- 18 11月, 2021 1 次提交
-
-
由 jakpiase 提交于
* fix * ci rerun * ci rerun * ci Rerun
-
- 17 11月, 2021 1 次提交
-
-
由 piotrekobiIntel 提交于
* Change first batch of mkldnn headers and namespace names to dnnl * Revert changes to tensor.h, which require approval * Format changes with pre-commit * Add int32 tests * Fix int32 tests and call GetDataFromTensor for int32 * Fix test
-
- 10 11月, 2021 1 次提交
-
-
由 jakpiase 提交于
* added stack oneDNN FP32 op * minor change * CI fix * added skipping for gpus * fix for stack op * CI fix * CI fix * Added comment * CI fix
-
- 07 10月, 2021 1 次提交
-
-
由 Adam Osewski 提交于
* Remove unused header. * Use ConvMKLDNNHandlerT for conv2d INT8. * Use absolute module path to import.
-
- 15 9月, 2021 1 次提交
-
-
由 jakpiase 提交于
-
- 30 8月, 2021 1 次提交
-
-
由 Jacek Czaja 提交于
-
- 28 4月, 2021 1 次提交
-
-
由 Jacek Czaja 提交于
* - Added clearing oneDNN per executor * - Executor is nt always having FLAGS_use_mkldnn set to true
-
- 09 4月, 2021 1 次提交
-
-
由 Jacek Czaja 提交于
-
- 18 2月, 2021 1 次提交
-
-
由 joanna.wozna.intel 提交于
* Add conv transpose BF16 * Share function GetWeightsTz * Adjust to review and fix op compatibility * Add bias to unique handler name * Remove errors related to paddle enforce * Add conv2d_transpose to bf16 list and kernel refator
-
- 25 1月, 2021 1 次提交
-
-
由 Jacek Czaja 提交于
-
- 17 12月, 2020 1 次提交
-
-
由 Jacek Czaja 提交于
-
- 14 12月, 2020 1 次提交
-
-
由 Jacek Czaja 提交于
-
- 08 12月, 2020 1 次提交
-
-
由 jakpiase 提交于
* added external reorder to profiler * added external and internal reorders to profiler * added internal and external reorder to profiler * added formatting to int/ext reorder commit * removed unnecessary comment
-
- 27 11月, 2020 1 次提交
-
-
由 arlesniak 提交于
-
- 23 11月, 2020 1 次提交
-
-
由 Jacek Czaja 提交于
-
- 28 10月, 2020 1 次提交
-
-
由 Jacek Czaja 提交于
-
- 01 10月, 2020 1 次提交
-
-
由 Jacek Czaja 提交于
* - condidate fix to issue #25537 test=develop * - UT for transpose NHWC test=develop
-
- 14 9月, 2020 1 次提交
-
-
由 joanna.wozna.intel 提交于
-
- 03 9月, 2020 1 次提交
-
-
由 joanna.wozna.intel 提交于
-
- 21 8月, 2020 1 次提交
-
-
由 Adam 提交于
* Add mechanism for blocking oneDNN cache clearing * Review changes and Add thread guards
-
- 08 8月, 2020 1 次提交
-
-
由 joanna.wozna.intel 提交于
* 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
-
- 06 8月, 2020 1 次提交
-
-
由 Adam 提交于
* Add oneDNN fusion_gru kernel and fix fc+gru pass test=develop * Formatting changes test=develop * Lint fixes test=develop * Add memory::format_tag::any to GRU weights test=develop * Fix build with CUDA * Fix build with CUDA v2
-
- 28 7月, 2020 1 次提交
-
-
由 arlesniak 提交于
* 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
-
- 09 7月, 2020 1 次提交
-
-
由 Jacek Czaja 提交于
test=develop
-
- 22 4月, 2020 1 次提交
-
-
由 Jacek Czaja 提交于
-
- 11 4月, 2020 1 次提交
-
-
由 Michał Gallus 提交于
* Initial FP32 DNNL MatMul Implementation * Implement int8 DNNL MatMul * Unify in-kernel-naming, clean UTs * MatmuL: Introduce op caching * Final adjustments test=develop * Remove dy_graph disablement test=develop * Change dnnl header name to new one test=develop * Contrain multi head check to prevent fails test=develop * Resolve dnnl header problems on MAC CI * Variable namings to kernel and skip_grad_ci added test=develop * Prevent MAC CI from failing * Prevent windows build from failing test=develop * Modify UTs to conform to the rules * Modify MatMul aux functions namings test=develop
-
- 07 1月, 2020 1 次提交
-
-
由 bingyanghuang 提交于
-
- 06 1月, 2020 1 次提交
-
-
由 Jacek Czaja 提交于
-
- 05 1月, 2020 1 次提交
-
-
由 Jacek Czaja 提交于
-
- 10 12月, 2019 1 次提交
-
-
由 Adam 提交于
* MKLDNN v1.0 rebase to Paddle 1.6 test=develop * Add hacky paddle::string::to_string() implementation * vectorize<int64-t>() -> vectorize() cleanup test=develop * PADDLE_ENFORCE and void_cast fixes test=develop * Rebase changes test=develop * Cosmetics test=develop * Delete MKL from mkldnn.cmake test=develop * CMake debug commands test=develop * Delete MKLDNN_VERBOSE and rebase fixes test=develop * Rebase fixes test=develop * Temporarily disable int8 resnet101 vgg16 and vgg19 tests test=develop * Add libmkldnn.so.1 to python setup test=develop * Add libmkldnn.so.1 to inference_lib cmake after rebase test=develop * Post rebase fixes + FC int8 changes test=develop * Fix LRN NHWC test=develop * Fix NHWC conv3d test=develop * Windows build fix + next conv3d fix test=develop * Fix conv2d on AVX2 machines test=develop
-
- 07 11月, 2019 1 次提交
-
-
由 Adam 提交于
* Add asymetric padding support for mkldnn pooling test=develop * Add asymetric padding support for mkldnn conv test=develop * Add asymetric padding support for mkldnn conv_transpose test=develop
-
- 22 10月, 2019 1 次提交
-
-
由 Adam 提交于
test=develop
-
- 17 9月, 2019 1 次提交
-
-
由 Adam 提交于
test=develop
-
- 14 9月, 2019 1 次提交
-
-
由 Adam 提交于
test=develop
-
- 10 9月, 2019 1 次提交
-
-
由 Adam 提交于
* MKLDNN handler cleanup * MKLDNN handler cleanup test=develop
-
- 03 9月, 2019 1 次提交
-
-
由 Adam 提交于
* using MKLDNNMemoryFormat = mkldnn::memory::format changes test=develop * PADDLE_ENFORCE update test=develop
-
- 30 8月, 2019 1 次提交
-
-
由 Jacek Czaja 提交于
- Refactor step 1 - Compilation fix - Yet another compilation fix - Even more compilation fix - Lint fixes test=develop - Removed deprectaed PADDLE_ENFORCE occurance test=develop - Candidate fix to BN forward - Lint fixes test=develop - Refactoring in data_layout_transform - compilation fix - Another comppilation fix - Step further into darkness - Yet another compilation fix - Yet another compilation fix - missing header - compilation fix - Added MKLDNN -> Paddle conversion in fetch op test=develop - Compilation fix test=develop - Lint test=develop - Mul fix - Fix to MKLDNN MUL op and Elementwise MUL UT test=develop - Workaround for diffrent weights with groups representation Paddle vs MKL-DNN. test=develop - Candidate fix for 5D convolution with groups - Refactor of fix for conv3d and conv2d in fetch op test=develop - Compilation fix - Still same compilation fix - Compilation fix - Compilation fix - Reverted refactoring of fixes - Adapted test_conv2d_int8_mkldnn so it exects data in NCHW format not NHWC test=develop - minor fix in UT test=develop - Lint fixes test=develop
-
- 25 7月, 2019 1 次提交
-
-
由 lidanqing 提交于
* change INT8 to template so that checking dst_dt with if-else could be removed. CI will be enabled after fixing reviews * reverse user_residual_memory_p and user_bias_memory_p declaration scope test=develop
-
- 09 7月, 2019 1 次提交
-
-
由 Physher 提交于
-
- 03 12月, 2018 1 次提交
-
-
由 Yihua Xu 提交于
-