1. 08 Jan, 2020 1 commit
  2. 06 Jan, 2020 1 commit
  3. 01 Jan, 2020 1 commit
  4. 05 Dec, 2019 1 commit
  5. 26 Nov, 2019 1 commit
  6. 21 Nov, 2019 1 commit
  7. 04 Nov, 2019 1 commit
  8. 19 Sep, 2019 1 commit
  9. 12 Sep, 2019 1 commit
  10. 06 Sep, 2019 1 commit
  11. 03 Sep, 2019 1 commit
  12. 30 Aug, 2019 1 commit
  13. 20 Aug, 2019 1 commit
  14. 07 Aug, 2019 1 commit
  15. 31 Jul, 2019 1 commit
  16. 26 Jul, 2019 1 commit
    • gcwenger's avatar
      Fixed double-buffering timing (#3309) · c04b5588
      gcwenger authored
      API is synchronous per thread and threads are coordinated so that
      we know when we hit the last iteration everything is done.
      Using join() to gate end of iterations was introducing too much
      overhead to timing as verified via checking traces.
      c04b5588
  17. 23 Jul, 2019 5 commits
  18. 21 Jul, 2019 8 commits
  19. 17 Jul, 2019 2 commits
  20. 11 Jul, 2019 1 commit
  21. 09 Jul, 2019 2 commits
  22. 08 Jul, 2019 1 commit
  23. 05 Jul, 2019 1 commit
  24. 12 Jun, 2019 1 commit
    • Rob Earhart's avatar
      Update PlaidML backend for current nGraph (#3030) · 397740fe
      Rob Earhart authored
      * Rename PlaidML_Executable::save -> save_as_format
      
      * Repair regression in PlaidML tensor impl
      
      This was caused by the recent removal of the offset parameter for tensor read/write operations -- we missed a
      spot where read/write were being called for synchronization purposes.
      
      * Disable a few more PlaidML tests pending triage
      
      * Skip elision of reshape->reshape
      
      It turns out this doesn't work, because the downstream reshape's input_order axis vector is incorrect if the
      upstream reshape is removed.
      
      * Add element type to PlaidML tensor debug output
      
      * Use nGraph booleans for PlaidML boolean data
      
      We'd previously been using i8; that's been deprecated for boolean data now that we have an explicit boolean
      element type.
      
      * Set PlaidML convolution output shapes correctly
      
      We weren't transposing the output shape; we were computing the right data, but the incorrect shape metadata
      causes validation to fail.
      
      * Add a PlaidML implicit broadcast op
      
      Better nGraph shape validation was tripping up PlaidML's use of a reshape to replace explicit broadcasts with
      implicit NumPy-style broadcasts (since the reshape's output shape would be incorrect for the downstream
      elementwise operation).  Adding this implicit broadcast operation lets PlaidML tell nGraph something useful
      about the shapes, making validation pass (when it's otherwise correct).
      397740fe
  25. 05 Jun, 2019 1 commit
    • Robert Kimball's avatar
      Remove tensor offset from tensor read/write calls because it was never used (#2979) · c555b36a
      Robert Kimball authored
      * remove tensor offset from tensor read/write calls because it was never used
      
      * fix build errors
      
      * fix build errors
      
      * fix python test errors
      
      * more python fixes
      
      * revert change
      
      * Make old version of read/write deprecated
      
      * fix python read overload
      
      * one more try to fix python binding
      
      * fix python
      
      * yet another try
      
      * why is this so hard
      
      * fix?
      
      * add text to changes.md
      c555b36a
  26. 02 Jun, 2019 1 commit
  27. 23 May, 2019 1 commit