1. 26 Sep, 2019 1 commit
  2. 11 Sep, 2019 1 commit
  3. 12 Jun, 2019 1 commit
  4. 02 May, 2019 1 commit
  5. 03 Jan, 2019 1 commit
  6. 08 May, 2018 1 commit
  7. 24 Mar, 2018 1 commit
  8. 08 Mar, 2018 1 commit
  9. 28 Jan, 2018 1 commit
  10. 19 Dec, 2017 2 commits
  11. 13 Dec, 2017 1 commit
  12. 03 Dec, 2017 1 commit
  13. 21 Nov, 2017 2 commits
  14. 17 Sep, 2017 1 commit
  15. 08 Sep, 2017 1 commit
    • Clément Bœsch's avatar
      checkasm: use perf API on Linux ARM* · e0d56f09
      Clément Bœsch authored
      On ARM platforms, accessing the PMU registers requires special user
      access permissions. Since there is no other way to get accurate timers,
      the current implementation of timers in FFmpeg rely on these registers.
      Unfortunately, enabling user access to these registers on Linux is not
      trivial, and generally involve compiling a random and unreliable github
      kernel module, or patching somehow your kernel.
      
      Such module is very unlikely to reach the upstream anytime soon. Quoting
      Robin Murphin from ARM:
      
      > Say you do give userspace direct access to the PMU; now run two or more
      > programs at once that believe they can use the counters for their own
      > "minimal-overhead" profiling. Have fun interpreting those results...
      >
      > And that's not even getting into the implications of scheduling across
      > different CPUs, CPUidle, etc. where the PMU state is completely beyond
      > userspace's control. In general, the plan to provide userspace with
      > something which might happen to just about work in a few corner cases,
      > but is meaningless, misleading or downright broken in all others, is to
      > never do so.
      
      As a result, the alternative is to use the Performance Monitoring Linux
      API which makes use of these registers internally (assuming the PMU of
      your ARM board is supported in the kernel, which is definitely not a
      given...).
      
      While the Linux API is obviously cross platform, it does have a
      significant overhead which needs to be taken into account. As a result,
      that mode is only weakly enabled on ARM platforms exclusively.
      
      Note on the non flexibility of the implementation: the timers (native
      FFmpeg vs Linux API) are selected at compilation time to prevent the
      need of function calls, which would result in a negative impact on the
      cycle counters.
      e0d56f09
  16. 13 Jul, 2017 1 commit
  17. 03 Jul, 2017 1 commit
  18. 28 Jun, 2017 1 commit
  19. 21 Jun, 2017 1 commit
  20. 14 Jun, 2017 2 commits
  21. 11 Apr, 2017 1 commit
  22. 01 Mar, 2017 1 commit
  23. 22 Oct, 2016 1 commit
  24. 16 Oct, 2016 2 commits
  25. 02 Oct, 2016 1 commit
  26. 22 Sep, 2016 2 commits
  27. 03 Aug, 2016 1 commit
  28. 22 Jul, 2016 1 commit
  29. 08 Jul, 2016 1 commit
  30. 21 Jun, 2016 1 commit
    • Martin Storsjö's avatar
      checkasm: Issue emms after benchmarking functions · dc7501e5
      Martin Storsjö authored
      The functions may not clean up properly after using MMX
      registers. For the normal testing calls, the checkasm_checked_call
      functions will do the cleanup (and check that functions that
      should clean up do it as well), but when benchmarking functions
      that don't clean up, we don't currently properly clean up at all.
      
      This causes issues if a benchmarked function is followed by testing
      of a function that is supposed to not clobber the MMX/FPU state but
      doesn't touch it at all.
      Signed-off-by: 's avatarMartin Storsjö <martin@martin.st>
      dc7501e5
  31. 17 Jun, 2016 1 commit
  32. 12 Apr, 2016 1 commit
  33. 18 Feb, 2016 1 commit
  34. 14 Feb, 2016 1 commit
  35. 31 Jan, 2016 1 commit