* update concat and unsqueeze, test=develop

add cuda kernel:lookup table

* fix pooling bug and speed

* fix build error

* delete VLOG in pool, test=develop

* add openmp, test=develop

* fix lite/kernels/arm/pool_compute_test basic_pooling compute error bug, test=develop

* move multiclass_nms kernel back to host test=develop

* move layer_norm OP and arm_kernel into extra type since it's added after release/v2.0-beta1 and not related with CV test=develop

* fix code_style test=develop

[LITE][NPU] Add fusion_elementwise_add_activation bridge, remove the limitation of the dimensions of input tensors in the graph compute kernel, and refine log message (#2395)

test=develop

fix jit::matmul bug. Input x shape is (m, k), weight shape is (k, n). When k < 512, m==1, and n is a multiple of 16, the weight pointer is not correctly updated in the group calculation in the implementation of jit::matmul, resulting in the result diff 

mv deviceinfo.workspace and other relative member to thread_local_storage

* Add CMAKE_BUILD_TYPE check for strip. test=develop

We have changed 11 arm_kernels into extra type in #2347 , which has caused test_compiling failure. In this PR , we move their 11 related arm_kernel_test into build_extra=ON

* add channel_wise_dequantized_max_abs op and ChannelWiseDequantOpFuser, test=develop

optimise conv 1x1 ... ,test=develop (#2388)

update reshape op to support multiple input types of shape.
priority: input(ShapeTensor) > input(Shape) > attr(shape)

update slice op to support multiple iput types of starts and ends.
priority: input(StartsTensor) > input(StartsTensorList) > attr(starts)

fill_constant kernel only registered float type, only the float data type is produced, which is obviously a bug.

Now, produce data based on the data type attr.

By the way, fix the cast kernel bug.

* fix: fix omp thread bug

* fix: fix compile android level & test=develop

* fix: fix omp bug

* fix: fix omp bug
test=develop

test=develop

update FPGA v2 kernel file including proposal， sigmoid and anchor generator, test=develop  Closes #2369 (#2370)

* update proposal and psroipool kernel file in FPGA V2 track

* update, test=develop

* fix step rnn model run bugs test=develop

* move some basic ops into extra type to reduce library size test=develop (#2347)

test=develop

* add mem opt option for high api ,test = develop

* fix is_lod params && test-performance ,test=develop

* fix useless init emptyimage , test = develop

* [XPU] add batchnorm op bridge and unit test

test=develop

* fix DMLC_USE_GLOG

test=develop

* delete remaining opencl headers test=develop

* checkout specific commit for opencl headers test=develop

* add opencl headers by git clone test=develop

* add opencl headers by git clone test=develop

fix buf: model_optimize_tool can not compile preperly on mac environment (#2326)

* add mem opt option for high api ,test = develop

* fix is_lod params && test-performance ,test=develop

* fix model_opt_tool bug : judge WITH_MKL to choose whether to compile MKL test=develop

* Fix conv bn bug. test=develop

* Fix bug in pattern_matcher. test=develop

* add GPU_CL for test_net_benchmark.

* test compile

* fix mobile build error

Fix compiling bug in android_armv7_demo : cxx demo can not compile properly because demo' android version is different from that of library file (#2308)

link armv7 demo to android-23 to make sure the demo can compile properly
cxx demo can not compile properly because demo' android version is different from that of library file, we fix this bug by linking armv7 demo to android-23

Add 'inference' folder into build.lite.x86, 'inference' folder contains head files、library files and demo of x86 compiling (#2301)

Add inference folder into build.lite.x86, build.lite.x86/inference folder contains head files、library files and demo of x86 compiling

* alter the unit tests api for googlenet, resnet50, inceptionv4, mobilenetv1, mobilenetv2 and thier corresponding cmake, test=develop

* disable checks and correct some incorrect statement, test=develop