nihui
7c079b853e
default to big cpu count
2021-03-22 18:50:51 +08:00
nihui
67e24e0703
use local pool allocator ( #2736 )
...
* use local pool allocator
* detach extract feat from local allocator
* fix test
2021-03-16 16:23:28 +08:00
Youngsoo Lee
b9bed8d993
feat: add denormal options ( #2656 )
...
* feat: add denormal options
Flush-To-Zero(FTZ) and Denormals-Are-Zero(DAZ) are modes that bypass IEEE754 methods of dealing with denormal floating-point numbers on x86_64 and some x86 CPUs.
* feat: Integrate `flush_denormals` into `Extractor::extract`
* chore: replace global variable with `ThreadLocalStorage`
2021-02-19 12:21:55 +08:00
nihui
54c0a13b9f
build shared library ( #2525 )
...
* 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
2021-01-01 22:55:10 +08:00
nihui
b9296c259d
bring up vulkan 1.1 ( #2191 )
...
* query subgroup features
* compile spirv 1.3
* drop offline spirv build
* do not build tests for android and ios, as they are never tested anyway
* code style
2020-10-11 22:53:38 +08:00
nihuini
6238bfd77f
roi variant for from pixels family, enable fp16a by default
2020-09-08 18:54:09 +08:00
nihuini
4e4f0baa73
set openmp blocktime 20 for reducing power consumption, blocktime option
2020-07-23 14:20:54 +08:00
nihui
11cffce114
armv8.2 infrastructure ( #1856 )
...
* 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
2020-07-19 19:29:52 +08:00
nihui
164273de61
online pipeline cache ( #1792 )
...
* 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
2020-07-04 12:30:50 +08:00
nihui
3ef995ed1e
format code style and setup restyled.io ( #1840 )
2020-06-13 22:17:51 +08:00
nihui
9a9a618229
image storage is mandatory, less options makes life easier
2020-05-08 00:09:35 +08:00
nihui
62da1228e1
adreno image shader + fp16 + fp16a ( #1714 )
...
* wip
* wip
* fix
* image and imageview can not be destroyed until command execution ends
* fast copy path for tightly packed data
* wip
* texture load works
* 1d 3d image
* record clone image, multiple commands share one image reference
* upload download image
* layer forward accept vkimagemat
* vkimagemat graph works
* staging vkimagemat for passing dynamic parameters, macro for fp32+image shader, padding image shader
* vkimagemat elemsize
* convolution test pass
* conv1x1s1 image shader
* fast staging image allocator from host memory, pooling image shader
* convolutiondepthwise image shader
* innerproduct image shader
* packing image shader
* crop deconvolution image shader
* resolve spirv binding types
* image fp16 and fp16a, cast image shader
* eltwise image shader
* wip
* absval image shader
* deconvolutiondepthwise image shader
* concat image shader, squeezenet works
* noop split image shader
* uniform precision hint
* layer support_image_storage
* wip
* vulkan device utility operator
* command is storage and packing option aware
* fallback to cpu on image allocation failed, mobilenetssd works
* flatten image shader, enable more test
* ci test
* check imgfp32 imgfp16 imgfp16a features
* fix ci test
* fix ci test
* upgrade swiftshader
* wip
* opt aggressive
* imgfp16p
* opt none
* convolution winograd image shader
* fix flush range, fast copy path for continous buffer
* minor fix
* fix innerproduct
* wip ...
* wip
* cast fix
* packing test
* wip
* image fp16p is fp16p
* wip
* silence
* more line info
* code clean
* softmax image shader
2020-04-30 17:08:30 +08:00
nihui
d85b2bc285
enable packing_layout by default
2020-04-12 18:06:47 +08:00
nihuini
4c6bf24205
explicit cpu thread affinity
2020-03-19 11:24:05 +08:00
nihui
7d1eec3d5d
the use_bf16_storage option
2020-03-10 22:50:48 +08:00
nihui
a718129d76
shader pack8 option works
2020-01-29 13:59:17 +08:00
nihuini
834224fea8
new option use_packing_layout
2019-07-19 19:53:14 +08:00
nihuini
73911492d7
fix validation warning on querypool destruction, enable fp16p by default
2019-06-10 19:51:27 +08:00
nihuini
838c5df839
option api changes
2019-06-04 14:20:18 +08:00
nihui