1. 23 Feb, 2022 1 commit
    • Jianfeng Yan's avatar
      Conv3d new (#94) · 6dfb92bb
      Jianfeng Yan authored
      
      
      * conv3d compiles but has memory error
      
      * conv3d works
      
      * fix performance issue by using __builtin_amdgc_readfirstlane
      
      * change MakeBlock2CTileMap to MakeDefaultBlock2CTileMap; change c_blockid_to* to cblockid_to*
      
      * clang-format
      
      * remove CK_EXPERIMENTAL_PASS_TENSOR_DECRIPTOR_BY_*; moved wrapper into DeviceConv3d
      
      * format
      
      * remove useless marc
      
      * add comment
      Co-authored-by: default avatarChao Liu <chao.liu2@amd.com>
      6dfb92bb
  2. 30 Nov, 2021 1 commit