* runtime cpu dispatch

* force thread one

* disable openmp for coverage

* simplify test layer

* print NCNN_TARGET_ARCH

* less ci build variants

* weight fp16 storage option

* test convdw int8

* apple a12 a13

* ncnn_add_layer ncnn_add_shader cmake macro

* online pipeline cache wip

* device-wide pipeline cache

* enable model-wide pipeline cache

* drop pre-created shader modules

* always use pipeline cache

* use implicit model-wide pipeline cache, code format

* code clean

* added avx versions of commonly used layers

* Restyled by clang-format

* Restyled by astyle

* Restyled by clang-format

* Restyled by astyle

* Unroll loops and increase test coverage

* Restyled/pull 1897 (#13)

* Restyle

Co-authored-by: Restyled.io <commits@restyled.io>

* cleanup variable declaration

* fix ctest

* Restyled/pull 1897 (#14)

Restyle
Co-authored-by: Restyled.io <commits@restyled.io>

* Fix ctest for convolutions without AVX.

Co-authored-by: Restyled.io <commits@restyled.io>

* added fp16 weight storage version

* Small changes

* Fixed fp16 weight storage layers

* fix innerproduct

* fix loop error

* Fix windows build.

Disable fp 16 conversion when detecting int8 weights.

Implement requested changes.

* Restyled by clang-format

* Restyled by astyle

* Restyled by clang-format

* Restyled by astyle

* Update option.cpp

Set fp16 storage based on vulkan being used or not.

* added ability for storing state in lstm layer

* added avx lstm

* added arm lstm

* fix innerproduct activation location and add 4 parallel channel version

* Restyled by clang-format

* Restyled by astyle

* Restyled by clang-format

* Restyled by astyle

* revert arm file

* commit before switch

* implement requested changes

* Restyled by clang-format

* Restyled by astyle

* Restyled by clang-format

* Restyled by astyle

* More x86 optimized implementations of common layers.

Added LSTM layers for arm and x86 + a ctest to verify the layer accuracy

Added fp16 innerproduct for arm

* fix non avx build

* Add fp16 arm compiler and cpu checks. Remove statefullness from LSTM implementation.

* Fix build check for fp16 arm

* Bypass lstm_fp16 if not supported

* Build order was incorrect

* fix std::min missing in windows build

* Restyled by clang-format

* Restyled by astyle

* Restyled by clang-format

* Restyled by astyle

* attempting to fix gnu build by enabling: -mfp16-format=ieee to fix the missing __fp16 type

* remove double "fix"

* Specify ieee fp16 format

* implement requested changes

* fix arm non-fp16 build

* fix arm lstm

* Restyled/pull 1881 (#15)

* Restyled by clang-format

* Restyled by astyle

* Restyled by clang-format

* Restyled by astyle

Co-authored-by: Restyled.io <commits@restyled.io>

* Check blob size on arm lstm

* fix styling

Co-authored-by: Restyled.io <commits@restyled.io>

* Fix winograd 3x3 avx and extend test converage

* fix ctest on non-avx path

* Restyled by clang-format

* Restyled by astyle

* Restyled by clang-format

* Restyled by astyle

* remove unused broadcasts

* Comment with #if 0

Co-authored-by: Restyled.io <commits@restyled.io>

* added fp16 weight storage version

* Small changes

* Fixed fp16 weight storage layers

* fix innerproduct

* fix loop error

* Fix windows build.

Disable fp 16 conversion when detecting int8 weights.

Implement requested changes.

* Restyled by clang-format

* Restyled by astyle

* Restyled by clang-format

* Restyled by astyle

* Update option.cpp

Set fp16 storage based on vulkan being used or not.

* fix innerproduct activation location and add 4 parallel channel version

* Restyled by clang-format

* Restyled by astyle

* Restyled by clang-format

* Restyled by astyle

* revert arm file

* implement requested changes

* Restyled by clang-format

* Restyled by astyle

* Restyled by clang-format

* Restyled by astyle

Co-authored-by: Restyled.io <commits@restyled.io>

* Added 3x3 pack8 winograd implementation

* working winograd 3x3 and direct 2x2

* Remove typo

* remove debug print

* Restyled by clang-format

* Restyled by astyle

* Restyled by clang-format

* Restyled by astyle

* fix non avx build

* Added flatten and reshape avx implementations

* attempt to fix ios sim build

* Fix build

* Revert include removal

* Restyled by clang-format

* Restyled by astyle

* Restyled by clang-format

* Restyled by astyle

Co-authored-by: Restyled.io <commits@restyled.io>

* added avx implementations of FC and Max pool

* Specify AVX2

* Small fixes and using Fused avx activations

* fix type casting

* fixing some CI errors

* Fix code format

* fix pooling test

* remove vector typedef

* More compile fixes

* remove vector typedef

* set c++ version to 17

* Force c++ 17

* Fixing mathfun

* Try and workaround typedef issues

* typefix

* Remove typedef

* switch to static inline

* attempting to fix msvc bug

* Verified MSVX FIX

* Fixing clang build

* commit before switch

* More avx and packing implementation

* Fix ctest

* starting the depthwise pack 8 implementation

* Unrolled loop

* add depthwise pack 8 implementations

* Working 1x1 pack 8 implementation added

* revert incorrect changes

* added conact elempack 8

* more elempack enabled layers added and started on the conversion of the winograd pack4 conv 3x3

* Added code formatting

* fix styling

* Unroll loops

* unrolling loops

* Added more elempac layers for mobilenet v3

* revert commit

* fix code style

* remove arm neon references

* remove pack4 references

* More cleanup

* added packing avx code

* fixing linux build ctests

* remove usage of aligned loads

* More aligned mem ops removed

* Cleanup, revert some files and remove not working winograd and shufflechannel implementation

* add stackoverflow referal

* Fix windows build

* Restyled by clang-format

* Restyled by astyle

* Restyled by clang-format

* Restyled by astyle

* implement requested chaanges

* remove reshape

* revert arm file change

* Restyled by clang-format

* Restyled by astyle

* Restyled by clang-format

* Restyled by astyle

* fix unterminated directive

Co-authored-by: Restyled.io <commits@restyled.io>

* added avx implementations of FC and Max pool

* Specify AVX2

* Small fixes and using Fused avx activations

* fix type casting

* fixing some CI errors

* Fix code format

* fix pooling test

* remove vector typedef

* More compile fixes

* remove vector typedef

* set c++ version to 17

* Force c++ 17

* Fixing mathfun

* Try and workaround typedef issues

* typefix

* Remove typedef

* switch to static inline

* attempting to fix msvc bug

* Verified MSVX FIX

* Fixing clang build

* fix pooling on MSVC

* Remove c++ 17

* Implement requested changes

* small cleanup

* fix aligment

* fix pooling import

* revert "Implement requested changes"

This reverts commit 5d8cc9494b.

* fix import order

* Undo aligned load

* Add channel padding and blazeface model support.

* remove python binding

* remove std::min usage

* fix reference blob usage

* Increased padding test  coverage

* implement requested changes

* add copy_cut_border check; fix compile warnings

* update roialign

* update tool for roialign

* fix ceil for roialign

* fix ios build

* fix

* fix

* make it compatibile with the old version

* fix ios build

* trigger CI

* fix test

* order

* build

* remove code

* merge roialign

* accelerate ROIAlign

* update note

* rename func

* roialign version

* trigger CI

* fix roialign

* use ref for pre-calc in roialign

* retrigger CI

* pre-alloc

* fuse mish and depthwise convolution

* darknet2ncnn: support enet-coco conversion.

* add swish layer

* add swish test

* add statisticspooling layer

* update my license, delete "#include <algorithm>, #include <functional>" in src/layer/statisticspooling.cpp, add ncnn_add_layer entry in src/CMakeLists.txt.

* Move ncnn_add_layer(StatisticsPooling) to tail of the layer list. Because the layer enum index is generated from this order. Inserting would break binary compatibility.