3d750f9c5a
[Feature] Fp16 training for resnet50 ( #14850 )
...
* wip
* wip
* wip
* wip for test
* add fp16 tests test=develop
* fix cpu build test=develop
* fix test=develop
* fix py3 tests test=develop
* fix lr_scheduler dtype test=develop
* fix test=dvelop
* test fix ci compile test=develop
* fix build and merge test=develop
* fallback momentumop change to general test=develop
6 years ago
679d1a9e0b
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into accelerate_lstm
6 years ago
83ac85158a
polish code
...
test=develop
6 years ago
045dc12766
merge develop
...
test=develop
6 years ago
ce4a26ddad
clean code
...
try to fix mac compile bug?
test=develop
6 years ago
e9eee0de6a
MKLDNN residual connection fuse: fixing accuracy problem ( #14874 )
...
* MKLDNN residual connection fuse: conv op reused
test=develop
* MKLDNN residual connection fuse: added prints for checking fuse
test=develop
* MKLDNN residual connection fuse: add more prints
test=develop
* MKLDNN residual connection fuse: add hash function. test=develop
* MKLDNN residual connection fuse: add hash to elementwise_add
test=develop
* MKLDNN residual connection fuse: add more hashes. test=develop
* MKLDNN residual connection fuse: added hashes to relu
test=develop
* MKLDNN residual connection fuse: do not fuse when fuse_relu is on
* MKLDNN residual connection fuse: check if fuse_relu attribute is set
test=develop
* MKLDNN residual connection fuse: comment out some printouts
* MKLDNN residual connection fuse: remove unused functions in the pass code
* MKLDNN residual connection fuse: delete commented hashes and printouts
* MKLDNN residual connection fuse: remove unnecessary includes. test=develop
6 years ago
53f6c6991a
polish code
...
test=develop
6 years ago
74a8e6b032
merge develop
...
fix conflict
test=develop
6 years ago
1fe3ac352a
move more and fix while
...
test=develop
6 years ago
ae6f46a1a9
rewrite variable type
...
test=develop
6 years ago
9ef8a76873
convert more
...
test=develop
6 years ago
876993887b
convert more interface to avoid scope
...
test=develop
6 years ago
8c19f0bfe3
fix
...
test=develop
6 years ago
9035bb81fe
Enable mul operator for a ngraph engine ( #14801 )
...
* Enable mul operator for a ngraph
test=develop
* Enable activation ops test
test=develop
* Remove unused line
test=develop
6 years ago
4dd61e7260
convert GetInputVarPtrs and GetOutputVarPtrs
...
test=develop
6 years ago
52d3903a12
fix
...
test=develop
6 years ago
0e0983cc1d
convert more infer shape
6 years ago
62eb43ba98
convert more
...
test=develop
6 years ago
dfcf746ea1
Merge pull request #14904 from panyx0718/clean2
...
refactor RunImpl
6 years ago
3f3a84b6dc
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into multithread-sparse-adam
...
test=develop
6 years ago
a500dfa579
rewrite ddim
...
test=develop
6 years ago
16c244bc3f
Merge pull request #14928 from sneaxiy/fix_gc
...
Fix gc bug
6 years ago
f897bd16c0
clean
...
test=develop
6 years ago
70981f5d79
clean
...
test=develop
6 years ago
44ad2f4479
Merge pull request #14873 from colourful-tree/develop
...
add pslib(pserver) to paddle, an industrial scale high performance parameter server library
6 years ago
69642000dc
Hide KeyHasher
...
test=develop
6 years ago
a9fb34fad8
Merge pull request #14903 from NHZlX/add_conv_elementwise_pass
...
Add conv + elementwiseAdd pass
6 years ago
7cd24b1318
add ir memory optimize. ( #14530 )
...
* follow comments. test=develop
* Fix typo
* fix compile error. test=develop
* merge develop branch. test=develop
* Remove set_equal
* Polish code
* Delete unused functions
test=develop
* polish code. test=develop
* follow comment
* polish code.
* fix windows compile error. test=develop
* fix op handle.
* rerun ci. test=develop
* rerun ci. test=develop
* rerun macci. test=develop
* polish code. test=develop
* rewrite sort code. test=develop
* remove unused code. test=develop
* fix tests. test=develop
* fix conflict. test=develop
* follow comment. test=develop
* merge develop branch. test=develop
* fix tests. test=develop
* remove ToTypeIndex. test=develop
* rerun ci. test=develop
6 years ago
fb8ae30331
fix
...
test=develop
6 years ago
a79a3ea2f0
Merge branch 'develop' into develop
6 years ago
0f085f0a5a
Merge pull request #14892 from wopeizl/windows/port3
...
fix script issue
6 years ago
06936a2ff5
fix 1gpu test=develop
6 years ago
c631412eab
fix gc bug
...
test=develop
6 years ago
eaf8ba35b5
change input
...
test=develop
6 years ago
840e6729e2
inject context
...
test=develop
6 years ago
bbff0df320
try cache variables
...
test=develop
6 years ago
52bc4ee75a
delay infer scope
...
test=develop
6 years ago
d3a4da5cf6
fix comment test=develop
6 years ago
49870f507d
delete unused code test=develop
6 years ago
3bd54ed769
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into multithread-sparse-adam
6 years ago
27a0d6c2dc
Polish code
...
test=develop
6 years ago
aa41ee75a1
Accelerate PADDLE_ENFORCE
6 years ago
fcc93d96d5
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into add_conv_elementwise_pass
...
fix conflicts
test=develop
6 years ago
a7d6b1f921
code cleanup test=develop
6 years ago
728e7e88fb
Use xxHash as scope's hash algorithm
...
test=develop
6 years ago
a760a550b0
Merge branch 'develop' of github.com:PaddlePaddle/Paddle into parallel_graph_mode
6 years ago
fd144954ed
redefine api test=develop
6 years ago
81651fca45
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into accelerate_ddpg
...
test=develop
6 years ago
bacf1d2399
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into feature/tensor_type
6 years ago
e439257ef7
Fix include style
...
test=develop
6 years ago
c0c9fcd9c7
add source file
...
test=develop
6 years ago
4c0a769d1d
avoid clock time in WIN32 mode
...
test=develop
6 years ago
66522046ad
remove clock time in WIN32 mode
...
test=develop
6 years ago
f2b92d77b5
remove clock time in WIN32 mode
6 years ago
4e4a777243
add conv+elementwiseadd pass
...
test=develop
6 years ago
0b1c7d838c
Add brpc serialization support. ( #11430 )
6 years ago
a985949be9
Fea/fuse conv elementwise add fuse ( #14669 )
6 years ago
4a4ccac1d0
update by comment test=develop
6 years ago
04a570b463
Fix ut
...
test=develop
6 years ago
09d669ba40
fix static_cast to const_cast
6 years ago
23dec78772
fix script issue
...
test=develop
6 years ago
bd1c1724aa
add ps_instance doc
6 years ago
62b5772ffb
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into feature/tensor_type
6 years ago
fac8702269
adam support multithread
6 years ago
e213050223
Fix multi-threading bug with WItH_MKL=ON ( #14882 )
...
fixes #14884
6 years ago
4f304eaa6f
fix unittest test=develop
6 years ago
d839bd0dd4
simple commit
6 years ago
3bb9b0cac2
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into accelerate_ddpg
...
test=develop
6 years ago
a81495d6f4
Fix code
6 years ago
ad6ae0b071
1. Add SpinLock
...
2. Seperate the lock of kids and vars in Scope
test=develop
6 years ago
c722b1dcb6
Merge branch 'develop' of github.com:PaddlePaddle/Paddle into parallel_graph_mode
...
test=develop
6 years ago
4ecdb6f486
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into feature/tensor_type
...
test=develop
6 years ago
f6741df462
merge develop
...
fix bug
test=develop
6 years ago
1b564bc49a
Merge pull request #14670 from sneaxiy/refactor_eager_deletion
...
Rewrite eager deletion
6 years ago
c9b799896e
fix tag in async_executor
6 years ago
f81957a753
refine cmake for pslib & pre_define
6 years ago
2328bee1cc
fix Windows compile bug
...
test=develop
6 years ago
23eb8c4299
fix ci test=develop
6 years ago
2912d5311b
fix code style bug & change pslib.cmake & change Cmakelist adapt pslib
6 years ago
c59cdf3a24
refine executor_thread_worker.h and executor_thread_worker.cc code style
6 years ago
3c01cdeff0
refine executor_thread_worker.cc & executor_thread_worker.h code style
6 years ago
c71279bc69
refine code style for async_executor.h and async_executor.cc
6 years ago
162637b64a
Fix ngraph compile
...
test=develop
6 years ago
33ee5cad61
format code style of executor_thread_worker.cc
6 years ago
194e66f785
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into feature/tensor_type
6 years ago
7bd16e3afa
fix some bug & add log
6 years ago
30aad88449
Merge pull request #14839 from panyx0718/infer3
...
fix clang
6 years ago
db2daefe50
merge develop
...
test=develop
6 years ago
106e285236
add unittest for parllelgraph mode test=develop
6 years ago
a61eb543f5
Add RWLock to Scope
6 years ago
e82772f425
fix cmake conflict
...
test=develop
6 years ago
0c554a59fa
merge develop
...
test=develop
6 years ago
1b61021cb3
Polish code
6 years ago
b75bd29c3a
Remove debug info
6 years ago
7a43e51703
Add gperf tools
6 years ago
c00e07cda0
Fix distribute compile
...
test=develop
6 years ago
d846fb03a8
Merge pull request #14807 from baojun-nervana/ngraph_follow_up
...
Follow ups on nGraph PR comments
6 years ago
ca84c2ca8f
merge develop
...
test=develop
6 years ago
e240ba2918
implement backward
...
test=develop
6 years ago
06f8aa5b97
remove while_op support temporarily
...
test=develop
6 years ago
81520a24cf
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into feature/refine_eigen_tensor
6 years ago
9bd70a1e04
Change tensor uses proto::VarType::type
...
test=develop
6 years ago
8175983ef9
Merge pull request #14814 from reyoung/feature/gprof
...
Add gperftools supports for PE
6 years ago
10ed9e0a6e
download & run & instance
6 years ago
5cc83f79bf
update by comment
6 years ago
82726402be
exception safe
6 years ago
570338699b
Add debug info
6 years ago
9f8d86858e
Revert data_type
...
test=develop
6 years ago
7923042365
merge develop
...
test=develop
6 years ago
3243b45bb2
Merge pull request #14651 from luotao1/has_attr
...
add Opdesc's HasProtoAttr
6 years ago
1735022a1b
fix clang
...
test=develop
6 years ago
016a068775
stop server
6 years ago
067ed70f2d
add HasProtoAttr function in op_desc.h, clean node.h
...
test=develop
6 years ago
8e3fe2d735
add skip op
6 years ago
79082c9459
fix pyreader failed
6 years ago
202b2f1fa7
Move the beta pow scale calculation into Adam Op
6 years ago
b22d638d8f
Speed up SizeOfType
...
test=develop
6 years ago
4a716a70c6
Merge pull request #14811 from panyx0718/revert-14782-revert-14398-imperative
...
Imperative
6 years ago
9623b45f40
Remove unnecessary MKLDNN reorder ( #14799 )
...
When data flow from a MKLDNN OP kernel to a non-MKLDNN OP kernel,
data layout transform (via MKLDNN reorder) will occur even when
those two OP kernels share same layout. Add code to remove this
unnecessary reorder.
test=develop
6 years ago
2dda19f756
Merge branch 'develop' of github.com:PaddlePaddle/Paddle into parallel_graph_mode
6 years ago
e99597d35c
Merge branch 'develop' into luotao1-has_attr
6 years ago
f0c0bf328d
Add gperftools supports for PE
6 years ago
748549b2e3
Revert "Merge pull request #14798 from PaddlePaddle/revert-14786-revert-14782-revert-14398-imperative"
...
This reverts commit b1d3a1c8b4f1fb64b17f
6 years ago
943ad4781f
One possible solution to add flexibility for mkldnn placement pass ( #14768 )
...
* Choose to turn on use_mkldnn attribute v1
* Fix mkldnn_op empty bug
* format change test=develop
* fix ci test=develop
* fix ci test and add test in dam test=develop
* add example to dam compare test test=develop
* review changes test=develop
6 years ago
fddbd87c0a
Rename argument
...
test=develop
6 years ago
22ac2133e4
Rename class
...
test=develop
6 years ago
bfde5e10ce
Move ngraph compile control to cmake
...
test=develop
6 years ago
2c6159a151
fix unittest
...
fix cmake
test=develop
6 years ago
c049fa7cf7
Revert "Revert "Revert "Imperative"""
7 years ago
f1fb64b17f
Add reduce sparse tensor feature. ( #14757 )
7 years ago
eb8252466b
polish code
...
add unittest model containing while_op
remove unnecessary codes
test=develop
7 years ago
c83d5b7a16
Merge pull request #14709 from yihuaxu/develop_4f71a6ee2_conv3d_bias_fusion_mkldnn_impl
...
Implement the fusion of convolution 3D and bias for mkldnn
7 years ago
47740ace28
fix performance
7 years ago
220db4f334
clean code
7 years ago
cb8a24be14
clean code
7 years ago
575ae7c6c3
refine pslib inferface & fix some bugs
7 years ago
3821fc3950
Merge branch 'develop' into develop_4f71a6ee2_conv3d_bias_fusion_mkldnn_impl
...
test=develop
7 years ago
240d974ac5
Clean Code
...
test=develop
7 years ago
2538ef64f1
Revert "Revert "Imperative""
7 years ago
b82a44ea85
Merge pull request #14778 from wangguibao/async_executor_bugfix
...
Async executor bugfix: Tensor changed to LoDTensor
7 years ago
8095fb5e68
fix code bug in CPU compilation
...
test=develop
7 years ago
387bac46b5
refine code
...
test=develop
7 years ago
cf66133857
Merge pull request #14734 from luotao1/memory_load
...
support loading from memory
7 years ago
6217f42ab7
Revert "Imperative"
7 years ago
743cb840f1
update with comments
...
test=develop
7 years ago
c9de6f1b05
init parallel graph mode
7 years ago
5a2cd4505b
AsyncExecutor bugfix: Tensor to LoDTensor
...
test=develop
7 years ago
5f98d80039
AsyncExecutor bugfix: Tensor change to LoDTensor
7 years ago
923b18877e
Merge branch 'develop' into memory_load
...
test=develop
7 years ago
405b2486db
support loading from memory
...
test=develop
7 years ago
b52f5d2870
Merge pull request #14398 from panyx0718/imperative
...
Imperative
7 years ago
d3ca359e44
config init & adapt to interface
7 years ago
73b4d1aa72
Merge pull request #14742 from panyx0718/infer2
...
support customized kernel selection
7 years ago
82d68281c0
follow comments
...
test=develop
7 years ago
41c28d54c6
allow customize kernel selection
...
test=develop
7 years ago
439af8d50a
Merge pull request #14717 from panyx0718/infer
...
fix a const_cast and avoid using stale program.
7 years ago
d0c8b9b9b3
remove timeout unittest
...
test=develop
7 years ago
419506f510
refine for compile pslib.so
7 years ago
29d9fb53fc
[Feature] multi process multi gpu dist training, boost v100 performance by 20% ( #14661 )
...
* wip multi process multi gpu dist training
* workable for p2p
* update test=develop
* change back env name test=develop
* fix alloc init
* fix cpu build test=devlop
* fix mac tests test=develop
* refine code
* refine test=develop
7 years ago
e694d0c2e4
fix while_op eager deletion bug
...
add unittest
test=develop
7 years ago
dc458b1482
Merge pull request #14713 from panyx0718/api
...
add more files to protected file list
7 years ago
2301abc481
cc libaray add pslib
7 years ago
35a2578426
fix bug
...
test=develop
7 years ago
abbe382e1e
Revert "Add EstiminateFlops"
7 years ago
0591ba96ec
fix hack
...
test=develop
7 years ago
64ad051b9a
merge develop
...
test=develop
7 years ago
c47c451a00
fix bug
7 years ago
a77fa67bbd
async_thread_trainer & libmct & pslib.cmake
7 years ago
3437e17713
Merge branch 'has_attr' of https://github.com/luotao1/Paddle into luotao1-has_attr
7 years ago
bcf36d8401
add more files to protected file list
...
test=develop
7 years ago
0e3048db43
Merge pull request #14659 from luotao1/update_pass
...
update is_test_pass and mkldnn_placement_pass
7 years ago
7e0801d4ed
Merge pull request #14441 from baojun-nervana/intel/ngraph_op
...
Implementing ngraph engine
7 years ago
b80fe8264a
polish
...
test=develop
7 years ago
64e261c6cd
Implement the fusion of convolution and bias for mkldnn
...
(test=develop)
7 years ago
8d6984eb9b
change OpHasAttr to RuntimeHasAttr, add some comments
...
test=develop
7 years ago
a6ac42669c
Merge branch 'develop' into update_pass
7 years ago
0f0e197914
Merge pull request #14666 from reyoung/feature/estiminate_flops
...
Add EstiminateFlops
7 years ago
aeb74af54c
allow operator to run imperatively
7 years ago
b1f6fda5e5
run forward
7 years ago
08233beed7
add the comment for CheckFile function. test=develop
7 years ago
d62a3dd72d
add the comment for CheckFile function. test=develop
7 years ago
d89108766c
update CheckFile function in data_feed for ignore the space at the end of each line of data(for example, it may be added '\t' character to the end of the reduce task output when processes data by hadoop, which does not affect the correctness of the data). test=develop
7 years ago
61ae88b760
Revert "Fix for accuracy problem for inplace operators when MKL-DNN mode is enabled"
7 years ago
52a0be7bb4
add mct into CMakeLists.txt
7 years ago
99177b424b
Merge pull request #14693 from kbinias/fix-for-accuracy-problem-for-inlplace-operators
...
Fix for accuracy problem for inplace operators when MKL-DNN mode is enabled
7 years ago
3c239cd640
pslib
7 years ago
bc7db6cec9
Fix for accuracy problem for inplace operators when MKL-DNN mode is enabled
...
test=develop
7 years ago
41e19eb431
AsyncExecutor ( #14627 )
...
* AsyncExecutor: C++ side
* Google naming conventions
* Rename MultiExecutor to AsyncExecutor
* pybind with async_executor
* Naming convention
* remove some flags and unused code
* add refactored file of async_executor and data_feed
* clear async executor interface and add data feed factory
* split async executor into executor_thread_worker and async_executor, refactor pybind, add datafeed and corresponding proto
* Fix async_executor interfaces: 1) Remove all protobufs; 2) Stop after each epoch
* refine async_executor_refactor.cc
* add some files about datafeed
* Revert "add some files about datafeed"
This reverts commit 8ee8133ab841196925a2812b76f18d2812a6701d.
* Interface rework
* add MultiSlotDataFeed
* Creating DataFeedDesc from .proto file, then manipulate it (add/del fields etc) from python side
* update data_feed for add MultiSlotDataFeed
* update datafeed and async_executor to run bow_net demo
* fix bug that finish_set_filelist failed in multithread
* delete finish_binding_memory_(flag), because it can not be marked under the current interface
* Fix bug
* update async_executor.py for support set_use_slots
* update async_executor.py for support set_use_slots and set set_dense_slots
* fix bug that when the number of files is less than the number of threads, it will fetch nan
* remove redundant code, and make executor exit when set a illegal queue size
* add batch_size check
* add MultiSlotDesc
* Revert "add MultiSlotDesc"
This reverts commit 2e72ebfad364ed6b5dcc75f38ffb2a1fdec83d8e.
* add some checkpoint in DataFeedDesc
* add CheckFile function in MultiSlotDataFeed
* update something error info
* fix deaded lock bug
* Fix fetch variable
* Merge error
* fix code style in async_executor
* using one lock blocking queue replace two lock blocking queue because of some bugs
* update code style
* add utest for data_feed
* Fix fetch var
* update utest for data_feed for multithread
* update SetFileList info
* fix bug in utest of data_feed
* Add comments for python
* Add comments for python code
* Fix pybind.cc with new pybind11 version
* add note for DataFeedDesc's set_use_slots function
* Add save_model
* update data_feed_test for multi-type
* add comment for executor_thread_worker
* Remove unused code
* update data_feed_test for generate test data file
* removed unnecessary interfaces and add comments
* c++ style check
* update data_feed.cc
* AsyncExecutor: C++ side
Google naming conventions
Rename MultiExecutor to AsyncExecutor
pybind with async_executor
Naming convention
remove some flags and unused code
add refactored file of async_executor and data_feed
clear async executor interface and add data feed factory
split async executor into executor_thread_worker and async_executor, refactor pybind, add datafeed and corresponding proto
Fix async_executor interfaces: 1) Remove all protobufs; 2) Stop after each epoch
refine async_executor_refactor.cc
add some files about datafeed
Revert "add some files about datafeed"
This reverts commit 8ee8133ab841196925a2812b76f18d2812a6701d.
add MultiSlotDataFeed
Interface rework
Creating DataFeedDesc from .proto file, then manipulate it (add/del fields etc) from python side
update datafeed and async_executor to run bow_net demo
update async_executor.py for support set_use_slots
Fix bug
update async_executor.py for support set_use_slots and set set_dense_slots
fix bug that when the number of files is less than the number of threads, it will fetch nan
remove redundant code, and make executor exit when set a illegal queue size
add MultiSlotDesc
Revert "add MultiSlotDesc"
This reverts commit 2e72ebfad364ed6b5dcc75f38ffb2a1fdec83d8e.
add some checkpoint in DataFeedDesc
Fix fetch variable
fix code style in async_executor
Fix fetch var
add utest for data_feed
Add comments for python
update utest for data_feed for multithread
fix bug in utest of data_feed
Add comments for python code
Fix pybind.cc with new pybind11 version
add note for DataFeedDesc's set_use_slots function
update data_feed_test for multi-type
Add save_model
update data_feed_test for generate test data file
removed unnecessary interfaces and add comments
add comment for executor_thread_worker
Remove unused code
update data_feed.cc
c++ style check
* commit for code style
* commit for code style
* commit for code style
* commit for code style
* Comment away __init__ in async_executor.py
* clang-format fix test=develop
* use PADDLE_THROW instead of exit(-1); use unique_ptr to manage scope var in data_feed_test.cc
* commit for update code style
* commit for update code style
* Add async_executor demo; Remove some methods
test=develop
* commit for update code style
* commit for update code style
* commit for update code style
* update API.spec
* AsyncExecutor
test=develop
* AsyncExecutor
test=develop
* AsyncExecutor
test=develop
* AsyncExecutor
test=develop
* Fix API.spec
test=develop
* Fix API.spec
test=develop
* Fix windows build error
test=develop
* FIx windows build error
test=develop
* FIx windows build error
test=develop
* FIx windows build error
test=develop
* Fix Windows Build
test=develop
* Fix Windows Build
test=develop
* Fix Windows Build
test=develop
* Fix code style
test=develop
* Fix code style
test=develop
* update datafeed
* Fix code style
test=develop
* update data_feed_test for test Tensor test=develop
* Fix code style
test=develop
* Fix windows build failure
test=develop
* Fix code style and windows build failure
test=develop
* Fix PYTHON3.5 build failure
test=develop
* AsyncExecutor API
test=develop
7 years ago
fc61bf1b16
Renamed methods
...
test=develope
7 years ago
096673f675
refactor eager deletion
...
test=develop
7 years ago
c856ac8721
add OpHasAttr in node.h, update is_test_pass and mkldnn_placement_pass
...
test=develop
7 years ago
44debca844
Merge pull request #14589 from jacquesqiao/refactor-prefetch
...
Refactor prefetch
7 years ago
5db273d874
enhance HasAttr to fix ci
...
test=develop
7 years ago
589b863b98
Add EstiminateFlops
...
test=develop
7 years ago
d5ee05e6c3
Replaced VarIsTensor
...
test=develop
7 years ago
e6bd53be60
Named to RuntimeInferShape
...
test=develop
7 years ago
a29696146c
Added annotation
...
test=develop
7 years ago
caf4b937b3
Added RunInferShape
...
test=develop
7 years ago
1d19eb2bd4
Implemented ngraph engine
...
test=develop
7 years ago
fe915901cd
update Opdesc's HasAttr
...
test=develop
7 years ago
6776e92846
refine tensor_array_write_read ( #14643 )
...
test=develop
7 years ago
8ebde595c9
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into refactor-prefetch
...
test=develop
7 years ago
145c535750
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into refactor-prefetch
...
test=develop
7 years ago
a02ce58f2c
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into revert_vlog
...
test=develop
7 years ago
7594787deb
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into enhance_hierachical_sigmod_op
7 years ago
3c77ce3751
Merge pull request #14593 from panyx0718/fix5
...
Protect important header files.
7 years ago
e8ef14d2a7
Merge pull request #14610 from Superjomn/revert/cache_fix
...
Revert "fix transfer cache thread_local bug (#14581 )"
7 years ago
87648f8edf
merge develop, test=develop
7 years ago
db9284ecde
Merge pull request #14617 from wopeizl/windows/online
...
Windows/online
7 years ago
c3c3c0b33c
polish code, test=develop
7 years ago
867c312bc4
Fix allreduce dependency order. ( #14586 )
7 years ago
9589babe12
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into refactor-prefetch
...
test=develop
7 years ago
38715e6fd0
minor fix
7 years ago
7e4bd695e6
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into enhance_hierachical_sigmod_op
7 years ago
b10df8bcfa
refine code and add none bias ut, test=develop
7 years ago
dc249d3b69
Revert "fix transfer cache thread_local bug ( #14581 )"
...
This reverts commit 5c073a4db2
7 years ago
be04d99fe4
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into revert_vlog
...
test=develop
7 years ago
af2f5fc824
fix some bugs
7 years ago
3e665862b8
Protect important header files.
...
test=develop
7 years ago
53433d7f2e
Revert the changes of VLOG
...
test=develop
7 years ago
30849d1f20
Merge remote-tracking branch 'upstream/develop' into windows/build
7 years ago
5c073a4db2
fix transfer cache thread_local bug ( #14581 )
7 years ago
87332bb18d
Merge pull request #14579 from Superjomn/fix/transfer-cache-compile-error
...
fix compile
7 years ago
36cd18b549
Merge remote-tracking branch 'upstream/develop' into windows/build
7 years ago
1afa9492af
Recover the profiler
7 years ago
bf222f197d
Use sub scope in tensor_array_to_tensor op. ( #14524 )
...
test=develop
7 years ago
4b40c0013b
fix compile
...
test=develop
7 years ago
a7188d5bc7
fix executor transfer cache bug ( #14518 )
7 years ago
42470f14b7
test=develop
7 years ago
36f08eef3b
CUDA kernel for density_prior_box_op. ( #14513 )
...
* CUDA kernel for density_prior_box_op.
* Support flatten to 2D.
7 years ago
7c8c9dc9bf
fix unit test cases
7 years ago
3c6102a367
test=develop
7 years ago
488610a65a
merge develop
...
test=develop
7 years ago
d9a1f3e58e
Windows/online ( #14474 )
...
* add recordio support
* disable the openblas multi-thread on windows since no support
adjust the python script
* code style
* code style
test=develop
* add create_recordio_file_reader back
* fix code style
test=develop
* fix the gtest.cmake on windows
* fix cc_test on windows
* fix the win build
test=develop
* remove fused compile support on windows
test=develop
* add the jit support
test=develop
* add the jit support, test=develop
* add the jit support, test=develop
* add the jit back
fix compile error on windows
* rollback test=develop
* test case fix
* disable DSO by default on windows
* exclude warpctc_op on windows
* exclude the dynload_warpctc out on windows
test=develop
* fix the scripts error
test=develop
* disable avx on windows by default
test=develop
* re-organize the cmake file
* disable mkl on windows by default
* add warp_ctc back
* fix the dependency
* fix the dependency
* fix the build issue on windows
* remove unsupported flag on windows
* code style
* code style
test=develop
* fix issue
* add profiler, parallel_executor back
* clean up the pre-definitions on windows
* fix build issue
* test=develop
7 years ago
3912545ffe
add dlpack support
...
test=develop
7 years ago
f7b55de9e5
Merge branch 'develop' into enhance_hierachical_sigmod_op
7 years ago
af9a3301da
test=develop
7 years ago
014e50c284
test=develop
7 years ago
6e66fadb95
clean up the pre-definitions on windows
7 years ago
67562a6fcd
Merge remote-tracking branch 'upstream/develop' into windows/build
7 years ago
703b26e697
add profiler, parallel_executor back
7 years ago
10fb4ceefc
Merge pull request #14351 from tpatejko/tpatejko/mkldnn-elementwise_mul
...
[MKLDNN][JIT][AVX512] Elementwise Mul
7 years ago
25adf970b2
Merge remote-tracking branch 'upstream/develop' into windows/build
7 years ago
a94a7355f0
Refine the GraphNum check ( #14144 )
...
* refine GraphCheck
test=develop
* fix ci fail
test=develop
7 years ago
3a72a634cf
Merge remote-tracking branch 'upstream/develop' into windows/build
7 years ago
cf685f361b
Merge pull request #14458 from tpatejko/tpatejko/mkldnn-skip-connections
...
[WIP] Correcting and extending MKLDNN residual connection fuse pass
7 years ago
98bbfc17be
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into rewrite_allocation
...
test=develop
7 years ago
d424115f9e
Clean code
...
test=develop
7 years ago
1cc23ef67d
merge from paddle:develop
7 years ago
4e54ab76ec
Add HasAttr method to Operator
7 years ago
a2d9b34417
Refine operator cmake ( #14413 )
...
* wip simplify operator framework
* wip
* wip
* done test=develop
* clean test=develop
* fix test=develop
* fix deps test=develop
* fix cpu build test=develop
* fix tensorrt build test=develop
* fix tests test=develop
* fix test=develop
* fix cpu build test=develop
7 years ago
53da846d1e
MKLDNN residual connections fuse pass: initial implementation of fusion for projection pass
...
test=develop
7 years ago
dbc4fcd722
MKLDNN residual connections fuse pass: unit tests enabled and added
7 years ago
4224089354
MKLDNN residual connections fuse pass: Maybe removed and boost::optional used where it makes sense
7 years ago
86fd3b32be
MKLDNN residual connections fuse pass: counting statistics added to the pass
7 years ago
ee6f778beb
MKLDNN residual connections fuse pass: further refactoring
7 years ago
7423748e37
MKLDNN residual connections fuse pass:
...
* implements reachability check between identity node and non-identity argument to elementwise_add
* implements handling identity node as x and as y argument to elementwise_add
7 years ago
6d0d5a76eb
Merge remote-tracking branch 'upstream/develop' into windows/build
7 years ago
7796f65f89
fix inference on gpu out of mem ( #14414 )
...
* fix inference on gpu out of mem
the transfer logic in operator.cc will keep creating new scopes.
7 years ago
c8f6e70ab4
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into rewrite_allocation
...
test=develop
7 years ago
8a1eeec579
add mkldnn prop_kind phase for inference-only case to pooling and activations ( #14278 )
...
* add is_test to pooling and activations
add prop_kind support for layers activation. conv and pooling
add a pass that sets is_test to true
add transpiler version of is_test pass
test=develop
* patch test and pass
test=develop
* add pass to analyzer.h
test=develop
* add is_test attr description & pass only on mkldnn
in:
activation_op.cc
batch_norm_op.cc
conv_op.cc
dropout_op.cc
lrn_op.cc
pool_op.cc
sequence_pool_op.cc
softmax_op.cc
* fix is_test handling for activation pool and conv
* change description of is_test for all layers again
* remove GetAttr(use_mkldnn) from pass
* rename correct_mkldnn_test_phase to is_test
and remove dependency on MKLDNN
test=develop
* review fix magic number
* two if(..)s into one
* Check is_test once and pass mkldnn forward prop kind
* dereference shared_ptr with * (without get())
test=develop
* add is_test_pass back
test=develop
7 years ago
d1429ac4a5
add recordio support
7 years ago
0d6718fcbd
Pass compile
7 years ago
5ef123c778
Merge branch 'develop' into dam_fc
7 years ago
d3aed98d86
Merge pull request #14320 from wopeizl/windows/online
...
Windows/online
7 years ago
be332a13bc
Merge remote-tracking branch 'upstream/develop' into windows/build
7 years ago
8cfda7ee0c
Merge pull request #14382 from panyx0718/fix4
...
Refine the pass builder and buildstrategy
7 years ago
980a6753a8
fix typo to pass the ci
...
test=develop
7 years ago
c7b3bfcdf1
Merge pull request #14376 from baojun-nervana/intel/ngraph_fusedop
...
Adding fused operator for ngraph
7 years ago
1a9008c420
code style fix
...
test=develop
7 years ago
8ea13e336a
add in_num_col_dims for fc
7 years ago
08d1dc84a9
fix
7 years ago
30ddc07a7e
Merge remote-tracking branch 'upstream/develop' into windows/build
7 years ago
e65cbd3b06
Merge pull request #14387 from jacquesqiao/lookup_sparse_table_add_test_mode
...
Lookup sparse table add test mode
7 years ago
7066b3850a
Merge pull request #14395 from sneaxiy/fix_num_threads_in_fast_pe
...
Fix num_threads settings in fast_pe
7 years ago
9f252e0032
Combine Inference Analysis with IR ( #13914 )
7 years ago
51a538e055
Fix style and use enum
...
test=develop
7 years ago
38d32c98b8
merge develop
...
test=develop
7 years ago
eb18d532a5
fix num_threads in fast_pe
...
test=develop
7 years ago
51f3838f96
add log for not exist code
...
test=develop
7 years ago
7aa8b2ccf2
optimize code
7 years ago
8d205c853c
add is_test for lookup_sparse_table
7 years ago
ea3538d8dd
Added fused operator
...
test=develop
7 years ago
759ffca423
some improvements
...
test=develop
7 years ago
99dffb91d6
allow to repeatedly share and update BuildStrategy
...
test=develop
7 years ago
6c32945556
Merge pull request #14372 from luotao1/speedup_analysis
...
speedup DetectPatterns
7 years ago
668ae523d2
speedup DetectPatterns
...
test=develop
7 years ago
9a6e239281
fix mac graph detector sort ( #14356 )
7 years ago
1b75fd2236
revert
7 years ago
7840d181c9
fix style issue
7 years ago
dc339b78d7
fix code style
7 years ago
d231e55065
merge develop
...
test=develop
7 years ago
c8801e100f
grad diff problem to be fixed and need api spec change to be done
7 years ago
e23061e0dc
Merge remote-tracking branch 'upstream/develop' into windows/build
7 years ago
6c6e638550
Add InferVarType for some op ( #14201 )
...
* add_infer_var_type
test=develop
* InferVarTypeHelper-> VarTypeInferenceHelper
test=develop
* PassInputTypeAndDTypeOnOutput
test=develop
* follow comment
test=develop
7 years ago
ca60e1d34d
Merge remote-tracking branch 'upstream/develop' into windows/build
7 years ago
d08334011a
fix merge issue
7 years ago
52f7644f53
Merge remote-tracking branch 'upstream/develop' into windows/build
7 years ago
abe209234f
Exhaustive search for cuDNN conv. ( #14286 )
...
* exhaustive search for cuDNN conv.
* Refine code and add unit testing.
* Fix model load in fluid/inference and unit testing in conv2d
* Follow comments.
* Fix compiling test=develop
7 years ago
fdc689142c
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into rewrite_allocation
...
test=develop
7 years ago
Wu Yi
minqiyang
sneaxiy
Tomasz Patejko
Xin Pan
mozga-intel
Qiao Longfei
Zeng Jinle
colourful-tree
Zhaolong Xing
dzhwinter
guru4elephant
wopeizl
Yancey1989
Yu Yang
dongdaxiang
gongweibao
Yan Chunwei
peizhilin
Wang Guibao
tensor-tang
Yu Yang
Tao Luo
Brian Liu
bingyanghuang
baojun-nervana
Yihua Xu
wangguibao
zhang wenhui
barrierye
Krzysztof Binias
chengduo
JiabinYang
Yiqun Liu
qingqing01
Michal Gallus
Sylwester Fraczek