diff options
| author | Eric Anholt <[email protected]> | 2013-12-24 15:11:54 -0800 |
|---|---|---|
| committer | Carl Worth <[email protected]> | 2014-01-09 12:24:44 -0800 |
| commit | 3a6271890cd40c1e37870802f9f3231b3170d27f (patch) | |
| tree | 57555cc10412d94a8e2b0d1260880e79c2454a8a /src/mesa/drivers/dri | |
| parent | 9b3ed4c8c2e985506628ff9e6be2431b4b01393f (diff) | |
i965: Don't do the temporary-and-blit-copy for INVALIDATE_RANGE maps.
We definitely want to fall through to the unsynchronized map case, instead
of wasting bandwidth on a copy. Prevents a -43.2407% +/- 1.06113% (n=49)
performance regression on aa10perf when teaching glamor to provide the
GL_INVALIDATE_RANGE_BIT information.
This is a performance fix, which I usually wouldn't cherry-pick to stable.
But this was really was just a bug in the code, its presence would
discourage developers from giving us the best information they can, and I
think we've got fairly high confidence in the unsynchronized map path
already.
Cc: 10.0 9.2 <[email protected]>
Reviewed-by: Kenneth Graunke <[email protected]>
(cherry picked from commit f46563fe1c8a5560e4de0adf03e3d8770b7fc734)
Diffstat (limited to 'src/mesa/drivers/dri')
| -rw-r--r-- | src/mesa/drivers/dri/i965/intel_buffer_objects.c | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/src/mesa/drivers/dri/i965/intel_buffer_objects.c b/src/mesa/drivers/dri/i965/intel_buffer_objects.c index 779198f9e51..a87ebf7c593 100644 --- a/src/mesa/drivers/dri/i965/intel_buffer_objects.c +++ b/src/mesa/drivers/dri/i965/intel_buffer_objects.c @@ -357,7 +357,8 @@ intel_bufferobj_map_range(struct gl_context * ctx, * BO, and we'll copy what they put in there out at unmap or * FlushRange time. */ - if ((access & GL_MAP_INVALIDATE_RANGE_BIT) && + if (!(access & GL_MAP_UNSYNCHRONIZED_BIT) && + (access & GL_MAP_INVALIDATE_RANGE_BIT) && drm_intel_bo_busy(intel_obj->buffer)) { if (access & GL_MAP_FLUSH_EXPLICIT_BIT) { intel_obj->range_map_buffer = malloc(length); |