673 Commits (3d015f1cf529915ab52cb8aef7c475f67fb128b5)

Author	SHA1	Message	Date
Pei Yang	8a4f85feb9	Add unittests and OP version registry for quant_conv2d_dequant_fuse_pass (#27689)	4 years ago
joanna.wozna.intel	b0ee1405f7	Add conv2d bfloat16 support (#27325)	4 years ago
cc	c5c13473c6	Add compatibility check for four mkldnn pass (#27364) ... * Add pass compatibility check for four mkldnn pass, test=develop	4 years ago
Wilber	3d5522146e	register seq_concat_fc_fuse pass. (#27479)	4 years ago
wanghuancoder	df43905f12	use iwyu clean include (#27267) ... * use iwyu clean include, test=develop, test=win * compilation error, test=develop * fix compilation error2, test=develop * fix compilation error3, test=develop * fix compilation error4, test=develop * fix compilation error5, test=develop * fix compilation error6, test=develop * fix compilation error7, test=develop * fix compilation error8, test=develop * fix compilation error8, test=develop * fix compilation error10, test=develop * fix compilation error11, test=develop	4 years ago
Pei Yang	8182337096	clear pass logs (#27434)	4 years ago
Shang Zhizhou	d93661942e	fix bug sequececonv_eltadd_relu_fuse_pass (#27404) ... * fix bug sequececonv_eltadd_relu_fuse_pass, output error when sequence_conv's padding_start > 0 * fix seqconv_eltadd_relu_fuse_pass unitest error	4 years ago
Leo Chen	aba759ba16	[Feature] Enhance inplace addto strategy for gradient accumulation in static graph (#27112) ... * support use add instead of sum to do gradient accumulation * add inplace addto pass * add grad_add op and inplace addto pass * remove debug code * code refine * fix bug when sereral sum ops inserts at same op_idx * fix Flags type * add addto attribute for conv3d * fix ut * code clean * fix type	4 years ago
Wilber	39546aa2f3	Add pass compatible and unit test. (#27377)	4 years ago
Pei Yang	fd7ab4e63c	register pass compatibility (#27357) ... * pass compatibility * add compatibility registry * add unittests for different padding * add assert * drop errmsg	4 years ago
haozech	7e6dfcf9b2	Add 3 pass version check (#27283)	4 years ago
Shang Zhizhou	3c11717988	add op version checker to ir passes (#27329)	4 years ago
Wilber	f827665ae6	[Pass Compatible] Bind python compatible. (#27262)	4 years ago
joanna.wozna.intel	1483ea2304	Add bfloat16 passes (#26999)	4 years ago
Pei Yang	5fb8c92054	fix multihead matmul shared params (#27121)	4 years ago
Adam	8bcb1f29d9	Add conv+affine_channel fuse pass to MKLDNN pass strategy and fix it (#26779)	5 years ago
Pei Yang	e3f8e5cf5c	trt int8 support conv2d_transpose (#26636)	5 years ago
joanna.wozna.intel	eb097d64f6	Fix int8 performace drop cpu_quantize_placement_pass (#26715) ... * Fix cpu quantize placement pass * Include string lib	5 years ago
joanna.wozna.intel	559e43eee4	Small change in conv2d and quantize pass (#26671)	5 years ago
Pei Yang	b757466b0d	fix trt dynamic ernie serialization unit test (#26228)	5 years ago
cc	3f816bc8b4	[Quantization] Conv2d_transpose and mul support channnelwise quantization (#25639) ... * Conv2d_transpose and mul support channnelwise quantization, test=develop * Skip collecting out threshold for output tensor of which the type is not fp32 or fp64, test=develop * Fix error in test_user_defined_quantization, test=develop * Add depthwise_conv_bn_fuse, test=develop * Add conv_transpose_bn_fuse_pass for post_training_quant, test=develop	5 years ago
Yiqun Liu	1be6bf45ae	Add assign to fusion_group and enhance inplace execution in fusion_group. (#26121)	5 years ago
joanna.wozna.intel	734cf1c3e9	Change use_quantizer attribute name and data type (#25838) ... * Change use_quantizer attribute name and data type * Fix problem with setting attribute * Add changes due to review * Small change in function * Restore use_quantizer attr for compatibility	5 years ago
Zhou Wei	e0a9115e28	fix random compile failure due to missing file (#25661)	5 years ago
arlesniak	e52df3b125	Added DNNL cache management for DyGraph (#25624) ... * Added DNNL cache management for DyGraph * move FLAGS_use_mkldnn to more general CMakeLists, getu use of the flag in ClearGradients * missing file * Fixes after review * Bringing back original idea of place for 'use_mkldnn' flag to be accessible from platform nad imperative. * Removed duplicate and added docs * Fixes for CI	5 years ago
Adam	98899b73d2	Fix FC + GRU fuse pass (#25687)	5 years ago
wanghuancoder	1917b38099	fix some errmsg report,in framework/ir/, about 21 files (#25525) ... * fix error msg report in ir/, about 19 files, test=develop * modified some unclear descriptions, test=develop * modified some unclear descriptions, test=develop * modify unit test pass_test.cc, because the error report in pass.cc is used by pass_test.cc, test=develop	5 years ago
wanghuancoder	9b46fe0440	fix some errmsg report,in framework/ir/, about 5 files (#25539) ... * fix error msg report in ir/, about 5 files, test=develop * fix error msg report in ir/, about 5 files, test=develop * fix error msg report in ir/, about 5 files, test=develop	5 years ago
wanghuancoder	e65c5b8e83	fix some errmsg report, in framework/ir/ (#25471) ... * fix paddle/fluid/framework/ir/ error msg reoprt, test=develop * modify error msg reoprt in ir/, about errortype, grammar, supplementary infor, test=develop * modified some unclear descriptions, test=develop * Modify the problem that report msg is less than 20 characters, test=develop	5 years ago
wanghuancoder	6c0982b942	fix some errmsg report, in framework/ir/mkldnn (#25467) ... * fix paddle/fluid/framework/ir/mkldnn/ error msg reoprt, test=develop * modify error msg reoprt, about errortype, grammar, supplementary infor, test=develop * modified some error descriptions, test=develop	5 years ago
wanghuancoder	fce6466217	fix some errmsg report, in framework/ir/ subdir(memory,optimizer,multi_device) (#25460) ... * fix paddle/fluid/framework/ir/multi_devices_graph_pass/ error msg reoprt, test=develop * fix paddle/fluid/framework/ir/memory_optimize_pass/ error msg reoprt, test=develop * fix paddle/fluid/framework/ir/fuse_optimizer_ops_pass/ error msg reoprt, test=develop * fix paddle/fluid/framework/ir/memory_optimize_pass/ error msg reoprt about PADDLE_ENFORCE, test=develop * modify error msg reoprt,about errortype，grammar. test=develop * modify error msg reoprt,about PADDLE_ENFORCE to PADDLE_ENFORCE_XXX, test=develop * modify error msg reoprt,about PADDLE_ENFORCE to PADDLE_ENFORCE_XXX, and %s to %d, test=develop * modified some error descriptions, test=develop	5 years ago
Zhaolong Xing	7b7e605189	[Fix BUGs]: fix multhead matmul pass's instable bug (#25123) ... * fix multhead matmul's instable test=develop * fix multihead matmul bug test=develop * fix converage problem test=develop	5 years ago
Wojciech Uss	d0a921ba98	Quant2 updates and fixes (#25313)	5 years ago
Jacek Czaja	17c751bec6	[oneDNN] Fix to #25078 (#25256)	5 years ago
Sylwester Fraczek	36abeff44f	adding elementwiseadd quantization (#25178)	5 years ago
Pei Yang	b2f5a149e7	[Paddle-TRT] Better Paddle-TensorRT support for PaddleSlim quant models (#25097) ... * Paddle-TensorRT support slim QAT. test=develop * add comments. test=develop * use RenameInput instead of ResetInputs. test=develop	5 years ago
Shibo Tao	19c4db1b56	don't re-generate header file if content doesn't change (#25130) ... * don't re-generate header file if content doesn't change. test=develop * add copy_if_different function. test=develop	5 years ago
Jacek Czaja	a7944904d3	[oneDNN]elementwise_add and elementwise_mul int8 support (#24984) ... * Start implementing int8 eltwise add test=develop * - Fix to Michal PR * - Fix test=develop * - Lint fixes test=develop * - Added checking if elementwise_mul can be used test=develop * - Added attribs to skip_attrs_set test=develop * - Improved broadcasting test=develop - fixes to compilation - fix - fix - Lint fixes test=develop * - removed redundant condition test=develop Co-authored-by: Michal Gallus <michal.gallus@intel.com>	5 years ago
Sylwester Fraczek	53d563a0fe	Reshape transpose matmul coverage (#24970) ... * remove gmock from ut test=develop * coverage enabled for r+t+m fuse pass test=develop	5 years ago
Sylwester Fraczek	a7ee634b45	fix WARNING: ThreadSanitizer: heap-use-after-free (#24929) ... test=develop	5 years ago
Jacek Czaja	40a5f3fd86	[oneDNN] Clearing mkldnn cache in naiveexecutor destructor (#24756)	5 years ago
Chen Weihang	d1062d5278	Replace all errors thrown by LOG(FATAL) with PADDLE_THROW (#24759) ... * remove REPLACE_ENFORCE_GLOG compile option & add ci rule prohibit LOG(FATAL) using, test=develop * remove ci test case, test=develop * replace all LOG(FATAL) & polish message, test=develop * fix typo, test=develop * polish error info detail, test=develop	5 years ago
Wojciech Uss	78d4f0cc91	add option to exclude ops by id from quantization (#24689)	5 years ago
Wilber	ba2f8f0ce4	fix embedding_eltwise_layernorm_fuse_pass. test=develop (#24592)	5 years ago
Yiqun Liu	6b464f969a	Add an operator node in unittest to make the fusing result unique. (#24617)	5 years ago
Yiqun Liu	560c815390	Add some check for CUDA Driver API and NVRTC (#22719) ... * Add the check for whether CUDA Driver and NVRTC is available for the runtime system. * Call cuInit to initialize the CUDA Driver API before all CUDA callings. test=develop * Change the behavior when libnvrtc.so can not be found, printing a warning instead of exiting. test=develop * Do not initialize CUDA Driver API for windows and macos. test=develop * Remove the call of cuInit when entering paddle and enable the test_code_generator. test=develop * Add some built-in functions for __half. test=develop * Change save_intermediate_out to false in unittest. test=develop * Fix error reference to tempropary variable when seting including path for device_code. test=develop	5 years ago
Jacek Czaja	8b88cd5167	[oneDNN] Fix to inplace pass (#24442) ... * - Disabling inplace pass test=develop - Disable cycles test=develop - fix test=develop - Enhancement to in-place - Lint fixes test=develop * - Lint fixes test=develop	5 years ago
Chen Weihang	aa0f254fbe	Add macro BOOST_GET to enrich the error information of boost :: get (#24175) ... * add new macro BOOST_GET_SAFELY & unittests, test=develop * add different macro type, test=develop * fix get macro type in executor, test=develop * four macro part change backup * using one macro for all case, test=develop * revert attribute change, test=develop * change to three func to solve gcc4.8 bug, test=develop * polish some details, test=develop	5 years ago
Wojciech Uss	db052009c7	Enabled quantize all and skip missing in QAT (#24281) ... * Enabled quantize all and skip missing in QAT	5 years ago
Huihuang Zheng	8a1a2af82e	Add Assert Op (#24280) ... 1. To make ProgramTranslator to support `assert` grammar, this PR adds `assert` python API and C++ code. 2. Fix a bug: graph_pattern_detector.h #include <gtest/gtest_prod.h> but didn't declared dependency at CMakeLists, which can cause single build failure. 3. Refactoring `Formatter` in print_op to make it reusable and reuse the formatter to print in assert op.	5 years ago
joanna.wozna.intel	356f5ee220	[Refactoring] Unify op-dequant squashes (#24277)	5 years ago
joanna.wozna.intel	b43b46e619	[INT8] Add requant-op squash (#24143)	5 years ago
Sylwester Fraczek	e1a7a88057	added reshape transpose matmul fuse pass (#23754)	5 years ago
wangchaochaohu	fa43d74a3a	fix the intermediate node of graph for fusion group test=develop (#24184)	5 years ago
liuwei1031	9a93f6aae0	improve efficiency of runtime InferVarType (#22778) ... * save InferVarType changes, test=develop * remove code comments, test=develop * tweak code, test=develop * fix compilation warning, update merge_ids_op split_ids_op to new interface, test=develop * modify fused_bn_activation_op, test=develop * fix error of fused_bn_activation_op, test=develop * fix PADDLE_ENFORCE and unittest coverage issue, test=develop * tweak PADDLE_ENFORCE messages, test=develop * improve unittest coverage, test=develop * add StaticGraphInferVarType class, test=develop * rebase develop branch, test=develop * fix unittest error, test=develop * remove comments, test=develop * improve unittest coverage, test=develop * imporve error message and imporve unittest coverage, test=develop * upgrade InferVarType API, test=develop * tweak pyfunc error message, test=develop * fix compilation conflict - save_combine_op, test=develop	5 years ago
wangchaochaohu	2270864019	Fusion group optimize for cuda codegen(#23940)	5 years ago
Jacek Czaja	eb411613e9	[DNNL] refine activations Inplace support (#24145)	5 years ago
Jacek Czaja	461e6a01ec	[DNNL] activations Inplace support (#24123)	5 years ago
arlesniak	d31a174f51	added fusing matmul-transpose-reshape pass (#23866)	5 years ago
Zeng Jinle	acef55df04	fix isolated var fetch bug, test=develop (#24070)	5 years ago
Jacek Czaja	c6c65c65c7	[DNNL] Added elementwise_add mkl-dnn inplace (#23477)	5 years ago
Yiqun Liu	071a702060	Fix the error misjudgment when there are control nodes in graph. (#23943)	5 years ago
Zeng Jinle	c49791362f	Correct reader device index (#23802) ... * correct reader device index, test=develop * fix async executor scope var initialization, test=develop	5 years ago
joanna.wozna.intel	12ba05ce0c	Add scale-matmul fuse pass (#23734)	5 years ago
Chen Weihang	532079a222	API (CompiledProgram) error message enhancement (#23559) ... * api compild program error polish, test=develop * fix coverage problem, test=develop * fix details & add unittests, test=develop * add test for coverage, test=develop	5 years ago
chenhaoze	9b06dd8628	Add three passes and api reference of paddle_pass_builder. test=develop (#23741) ... * Add three passes and api reference of paddle_pass_builder.h	5 years ago
joanna.wozna.intel	5ee099ca57	Op-requant squash (#23665) ... * Op-requant squash test=develop * Add matmul to op-requant test test=develop	5 years ago
mozga-intel	3baaee9aab	Remove: NGraph engine from PDPD repository (#23545) ... * Remove the NGraph engine from PDPD repository 1. Each operator was removed from the operator's directory 2. Each test was removed from the unittest directory 3. The parallel executor support was removed from the PDPD 4. The CMake file was removed from the PDPD 5. The NG flags were removed from the repository test=develop * Remove ngraph from: 1. Cmake file 2. Python file test=develop	5 years ago
joanna.wozna.intel	3cb5623dad	Add matmul dequant squash (#23505) ... test=develop	5 years ago
wangchaochaohu	c1187cd6f4	Fp16 refine for fusion group (#23472)	5 years ago
joanna.wozna.intel	ce08fdcf2b	Add support for INT8 matmul in C-API quantization (#23463) ... * Integrate matmul with cpu_quantize_pass test=develop * Add matmul checking scales test=develop * Change condition of matmul quantization test=develop * Remove redundant var test=develop	5 years ago
wangchaochaohu	d085f79228	fix untime fail for output var stop_gradient=True for fusion group (#23317)	5 years ago
Kaipeng Deng	d223a24904	Fix inplace_abn compile error on Windows (#23464) ... * fix inplace_abn windows compile error. test=develop	5 years ago
wangchaochaohu	5c60778731	polish the code of fusion group test=develop (#23370)	5 years ago
Yiqun Liu	bc2981e998	Disable test_code_generator and test_post_training_quantization_mobilenetv1 (#23440)	5 years ago
joanna.wozna.intel	8c463700e1	Add default pass attributes (#23042)	5 years ago
Kaipeng Deng	21d95be0db	Add inplace abn op (#22806) ... * add inplace_abn_op. test=develop	5 years ago
Zeng Jinle	3a21980b78	add reader dependency pass, test=develop (#23301)	5 years ago
wangchaochaohu	d280106007	Add support for attr type Op and add fill_constant Op and scale Op (#23163) ... * add attr support for fusion group and add support for fill_constant and scale Op	5 years ago
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