how
+We welcome community contributions to oneDNN. If you have an idea on how
 to improve the library:
 
 * For changes impacting the public API, submit
@@ -261,7 +261,7 @@ contributors are expected to adhere to the
 
 # License
 
-DNNL is licensed under [Apache License Version 2.0](LICENSE). Refer to the
+oneDNN is licensed under [Apache License Version 2.0](LICENSE). Refer to the
 "[LICENSE](LICENSE)" file for the full license text and copyright notice.
 
 This distribution includes third party software governed by separate license

THIRD-PARTY-PROGRAMS

@@ -1,4 +1,4 @@
-Deep Neural Network Library Third Party Programs File
+oneAPI Deep Neural Network Library (oneDNN) Third Party Programs File
 
 This file contains the list of third party software ("third party programs")
 contained in the Intel software and their required notices and/or license

cmake/TBB.cmake

@@ -40,3 +40,4 @@ if(TBB_FOUND)
     unset(_tbb_include_dirs)
     unset(_tbb_root)
 endif()
+

cmake/Threading.cmake

@@ -51,7 +51,7 @@ macro(find_package_tbb)
             TBB_INTERFACE_VERSION "${_tbb_stddef}")
         if (${TBB_INTERFACE_VERSION} VERSION_LESS 9100)
             if("${mode}" STREQUAL REQUIRED)
-                message(FATAL_ERROR "DNNL requires TBB version 2017 or above")
+                message(FATAL_ERROR "oneDNN requires TBB version 2017 or above")
             endif()
             unset(TBB_FOUND)
         endif()

cmake/gen_mkldnn_compat_cmakes.cmake

@@ -14,7 +14,7 @@
 # limitations under the License.
 #===============================================================================
 
-# Creates cmake config for MKLDNN based on DNNL one
+# Creates cmake config for MKLDNN based on oneDNN one
 # (by replacing DNNL with MKLDNN)
 # Parameters:
 #   DIR -- path to cmake install dir

cmake/lnx/TBBConfig.cmake

@@ -34,7 +34,7 @@ if (NOT _tbbmalloc_proxy_ix EQUAL -1)
     endif()
 endif()
 
-# DNNL changes: use TBBROOT to locate Intel TBB
+# oneDNN changes: use TBBROOT to locate Intel TBB
 # get_filename_component(_tbb_root "${CMAKE_CURRENT_LIST_FILE}" PATH)
 # get_filename_component(_tbb_root "${_tbb_root}" PATH)
 if (NOT TBBROOT)
@@ -126,7 +126,7 @@ foreach (_tbb_component ${TBB_FIND_COMPONENTS})
     set(_tbb_release_lib "${_tbb_lib_path}/lib${_tbb_component}.so.2")
     set(_tbb_debug_lib "${_tbb_lib_path}/lib${_tbb_component}_debug.so.2")
 
-    # DNNL change: check library existence (BUILD_MODE related only, not both)
+    # oneDNN change: check library existence (BUILD_MODE related only, not both)
     string(TOUPPER "${CMAKE_BUILD_TYPE}" UPPERCASE_CMAKE_BUILD_TYPE)
     if (UPPERCASE_CMAKE_BUILD_TYPE STREQUAL "DEBUG")
         if (EXISTS "${_tbb_debug_lib}")

cmake/mac/TBBConfig.cmake

@@ -34,7 +34,7 @@ if (NOT _tbbmalloc_proxy_ix EQUAL -1)
     endif()
 endif()
 
-# DNNL changes: use TBBROOT to locate Intel TBB
+# oneDNN changes: use TBBROOT to locate Intel TBB
 # get_filename_component(_tbb_root "${CMAKE_CURRENT_LIST_FILE}" PATH)
 # get_filename_component(_tbb_root "${_tbb_root}" PATH)
 if (NOT TBBROOT)

cmake/mkldnn_compat.cmake

@@ -17,7 +17,7 @@
 # Provides compatibility with Intel MKL-DNN build options
 #===============================================================================
 
-# Sets if dnnl var is unset, copy the value from mkldnn var
+# Sets if DNNL_* var is unset, copy the value from corresponding MKLDNN_* var
 macro(mkldnn_compat_var dnnl_var mkldnn_var props)
     if (DEFINED ${mkldnn_var} AND NOT DEFINED ${dnnl_var})
         if ("${props}" STREQUAL "CACHE STRING")

cmake/options.cmake

@@ -27,7 +27,7 @@ set(options_cmake_included true)
 # ========
 
 option(DNNL_VERBOSE
-    "allows DNNL be verbose whenever DNNL_VERBOSE
+    "allows oneDNN be verbose whenever DNNL_VERBOSE
     environment variable set to 1" ON) # enabled by default
 
 option(DNNL_ENABLE_CONCURRENT_EXEC
@@ -43,24 +43,24 @@ option(DNNL_ENABLE_PRIMITIVE_CACHE "enables primitive cache.
     # disabled by default
 
 option(DNNL_ENABLE_MAX_CPU_ISA
-    "enables control of CPU ISA detected by DNNL via DNNL_MAX_CPU_ISA
+    "enables control of CPU ISA detected by oneDNN via DNNL_MAX_CPU_ISA
     environment variable and dnnl_set_max_cpu_isa() function" ON)
 
 # =============================
 # Building properties and scope
 # =============================
 
 set(DNNL_LIBRARY_TYPE "SHARED" CACHE STRING
-    "specifies whether DNNL library should be SHARED or STATIC")
+    "specifies whether oneDNN library should be SHARED or STATIC")
 option(DNNL_BUILD_EXAMPLES "builds examples"  ON)
 option(DNNL_BUILD_TESTS "builds tests" ON)
-option(DNNL_BUILD_FOR_CI "specifies whether DNNL library should be built for CI" OFF)
+option(DNNL_BUILD_FOR_CI "specifies whether oneDNN library should be built for CI" OFF)
 option(DNNL_WERROR "treat warnings as errors" OFF)
 
 set(DNNL_INSTALL_MODE "DEFAULT" CACHE STRING
     "specifies installation mode; supports DEFAULT or BUNDLE.
 
-    When BUNDLE option is set DNNL will be installed as a bundle
+    When BUNDLE option is set oneDNN will be installed as a bundle
     which contains examples and benchdnn.")
 
 set(DNNL_CODE_COVERAGE "OFF" CACHE STRING
@@ -98,7 +98,7 @@ set(DNNL_ARCH_OPT_FLAGS "HostOpts" CACHE STRING
 # ======================
 
 option(DNNL_ENABLE_JIT_PROFILING
-    "Enable registration of DNNL kernels that are generated at
+    "Enable registration of oneDNN kernels that are generated at
     runtime with Intel VTune Amplifier (on by default). Without the
     registrations, Intel VTune Amplifier would report data collected inside
     the kernels as `outside any known module`."

cmake/win/TBBConfig.cmake

@@ -34,7 +34,7 @@ if (NOT _tbbmalloc_proxy_ix EQUAL -1)
     endif()
 endif()
 
-# DNNL changes: use TBBROOT to locate Intel TBB
+# oneDNN changes: use TBBROOT to locate Intel TBB
 # get_filename_component(_tbb_root "${CMAKE_CURRENT_LIST_FILE}" PATH)
 # get_filename_component(_tbb_root "${_tbb_root}" PATH)
 if (NOT TBBROOT)