* x86 vulkan fallback
* comment about bf16s

* quantize gemm

* write gemm quantize scales

* update doc

* less openmp args

* x86 riscv fallback

* skip gemm vulkan int8

* fix noint8 test, fix arm bf16 test

* enable vfpv4 on neon build only

* fix gemm vulkan without C

* fp16 pack8 output

* enable elempack=8 only for asimdhp+

* tiled gemm int8 test

* opt arm64 tiles, fix asimdhp dispatch

* quantize and dequantize tests

* unify activation and usability function

* drop NCNN_REQUANT cmake option, test dequantize requantize pack8, fix webassembly build

* benchmark use requantize int8 model

* build shared lib and enable lto

* reserved for layer and option

* allocator pimpl

* datareader pimpl

* paramdict pimpl, disable copy assign for allocator and datareader

* modelbin pimpl

* net extractor pimpl

* gpu pimple

* disable copy assign vulkandevice, code format

* command pimpl, dummy image readonly

* pipeline pipelinecache pimpl, export platform class

* code format, export simple family

* update ci

* disable lto on android armv7, merge webassembly ci

* link libgcc, fix macos dylib version

* pipeline pimpl, gpu info pimpl

* destroy gpu info after vulkan device

* ignore msvc stl class warning

* fix ncnn_paramdict_get_float return type

* fix vktransfer upload fp16 without flatten, add command test

* 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

* 1. for cross platform, use cv::CommandLineParser instead of getopt.h
2. use cv::glob to search folder instead of dirent.h
3. fix some other warnings of function from cstdlib
4. add some const and some auto

* 1. fix some other warnings of function from cstdlib
2. add some const and some auto
3. i forgot...

* switch quantize tools default on

* check OpenCV first, if not found, disable quantize tools

* add _CRT_SECURE_NO_DEPRECATE for msvc and remove *_s functions

* add _CRT_SECURE_NO_DEPRECATE for msvc and remove *_s functions

* keep the one line style block

* folding bracket

* dynamic_cast -> static_cast

* fix onnx2ncnn MemoryData dims problem #1330

* fix ncnn2int8 bug (see #1336)

* fix bug that MemoryData as multi operations input

* fix ncnn2table find_blob_index_by_name data failed bug, see #1338

* fix ncnn2table find_blob_index_by_name data failed bug, see #1338, fix change requested

* fix Reduction operation attribution bug

* fix #1363 request changes

* fix onnx2ncnn MemoryData dims problem #1330

* fix ncnn2int8 bug (see #1336)

Fix compile issue with ncnn2int8

asymmetric padding parameter for convolution and deconvolution family

* initial the ncnn post training quantization tools

* clear some comments of tools

* fix the Travis ci compiler error