1. 22 11月, 2019 3 次提交
    • H
      add NHWC NCHW transform, test=develop (#2381) · 6b3c341f
      HappyAngel 提交于
      * add nhwc to nchw
      
      * add layout in funcs
      
      * change layout as extra, test=develop
      
      * change make, test=develop
      
      * use template class method to update layout NNCHHW and NHWC transform, test=develop
      
      * fix cmake error, set layout to extra, test=develop
      
      * fix test_layout_compute_arm test, its extra
      
      * layout is extra, test=develop
      
      * fix error in kernels/arm/layout_comput.cc when register kernel, DataLayout must be NCHW, test=develop
      
      * delete extra note, test=develop
      
      * delete extra test
      
      * delete layout_test, test=develop
      
      , its in tests/math/layout_comput_test
      
      * delete extrat test, test=develop
      6b3c341f
    • Y
      [ARM] add sgemmc4 common and small kernel, support for winograd, test=develop (#2471) · 66d2ae25
      yiicy 提交于
      * unfinish sgemmc4
      
      * finish armv8 sgemmc4
      
      * arm add sgemmc4 with deal with remain
      
      * [ARM] add sgemmc4 small kernel, test=develop
      66d2ae25
    • H
      update pooling 2-padding to 4-padding (#2410) · a7f7d49b
      HappyAngel 提交于
      * fix pooling bug and speed
      
      * fix build error
      
      * delete VLOGin pool, test=develop
      
      * add openmp, test=develop
      
      * fix lite/kernels/arm/pool_compute_test basic_pooling compute error bug, test=develop
      
      * update pooling 2-pad to 4-pad, test=develop
      
      * fix 2-pad to 4-pad in operators/pool_op.h, AttachKernel will set param, so 2-pad to 4-pad funcs should put in AttachKernel. test=ddevellop
      
      * put 2-pad to 4-pad in AttachImpl, test=develop
      
      * according to reviews, fix some format error. test=develop
      
      * fix format errorr, add (). test=develop
      
      * change paddings type to support dynamically modify, test=develop
      
      * update padding type int other devices, test=develop
      
      * fix x8d build error on shared_ptr, test=ddevelop
      
      * fix formmat in operators pool_op.cc, test=develop
      a7f7d49b
  2. 21 11月, 2019 1 次提交
  3. 20 11月, 2019 1 次提交
  4. 19 11月, 2019 2 次提交
  5. 18 11月, 2019 1 次提交
    • Y
      [LITE][OPENCL] Enable full and light api for OpenCL (#2331) · d242bdfb
      Yuan Shuai 提交于
      * Fix bug target for kHost and kARM not equal. test=develop
      
      * Fix license. test=develop
      
      * add debug -g option. test=develop
      
      * enable opencl demo. test=develop
      
      * Fix model_optimize_tool found no opencl kernel. test=develop
      
      * add more vlog. test=develop
      
      * remove macro LITE_WITH_OPENCL, LITE_WITH_FPGA in passes. test=develop
      
      * Fix valid_places in mobilenetv1_test. test=develop
      
      * Fix bug of find no real output of fetch, after tool OPs of optimzer passes. test=develop
      
      * Fix vlog as log message in model_optimize_tool. test=develop
      
      * fix miscs. test=develop
      
      * fix comment. test=develop
      
      * Fix misspell of opencl, fpga kernels name in lite/api/CMakeLists.txt. test=develop
      
      * add opencl macro in full_api of demo. test=develop
      d242bdfb
  6. 17 11月, 2019 1 次提交
  7. 14 11月, 2019 1 次提交
  8. 13 11月, 2019 1 次提交
  9. 11 11月, 2019 1 次提交
    • H
      fix pool bug and speed, test=develop (#2385) · d197de00
      HappyAngel 提交于
      * fix pooling bug and speed
      
      * fix build error
      
      * delete VLOG in pool, test=develop
      
      * add openmp, test=develop
      
      * fix lite/kernels/arm/pool_compute_test basic_pooling compute error bug, test=develop
      d197de00
  10. 08 11月, 2019 1 次提交
  11. 07 11月, 2019 1 次提交
    • W
      fix jit_matmul bug according to paddle pr#20948 test=develop (#2392) · f51c4891
      Wilber 提交于
      fix jit::matmul bug. Input x shape is (m, k), weight shape is (k, n). When k < 512, m==1, and n is a multiple of 16, the weight pointer is not correctly updated in the group calculation in the implementation of jit::matmul, resulting in the result diff 
      f51c4891
  12. 30 10月, 2019 1 次提交
  13. 29 10月, 2019 2 次提交
  14. 28 10月, 2019 1 次提交
    • H
      [LITE][XPU] initial support for XPU (#2202) · 06d058fe
      hong19860320 提交于
      * Initial support for XPU
      * Fix compiling errors of XPU
      * Move XPU op kernel bridges from backends to kernels to fix deps order
      * Change the namespace and directory of XPU bridges
      * Add XPU SDK
      * Fix header files and namespace of XPU SDK
      * Add unit tests for relu and conv2d ops
      * Restore the modification of paddle_api_test
      * Supports simple model which contains only a relu layer
      * Add compiling scripts for XPU
      * Fix compiling errors of XPU
      * Add comments for XPU LoadModel and BuildModel
      06d058fe
  15. 24 10月, 2019 1 次提交
    • X
      Fix gemv int8 error (#2249) · 3406a11a
      Xiaoyang LI 提交于
      * remove log in reshape, fix conv error when padding size=4, test=develop
      
      * fix style, test=develop
      
      * remove useless code, test=develop
      
      * remove redundant model test file, test=develop
      
      * change cluster to power_mode, test=develop
      
      * fix build error, test=develop
      
      * change cluster to power_mode, test=develop
      
      * change opt_nb to use_optimize_nb, test=develop
      
      * null, test=develop
      
      * add gemv-int8 test, fix clang build error, test=develop
      
      * fix gemv-int8 error when build with clang, test=develop
      3406a11a
  16. 23 10月, 2019 3 次提交
  17. 22 10月, 2019 1 次提交
    • T
      Transformer pr (#2214) · f0a6c1eb
      TianXiaogang 提交于
      * feat: add beam_search_special function for support nlp model
      
      * fix: add beam_search_compute kernel input and output
      
      * feat: add assign op & copy_compute kernel
      
      * feat: add fill_const_batch_size_like op & kernel
      
      * feat: add layer_norm op and kernel and ut
      
      * fix: fix some bugs
          fix mul_op infer_shape bug when x_dim_idx = 2, x_dims.size()=3 & y_dim_idx = 1, y_dims.size()=2
          fix elementwise_compute bug when y axis is all 1
          fix beam_search choose math_func wrong bug
          fix layer_norm get attr bug
          fix fill_constant_batch_size_like shape_set bug
      
      * feat: add gather op and kernel & and transform ut
      
      * feats: add ops and fix bugs to support transformer op
             fix type_cast passes to skip `while`
             fix elementwise infer_shape bug when x.dims=3 and y.dims={1} & axis=0
             fix lookup_table compute bug
             fix read_from_array/beam_search/increment/compate/gather ops data_type problems
      
      * fix:
          transfomer ut add word read inferface
          fix copy/gather/norm/layer_norm include path problem
      
      * fix:debug info
      
      * fix: fix input reshape bug
      
      * fix: fix norm bug
      
      * style: style fix & test=develop
      
      * style: fix operators cmakelist
      
      * style: fix operators cmakelist; test=develop
      
      * fix and test=develop
      
      * fix and test=develop
      
      * style: style fix; test=develop
      f0a6c1eb
  18. 21 10月, 2019 2 次提交
  19. 17 10月, 2019 2 次提交
    • Z
      fix npu path (#2210) · 7c722a37
      zhupengyang 提交于
      * move lite/backends/npu/bridges --> lite/kernels/npu/
      
      test=develop
      
      * fix namespace for npu
      
      test=develop
      
      * mv npu runtime file to lite/backends/npu
      
      test=develop
      7c722a37
    • H
      speedup fp32 depthwise conv · 2f6d5f9e
      HappyAngel 提交于
      * update con_dw
      
      * update
      
      * add conv_depthwise_3x3s1.cc and conv_depthwise_3x3s2.cc
      
      * add conv_depthwise_3x3s1_fp32 and conv_depthwise_3x3s2_fp32
      
      * add new conv_dw
      
      * only support conv_dw pad=0, 1
      
      * add conv_dw_s1 conv_dw_s2 fp32
      
      *     //conv2_func _impl2{nullptr};
      update conv_dw, add conv_3x3s1 and conv_3x3s2, pad=[0,1]
      
      * fix format, test=develop
      
      * fix formmat, test=develop
      2f6d5f9e
  20. 16 10月, 2019 1 次提交
  21. 15 10月, 2019 2 次提交
    • Y
      [LITE][OPENCL] Fix layout, target pass for OpenCL, add macro of... · 72c11758
      Yuan Shuai 提交于
      [LITE][OPENCL] Fix layout, target pass for OpenCL, add macro of CONVERT_TYPE_TO and READ/WRITE image, memory reuse in ResetLazyImage2D (#2170)
      
      * add macro of CONVERT_TYPE_TO and READ/WRITE image. test=develop
      
      * add data type control. test=develop
      
      * fix io op as general layout and precision. test=develop
      
      * Fix memory reuse strategy for opencl image2d. test=develop
      
      * remove std::array, std::map in about opencl backend. test=develop
      72c11758
    • H
      [NPU] Fix and refine the supporting of multi NPU models (#2037) · 7a731b7f
      hong19860320 提交于
      * [NPU] Fix the bug of loading multi NPU models
      test=develop
      
      * [NPU] Use lite tensor to store NPU model, fix the management of multi NPU models, support loading NPU model from memory and reduce the modification of framework
      test=develop
      
      * [NPU] Remove redundant header files for NPU bridges,
      test=develop
      
      * [NPU] fix NPU deps
      test=develop
      
      * [NPU] refine the compiling script for NPU
      test=develop
      
      * [NPU] remove redundant subdirectory in lite/CMakeLists.txt
      test=develop
      
      * [NPU] Fix and refine NPU test case
      test=develop
      
      * [NPU] revoke the modification of other non-NPU modules
      test=develop
      
      * [NPU] Remove NPU bridges if target is tiny publish
      test=develop
      7a731b7f
  22. 14 10月, 2019 2 次提交
  23. 11 10月, 2019 3 次提交
    • J
      add rsqrt op, test=develop (#2176) · dfce4621
      juncaipeng 提交于
      dfce4621
    • Z
      CUDA: can run yolov3 int8 (#2172) · 7931104f
      Zhaolong Xing 提交于
      * add conv int8 support(in condition which the input or output channel not be the times of 4)
      add add_kernel for cuda.
      
      * can run yolov3 fp32
      test=develop
      
      * 1. fix bug with yolov3 run
      test=develop
      
      * can run yolov3 int8 test=develop
      7931104f
    • Y
      [LITE][OPENCL] support image2d type (#2158) · 77cdbdce
      Yuan Shuai 提交于
      * [LITE][OPENCL] support image2d. test=develop
      
      * add context changed with consider image*. test=develop
      
      * add layout, relu image kernels. test=develop
      
      * replace image_data with data, mutable_image_data with mutable_data, test=develop
      
      * comment unused var. test=develop
      
      * remove unused var. test=develop
      77cdbdce
  24. 10 10月, 2019 1 次提交
  25. 09 10月, 2019 1 次提交
    • Y
      improve dw conv performance · 4b9df8fb
      yiicy 提交于
      *  imporve prepack_input func speed in int8 3x3s1 dw conv
      
      * fix code style
      
      * fix code style
      
      * improve 3x3s1 dw fp32 conv speed a little
      
      * arm add 5x5s1 int8 dw conv, test=develop
      4b9df8fb
  26. 27 9月, 2019 1 次提交
    • Z
      can run yolov3 fp32 on cuda devices (#2092) · 3d6d744f
      Zhaolong Xing 提交于
      * add conv int8 support(in condition which the input or output channel not be the times of 4)
      add add_kernel for cuda.
      
      * can run yolov3 fp32
      test=develop
      
      * 1. fix bug with yolov3 run
      test=develop
      3d6d744f
  27. 25 9月, 2019 1 次提交
  28. 19 9月, 2019 1 次提交