544 Commits (0536b5263d188c54069765c4168bdba91ad250c7)

Author	SHA1	Message	Date
Jacek Czaja	2bb1b0e89e	[DNNL] Added MKL-DNN inplace pass for C-API inference (#23315)	5 years ago
Wojciech Uss	f836c8aa8f	add check for scales and a message (#23119)	5 years ago
Tao Luo	c00d427d52	simplify the cmake log of ir/CMakeLists.txt (#23262) ... test=develop	5 years ago
Zeng Jinle	bae5930ba1	fix graph attr copy issues, test=develop (#23191)	5 years ago
Zeng Jinle	acfc9b8a70	Reader sequential and inference partial feed (#22699) ... * sequential reader stage 1, test=develop * fix ut, test=develop * fix iterable=False reset bug, add some logs and polish code, test=develop * inference feed partial data, test=develop * Turn on keep_order=True for test, test=develop * enhance ut to test more cases, test=develop * test commit for reverting * Revert "test commit for reverting", test=develop This reverts commit 80aef42ef52ba1ee79627d6f663a624ec4f12f58. * add ut of merged and unmerged results, test=develop * add more uts for coverages and add en doc of api, test=develop * follow comments, test=develop * change note style, 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
Yiqun Liu	3af4771122	Add the detection and code-generation of sqrt and square in fusion_group (#23095)	5 years ago
Sylwester Fraczek	abee05a8c8	added mkldnn swish activation (#23041)	5 years ago
wangchaochaohu	3757e0687c	Add Unittest for backward of fusion group (#22932) ... * add fusion group test for backward and refine code	5 years ago
wangchaochaohu	f0d193a23c	Cast fusion for fusion group (#22876) ... * add support for expression type convert and add cast Op support in fusion group	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
liu zhengxi	61fef9754b	Fix fc padding bug during inference fusion (#22860) ... * fix fc padding during fusion, test=develop * fix optim model inference after SaveOptimModel, test=develop	5 years ago
wangchaochaohu	ca9e77a8d4	add sum op support for fusion group (#22771) ... * Add the codegen and auto fusion for sum Op in fusion group	5 years ago
tianshuo78520a	433cef03e5	fix typo word (#22784)	5 years ago
GaoWei8	cdf5f6fb8c	Add an inference interface to disable FC padding (#22097) ... * Add an interface of disabling FC padding * fix bert regression * polish fc padding interface * recover pass function * fix argument error * fix mkldnn error	5 years ago
tianshuo78520a	d2ba91aad1	fix typo words (#22653)	5 years ago
Yiqun Liu	22bbd54719	Add the support of fp16 in fusion_group (#22239)	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
Zhaolong Xing	8acd745c25	[Ernie GPU Optim]: Fuse three fc to multihtead matmul (#22486) ... * 1. optim multihead matmul: fuse three fc to multihtead matmul test=develop * fix conflict test=develop * fix comments test=develop	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
joanna.wozna.intel	17f2c0899f	Add dequant-scale squash (#22409) ... * Add dequant scale squash test=develop * Correct dequant-scale squash test test=develop	5 years ago
Wilber	7bc4b09500	add WITH_NCCL option for cmake. (#22384) ... cmake选项中添加了WITH_NCCL，显示指定是否编译NCCL的部分代码，WITH_NCCL默认打开，但如果WITH_GPU为OFF，则关闭WITH_NCCL 添加了PADDLE_WITH_NCCL定义 单机单卡能够关闭NCCL编译，多卡的话需要默认打开NCCL，如果关闭NCCL，则只能使用单卡 Co-authored-by: 石晓伟 <39303645+Shixiaowei02@users.noreply.github.com>	5 years ago
石晓伟	e1b0d7cbb1	remove anakin from code, test=develop (#22420)	5 years ago
Michał Gallus	269db0d1d1	[DNNL] Fix accuracy in INT8 FC (#22404) ... * Enable quantize to reorder to nchw as well * Correct FC MKL-DNN input dim requirements to accept 3D * Improve DNNL FC format, error and 3D input handling test=develop * Improve error checking in FC test=develop * Improve PADDLE_ENFORCE messages in fc-related files * Remove data layout attribute from obligatory pass args test=develop * Fix message in fc_mkldnn_pass to be logically correct test=develop	5 years ago
joanna.wozna.intel	3099d9d47c	Restore requantize squash (#22399)	5 years ago
Yiqun Liu	b7cac50b64	Implement a common python unittest to test the ir passes. (#22209) ... * Implement a common python unittest to test the ir passes. test=develop * Save the results in np.array and support to startup on CPU. test=develop * Fix the unittest. test=develop * Add check_program to check whether the optimized program is different from the origin one. test=develop * Remove the inferface all_ops. test=develop * Add exception test in pass_test. test=develop	5 years ago
lidanqing	895f8da7d6	change std::cout to log(INFO), vlog (#22316)	5 years ago
Zhen Wang	e40cfb1010	fix the bug of assert_is_op_output. test=develop (#22262)	5 years ago
Wojciech Uss	d3a6647372	improve placement pass tests code coverage (#22197)	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
joanna.wozna.intel	5b2e98aa17	Add multiple quantize operators fuse (#22062)	5 years ago
Yiqun Liu	96980c2244	Polish the PADDLE_ENFORCE in fusion_group pass related codes. (#22144) ... * Polish the PADDLE_ENFORCE in fusion_group pass related codes. test=develop * Correct the unittest because of the change relu_grad's formula. test=develop	5 years ago
liu zhengxi	724b13e459	fix xception precision problem, test=develop (#22124)	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	d48320777e	Add the first implememtation of fusion_group op (#19621) ... * 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 * Refine the calling of PADDLE_ENFORCE. test=develop	5 years ago
Michał Gallus	6192108408	[DNNL] 3D Fully-Connected (#21746)	5 years ago
liu zhengxi	196e20dfbb	Fix multi-threads memory out of bounds error for passes (#21920) ... * fix seqconv_eltadd_relu pass during multi-threads predictor, test=develop * fix attention_lstm_fuse_pass during multi-threads inference, test=develop * fix embedding_fc_lstm_fuse_pass during multi-threads inference, test=develop * fix fc_lstm_fuse_pass during multi-threads inference, test=develop * fix seq_concat_fc_fuse_pass during multi-threads inference, test=develop	5 years ago
石晓伟	03479469a7	fix multi-thread error of fc_gru_fuse_pass.cc, test=develop (#21841) ... * fix multi-thread error of fc_gru_fuse_pass.cc, test=develop * export FLAGS and GLOG symbols, test=develop	5 years ago
Pei Yang	3e5008ad01	fix trt calib not working bug, test=develop (#21934)	5 years ago
Aurelius84	51a86d2b6b	Optimize adam speed (#21777) ... * optimize adam speed by removing _finish_update test=develop * fix SparseAdamFunctor param list test=develop * Remove scale_op in expect_list of adam_op test=develop * fix test optimizer loss assert error test=develop * fix test optimizer loss assert error test=develop * modify PADDLE_ENFORCE usage test=develop * fix op_type in lamb_op.cc test=develop * fix errors ostream format bug test=develop * add betaPowOut in ngraph op test=develop * fix ngraph::op api for gcc8 test=develop * clean code test=develop * modify struct into class test=develop * remove code of beta1Tensor in lamb_op test=develop	5 years ago
lidanqing	d3a96632fa	Add fc-dequantize squash in cpu_quantize_squash_pass for ernie model (#21714) ... * fc-dequantize squash test=develop * change according to reviews test=develop * change PADDLE_ENFORCE test=develop * add second test when fc-dequant do not fuse test=develop * change all related PADDLE_ENFORCE test=develop	5 years ago
joanna.wozna.intel	d419b859c0	Add reshape int8 mkldnn op (#21428) ... * Add reshape int8 op test=develop * Change test to CPUPlace test=develop * Correct tests test=develop	5 years ago
Tao Luo	01fa4ead61	fix -Wno-error=sign-compare warning in gcc8 (#21434) ... * fix -Wno-error=sign-compare warning in gcc8 test=develop * fix warning in distributed codes test=develop	5 years ago
Zeng Jinle	89966525f1	Polish reference count pass (#21324) ... * fix ref_cnt pass, test=develop * add cpp unittests to reference_count_pass, test=develop * follow comments, test=develop	5 years ago
GaoWei8	8493f20ebc	Polish the codes of fc when needs padding (#21378) ... test=develop	5 years ago
Michał Gallus	5d7d548275	INT8 Fully-connected (#17641) ... * Implement Int8 FC * Integrate FC into INT8v2 test=develop * int8 FC: transpose weights before computing scales test=develop * Add support for activation_type string in FC test=develop * Disable MKL-DNN's FC in VGG16 and 19 test=develop * Disable FC quantization when mkldnn FC is disabled test=develop * Solve PADDLE_ENFORCES in FC int8 * Fix Paddle enforces and remove const cast test=develop * Fix style changes test=develop * Fix quantizer_tester test and add fc quantization test=develop * Fix FC test fail on CUDA * Remove unnecessary log from quantize placement pass test=develop * Add Thread ID to FC hash key test=develop * Add comments to MKL-DNN FC Kernel test=develop * Refactor quantizer test=develop * Fix linter issues test=develop * Fix crash in slim googlenet test=develop * Fix PADDLE_ENFORCE messages test=develop	5 years ago
GaoWei8	234060f88f	Add fc padding to improve mkl GEMM's performance when N and K are multiple of 128. (#20972) ... * Add fc padding to solve mkl performance test=develop * fix gpu pass and error information test=develop * fix fc_fuse_pass_test test=develop * fix error information test=develop * fix error information test=develop * fix name and add fc op padding test test=develop * fix attributes test=develop * optimize fc padding test=develop * fix test test=develop	5 years ago
zhouwei25	345b67b5e2	remove warning LNK4006 and warning LNK4221 (#21226)	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