1. 14 4月, 2022 3 次提交
    • S
      FC+elementwise_add (residual connection) (#41776) · 92d8d0bc
      Sławomir Siwek 提交于
      * Change tensor name to match activation
      
      * declare fc_eltwise_add pass
      
      * merge conv_eltwise refactor PR
      
      * first compilable draft
      
      * unittest feedback tools
      
      * Fuse pass tester
      
      * Move IsReachable() to shared file
      
      * 100% coverage of fuse_pass_tester.cc
      
      * register pass
      
      * Add bias node
      
      * Improve unit tests / remove bias node from pattern
      
      * improve fc_eltwiseadd_unittest
      
      * cancel eltwise_add fuse if act is already fused
      
      * Add elementwise_input scale
      
      * Residual MVP
      
      * Add new FC attrs
      
      * Add more test cases
      
      * Add missing op attrs
      
      * Adapt code to new Elementwise pattern
      
      * reuse existing fcpattern
      
      * improve code style
      
      * remove unused arguments
      
      * fix typo
      
      * remove whitespace
      
      * remove int8 related code
      
      * Remove attributes from base ops
      
      * style
      
      * style check
      
      * Remove input from base op
      
      * Set attribute during fuse
      
      * ut timeout
      
      * download and test model
      
      * DRY
      
      * apply feedback from review
      
      * Style check
      
      * fix typo
      
      * cosmetic changes
      
      * explicitly set residual as output
      
      * VIT-OCR accuracy check
      
      * trigger CI
      
      * remove whitespaces
      
      * fix missing data file
      92d8d0bc
    • B
      add mkldnn int8 pass [step3] (#41599) · 8e2d4d30
      baoachun 提交于
      * add mkldnn int8 pass [step3]
      
      * Add test for compute_propagate_scales_mkldnn_pass
      
      * update pass
      
      * update api comment and python api
      Co-authored-by: Nwozna <joanna.wozna@intel.com>
      8e2d4d30
    • J
      Added shuffle_channel BF16/FP32 FWD oneDNN kernel (#39756) · c7623d72
      jakpiase 提交于
      * added shuffle_channel bf16/fp32 fwd kernel
      
      * added missing files
      
      * CI fix
      
      * changed from pten to phi
      
      * tmp save
      
      * added reviewers suggestions
      
      * fix for test
      c7623d72
  2. 10 4月, 2022 2 次提交
  3. 07 4月, 2022 1 次提交
  4. 06 4月, 2022 1 次提交
  5. 04 4月, 2022 1 次提交
  6. 02 4月, 2022 1 次提交
  7. 31 3月, 2022 2 次提交
  8. 30 3月, 2022 1 次提交
  9. 24 3月, 2022 2 次提交
  10. 23 3月, 2022 1 次提交
  11. 21 3月, 2022 2 次提交
  12. 18 3月, 2022 1 次提交
  13. 17 3月, 2022 2 次提交
  14. 16 3月, 2022 2 次提交
    • Z
      Quantize elementwise mul (#40546) · 2def79bc
      Zuza 提交于
      * Quantize elementwise mul op
      
      * Parametrize elementwise functions
      
      * Fix code formatting
      2def79bc
    • Y
      [Auto Parallel] Add the support for the auto completion of while_op (#39939) · ec6b8fbd
      Yulong Ao 提交于
      * [Auto Parallel] Support the auto completion of while_op
      
      * [Auto Parallel] Improve the completion algorithms
      
      * [Auto Parallel] Fix bugs for ernie inference
      
      * [Auto Parallel] Remove attrs which cannot be pickled
      
      * [Auto Parallel] make the dims_mappings of LodTensorArray vars empty
      
      * [Auto Parallel] Fix bugs for the ernie inference in the pipeline parallel
      
      * [Auto Parallel] Remove unncessary comments
      
      * [Auto Parallel] Fix a bug of the CMakeLists
      
      * [Auto Parallel] Use the newest APIs to write the unit test
      
      * [Auto Parallel] Remove unnecessary statements
      ec6b8fbd
  15. 15 3月, 2022 2 次提交
    • J
      oneDNN NHWC fixes (#40049) · dde9cec0
      Jacek Czaja 提交于
      * - Prototype of third solution
      
      - fix
      
      - compilation fixes
      
      - fix
      
      - fixe
      
      - fix
      
      - fix
      
      - compilation fix
      
      - comment fix
      
      - lint
      
      update mkldnn conv_elementwise_add_fuse_pass ut
      
      - NHWC changes to prelu
      
      - alhpa dims
      
      - UT fix
      
      - fix to UT
      
      - lint
      
      - Some fixes
      
      - added to BWD of prelu NHWC support
      
      - reverted removal of resetting cu_layout in clearing of caching
      
      * - Small changes
      
      * - compilation fix
      
      * - fix
      
      * - fix
      
      * lint
      
      * - fixes after internal review
      
      * - compilation fix
      
      * - lint
      dde9cec0
    • Y
      [Phi]Move Tanh/BRelu/LeakyRelu/ThresholdedRelu Kernels to Phi (#40385) · d7112180
      YuanRisheng 提交于
      * move activation op
      
      * adjust code format
      
      * fix compile bugs
      
      * fix ci bugs
      
      * code format adjust
      
      * code format adjust2
      
      * activate ci status
      
      * modify according to comment
      
      * move activation kernel
      
      * revert relu6
      
      * reduce add code
      
      * perfect use_phi_functor
      
      * completing func name
      
      * fix bugs when run ci
      
      * fix bugs when run infr
      
      * modifpy infrt get kernel signature
      d7112180
  16. 14 3月, 2022 1 次提交
    • T
      Add an elementwise + activation fusion pass. (#36541) · 3f219160
      Tomasz Socha 提交于
      * Add elementwise add and activation fuse pass
      
      * Fix copy ellision
      
      * More flexible pattern detector
      
      * More flexible fusion pass
      
      * Update lists for pass
      
      * Add support for Pow operator
      
      * Add support for more activation types
      
      * Style
      
      * Rename fusion pass
      
      * First version of tests
      
      * Dirty version of pass
      
      * Polished version
      
      * Update pbtxt
      
      * Style
      
      * Update names
      
      * Style
      
      * Use PADDLE_ENFORCE_EQ
      
      * Save error message to variable
      
      * WO for error checks
      
      * CR
      
      * Static style check
      
      * Add missing 'activation_scale' attribute
      
      * Add relu6 and sigmoid activations
      
      * Style
      
      * Fix fuse list formating
      
      * Sync filenames for fuse pass files
      
      * Fix cmake after move
      
      * Fix registration
      
      * Fix pass name in tests
      
      * Add missing activations to checker
      
      * WIPS
      
      * Working mul op
      
      * Working sub
      
      * Working Add
      
      * Remove pten includes
      
      * Remove some forward declarations
      
      * Remove Includes
      
      * Fixes
      
      * Remove default kernels
      
      * Add check if post_ops attributes are avaliable
      
      * Style
      
      * Code adjustment
      
      * Register default kernels
      
      * We have year 2022 not 2021...
      Co-authored-by: Njakpiase <jakpia21@gmail.com>
      Co-authored-by: NSylwester Fraczek <sylwester.fraczek@intel.com>
      
      * Fast review fixes
      Co-authored-by: Njakpiase <jakpia21@gmail.com>
      Co-authored-by: NSylwester Fraczek <sylwester.fraczek@intel.com>
      
      * Review Fix
      
      * Rename one_dnn -> onednn
      
      * Style after review
      
      * Fast and dirty fix for quantization
      
      * Update tests
      
      * Style
      
      * Fix mkldnn_quantizer config
      
      * Add Joanna's suggestion.
      
      * Check if operator is explicitly disables on OneDNN
      
      * Try to use unregistered attributes
      
      * Style
      
      * Test new framework
      
      * FXI
      
      * FXII
      
      * Update test
      
      * Style
      Co-authored-by: Njakpiase <jakpia21@gmail.com>
      Co-authored-by: NSylwester Fraczek <sylwester.fraczek@intel.com>
      3f219160
  17. 11 3月, 2022 2 次提交
  18. 10 3月, 2022 1 次提交
  19. 08 3月, 2022 1 次提交
  20. 07 3月, 2022 1 次提交
    • M
      cuBlasLt Epilogue To Fuse Linear + ReLU|GeLU (#39437) · 2a3d9eca
      Ming-Xu Huang 提交于
      * Added cuBlasLtHandle_t to device context.
      
      * Added fused_gemm_epilogue op.
      
      1. Added fused_gemm_epilogue op to leverage cuBlastLt Epilogue.
      2. Support fusion Act(X*Y + bias), X'dims >=2 and Y'dims shoule be 2.
      2. Act currently only be supported ReLU. (Will add GeLU in the future).
      
      * Added UT to fused_gemm_epilogue op.
      
      * Added LinearAct Pattern
      
      1. Added LinearAct into graph_pattern_detector.* to define (2.)'s
      pattern.
      2. LinearAct is used to detect act(element_add(matmul_v2(x, w), bias)).
      3. act currently only support ReLU (Will support GeLU in the future).
      
      * Added FuseGemmEpiloguePass
      
      1, Added FuseGemmEpiloguePass to handle nn.Linear + Act{ReLU}
      fusion (GeLU will be supported in the future).
      2. Only support matmul_v2 from nn.Linear.
      
      * Added pybind to BuildStrageter.fuse_gemm_epilogue_.
      
      * Added UT for fuse_gemm_epilogue_pass.
      
      * GeLU support and EpilogueSingleton
      
      1. Added GeLU support to fused_gemm_epilogue op.
      2. Added EpilogueSingleton to cache auxiliary pointer.
      3. Added related UTs.
      
      * Rename cublaslt_epilogue_opto gemm_epilogue_op.*.
      
      * Added both train and infer pattern to LinearAct.
      
      1. Added support of fwd graph with grap_ops linking to LinearAct.
      2. Added related changes to fuse_gemm_epilogue_pass for above
      modification.
      
      * Changed CUDA requirement from 11.4 to 11.6 for fuse_gemm_epilogue_pass.
      
      * Added identity activation support to gemm_epilogue_op.
      
      * Added Linear Fusion (matmul_v2 + ele_add)
      
      1. Added matmul_v2 + ele_add pattern to LinearActPattern.
      2. Added matmul_v2 + ele_add support to fuse_gemm_epilogue_pass.
      
      * Rename gemm_epilogue_op.* to fused_gemm_epilogue_op.*
      
      * Add fused_gemm_epilogue_grad op.
      
      1. Added fused_gemm_epilogue_grad to support backward epilogue fusion.
      
      * Add UTs to fused_gemm_epilogue_grad_op.
      
      * Change attribute name in fused_gemm_epilogue_grad_op for clearing.
      
      * Allow DX and DBias be dispensable to fused_gemm_epilogue_grad op.
      
      * Added ElementwiseAdd+Matmul+Act graph pattern detection.
      
      * Fuse backward of Linear( Act(x))
      
      1. Added backward fusion pass to Linear( Act(x)).
      2. Added backward fusion pass to Linear(x).
      
      * Added UTs to backward fusion of Linear(Act(x)).
      
      * Complete document of arguments to fused_gemm_epilogue_op.
      
      * Made arguments of some functions pass by reference.
      
      * Modify code with review comments.
      
      1. Made arguments of some function pass by reference.
      2. Removed redundant code.
      3. Followed Google code style to change code.
      
      * Made 'const' code style be consistent
      
      * Fixed random seed of python UTs.
      
      * Set Compiling constrains to cuBlasLt
      
      1. Require CUDA 11.6+
      2. Remove fuse_gemm_epilogue related tests when CUDA < 11.6.
      
      * Code Reivew from Paddle
      
      1. Changed arguments name is_first_gemm to without_x_gradient for
      clearing.
      2. Applied PADDLE_THROW in fused_gemm_epilogue_op.
      
      * Remove EpilogueSingleton
      
      1. Applied ReserveSpace to replace Epilogue for passing auxiliary
      pointers between FWD and BWD.
      
      * Fix a logical error and enhance UTs.
      
      1. Added act op count checking in UTs.
      2. Fix issue to fuse backward or ReLU(Linear(X)).
      3. TODO: solve GELU fusion issues.
      
      * Fix Linear and GeLU fusion issues.
      
      1. Modified graph_detech_pattern to fit with both linear wiht gelu or
      relu.
      2. Modified data range in Uts to allow negative values.
      
      * Removed fused_gemm_epilogue_op.h.
      
      * Rename namespace pten to phi.
      
      * Rename name of arguments in fused_gemm_epilogue_op
      
      1. bias -> Bias.
      2. out -> Out.
      3. reserve_space -> ReserveSpace.
      
      * Change EpiloguePassActivationCache as local variable.
      
      1. Removed singleton in EpiloguePassActivationCache.
      2. Made EpiloguePassActivationCache as an argument to each pass
      functions.
      2a3d9eca
  21. 03 3月, 2022 1 次提交
    • H
      Move bn to pten (#39347) · ebd0f512
      hong 提交于
      * add bn cpu version; test=develop
      
      * move batch norm to pten
      
      * move batch norm to pten; test=develop
      
      * fix bug; test=develop
      
      * fix func::tranpose depend bug; test=develop
      
      * fix compile bugs; test=develop
      
      * fix use_op batch_norm bug; test=develop
      
      * fix cudnn bn add relu test; test=develop
      
      * fix pten context build and double grad bug; test= develop
      
      * remve useless code; test=develop
      
      * add batch norm gpu fp16 support; test=develop
      
      * fix test bn op bug; test=develop
      
      * remove output dtype set; test=develop
      
      * fix bug; test=develop
      
      * fix bug; test=develop
      
      * fix applay pass to program bug; test=develop
      
      * revert to develop; test=develop
      
      * fix rocm bug; test=develop
      
      * revert operator to develop; test=develop
      
      * fix pre_commit; test=develop
      
      * fix statci check error; test=develop
      
      * resolve conflict; test=develop
      
      * ana batch norm bug;
      
      * revert batch norm op
      
      * resolve conlict
      
      * fix nan inf and speed bug; test=develop
      
      * fix bug; test=develop
      
      * fix error; test=develop
      
      * test expand op; test=develop
      
      * fix bug; test=develop
      
      * resolve confilct
      
      * resolve confilct; test=develop
      
      * polish code; test=develop
      
      * polish code; test=develop
      
      * change mutable data to ctx alloc; test=develop
      
      * make format same with ci; test=develop
      
      * fix format error with ci; test=develop
      ebd0f512
  22. 01 3月, 2022 1 次提交
  23. 28 2月, 2022 1 次提交
  24. 25 2月, 2022 1 次提交
    • C
      [Phi] Support cudnn kernel moving & move softmax kernels (#39547) · 8895379a
      Chen Weihang 提交于
      * support cudnn kernel moving
      
      * polish cmake rules
      
      * add unittest for coverage
      
      * remove orig kernel
      
      * remove softmax cudnn kernel
      
      * fix softmax test failed
      
      * fix npu func error
      
      * resolve conflict
      
      * rename gpu dnn kernels
      
      * fix name rule error
      
      * fix compile error
      
      * update fp16 namespace
      8895379a
  25. 24 2月, 2022 1 次提交
  26. 22 2月, 2022 2 次提交
  27. 21 2月, 2022 1 次提交
    • C
      Update record interface using part2 (#39694) · c984cd85
      chenjian 提交于
      * fix RecordEvent interface
      
      * modify default level to 4
      
      * update interface use
      
      * add const default trace level
      
      * update record event interface using
      
      * update record event interface using
      
      * update operator.cc
      
      * update part2
      
      * update part1
      
      * fix include profiler.h header in ps server
      
      * fix include profiler.h header in ps server
      
      * fix profiler.h header
      c984cd85
  28. 20 2月, 2022 1 次提交
  29. 19 2月, 2022 1 次提交
    • A
      [Pten]Unify paddle/pten::framework::ddim into pten::ddim (#39614) · 2fe04264
      Aurelius84 提交于
      * Unify paddle/pten::framework::ddim into pten::ddim
      
      * fix paddle namespace
      
      * compile sucessfully
      
      * fix npu src file
      
      * fix conflict
      
      * fix conflict
      
      * fix tensorrt compiler error
      
      * fix conflict
      
      * fix conflict
      
      * fix tesst file conflict
      
      * fix conflict
      
      * fix mlu file conflict
      
      * fix mlu file conflict
      
      * fix cinn header file conflict
      
      * fix conflict
      
      * fix conflict
      
      * fix conflict
      
      * fix conflict
      2fe04264