diff options
| author | Eric Anholt <[email protected]> | 2017-11-28 16:17:16 -0800 |
|---|---|---|
| committer | Eric Anholt <[email protected]> | 2017-12-01 15:37:28 -0800 |
| commit | 0ed952c7e9b811bc11dec64bd4bebcdf4222cc85 (patch) | |
| tree | 3f559f6dd6705c0724f3494736fbeebf1d7d96f5 /src/intel | |
| parent | 230e646a4013ed5d9c80c54d48ef0ac9ee4edbb0 (diff) | |
broadcom/vc4: Use a single-entry cached last_hindex value.
Since almost all BOs will be in one CL at a time, this cache will almost
always hit except for the first usage of the BO in each CL.
This didn't show up as statistically significant on the minetest trace
(n=340), but if I lop off the throttled lobe of the bimodal distribution,
it very clearly does (0.74731% +/- 0.162093%, n=269).
Diffstat (limited to 'src/intel')
0 files changed, 0 insertions, 0 deletions