* add diag init in Uniform_random op test=develop

* modify api.spec test=develop

* fix unform_batch_size_like maker test=develop

* add diag_num and diag_step assert check test=develop

* update parallel.py
test=develop

* stronger the error message of tensor's mutable_data

test=develop

* update error message

test=develop

* increase test_parallel_executor_seresnext time limit
test=develop

* split test_parallel_executor_seresnext
test=develop

* temporally disable reduce_and_allreduce test because of the random failure.
test=develop

* split gpu and cpu
test=develop

test=develop

* Add generalized Conv+Activation MKLDNN fuse pass creation Part2
test=develop

* Undefined behaviour of GetAttrIfExists<> FIX
test=develop

* add elementwise_mul_mkldnn UT with [conv + elt_mul + conv] to cover avx512=True branch
test=develop

* change a typo.
test=develop

For small case use 1D block is better than 2D block.

Refer to this issue: #19275

* replace part of PADDLE_ASSERT to PADDLE_ENFORCE

test=develop

* remove unused fallback_alloc_size_

* add unit-test of CUDAPinnedAllocator

test=develop

test=develop, test=document_preview

* Implement the operator with sprase matrix multiply

* Update the URL of mklml library.

test=develop

* Disable MKLML implematation when using no-linux.

test=develop

* Ignore the deprecated status for windows

test=develop

* cuda optimie for dropout

* remove tmp swp file

* fix compile error test=develop

* test=develop optimize the cuda realization of dropout op

* remove unsed code test=develop

* remove tmp file test=develop

distribute launch : add use_paddlecloud argument 

* fix mask rcnn bug:
1. affine channel fuse (diff)
2. condition block op (memory leak)
3. merge lod tensor op (diff)
4. memroy optim (diff)
test=develop

* fix ci aboud PADDLE_ENFOCE
fix merge lod infer op ut
test=develop

* add matrch_matrix_tensor op test=develop

* fix ignore unittest if with_mkl=off test=develop

* clean code and rm is_test param test=develop

* modify API.spec test=develop

* rm useless code in search_compute.h test=develop

* modify api.spec test=develop

* modify default_grad.spec test=develop

* Add API test code test=develop

* clean code in search_computer.h

* modify PADDLE_ENFORCE and clean search_compute.h test=develop

* fix code style test=develop

* fix compilation issue in windows vs2017, test=develop

* fix gtest lib not found issue, test=develop

add fl_listen_and_serv op for Federated_learning and fl_distribute_transpiler add this op to pserver program . This op just listen the endpoint and sum&scale.

remove the warning for reminding user to avoid using the OriginProgram method, test=develop (#19244)

This log information may annoy users who don't need to care about it.

add python coverage launch when WITH_COVERAGE=ON

* print error code if cuda related API fails

* test=develop,fix the inference library compilation bug on windows

* test=develop,Fix the inference library compilation bug on windows

* test=develop,fix the bug that PYTHON_EXECUTABLE not exists

* correct then sample command of diff_api.py to align with paddle_build.sh

* make PADDLE_ENFORCE_EQ support cannot to string types, test=develop

* follow huihuang's comments, test=develop

* fix REGISTER_OP_WITHOUT_GRADIENT
test=develop

Unset unittests http_proxy env to avoid timeout.

* imporve the doc of decorate_reader API, test=develop

* udpate API.spec, test=develop

node_num is not needed for users, so remove them and fix the bugs about it!

modify checkMacPython2 and checkMacPython3 function to ensure python version used for paddle installation is EQ/GT than 2.7.15 on MacOS; modify checkMacPaddleVersion function to ensure paddle version is release version, because paddle don't have develop version on MacOS.

* fix temporal_shift OP PADDLE_ENFORCE. test=develop

* fix HasInput/HasOutpu ENFORECE. test=develop

* remove unused inference_transpiler unit-tests

test=develop

* remove InferenceTranspiler usage in quantize_transpiler.py

test=develop

* change the top1 comparison to mAP comparison
test=develop

* change the mobilenet-ssd tester demo data and batch_size settings
test=develop

* Fix recurrent op fails

For the variable used in outter block,
copy sub block's grad variable to outter block

test=develop
Signed-off-by: Nzhaoyuchen <zhaoyuchen01@baidu.com>

* Fix unicode error

test=develop
Signed-off-by: Nzhaoyuchen <zhaoyuchen01@baidu.com>

* Refine test code

test=develop
Signed-off-by: Nzhaoyuchen <zhaoyuchen01@baidu.com>

* Fix seq2seq case fails

test=develop
Signed-off-by: Nzhaoyuchen <zhaoyuchen01@baidu.com>

* remove unreasonable code.

test=develop
Signed-off-by: Nzhaoyuchen <zhaoyuchen01@baidu.com>

* Refine code according to comment

test=develop
Signed-off-by: Nzhaoyuchen <zhaoyuchen01@baidu.com>