summaryrefslogtreecommitdiff
path: root/src/sna/sna_io.c
AgeCommit message (Expand)Author
2013-03-05sna: Assert that the pixmap is not pinned before releasing the GPU boChris Wilson
2013-02-07sna: Force GTT readback if the GPU is wedgedChris Wilson
2013-01-30sna: Prefer to use snooped buffers for readbacksChris Wilson
2013-01-16sna: Restrict upload buffers to reduce sampler TLB missesChris Wilson
2013-01-12sna: After a size check, double check the batch before flushingChris Wilson
2013-01-11sna: Disable memcpy_to_tiled_x() uploads on 32-bit systemsChris Wilson
2012-12-08sna: Flush upon change of target if GPU is idleChris Wilson
2012-11-30Convert generation counter to octalChris Wilson
2012-11-13sna: Specialise the decision for inplace xor uploadsChris Wilson
2012-10-08sna: Fix check_reloc_and_exec typoChris Wilson
2012-10-07sna: Check that for batch overflows after advancing a BLTChris Wilson
2012-09-21sna: Force an inplace upload if already wedgedChris Wilson
2012-09-21sna: Use inplace X tiling for LLC uploadsChris Wilson
2012-09-13sna: Prefer to use indirect uploads for very small updatesChris Wilson
2012-09-13sna: Teach sna_replace__xor() how to tile large uploadsChris Wilson
2012-09-12sna: Also remove bogus assertion from sna_replace__xor()Chris Wilson
2012-09-12sna: Avoid readback inplace if the target is unmappableChris Wilson
2012-09-12sna: Flush after operating on large buffersChris Wilson
2012-07-20sna: Also check whether the first upload box can use the BLTChris Wilson
2012-07-19sna: Handle mixed bo/buffers in assertionsChris Wilson
2012-07-14sna: Aim for consistency and use stdbool except for core X APIsChris Wilson
2012-07-09sna: Simplify the DBG incarnationChris Wilson
2012-07-04sna: Pass a hint to the backends when using copy_boxes for readbackChris Wilson
2012-06-19sna: Double check that the source is busy before performing indirect readsChris Wilson
2012-06-18sna: Check if the busy is truly busy before commiting to an indirect uploadChris Wilson
2012-06-15sna: Tweaks for DBG missing glyphs through fallbacksChris Wilson
2012-06-14sna: Add a little bit more DBG to migration IO pathsChris Wilson
2012-06-04sna: Free clip boxes (if allocated) along error pathChris Wilson
2012-06-01sna/io: Free the heap clip boxes on error pathsChris Wilson
2012-05-17sna/io: Assert that we do not replace a bo->flush objectChris Wilson
2012-05-13sna: Tweak usage of kgem_bo_can_map vs kgem_bo_mappedChris Wilson
2012-05-08sna: Force remapping for IO transferChris Wilson
2012-05-08sna: Only avoid ring switching for indirect uploadsChris Wilson
2012-05-03sna: Debug option to force particular upload/download pathsChris Wilson
2012-05-03sna: Improve handling of inplace IO for large transfersChris Wilson
2012-04-28sna: Micro-optimise common case of checking a single fenced boChris Wilson
2012-04-04sna: Only engage the GPU detiler for multiple rowsChris Wilson
2012-03-21sna: Fallback to inplace upload if forced to tile the indirect replacementChris Wilson
2012-02-04sna: Apply redirection for the render copy into large pixmapsChris Wilson
2012-01-31sna: Split the tiling limits between upload and copyingChris Wilson
2012-01-31sna: Check that the intermediate IO buffer can also be used for blittingChris Wilson
2012-01-29sna: Limit the tile size for uploading into large pixmapsChris Wilson
2012-01-29sna: Allow ridiculously large bo, up to half the total GATTChris Wilson
2012-01-26sna: Prevent mapping through the GTT for large boChris Wilson
2012-01-18sna: Almagamate writes based on the total number of bytes writtenChris Wilson
2012-01-18sna: Debug uploadsChris Wilson
2012-01-17sna: Restore orginal shadow pointer before uploading CPU damageChris Wilson
2012-01-17sna: Add a render ring detiling read pathChris Wilson
2012-01-15sna: Use indirect uploads rather than teardown existing CPU mapsChris Wilson
2012-01-15sna: Prefer read-boxes inplace againChris Wilson
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-29 11:20:02 +0000