add: i32 and i64 test case

* add sequence_expand_as op on arm. test=develop

* fix format. test=develop

* Optimize obtaining quantized scale in inference, test=develop

add cv_ut. test=develop
add Anakin implement
add image_profiler test

[OP][HOST][KERNEL]Add uniform_random operator, and add host kernel for uniform_random. test=develop (#4264)

* platform portability of tls, test=develop

* update build_ios.sh, test=develop

* add static keyword for tls, test=develop

* rename the alias of tls, test=develop

[NPU] Disable scale_activation_fuse_pass which causes the wrong result in yolov3_mobilenetv3 (#4266)

* [BugFix][OpenCL] Fix concat image impl when concat axis is not 1

* fix code when axis == 1. test=develop

* fix illegal access when print debug info. test=develop

* fix typo

* [OpenCL] Delete redundant calling: InitializeDevice. test=develop

* [DOC] update compile doc, test=develop, test=document_fix

* fix conv3x3 group. test=develop
* remove useless. test=develop
* optimize 3x3 group

* add v8 4x8 implment. test=devvelop

* fix run error

* change sgemm compute. test=develop

* fix format. test=develop

[XPU] Disable the unit test of subgraph temporarily for XTCL, and refine the file name of unit tests of XPU (#4240)

* add conv+conv fusion requirment

* fix compute error
* fix format. test=develop

* fix format. test=develop

* fix according comments. test=develop