[Intel-gfx] [RFC i-g-t 0/1] intel_gpu_top: Per-client engine busyness

Tvrtko Ursulin tvrtko.ursulin at linux.intel.com
Fri May 10 13:23:11 UTC 2019


From: Tvrtko Ursulin <tvrtko.ursulin at intel.com>

Extension to intel_gpu_top which uses the corresponding sysfs interface proposal
to implement per client and per class engine utilization view. Example output:

==========================================================================
intel-gpu-top -  935/ 935 MHz;    0% RC6; 14.73 Watts;     1097 irqs/s

      IMC reads:     1401 MiB/s
     IMC writes:        4 MiB/s

          ENGINE      BUSY                                 MI_SEMA MI_WAIT
     Render/3D/0   63.73% |███████████████████           |      3%      0%
       Blitter/0    9.53% |██▊                           |      6%      0%
         Video/0   39.32% |███████████▊                  |     16%      0%
         Video/1   15.62% |████▋                         |      0%      0%
  VideoEnhance/0    0.00% |                              |      0%      0%

  PID            NAME     RCS          BCS          VCS         VECS
 4084        gem_wsim |█████▌     ||█          ||           ||           |
 4086        gem_wsim |█▌         ||           ||███        ||           |
==========================================================================


Tvrtko Ursulin (1):
  intel-gpu-top: Support for client stats

 tools/intel_gpu_top.c | 590 +++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 584 insertions(+), 6 deletions(-)

-- 
2.19.1



More information about the Intel-gfx mailing list