111 Commits (0536b5263d188c54069765c4168bdba91ad250c7)

Author	SHA1	Message	Date
Jacek Czaja	2bb1b0e89e	[DNNL] Added MKL-DNN inplace pass for C-API inference (#23315)	5 years ago
Tao Luo	c00d427d52	simplify the cmake log of ir/CMakeLists.txt (#23262) ... test=develop	5 years ago
Wilber	95b356a069	update embedding_eltwise_layernorm fuse and kernel. test=develop (#23114) ... update embedding_eltwise_layernorm fuse pass and fused kernel, to support multi input	5 years ago
Wilber	ff3ddbb502	add skip_layernorm pass. test=develop (#22895) ... * add skip_layernorm pass. test=develop	5 years ago
Zhaolong Xing	8d6dc102fe	[Ernie GPU Optimize]: Embedding_eltwise_layernorm Fuse (#22494) ... * 1. add embedding eltwise layernorm fuse 2. add embedding eltwise layernorm op 3. refine inplace_add_relu 4. refine fc_eltwise_layernorm test=develop * 1. refine fc test=develop * fix comments test=develop * fix comments test=develop	5 years ago
Wilber	9a8203aa25	fix fc_lstm_fuse when multi sub-graph use same fc_bias. test=develop (#22551) ... 当一个模型中有多个fc_lstm子图的时候，且其中fc共用了同一个persistable的bias，此时不应该将bias节点删除，只将非persistable的节点去除即可。	5 years ago
Yiqun Liu	dcfb603897	Enable the detection of subgraph composed of grad ops (#21223) ... * Add the first implememtation of fusion_group op #19621 (#3) * Add the dynamic load of nvrtc, and support runtime compiling of CUDA kernel using nvrtc. test=develop * Call CUDA driver api to launch the kernel compiled by nvrtc. test=develop * Disable for mac and windows. test=develop * Refine the codes to support manually specified num_threads and workload_per_thread. test=develop * Refine the CUDA kernel to support large dims. test=develop * Add DeviceCodePool to manage all device codes. * Add the first implementation fusion_group op. * Add unit-test for fusion_group op. * Add the check of result. * Add the check of nvrtc in unit-test. test=develop * Add comment to explain the inputs, outputs and features of fusion_group op. test=develop * Disable fusion_group op for mac and windows. test=develop * Make the compiling of device code return status instead of hanging up. test=develop * Add the check of whether there is CUDA driver library, and do not core dump when failing to call the CUDA driver API. * Unify fusion_group_op's input and output names. test=develop * Add the check of CUDA driver library in unittest. test=develop * Enable generating code for a given subgraph. #21126 (#4) * Enable generating code for a given subgraph. * Support sorting the subgraph. * Remove the rearange of expressions because we use the sorted subgraph directly. * Enable generating code for a subgraph which is composed of grad ops. * Use expression information to check the accuracy in unittest. * Separate load and store from computation expressions. test=develop * Improve the loading statements in generated codes. test=develop * Remove unused arguments from formal list. test=develop * Enable the detection of subgraph of grad ops. * Generate code for detected subgraph in fusion_group_pass. * Add an option in BuildStrategy to enable fusion_group_pass and add unittest. test=develop * Fix a bug when checking whether the shape of all inputs are the same. * Add debug information. * Remove subgraph_detector from inference/analysis to the common framework/ir directory. (#5) test=develop * Call subgraph_detector in fusion_group pass. test=develop * Disable fusion_group when WITH_GPU is OFF. test=develop * Refine all PADDLE_ENFORCE message. test=develop * Fix the case that some inputs are not defined in grad ops, and set op_role for fused op. test=develop * Follow review comments. test=develop	5 years ago
石晓伟	e1b0d7cbb1	remove anakin from code, test=develop (#22420)	5 years ago
Zhen Wang	46189b166d	Add bn and relu fuse pass (#22048) ... * add bn and relu fuse pass * add op attr assert and dtype assert * fix some inputs&&outputs bugs for the fused op and pattern. * add the unittest for fuse_bn_act_pass. test=develop * use normative enforce statements. test=develop * add the cpu test. test=develop * add the support of batch_size=1 for the bn with relu op. test=develop * add the error type for paddle throws. test=develop * add fused_batch_norm_act and fused_batch_norm_act_grad to op_has_unsed_vars_white_list. test=develop	5 years ago
Yiqun Liu	b1401fb74d	Remove subgraph_detector from inference/analysis to the common framework/ir directory. (#22094) ... test=develop	5 years ago
Yiqun Liu	c918788ba9	Disable fusion_group pass for windows and mac. We will do some experiments on Linux first. (#21310) ... * Disable fusion_group pass for windows and mac. We will do some experiments on Linux first. test=develop * Print the subgraph when check failed. test=develop	5 years ago
Yiqun Liu	b5f3be8330	Implement a pass detect fusion group of elementwise op (#19884) ... * Add fusion_group_pass and elementwise pattern. * Rewrite the detector of elementwise group. test=develop * Add a comment in codegen. * Add more unittest cases. test=develop * Move code_generator related code to fusion_group directory. * Correct the including path. * Add the definition of SubGraph and finish the insert of fusion_group op in pass. * Insert graph_vis_pass in tester to visualize the graph for debug.	5 years ago
wangchaochaohu	ba45dce35d	fix codetest for windows make test=develop (#20796)	5 years ago
zhaoyuchen2018	b8333edef6	Add Multihead matmul fuse pass (#20167) ... * Add multihead fuse pass for ernie opt * Refine softmax test=develop * Refine cuda kernel * Refine cuda version * Refine cmake test=develop * refine header file * refine test case and pass * refine comments	5 years ago
Adam	7faa3e9555	Add ConvTranspose + BatchNorm fuse pass (#20161) ... * Add ConvTranspose + BatchNorm fuse pass test=develop * Add tests for conv+bn and conv_transpose+bn passes test=develop	5 years ago
wangchaochaohu	c9ea317b36	codegen code for reconstruction (#19728) ... * codegen code for reconstruction test=develop * fix the cmake test=develop * fix review advice test=develop	5 years ago
Yiqun Liu	3cd985a669	Add a pass to fuse fc+elementwise_add+layernorm (#19776) ... * Add fc_elementwise_layernorm_fuse pass and unittest. * Add fused_fc_elementwise_layernorm op and its GPU kernel. test=develop * Apply fc_elementwise_layernorm_fuse_pass to GPU inference. * Add the setting of attrs in the definition of binary_op. test=develop * Add comment. * Implement the unittest. test=develop * Change the unittest name of layer_norm. test=develop	6 years ago
Yiqun Liu	c67c8758cb	Enhance fc_fuse_pass to enable fusing relu to fc_op (#19733) ... * 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 * Enhance fc_fuse_pass to enable fusing relu. * Allow print the shapes of var_desc in graph. test=develop * Enhance fc_fuse_pass_tester. * Remove the use of PADDLE_ENFORCE. test=develop * Correct the number of ops after fusing. test=develop * Fix a typo. test=develop * Set activation_type to null when there is no relu in fc. test=develop * Refine fc_fuse_pass's codes. * Enable the set of shape for tensor. * Refine repeated_fc_relu_pass and add unittest. test=develop	6 years ago
wangchaochaohu	ed8f44ea21	codegen for fused elementwise operation (#19520) ... * test=develop codegen for fused elementwise operation * fix test=develop	6 years ago
Yiqun Liu	c5548178b0	A a pass to enable the use of cudnn (#19346) ... * Add a interface to enable cudnn for inference. * Add cudnn_placement_pass. test=develop * Set the default value of cudnn_enabled_op_types to null. test=develop * Write the common basic class, placement_pass_base, to refine the codes. test=develop * Call EnableCUDNN in unittest. test=develop * Refine cudnn_placement_pass tester. * Enable the testing of cudnn_placement_pass in inference's unittest. test=develop * Add the check of op kernels. test=develop	6 years ago
Yiqun Liu	fcec365d29	Add a pass to replace dropout_op with scale_op when is_test is true (#19297) ... * Add simplify_with_basic_ops_pass to replace dropout_op with scale_op when is_test is true. test=develop * Delete dropout_op directly when upscale_in_train is true. test=develop * Improve the debug string, adding the print of op_desc information. * Fix the case when dropout's input x is reused as the next op's output. * Add the pass to inference. test=develop * Change the log level. test=develop * Add unittest for inplace case. * Add comment to explain the pass. * Apply the pass for CPU inference. test=develop * Fix the typo. test=develop * Add the check of AttrType. test=develop	6 years ago
Zhaolong Xing	76c95af000	Fix BUG: Mask RCNN inference diff When using AnalysisPredictor. (#19213) ... * 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	6 years ago
Adam	b837689e97	Add generalized Conv+Activation MKLDNN fuse pass creation (#19072) ... test=develop	6 years ago
石晓伟	ee2f296ef8	Fusion: seqpool_cvm_concat (#18471) ... * add fusion_seqpool_cvm_concat test=develop * simplify pass, test=develop * fix code style, test=develop	6 years ago
chengduo	fd3aad6cb3	Make fuse_optimizer_op_pass also work when the model contains sparse gradients. (#18664) ... * support sparse gradients test=develop	6 years ago
石晓伟	bce259e5bf	Update the Anakin interfaces for content-dnn and MLU (#17890) ... * update anakin-engine interfaces for content-dnn test=develop * support only-gpu mode of Anakin modify eltwise parse test=develop * modification for thread-safe test=develop * Integrated template instance test=develop * increase template parameters test=develop * support MLU predictor test=develop * update anakin cmake files test=develop * update TargetWrapper::set_device * update the initialization of anakin subgraph test=develop * use the default constructor of base class test=develop	6 years ago
mozga-intel	5eb81fe595	Capi for a ngraph engine (#17037)	6 years ago
Zhaolong Xing	61221ebc28	TRT: Support set dynamic range in int8 mode. (#17524) ... * fluid int8 train and trt int8 predict align. trt int8 predict init op converter * 2. align fluid int8 train and trt int8 inference. enhance quant dequant fuse pass enhance op converter, trt engine, trt engine op, trt subgraph pass. * 3. add delete_quant_dequant_pass for trt test=develop * 4. add the missing file test=develop * 5. i modify the c++ interface, but forget to modify the pybind code fix the IS_TRT_VERSION_GE bug, and fix elementwise op converter test=develop	6 years ago
Michał Gallus	0c39b97b4e	[MKL-DNN] Add Fully Connected Op for inference only(#15226) ... * fuse mul and elementwise add to fc * Reimplement the FC forward operator * Fix FC MKLDNN integration by transposing weights * Add FC MKLDNN Pass test=develop * FC MKLDNN Pass: change memcpy to std::copy * Fix MKLDNN FC handling of mismatch input and weights dims * Lower tolerance for MKL-DNN in resnet50 test test=develop * Adjust FC to support MKLDNN Op placement test=develop * Adjust Placement Op to set use_mkldnn attribute for graph test=develop * MKLDNN FC: fix weights format so that gemm version is called test=develop * FC MKLDNN: Remove tolerance decrease from tester_helper * FC MKL-DNN: Refactor the code, change input reorder to weight reorder * MKL-DNN FC: Introduce operator caching test=develop * FC MKL-DNN: Fix the tensor type in ExpectedKernelType test=develop * FC MKL-DNN: fix style changes test=develop * FC MKL-DNN: fallback to native on non-supported dim sizes test=develop * FC MKLDNN: fix CMake paths test=develop * FC MKLDNN: Refine placement pass graph mkldnn attribute test=develop * Fix Transpiler error for fuse_conv_eltwise test=develop * Fix missing STL includes in files test=develop * FC MKL-DNN: Enable new output size computation Also, refine pass to comply with newest interface. test=develop * FC MKL-DNN: enable only when fc_mkldnn_pass is enabled * FC MKL-DNN: Allow Weights to use oi or io format * FC MKL-DNN: Adjust UT to work with correct dims test=develop * Enable MKL DEBUG for resnet50 analyzer test=develop * FC MKL-DNN: Improve Hashing function test=develop * FC MKL-DNN: Fix shape for fc weights in transpiler * FC MKL-DNN: Update input pointer in re-used fc primitive * Add log for not handling fc fuse for unsupported dims test=develop * FC MKL-DNN: Move transpose from pass to Op Kernel test=develop * FC MKL-DNN: Disable transpose in unit test test=develop * FC MKL-DNN: Remove fc_mkldnn_pass from default list * Correct Flag for fake data analyzer tests test=develop * FC MKL-DNN: Add comment about fc mkldnn pass disablement test=develop * FC MKL-DNN: Disable fc in int8 tests test=develop	6 years ago
Sylwester Fraczek	5b2a3c4b12	Conv concat relu quantization (#17466) ... * add conv_concat_relu fuse test=develop * add test code test=develop * added missing include with unordered_map test=develop * review fixes for wojtuss test=develop * remove 'should (not) be fused' comment statements one of them was invalid anyway test=develop	6 years ago
guomingz	2281ebf0f3	Enable the convolution/relu6(bounded_relu) fusion for FP32 on Intel platform. (#17130) ... * Relu6 is the bottleneck op for Mobilenet-v2. As the mkldnn supports the conv/relu6 fusion, we implement it fusion via cpass way. Due to the int8 enabling for this fusion will be supported in MKLDNN v0.20, so this PR is focused on the fp32 optimization. Below table shows the benchmark(FPS) which measured on skx-8180(28 cores) Batch size | with fusion | without fusion -- | -- | -- 1 | 214.7 | 53.4 50 | 1219.727 | 137.280 test=develop * Fix the format issue test=develop * Add the missing nolint comments. test=develop * Fix the typos. test=develop * Register the conv_brelu_mkldnn_fuse_pass for the MKLDNN engine. test=develop * Adjust the indentation. test=develop * Add the test_conv_brelu_mkldnn_fuse_pass case. test=develop * Slightly update the code per Baidu comments. Let the parameter definition embedded into the code. That's will make the code easy to understand. test=develop	6 years ago
Tao Luo	32da5e9c3d	remove unused expected_kernel_cache_pass (#17486) ... test=develop	6 years ago
chengduo	04bd413acb	Code Clean: Move all pass to paddle::framework::ir (#17228) ... * move pass to ir * polish code test=develop * fix dependency test=develop	6 years ago
石晓伟	a72dbe9abf	Cherry-pick benchmark related changes from release/1.4 (#17156) ... * cherry-pick commit from 8877054 * cherry-pick commit from 3f0b97d * cherry-pick from 16691:Anakin subgraph support yolo_v3 and faster-rcnn (cherry picked from commit 8643dbc233) * Cherry-Pick from 16662 : Anakin subgraph cpu support (cherry picked from commit 7ad182e16c) * Cherry-pick from 1662, 16797.. : add anakin int8 support (cherry picked from commit e14ab180fe) * Cherry-pick from 16813 : change singleton to graph RegistBlock test=release/1.4 (cherry picked from commit 4b9fa42307) * Cherry Pick : 16837 Support ShuffleNet and MobileNet-v2 Support ShuffleNet and MobileNet-v2, test=release/1.4 (cherry picked from commit a6fb066f90) * Cherry-pick : anakin subgraph add opt config layout argument #16846 test=release/1.4 (cherry picked from commit 8121b3eccb) * 1. add shuffle_channel_detect (cherry picked from commit 6efdea8997) * update shuffle_channel op convert, test=release/1.4 (cherry picked from commit e4726a066f) * Modify symbol export rules test=develop	6 years ago
luotao1	226596a296	Merge branch 'develop' into core_opt_choose_kernel	6 years ago
nhzlx	d065b5bf2b	Anakin ssd support ... refine trt first run add quant dequant fuse pass omit simplify_anakin_priorbox_detection template omit transpose_flatten_concat_fuse template test=develop	6 years ago
nhzlx	953bdde058	Merge branch 'develop' of https://github.com/paddlepaddle/paddle into HEAD ... test=develop	6 years ago
Wojciech Uss	46677fb080	Move cpu_quantize_* passes into mkldnn subfolder ... test=develop	6 years ago
luotao1	056599a738	add expected_kernel_cache_pass ... test=develop	6 years ago
nhzlx	c407dfa3cb	cherry-pick from feature/anakin-engine: refine paddle-anakin to new interface. #16276	6 years ago
nhzlx	a25331bc26	cherry-pick from feature/anakin-engine: deal the changing shape when using anakin #16189	6 years ago
nhzlx	a1d200a5de	cherry-pick from feature/anakin-engine: Anakin support facebox #16111	6 years ago
luotao1	82af8031d9	add runtime_context_cache_pass ... test=develop	6 years ago
Tao Luo	7d2740db83	Revert "cache runtime_context"	6 years ago
Wojciech Uss	af03008890	Add cpu_quantize_placement_pass for C-API quantization (#16265) ... * Add cpu_quantize_placement_pass for C-API quantization test=develop * added a comment on required pass attributes test=develop	6 years ago
luotao1	a275fd6e0c	Merge branch 'develop' into runtime_context	6 years ago
Wojciech Uss	2579ade45f	Add cpu_quantize_pass for C-API quantization (#16127) ... * Add cpu_quantize_pass for C-API quantization test=develop * add cpu_quantize_pass test * fix lint: add include memory unorderd_map and unordered_set test=develop * fuse_relu 1 test=develop * tuned 2 without squash * fixes test=develop * remove unused vars test=develop * refactored test=develop * fix lint c-style cast -> C++ style cast test=develop * remove QuantMax and c style casts test=develop * last usage of QuantMax removed test=develop * Fix Analysis Predictor UT Check if memory_optimize_pass has already been added to the analysis config before adding a new one, so that it is not added multiple times. test=develop * change map to unordered_map fix the forgotten part of cpu_quantize_pass_tester.cc test=develop * removed quantized attribute * fixed cpu_quantize_pass_tester and op attr comments test=develop * removed redundant line test=debug * removed gmock test=develop * fix after merge	6 years ago
qingqing01	86e912c544	Fix windows compiling (#16230) ... test=develop	6 years ago
luotao1	1b59bed989	Merge branch 'develop' into runtime_context	6 years ago
luotao1	6ce25c99a0	Merge branch 'develop' into runtime_context	6 years ago