1. 15 4月, 2022 1 次提交
    • L
      Change cuDNN Conv kernel for auto tune feature (#41313) · 35acfeda
      limingshu 提交于
      * change cudnn helper for auto-tune
      
      * Add FLAGS_use_autotune to set the global status of autotune and change the order of choosing algorithm.
      
      * Fix the bug in calculating and printing current step cache hit rate.
      
      * Improve the autotune cache and fix unittest.
      
      * Change the key from AlgorithmType to int64_t.
      
      * Fix unittest for cpu-only env.
      
      * change ChooseAlgoByWorkspace for heuristic mode
      Co-authored-by: NLiu Yiqun <liuyiqun01@baidu.com>
      35acfeda
  2. 09 4月, 2022 2 次提交
  3. 05 4月, 2022 1 次提交
    • Z
      Implement AutoTuneStatus class for Kernel Auto Tune (#41218) · b0f8000e
      Zhang Ting 提交于
      * switch autotune
      
      * implement AutoTuneCache
      
      * implement AutoTuneCache class
      
      * add pybind api
      
      * add dygraph test
      
      * support static mode and eager mode and improve unittests
      
      * rename the SwitchAutoTune Class and improve tests
      
      * improve AutoTuneStatus and reduce the cost of tests
      b0f8000e