1. 14 Aug, 2017 2 commits
    • [TOPI] conv2d nchw gpu scheduler (#315) · cbff637f
      * __init__ updated
      
      * pull request updated
      
      * build_module added
      
      * typo fixed
      
      * another typo fixed
      
      * conv2d gpu scheduler for two layouts moved to tvm
      
      * changes made according to CR
      
      * conv2d_nchw formating updated, conv2d_hwcn tests updated
      
      * lint error fixed
      
      * element wise operator schedule fusing fixed for conv2d
      
      * conv2d_nchw topi test added, all resnet workloads now pass
      
      * conv compute lint error fixed
      
      * fixed python 3 compatibility problem
      
      * conv2d tensor input support added, test typo fixed, ir_pass.Simplify changed to util.get_const_int
      Leyuan Wang committed
    • [TOPI] Move topi.nn.util to topi.util (#319) · d76712d1
      * [TOPI] Move topi.nn.util to topi.util
      
      * update the path
      Tianqi Chen committed
  2. 13 Aug, 2017 3 commits
    • [WIP] C++ topi contributions (#312) · f08de2b6
      * [WIP] C++ topi contributions
      
      Summary:
      This diff implements C++ topi contributions for:
        - relu with parametrix threshold
        - pad with generic padBefore / padAfter specification
        - matmult with transposes
        - conv2d_nchw, conv2d_hwcn with runtime constant padding and strides
        - depthwise_conv2d_nchw with runtime constant padding and strides
        - group_conv2d_ngchw with runtime constant padding and strides
        - broadcast_to a broadcastable shape
        - broadcast_bop where bop is an usual binary op (+ - * / %)
      
      Convolution padding is implemented using the pad operation.
      To avoid extra memory consumption, it is generally recommended to inline the padding with the autoinliner.
      Unfortunately in its current form the elemwise checks are too restrictive to allow inlining.
      So this diff also proposes an extension to LHS injective (i.e. no reduction axis in the current IR design)
      
      Test Plan:
      Tested in C++ testsuite in a separate repository, I am looking for suggestions to quickly spin up some tests for tvm.
      
      Reviewers: tqchen
      
      Subscribers:
      
      Tasks:
      
      Tags:
      
      Blame Revision:
      
      * Review + Lint + GSG C++
      Nicolas Vasilache committed
  3. 12 Aug, 2017 1 commit
  4. 11 Aug, 2017 2 commits
  5. 10 Aug, 2017 3 commits
  6. 09 Aug, 2017 2 commits
  7. 08 Aug, 2017 3 commits
  8. 07 Aug, 2017 1 commit
  9. 06 Aug, 2017 1 commit
  10. 05 Aug, 2017 1 commit
  11. 04 Aug, 2017 2 commits
  12. 03 Aug, 2017 2 commits
  13. 01 Aug, 2017 6 commits
  14. 31 Jul, 2017 3 commits
  15. 29 Jul, 2017 1 commit
  16. 28 Jul, 2017 1 commit
  17. 27 Jul, 2017 3 commits
  18. 26 Jul, 2017 3 commits