* fix opencl backend. test=develop

* [ASCEND] Add Huawei Ascend310 support, test=develop

* [ASCEND] fix some typos, test=develop

* [ASCEND] address comments and fix opt ci python file, test=develop

* [ASCEND] update based on new ascend env, test=develop

* [ASCEND] update after develop merge, test=develop

* [Core][ARM] Fix beam_search, eltwise_mul supports broadcast and int64_t data type, add print op and kernel, add exeception
test=develop

* Fix the dims of parent idx of the arm kernel of beam_search op

* elementwise_mul supports int64_t data type with broadcasting

* Add print op and kernel for debugging

* Support throwing the exception when the internal error occurs

* Refine while and conditional_block op kernel

* Support the graph optimization on subblocks

* Pass program_desc and block_idx into the kernel of the control flow ops(while/conditional_block/subgraph), and create the RuntimeProgram online, it make it possiable to call the control flow ops recursively

*Add unit test for masked transformer model

* [LITE][XPU] accomodate resnet_cbam

* [LITE][XPU] accomodate content-dnn

* fix pr comments test=develop

* fix pr comments test=develop

* fix pr comments test=develop test=xpu

* fix compilation error, test=develop test=xpu

* [X86] Fix the unit test of slice op
test=develop test=xpu
Co-authored-by: Nhong19860320 <9973393+hong19860320@users.noreply.github.com>

* reduce .so size. test=develop

* compile all targets when LITE_ON_TINY_PUBLISH=OFF

* unordered_map is more convenient when key is customized class

* test=develop

[LITE][XPU] 1. Add precision switch(int16/int31) in XPUMultiEncoderOp; 2. Fix identity_dropout_eliminate_pass, |AttrType| of 'is_test' in OpDesc can be INT or BOOLEAN; 3. Enhance |__xpu__multi_encoder_fuse_pass|; (#3596)

* [LITE][XPU] Add precision switch(int16/int31) in XPUMultiEncoderOp

* [LITE][XPU] fix identity_dropout_eliminate_pass, |AttrType| of 'is_test' in OpDesc can be INT or BOOLEAN

* test=develop

* [LITE][XPU] suppress linkage error
test=develop

* [LITE][XPU] 1. Reorder |identity_dropout_eliminate_pass| before |__xpu__multi_encoder_fuse_pass|; 2. Enhance |__xpu__multi_encoder_fuse_pass|, it works well in more scenarios;
test=develop

* [LITE][XPU] Remove XPUConfig
test=develop

 fix reshape infer shape issue  
adaptive pool, 
support adaptive pool2,  
multi thread ok,   
optimize global pool, 
support faceboxes and behavior image, 
realize bm device info, 
multi device ok, 
support multi cards, 
support efficienet

* [lite][opencl] remove event with clfinish, add strict check for cl warning. add conv 3x3opt fallback opt layout cast ,test=develop

* [LITE][OPENCL]rm event in element_add_buffer_compute test=develop

* [LITE][OPENCL]suite cl_functions_test.cc test=develop

* [LITE][OPENCL] suite cl_common.sh lint check test=develop

* [LITE][OPENCL] suite conv_image_compute.cc lint check test=develop

* [LITE][OPENCL] suite cl_wait_list() lint check test=develop

lite cuda support exec multi-stream

[MLU] add some basic support for MLU, including related passes, kernels, gtests and some api in padddle_api.h
Passes：mlu_subgraph_pass ,mlu_postprocess_pass
Kernels:  act，batch_norm, concat, conv, elementwise, fc, interpolate, pool, scale, softmax

* [LITE][XPU] bind xpu resnet50 kernels

* [LITE][XPU] fuse resnet50 and encoder

* [LITE][XPU] bind xpu bert kernels

* [LITE][XPU] refine xpu_resnet_fuse_pass.cc

* [LITE][XPU] add xpu stack kernel

* [LITE][XPU] add xpu slice/tanh kernel

* [LITE][XPU] refine resnet50 and encoder fusor

* [LITE][XPU] split resnet50 and multi_encoder op from subgraph_op.h

* [LITE][XPU] clean workspace

* [LITE][XPU] add build script

* [LITE][XPU] fix compilation errors

* [LITE][XPU] fix kernel matmul

* [LITE][XPU] fix kernel ewadd ewsub

* [LITE][XPU] add xpu cast kernel

* [LITE][XPU] fix kernel slice

* [LITE][XPU] switch dev by LITE_XPU_DEV env

* [LITE][XPU] eliminate useless cast op

* [LITE][XPU] add PerThread Ops

* [LITE][X86] add SequenceUnpad op and kernel

* [LITE][XPU] add LITE_WITH_XTCL option

* [LITE][X86] add SequenceConv kernel

* [LITE][XPU] fix cmake dependency

* [LITE][XPU] add xpu sigmoid kernel

* [XPU] Remove the dependencies of framework.pb.h
test=develop

Change-Id: Icfb44efb0482a6369b365b5c09017765328fc10d

* [XPU] Fix the precision of cast kernel
test=develop

Change-Id: Icb18be47d7ab490de9fb9c92eae1165f49dbf492

* [Core] Fix the compiling error when build for the target that disable XPU
test=develop

Change-Id: I38ec53f222391d3bf06b70512e6c3ad1282e4683

* [XPU] Add io_copy kernel for xpu<->arm
test=develop

Change-Id: Iec7ea066f040534285557f9948b73e6a1970aed7

* fix
test=develop

Change-Id: I4db1c93df48e22afbba904ce6c3b0babd9fda4c3

* fix target matching of type_target_cast_pass and remove the unnecessary registration of io_copy kernel
test=develop

Change-Id: I432c10c9d1064e778d43fd0d12d8cf0599252f7a

* [X86] Add the keyword 'template' to avoid the compiling errors
test=develop

Change-Id: I015d5d323adafb3884029c8287ced66c90ad931e

* Fix the build.sh for XPU and x86
test=develop

Change-Id: I7d9575243669ce02af69a8ddbd6421db31902bd6

* [XPU] Add the keyword 'template' to avoid the compiling errors
test=develop

Change-Id: I46d0b3b6861286a73ee2999934b8e185e453e749

* [XPU] Add XTCL compiling option in build.sh
test=develop

Change-Id: I8b3fd998ca5f898d5bd2e665646e3874b3b73c80

* fix namespace conflicts, test=develop

* [API][XPU] Move the XPU related APIs into CxxConfig
test=develop

Change-Id: I75ac35e8bae96bcb835683f413f01b9db45afbf9

* [API][XPU] Remove the LITE_WITH_XPU in paddle_api.h
test=develop

Change-Id: Idbd64013bdf331ad876919511c1c349332d46f93

* [API][XPU] Remove XPUSetWorkspaceL3SizePerThread and XPUSetDevPerThread
test=develop

Change-Id: I515958f56f8e129280bae61c923513cc91fb9728

* [API][Core][XPU] Refine the test case and remove the necessary modifications
test=develop

Change-Id: I1e0e2957a2f9d5f4207b06c0bc98a5ab611fee56

* [Core] Remove useless code
test=develop

Change-Id: I6293faa10424aea2836d09d85ddb6a30f7811678

* [XPU] Refine the test cases
test=develop

Change-Id: I6818fc3addf1bca5b96a7d66ee99263242e3374f

* [XPU] Remove useless scripts and code
test=develop

Change-Id: I965ba6712d3cf881d0038f0473fec27d4c1bc684

* [XPU] Use InferShapeImpl in sequence_unpad, resnet50 and multi_encoder op
test=develop

Change-Id: I5375f524d36836a394d426b4b2bc9fb44be0b59c

* test=develop

Change-Id: I42ee68c8a5e891dd0f3e95d6cfbc498be7cf1519

* test=develop

Change-Id: If679e5aa73e1368e0ee5bd5f286d2e1b4c2f354e

* [XPU] Add __xpu__ prefix to the op and graph pass name of resnet50 and multi_encoder
test=develop

Change-Id: Idb61c99b4b8429cb87665bfd6835ab4d7d263be2

* [XPU] Fix and refine the xpu fuse pass
test=develop

Change-Id: If1c5b6788d994e2809c1a00d9384685a89440907

* test=develop

Change-Id: Icfa333e322fc4351700103692c46cfcb3d4f9a89

* [XPU] Remove the dependency on xpu api for xpu fuse passes
test=develop

Change-Id: I6094b5536f58ae18bab068284b32f9bd10a2ab92

* [XPU] Move unit tests from lite/api to lite/tests/api
test=develop

Change-Id: I7ba27abb23abeffb0c95fdbbefec7ac16cdbd250

* test=develop

Change-Id: I33230c84d6c4e61bf19f46668bae2baa3ef68794

* [XPU] Refine code
test=develop

Change-Id: I37bc5b948b4927e44cd3ea2594ebe3fd7671be06

* [XPU] Add env XPU_ENABLE_XTCL to enable xpu_subgraph_pass
test=develop

Change-Id: Ifb8e07e86f307f562adaca3ce792015a6f2a2204

* [XPU] refine code
test=develop

Change-Id: I1380654b930d51ae704dbc0cd855464d9c3b5b79

* [XPU] Refine code
test=develop

Change-Id: I73285c2718ccd3612490eb2635bef4fd608c9bde

* [XPU] Add comments for the XPU APIs
test=develop

Change-Id: Ieb5015f37984f8869b90c4c625c5894bb26164fd
Co-authored-by: Nmiaotianxiang <miaotianxiang@baidu.com>
Co-authored-by: NShixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>

* test=devellop

* add cl file into resulted lib test=develop

* test=develop

* test=develop

* Support bitman backend

[LITE][NPU][XPU] Refine subgraph pass, and support NPU/XPU model generation at execution time (#2576)

* fix cuda building, test=develop

* remove sequence_pool from cmake because build error, test=develop

* support build C++ cuda shared lib

add CUDAContext assignment operator to fix cuda compile bug

* Initial support for XPU
* Fix compiling errors of XPU
* Move XPU op kernel bridges from backends to kernels to fix deps order
* Change the namespace and directory of XPU bridges
* Add XPU SDK
* Fix header files and namespace of XPU SDK
* Add unit tests for relu and conv2d ops
* Restore the modification of paddle_api_test
* Supports simple model which contains only a relu layer
* Add compiling scripts for XPU
* Fix compiling errors of XPU
* Add comments for XPU LoadModel and BuildModel

* [NPU] Fix the bug of loading multi NPU models
test=develop

* [NPU] Use lite tensor to store NPU model, fix the management of multi NPU models, support loading NPU model from memory and reduce the modification of framework
test=develop

* [NPU] Remove redundant header files for NPU bridges,
test=develop

* [NPU] fix NPU deps
test=develop

* [NPU] refine the compiling script for NPU
test=develop

* [NPU] remove redundant subdirectory in lite/CMakeLists.txt
test=develop

* [NPU] Fix and refine NPU test case
test=develop

* [NPU] revoke the modification of other non-NPU modules
test=develop

* [NPU] Remove NPU bridges if target is tiny publish
test=develop

* [LITE][OPENCL] support image2d. test=develop

* add context changed with consider image*. test=develop

* add layout, relu image kernels. test=develop

* replace image_data with data, mutable_image_data with mutable_data, test=develop

* comment unused var. test=develop

* remove unused var. test=develop

* add conv int8 support(in condition which the input or output channel not be the times of 4)
add add_kernel for cuda.

* can run yolov3 fp32
test=develop

* 1. fix bug with yolov3 run
test=develop

* add full_api_static target and fix building errors, test=develop

* fix build errors, test=develop

* fix code style, test=develop

* fix lite/model_parser/pb/var_desc.cc, test=develop

* fix building errors, test=develop

* modify lite/tools/debug/CMakeLists.txt, test=develop

* paddle lite cuda init
can run model with leaky_relu

* add the missing file.
test=develop

* fix building ios tiny publish lib error

* support setting cluster and threads in MobileConfig

* fix build error, test=develop

* fix building server publish error, test=develop