summaryrefslogtreecommitdiff
AgeCommit message (Expand)Author
2011-10-21sna: Remove the memset(0) of the fill opChris Wilson
2011-10-21sna: Pass a BoxRec to the fill opChris Wilson
2011-10-21sna: Check whether we can blt whilst determining the PolyLine extentsChris Wilson
2011-10-21sna: Speed-up blitting of unclipped linesChris Wilson
2011-10-21sna/damage: Stash the last freed damage for quick reallocationChris Wilson
2011-10-21sna/damage: Only track the mode globallyChris Wilson
2011-10-20sna: Actually apply the composite offset for the self-copyChris Wilson
2011-10-20sna/dri: Perform a little dance to restore the gpu status on release of the boChris Wilson
2011-10-19sna: Reuse any partial write buffer for readbackChris Wilson
2011-10-19sna: Add some debug to discern the nature of the Cr fallbackChris Wilson
2011-10-19sna: Clean up some debug messages for 64bitChris Wilson
2011-10-19sna/blt: Use SCANLINE_BLT for multiple fill boxesChris Wilson
2011-10-19sna: The initial aperture check for a set of bo is unlikely to failChris Wilson
2011-10-19sna: Reset the ring flag upon idlingChris Wilson
2011-10-19sna: Don't rewrite the solid colour cache if it hasn't changedChris Wilson
2011-10-19sna: Enlarge the minimum pixmap size to migrate for RenderChris Wilson
2011-10-19sna/damage: Avoid reducing the damage for simple testsChris Wilson
2011-10-19sna/gen6: Apply the unknown blitter death workaroundChris Wilson
2011-10-19sna: Compute region extents in place to eliminate redundant stack spaceChris Wilson
2011-10-19sna: Use the unlikely wedged() throughoutChris Wilson
2011-10-19sna: Micro-optimise fill-spansChris Wilson
2011-10-18sna/gen6: Don't modify composite arguments whilst checking for BLTChris Wilson
2011-10-18sna/blt: Move the conditional out of the fill-many hotpathChris Wilson
2011-10-18sna/gen4: Add fill-oneChris Wilson
2011-10-18sna/gen6: Precompute floats_per_rectChris Wilson
2011-10-18sna/gen5: Add fill-one implementationChris Wilson
2011-10-18sna/gen6: Try continuing with the BLT if the last batch was also BLTChris Wilson
2011-10-18sna/gen6: Micro-optimise gen6_rectangle_beginChris Wilson
2011-10-18sna/gen2: Precompute floats-per-rectChris Wilson
2011-10-18sna/gen2: Prefer to use the BLTChris Wilson
2011-10-18sna/gen3: Prefer to use the BLT where possible for composite opsChris Wilson
2011-10-18sna/gen3: Prefer to use the BLT to clear the scratch glyph pixmapsChris Wilson
2011-10-17sna: Some more debug output for request/bo retirementChris Wilson
2011-10-17sna: Only retire the flush handler if nothing was submitted within the periodChris Wilson
2011-10-17sna/gen3: Use immediates for black/white solid sourcesChris Wilson
2011-10-17sna/gen3: More removal of memset(0)Chris Wilson
2011-10-17sna/gen5: Rearrange the BLT->RENDER workaroundChris Wilson
2011-10-17sna: Fast path common colour conversionsChris Wilson
2011-10-17sna/accel: Implement a simpler path for CopyArea between the same pixmapsChris Wilson
2011-10-17sna: Improve debug output for mi/fb fallbacksChris Wilson
2011-10-17sna/gen3: Remove memset(0) from fill_boxesChris Wilson
2011-10-17sna/damage: Clear damage->all when subtractingChris Wilson
2011-10-17snb,ivb: Workaround unknown blitter deathChris Wilson
2011-10-17sna/gen3: Micro-optimise gen3_rectangle_begin()Chris Wilson
2011-10-17sna/gen3: Store floats_per_rect alongside floats_per_vertexChris Wilson
2011-10-17sna/gen3: Improve reduction of render operator to bltChris Wilson
2011-10-17configure: Add a check for pixman versionChris Wilson
2011-10-17sna: Defer CPU fallback if fb calls into miChris Wilson
2011-10-16sna: Prefer to accelerate non-RENDER operations if already using the GPUChris Wilson
2011-10-16sna: Simplify busy tracking by trusting the bo->gpu flagChris Wilson