1. 11 Mar, 2014 1 commit
  2. 20 Jan, 2014 1 commit
  3. 10 Dec, 2013 1 commit
  4. 04 Nov, 2013 1 commit
  5. 04 Mar, 2013 2 commits
  6. 04 Jan, 2012 1 commit
  7. 04 Dec, 2011 2 commits
  8. 02 Dec, 2011 3 commits
  9. 30 Nov, 2011 1 commit
  10. 15 Sep, 2011 1 commit
  11. 08 Jul, 2011 1 commit
  12. 23 Jun, 2011 1 commit
  13. 20 Jun, 2011 1 commit
  14. 05 Jun, 2011 2 commits
  15. 04 Jun, 2011 1 commit
  16. 25 May, 2011 1 commit
  17. 01 Feb, 2011 2 commits
  18. 29 Jan, 2011 3 commits
  19. 23 Dec, 2010 1 commit
  20. 17 Dec, 2010 1 commit
  21. 08 Apr, 2010 1 commit
  22. 20 Feb, 2010 2 commits
  23. 12 Feb, 2010 1 commit
  24. 01 Feb, 2010 1 commit
  25. 12 Jan, 2010 1 commit
  26. 06 Jan, 2010 1 commit
  27. 15 Dec, 2009 1 commit
  28. 30 Nov, 2009 1 commit
  29. 07 Oct, 2009 1 commit
  30. 01 Sep, 2009 1 commit
    • Chris Wilson's avatar
      Add gem_fence_thrash test · 8f3f862b
      Chris Wilson authored
      This is a test case that overcommits fence registers between threads, which
      are copying from one fenced bo to another. In earlier versions of the driver
      this would cause excessive spinning as the first inactive (i.e. not in use
      by the GPU) would be used to service the next page. After all the fence
      registers had been allocated, in effect only the very first fence would then
      be used for all subsequent faults.
      8f3f862b
  31. 01 Jul, 2009 1 commit