summaryrefslogtreecommitdiff
AgeCommit message (Expand)AuthorFilesLines
2012-07-19sna: Re-register the SHM funcs every server generationChris Wilson3-13/+13
2012-07-18i810: DRI is not dependent upon XAAChris Wilson2-5/+3
2012-07-18sna/gen4+: Drop unsupported source formatsChris Wilson4-16/+0
2012-07-18sna/dri: Allow DRI2 to be loaded even if we are wedgedChris Wilson1-2/+1
2012-07-18sna/gen6: Micro-optimise render copy emissionChris Wilson3-344/+331
2012-07-18sna/gen7: Micro-optimise render copy emissionChris Wilson2-314/+284
2012-07-18sna: Enable runtime detection of set-cacheing ioctlChris Wilson3-43/+23
2012-07-18sna/trapezoids: Only reduce bounded operators to a single passChris Wilson1-19/+31
2012-07-18sna/trapezoids: Use pixman from within the spans to reduce two-pass operationsChris Wilson1-49/+109
2012-07-18sna: Fix processing of the last fallback boxChris Wilson1-1/+1
2012-07-18sna: Add more DBG for fallback processingChris Wilson6-56/+53
2012-07-18sna: Reuse the snoopable cache more frequently for upload buffersChris Wilson1-98/+129
2012-07-18sna: Maintain a short-lived cache of snoopable CPU bo for older genChris Wilson2-39/+195
2012-07-17i810: Replace XAAGet.*ROP() with local tablesChris Wilson3-4/+45
2012-07-17i810: Split xaa routines from common acceleration methodsChris Wilson4-301/+326
2012-07-17sna: Allow wedged CopyPlane to operate inplace on the destinationChris Wilson1-1/+1
2012-07-17sna: Allow inplace copies for wedged CopyAreaChris Wilson1-1/+2
2012-07-17sna: Allow operation inplace to scanout whilst wedgedChris Wilson1-2/+2
2012-07-17sna: Tweak fast blt pathChris Wilson1-21/+18
2012-07-17sna: prefer fbBlt over pixman_bltChris Wilson1-28/+13
2012-07-17sna/gen7: Bump the number of pixel shader threads for IVB GT2Chris Wilson1-1/+1
2012-07-17sna/dri: Do not allow an exchange to take place on invalid buffersChris Wilson1-5/+19
2012-07-17sna: Rebalance choice of GPU vs CPU boChris Wilson1-36/+31
2012-07-17sna: Avoid the CPU bo readback for render pathsChris Wilson1-3/+0
2012-07-17sna: Catch the short-circuit path for clearing clear on move-to-gpu as wellChris Wilson1-1/+2
2012-07-17sna: Limit the use of snoopable buffers to read/write uploadsChris Wilson1-53/+59
2012-07-17sna: Only drop the clear flag when writing to the GPU pixmapChris Wilson1-10/+12
2012-07-17sna: Fix glyph DBG to include clip extents and actual glyph originChris Wilson1-6/+37
2012-07-17sna: Promote an undamaged pixmap to use the full GPUChris Wilson1-16/+7
2012-07-16sna: Share the pixmap migration decision with the BLT composite routinesChris Wilson4-185/+155
2012-07-16sna: Disable snoopable bo for gen4Chris Wilson2-5/+13
2012-07-16sna: Disable snoopable uplaod buffers for gen4Chris Wilson3-4/+25
2012-07-16sna: Fixup pixmap validation for sna_copy_area()Chris Wilson1-1/+15
2012-07-16Wrap defines to avoid redefinition warningsChris Wilson3-0/+20
2012-07-16sna/trapezoids: Fix inplace unaligned fills (on gen4)Chris Wilson1-1/+1
2012-07-16sna/trapezoids: Add some DBG to unaligned fillsChris Wilson1-4/+19
2012-07-16sna: Move the disabling of CPU bo for gen4 to the render unitChris Wilson2-6/+3
2012-07-16sna: Use set-cache-level to allocate snoopable upload buffersChris Wilson1-3/+40
2012-07-16sna: Add a couple of DBG options to control accelerated up/downloadsChris Wilson1-4/+7
2012-07-16sna: Discard and recreate the CPU buffer when busy during move-to-cpuChris Wilson1-12/+8
2012-07-16sna: Add a few DBG to show when CPU bos are being used for xferChris Wilson1-13/+31
2012-07-16sna: Disable the scanout flush when switch off via DPMSChris Wilson1-24/+30
2012-07-16intel: Don't use stdbool without declaring itChris Wilson1-1/+1
2012-07-15uxa: Remove Shadow hackChris Wilson11-415/+29
2012-07-15configure: version bump for 2.20.0 releaseChris Wilson2-1/+43
2012-07-15sna: Avoid creating a CPU bo for uploads if we already have a large GPU boChris Wilson1-0/+13
2012-07-15sna: Prefer uploads to be staged in snoopable boChris Wilson1-7/+19
2012-07-15sna: Simply reverse all the boxes if dx <= 0 and dy <= 0Chris Wilson1-11/+15
2012-07-15sna: Keep track of the base pointer for the reordered boxesChris Wilson1-4/+3
2012-07-14sna: Make sure we check for a busy CPU bo before declaring is-cpuChris Wilson1-2/+1