* create layer decoupled
* no more virtual public
* allow build test with shared library
* decouple cpu vulkan
* drop old scripts

* convolution winograd pack16to1

* x86 deconvolution and deconvolutiondepthwise

* simpleomp allow 32 arguments

* drop shadow variable workaround

* less winograd test error

* add general fused activation
* add NCNN_FORCE_INLINE option

* 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] add toolchain file w/o stdcxx dependency

* [build] link m and gcc lib explicitly

* [ncnn] complete simple stl impl

* [ncnn] adapt for ncnn simplestl

* [test] adapt for ncnn simplestl

* [ncnn] fix missing algorithm and list when simplestl disabled

* [ncnn] fix guard for operator new and delete

* [style] fix the code style

* [build] fix build failed on darwin and emscripten

* [ci] do not import cxx to avoid operator conflict

* [ncnn] add temporary partial_sort impl using bubble sort

heap sort should be used for better perf.

* [ncnn] add std greater and less function

* [ncnn] fix placement new operator overload

* [ncnn] add operator delete with size info

* [build] disable exception, rtti, example and tools when simplestl on

* [build] add toolchain for arm simplestl

* [build] add toolchain for aarch64 simplestl

* [ncnn] move initializer to constructor

* [ncnn] use deteiled type instead of auto

* [ncnn] use plain lib name in target_link_libraries

* 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

* Fix warnings C4244, C4267 in src/layer/yolov3detectionoutput.cpp

C4244: '=': conversion from 'int' to 'float', possible loss of data
C4244: 'initializing': conversion from 'float' to 'int', possible loss of data
C4244: 'initializing': conversion from 'double' to 'float', possible loss of data
C4244: 'return': conversion from 'double' to 'float', possible loss of data
C4267: 'argument': conversion from 'size_t' to 'int', possible loss of data
C4267: 'initializing': conversion from 'size_t' to 'int', possible loss of data

* Fix warnings C4244, C4267 in src/layer/yolodetectionoutput.cpp

C4244: '=': conversion from 'int' to 'float', possible loss of data
C4244: 'initializing': conversion from 'float' to 'int', possible loss of data
C4244: 'initializing': conversion from 'double' to 'float', possible loss of data
C4244: 'return': conversion from 'double' to 'float', possible loss of data
C4267: 'argument': conversion from 'size_t' to 'int', possible loss of data
C4267: 'initializing': conversion from 'size_t' to 'int', possible loss of data

* Fix warning C4244 in src/layer/quantize.cpp

C4244: 'initializing': conversion from 'double' to 'int', possible loss of data

* Fix warnings C4244, C4267 in src/layer/detectionoutput.cpp

C4244: '=': conversion from 'int' to 'float', possible loss of data
C4244: 'initializing': conversion from 'double' to 'float', possible loss of data
C4267: 'argument': conversion from 'size_t' to 'int', possible loss of data
C4267: 'initializing': conversion from 'size_t' to 'int', possible loss of data

* Fix warning C4244 in src/layer/roipooling.cpp

C4244: 'initializing': conversion from 'double' to 'int', possible loss of data

* Fix warning C4244 in src/layer/sigmoid.cpp

C4244: '=': conversion from 'double' to 'float', possible loss of data

* Fix warning C4267 in src/layer/slice.cpp

C4267: '=': conversion from 'size_t' to 'int', possible loss of data
C4267: 'initializing': conversion from 'size_t' to 'int', possible loss of data

* Fix warning C4267 in src/layer/softmax.cpp

C4244: '=': conversion from 'double' to 'float', possible loss of data

* Fix warning C4244 in src/layer/interp.cpp

C4244: '=': conversion from 'float' to 'int', possible loss of data
C4244: 'initializing': conversion from 'double' to 'int', possible loss of data

* Fix warning C4244 in src/layer/instancenorm.cpp

C4244: 'initializing': conversion from 'double' to 'float', possible loss of data

* Fix warning C4244 in src/layer/deconvolutiondepthwise.cpp

C4244: '=': conversion from 'double' to 'float', possible loss of data

* Fix warning C4244 in src/layer/convolutiondepthwise.cpp

C4244: '=': conversion from 'double' to 'float', possible loss of data

* Fix warning C4244 in src/net.cpp

C4244: 'return': conversion from '__int64' to 'int', possible loss of data
C4267: 'argument': conversion from 'size_t' to 'int', possible loss of data
C4267: 'initializing': conversion from 'size_t' to 'int', possible loss of data
C4267: 'return': conversion from 'size_t' to 'int', possible loss of data

* Fix warning C4244 in src/layer/bnll.cpp

C4244: '=': conversion from 'double' to 'float', possible loss of data

* Fix warning C4267 in src/layer/concat.cpp

C4267: 'initializing': conversion from 'size_t' to 'int', possible loss of data

* Fix warning C4267 in tools/mxnet/mxnet2ncnn.cpp

C4244: 'initializing': conversion from 'double' to 'float', possible loss of data
C4267: '=': conversion from 'size_t' to 'int', possible loss of data
C4267: 'initializing': conversion from 'size_t' to 'int', possible loss of data
C4305: 'initializing': truncation from 'double' to 'float'

* initial the ncnn post training quantization tools

* clear some comments of tools

* fix the Travis ci compiler error

* optimize the conv sgemm int8 on arm64-v8a platform

* optimize int8 arm64-v8a with sadalp ins

* merge requantize op  into latest conv layer

* merge requantize op into conv-int8 op

* update the mobilenet.param in the benchmark

* Update README.md

update Kirin970 and RK3399

* try to fix the travis build error

* add the armv7a conv3x3s1 implement without overflow,remove old codes

* fix the bug of conv3x3s2 packed int8

* new int8 implement,weight quant by perchanel,better accuracy~

* fix the bug of conv3x3s1 packed int8 neon

* add the naive c fp32 and int8 winograd F(2,3)

* add the neon intrinsic int8 winograd F(2,3)

* optimize the armv7a int8 winograd F(2,3) with neon assembly

* optimize the armv7a int8 winograd F(2,3) input transform with assembly.

* add the requantize layer and int8 relu implement.

* add graph optimize conv1x1s2 -> conv1x1s1,begin optimize int8 aarch64.

* fix int8 bugs

* add the c naive im2col with sgemm

* add aarch64 int8 winograd f23, conv3x3s2 naive implement

* add the int8 sgemm conv7x7s2 on x86/armv7a platform

* optimize the int8 sgemm by neon intrinsic and packed kernel

* optimize the int8 sgemm with packed data

* optimize the int8 sgemm with armv7a neon assembly

* add the int8 sgemm on arm64-v8a platform

* perpare to merge latest codes from master

* add the int8 param files

* In the Class Net,add the fuse_network method

* init vec4 shader

* more vec4 shader ...

* convolutiondepthwise is depthwise

* pooling pack4, fix global pooling

* dropout pack4, relu pack4

* softmax pack4

* more shader vec4 ..

* fix staging remap, remove layer pipeline member, add destroy_pipeline interface, add pack4 glue code

* eltwise pack4 glue code

* add binary pack4, unary pack4

* add binaryop unaryop pack4 glue code

* vulkan infrastructure

* vkallocator and vkmat

* layer interface for vulkan compute

* wip...

* default vulkan device, command wrapper, upload model weight in load_model to simplify layer interface

* simplify command api, vkmat holds staging buffer, relu works

* initialize specialization constant, simplify command dispatch, fix staging buffer copy with different shape, convolution works

* init extension functions

* dynamic local size and group count

* group count=1 is invalid

* regard device max workgroup size limit

* fix relu oooops

* decouple command record and staging allocation

* create result blob

* add pooling shader

* buffer is faster than image :)

* fix pooling shader

* add innerproduct shader

* readonly writeonly decoration

* simplify buffer creation

* decouple command and layer, VK_KHR_descriptor_update_template extension makes descriptor binding update easy :D

* fix vulkan building issues in visual studio (#1)

* fix building issues on visual studio

* ignore benchmark

* cancel changes

* ... ...

* decouple paramdict and vulkandevice

* fix staging buffer destroy in model loading

* remove vkdev member in option

* add padding shader

* simplify vulkan layer creation, simplify convolution and pooling shader for no padding, less debug output

* add convolutiondepthwise and softmax shader

* specialization float type, add leakyrelu

* add dropout shader

* add batchnorm shader

* split vulkan forward

* add scale shader

* push constant type can be int or float

* set_optimal_local_size_xyz

* add eltwise shader

* concat vulkan forward

* fix convolution without bias

* add dummy shader for concat and split, more fix ...

* optional VK_KHR_descriptor_update_template and VK_KHR_push_descriptor

* check VK_KHR_push_descriptor for vkCmdPushDescriptorSetWithTemplateKHR

* binaryop and unaryop shader

* hide raw command buffer

* simple vkbenchncnn benchmark

* create device with transfer queue

* rename command to vkcompute, add vktransfer and layer upload_model interface

* external VkMat, copy and map wrt buffer offset

* command copy respect offset and size

* decouple weight upload and load, simplify upload weight api, use one big staging buffer for uploading weights

* fix build on android

* binding count can not vary :(

* barrier check state, fix sub-op destruction

* declare local_size_xyz constant, fix crash on radv

* fix local_size_xyz, second try

* more barrier and state fix

* fix softmax

* reconstruct buffer memory allocator, reuse blob buffer, less verbose output

* find unified memory type index

* weight staging buffer allocator and weight buffer allocator, respect descriptor buffer offset alignment

* use VK_KHR_descriptor_update_template for faster descriptor update if available, multithread pipeline creation

* find more useful vulkan extensions and enable them

* fix msvc build

* respect VK_KHR_dedicated_allocation for weight buffer allocation

* fix android build

* fix bias name conflicts with metal

* decouple pipeline and layer, building shader sources into shader module, dedicated create_pipeline api, simplify pipeline recording

* drop dummy shader, inplace softmax, multiple shader module works

* fix unique queue family index error

* flatten support vulkan

* mnasnet run

* find shader module by name, each entry point per shader module, fix attribute/id conflict on moltenvk

* some minor changes

* add some high level api

* use dedicated transfer queue to upload weight model

* prefer mappable buffer on unified memory

* global pooling and convolution fc, reuse staging buffer

* implement ring-buffer style blob allocator, add VkBufferMemory capacity

* use blob allocator for workspace blob, it works fine :)

* vulkan option off

* Update layer.cpp

* fix build with vulkan off

* less verbose output, fix crash on vulkan_compute off

* merge benchncnn tool

* allocator clear api, use new weight buffer allocator per net

* add default locked allocator

* mapped mat ptr api, persistent mapped memory works generally :)

* travis ci linux vulkan

* travis ci vulkan wip ...

* more gpu wip ...

* more gpu wip ...

* wip...

* wip...

* wip... ...

* wip... ios vulkan build...

* find glslangValidator on ios build

* use dynamic moltenvk library

* travis ci wip ...

* ios simulator does not support metal at all

* fix cpu only extractor

* optimize workgroup size, first try

* optimize workgroup size, second try

* conv1x1s1d1 vec4

* revert build system

* fix ncnn2mem build

* fix ncnn2mem build