27 Commits (bc16bcda4914d1af76d8192d35ee852a21e12d1c)

Author	SHA1	Message	Date
chengduo	79bd6dfa18	[Feature] Add Temporary Allocator (#14875) ... * Add Temporal Allocator * add Temporay Allocator to DeviceContext test=develop * code refine test=develop * fix mean_iou test=develop * Add DeviceTemporaryAllocator test=develop * fix conv_op bug test=develop * small fix test=develop * code refine test=develop * log refine test=develop * fix unit test test=develop * move double check * refine concat_and_split test=develop * add limit_of_temporary_allocation test=develop * fix name test=develop	6 years ago
Yu Yang	e439257ef7	Fix include style ... test=develop	6 years ago
Yu Yang	4ecdb6f486	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into feature/tensor_type ... test=develop	6 years ago
sneaxiy	2328bee1cc	fix Windows compile bug ... test=develop	6 years ago
Yu Yang	9bd70a1e04	Change tensor uses proto::VarType::type ... test=develop	6 years ago
sneaxiy	eb8252466b	polish code ... add unittest model containing while_op remove unnecessary codes test=develop	6 years ago
sneaxiy	d0c8b9b9b3	remove timeout unittest ... test=develop	6 years ago
sneaxiy	c47c451a00	fix bug	6 years ago
Yu Yang	8310ce6007	Fix cluster memory ... test=develop	6 years ago
Yu Yang	dbf9f6f408	Fix distribute compile ... test=develop	6 years ago
Yu Yang	31270e58d0	Add communication attr	6 years ago
Yu Yang	58ed412f68	refactor(memory): rewrite memory allocation and make it extentable ... Use OO style to rewrite memory allocation.	6 years ago
sneaxiy	d0b2453ecd	merge develop	7 years ago
sneaxiy	24ea39c4c6	feature/eager_delete_tensor	7 years ago
Michal Gallus	4a7f0698e0	Add consts to new MKLDNN integration ... Also replace memory types from int64_t to size_t	7 years ago
Michal Gallus	6588d0e039	Update MKLDNN to 0.15, fix conv integration	7 years ago
minqiyang	c4d000a990	Make code more efficient	7 years ago
mozga-intel	3ff9ba0e6b	Mkldnn layout (#11040) ... * Add MKLDNN layout support in Paddle Add MKLDNN layout in Paddle so that MKLDNN friendly memory layout can be used in MKLDNN enabled OP kernel. Before this commit, NCHW is hardcode to be used in all MKLDNN op kernels. As a result, non-optimized execution path is selected in MKLDNN primitive which bring worse performance. Besides framework change, three MKLDNN OP kernels were updated for using new MKLDNN layout. They are conv/pool2d/batch_norm. Other MKLDNN OP kernels need be also updated in similar way to achieve best performance. * Add MKLDNN layout support in activation OP * Don't populate layout from input to output when kMKLDNN in * Refine pool mkldnn op kernel * MKLDNN layout * Remove the inferitance from tensor file * MKLDNN layout: refactoring * Remove additional #define to register new operator * Prepare mkldnn tests to work with layout	7 years ago
yuyang18	fc9f2d282f	Extract method from tensor_impl.h to tensor.cc	7 years ago
chengduoZH	158d6c4d19	add unit test	7 years ago
chengduoZH	18eb77303d	add CUDAPinnedPlace	7 years ago
chengduoZH	39004080f4	replace use_pinned with is_pinned	7 years ago
chengduoZH	eaa90d38ad	add use_pinned	7 years ago
fengjiayi	ed5dc3d4ae	remove 'friend lod_tensor in tensor'	7 years ago
qingqing01	24509f4af9	Fix the grammar in copyright. (#8403)	7 years ago
Yi Wang	fc374821dd	Correct #include path	7 years ago
Yi Wang	90648f336d	Move file to fluid/; Edit CMakeLists.txt	7 years ago