* Support fp16 in fused_elemwise_activation_op.
* Fix unit testing in ONLY-CPU mode.

* Delete PadFuntion, include padding.h instead. test=develop

* move function(IsSymmetricPadding) from conv_cudnn_op.cu/conv_transpose_cudnn_op.cu to padding.h, test=develop

Improve elementwise operators performance in same dimensions

1.support asymmetric padding;
    2.support padding algorithm:"SAME" and "VALID";
    3.support channel_last: data_format NHWC and NDHWC;
    4.change doc of python API and c++;

    test=develop, test=document_preview

* fix pool2d pool3d:
1. support asymmetric padding;
2. support padding algorithm:"SAME" and "VALID";
3. support channel_last: data_format NHWC and NDHWC;
4. support inferring shape when input with negative dims in compile time;
5. change doc of python API and c++;
6. fix bug in cuda kernel when Attr(adaptive) is true.

test=develop,test=document_preview

* fix 'tensors' to 'Tensors'. test=develop,test=document_preview

* add test for converage ValueError.test=develop,test=document_preview

* resolve conflict in test_pool2d. test=develop

* make pad and split support fp16
test=develop

* add support of matmul with multiple head even different width and height

Original matmul with multiple head supports only the mat_a.width == mat_b.height,
in that case, mat_b will be horizontally split. In this patch, we extend the
support when mat_a.width != mat_b.height but mat_a.width/head_number == mat_b.height,
in this case, mab_b will be vertically split.

One example is A is [3, 8], B is [2, 16], head_number is 4. In this
case, A will be split as [3, 2], B will be (vertically) split as
[2, 4]. The final result will be 4 matrix of 4 matrix of [3,4], i.e. [3, 16]

test=develop

* add support of matmul with multiple head even different width and height

Original matmul with multiple head supports only the mat_a.width == mat_b.height,
in that case, mat_b will be horizontally split. In this patch, we extend the
support when mat_a.width != mat_b.height but mat_a.width/head_number == mat_b.height,
in this case, mab_b will be vertically split.

One example is A is [3, 8], B is [2, 16], head_number is 4. In this
case, A will be split as [3, 2], B will be (vertically) split as
[2, 4]. The final result will be 4 matrix of 4 matrix of [3,4], i.e. [3, 16]

test=develop

* refactor the code of matmul with multiple head even different width and height

test=develop

* fix softmax ce time limit check failed. test=develop

* refine softmax calc. test=develop

* support 2-level lod of input in sequence_pool test=develop

* fix lod level bug in .cu test=develop

TemporaryAllocator is a singleton used for allocating memory for Cudnn. Since it is a singleton, we can delete it for better performance in memory.

We replace TemporaryAllocator by CUDADeviceContextAllocator and CUDADeviceContextAllocation, which uses stream callback to delete the memory allocated for the stream to avoid singleton.

Also added data_feed_proto to operator to fix CI in CPU compilation

* Refine the codes related to fc op.

* Add GPU implementation for fc functor.

* Apply fc_fuse_pass in GPU inference.
test=develop

* Change the cmake for fc op.

* Change PADDLE_ENFORCE to PADDLE_ENFORCE_EQ.

* Add an attribute to set the activation type in fc_op.

* Enhance the unittest of fc_op.
test=develop

* Remove the declaration of FCOpGrad back to the header file.
test=develop

* Set default value for newly added arguments in test_fc_op.
test=develop

* test=develop,  communicator merge add => merge average

* remove assert.h

* change PADDLE_ASSERT_MSG to PADDLE_ENFORCE

test=develop

* fix tensorrt paddle_enforce

test=develop

test=develop

test=develop

test=develop

* remove unused PADDLE_ASSERT(_IS_NOT_ERROR)

* replace PADDLE_ASSERT with PADDLE_ASSERT_MSG

test=develop

* 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

* print error code if cuda related API fails

* fix depthwise conv gpu kernel bug, test=develop
* add more depthwise conv test, test=develop

* extend matmul op to support multiple head multiplication

With the support of multiple head, the multiplication of two big matrixes is
split into multiplication of several (head_number) small matrixes. e.g. if
Mat A is [3, 24] and Mat B is [24, 4], when multiple A and B with head_number
as 4, Mat A will be split as 4 matrix of [3, 6] and Mat B will be 4 matrix of
[6, 4]. The result of final matrix will be 4 matrix of [3, 4], i.e. [3, 16].

* add_elementwise_add_inplace_test,test=develop

* rename file, test=develop

* sequnce mask support max length tensor input; test=develop

* add rnn_impl.py; test=develop

* add basic gru lstm unittest; test=develop

* fix api spec; test=develop

* fix sequence_mask op bug;
test=develop
test=document_preview

* change +-*x to elmentwise_op; test=develop

* add mkl flag; test=develop

* fix rnn impl bug; test=develop

* update api spec; test=develop

* fix doc bug; test=develop

* fix lstm bugs; test=develop

test=develop

Optimize the concat and split cuda implementation for cases when the number of inputs/outputs is less than 5. (#17979)

test=develop

* Enable seq_pool op to accept len 0 input

test=develop

* Update sequence_pool's api

test=develop

* Add more unittest cases for seq_pool op

test=develop

* Remove legacy comments

test=develop

* Don't use template in op maker

test=develop

* Enhance fused_elementwise_activation op.
test=develop

* Move the api fused_elementwise_activation to contrib.
test=develop

* Add including files.
test=develop

* Add the support of sigmoid in fused_elementwise_activetion op.

* Update API.spec.
test=develop

Optimize the concat and split kernel for specical cases when the number of inputs/outputs is 2 (#17415)

* Optimize the concat and split kernel for special cases that the number of inputs/outputs is 2.
test=develop

* Refine codes.
test=develop

* Correct the condition.
test=develop

* Move the define of tmp_data outside the if statement.

* Print the cudnn minor version.
test=develop

* Fix the case when in_num/o_num is 1 in concat/split op.
test=develop

* Remove const_cast.
test=develop

* refine softmax fwd

test=develop

* refine cpu softmax bwd

test=develop

* fix batch size

test=develop

* fix compile issue with gpu

test=develop

* add value clip

* refine softmax fwd

test=develop

* fix compile issue wih gpu

test=develop

* add value clip to avoid exp

http://newicafe.baidu.com:80/issue/PaddleSec-33/show?from=page
http://newicafe.baidu.com:80/issue/PaddleSec-28/show?from=page
http://newicafe.baidu.com:80/issue/PaddleSec-25/show?from=page
http://newicafe.baidu.com:80/issue/PaddleSec-24/show?from=page
http://newicafe.baidu.com:80/issue/PaddleSec-21/show?from=page
http://newicafe.baidu.com:80/issue/PaddleSec-20/show?from=page

test=develop

* improve gru unit performance.
refine code

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

* Add conditional compile for gru opt

Not enable gru opt if compute ability < 700

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

* refine code.

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

test=develop

refine code

fuse cublas  calling and kernels into one cuda kernel.

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

* add attr axis infershape. test=develop

* add CUDA kernel. test=develop

* fix unittest. test=develop

* fix unittest for soft_label. test=develop

* fix fp16 unittest. test=develop

* remove comment code. test=develop

* refine test for axis. test=develop

* add python api. test=develop

* fix doc. test=develop

* fix fp16 unittest. test=develop

* fix ngraph test. test=develop

* fix ENFORCE for test_imperative_transformer. test=develop

* fit for ngraph test. test=develop

* fix after rebase develop. test=develop

* fix doc. test=develop

* fix API.spec. test=develop

* fix test_layers. test=develop

* fix format. test=develop