use neon instructions on arm (#1451)

Author: borg323

appveyor.yml

@@ -101,7 +101,7 @@ before_build:
 - cmd: IF %NAME%==cpu-dnnl SET EXTRA=-Db_vscrt=md
 - cmd: IF %ANDROID%==false meson build --backend vs2017 --buildtype release -Dgtest=%GTEST% -Dopencl=%OPENCL% -Dblas=%BUILD_BLAS% -Ddnnl=true -Ddx=%DX% -Dcudnn=%CUDNN% -Dispc_native_only=false -Dpopcnt=false -Dcudnn_include="%CUDA_PATH%\include","%CUDA_PATH%\cuda\include" -Dcudnn_libdirs="%CUDA_PATH%\lib\x64","%CUDA_PATH%\cuda\lib\x64" -Dopenblas_include="%PKG_FOLDER%\OpenBLAS\dist64\include" -Dopenblas_libdirs="%PKG_FOLDER%\OpenBLAS\dist64\lib" -Ddnnl_dir="%PKG_FOLDER%\dnnl_win_1.5.0_cpu_vcomp" -Dopencl_include="%PKG_FOLDER%\opencl-nug.0.777.77\build\native\include" -Dopencl_libdirs="%PKG_FOLDER%\opencl-nug.0.777.77\build\native\lib\x64" -Ddefault_library=static %EXTRA%
 - cmd: IF %ANDROID%==true meson arm64-v8a --buildtype release -Dgtest=false -Dopenblas_include="%PKG_FOLDER%\OpenBLAS\android-aarch64\include" -Dopenblas_libdirs="%PKG_FOLDER%\OpenBLAS\android-aarch64\lib" -Dembed=%EMBED% -Ddefault_library=static --cross-file crossfile-aarch64
-- cmd: IF %ANDROID%==true meson armeabi-v7a --buildtype release -Dgtest=false -Dopenblas_include="%PKG_FOLDER%\OpenBLAS\android-armv7a\include" -Dopenblas_libdirs="%PKG_FOLDER%\OpenBLAS\android-armv7a\lib" -Dembed=%EMBED% -Ddefault_library=static --cross-file crossfile-armv7a -Dispc=false
+- cmd: IF %ANDROID%==true meson armeabi-v7a --buildtype release -Dgtest=false -Dopenblas_include="%PKG_FOLDER%\OpenBLAS\android-armv7a\include" -Dopenblas_libdirs="%PKG_FOLDER%\OpenBLAS\android-armv7a\lib" -Dembed=%EMBED% -Ddefault_library=static --cross-file crossfile-armv7a -Dispc=false -Dneon=false
 build_script:
 - cmd: IF %ANDROID%==false call scripts\appveyor_win_build.cmd
 - cmd: IF %ANDROID%==true call scripts\appveyor_android_build.cmd

meson.build

@@ -48,6 +48,12 @@ endif
 if host_machine.system() == 'windows'
   add_project_arguments('-DNOMINMAX', language : 'cpp')
 endif
+if host_machine.cpu_family() == 'arm'
+  if get_option('neon')
+    add_project_arguments(cc.get_supported_arguments(['-mfpu=neon']), language : 'cpp')
+    add_project_link_arguments(cc.get_supported_arguments(['-mfpu=neon']), language : 'cpp')
+  endif
+endif
 
 # Files to compile.
 deps = []

meson_options.txt

@@ -123,6 +123,11 @@ option('pext',
        value: false,
        description: 'Use the pext instruction')
 
+option('neon',
+       type: 'boolean',
+       value: true,
+       description: 'Use neon instructions on arm processors')
+
 option('gtest',
        type: 'boolean',
        value: true,