summaryrefslogtreecommitdiff
path: root/src/sna/gen5_render.c
AgeCommit message (Expand)AuthorFilesLines
2012-04-02sna/gen3+: Fix sampling of borders around gradientsChris Wilson1-1/+1
2012-03-25sna/gen2+: Approximate expensive gradients when using imprecise renderingChris Wilson1-6/+18
2012-03-18sna/gen[345]: Convert CPU mappings to GTT for vertices on submitChris Wilson1-4/+21
2012-03-08sna/gen2+: Use the reduced operator from CompositeRectanglesChris Wilson1-18/+13
2012-03-08sna/gen2+: Prefer not to fallback if the source is busyChris Wilson1-26/+52
2012-03-07sna/gen5: Hook in the poor-man's linear gradientChris Wilson1-2/+130
2012-03-02sna: Pass usage hint for creating linear buffersChris Wilson1-2/+4
2012-03-01sna/gen5: Help the compiler avoid an uncached readChris Wilson1-4/+2
2012-02-25sna/gen3+: Keep the vertex buffer resident between batchesChris Wilson1-15/+41
2012-02-23sna/gen5 Refactor get_rectangles() to re-emit state after a flushChris Wilson1-72/+43
2012-02-23sna/gen3+: Force a batch flush when run out of CA vboChris Wilson1-0/+1
2012-02-22sna/gen4: Fix vertex flushing across batch flushingChris Wilson1-6/+4
2012-02-22sna/blt: Avoid clobbering the composite state if we fail to setup the BLTChris Wilson1-14/+1
2012-02-22sna/gen3+: Flush the vertices during vertex-finishChris Wilson1-14/+24
2012-02-21sna/gen3+: Re-emit composite state after flushing CA verticesChris Wilson1-9/+6
2012-02-21sna/gen3+: Only flush the vertices after checking for end-of-batchChris Wilson1-9/+15
2012-02-08sna/gen2+: Force upload rather than perform source transformations on the CPUChris Wilson1-1/+7
2012-02-07sna: Apply offsets correctly for partial src/dst in large copy boxesChris Wilson1-1/+2
2012-02-07sna: Set the damage for render->copy_boxes to NULL before useChris Wilson1-0/+1
2012-02-06sna: Use the proper sna_picture_is_solid() testChris Wilson1-9/+1
2012-02-06sna/gen2+: Exclude solids from being classed as requiring an uploadChris Wilson1-2/+5
2012-02-04sna: Apply redirection for the render copy into large pixmapsChris Wilson1-47/+89
2012-01-31sna/gen5: Always prefer to emit solid fills using the BLTChris Wilson1-10/+13
2012-01-29sna: Detect batch overflow and fallback rather an risk an ENOSPCChris Wilson1-9/+38
2012-01-29sna: Determine whether to use a partial proxy based on the pitchChris Wilson1-0/+1
2012-01-26sna/gen2+: Include being unattached in the list of source fallbacksChris Wilson1-1/+8
2012-01-26sna/gen2+: Do not force use of GPU if the target is simply clearedChris Wilson1-1/+1
2012-01-24sna: mark the pixmap as no longer clear after rendering videoChris Wilson1-0/+1
2012-01-20sna: Move the flush to the backendsChris Wilson1-10/+9
2012-01-16sna/gen[45]: clear the state tracker before setting the formatsChris Wilson1-10/+12
2012-01-16sna/gen[4567]: x1r5g5b5 is only a render target, not samplerChris Wilson1-44/+39
2012-01-15sna/gen5: Check reused source for validityChris Wilson1-8/+60
2012-01-14sna: Pass render operation to flush and avoid the implicit flush-on-batch-endChris Wilson1-28/+26
2012-01-14sna: Upload continuation vertices into mmapped buffersChris Wilson1-34/+113
2012-01-14sna: Be more lenient in not forcing to the GPU if the sources have CPU damageChris Wilson1-2/+2
2012-01-12sna: Reorder composite-done to destroy mask bo before source boChris Wilson1-5/+6
2012-01-12sna/video: Fix for changes in damage apiChris Wilson1-2/+4
2012-01-10sna/gen[23]: Tile render fill to oversized boChris Wilson1-3/+6
2011-12-23sna: Pass usage-hint to move-to-gpuChris Wilson1-2/+2
2011-12-23sna/gen2+: Reuse source channel for mask where possibleChris Wilson1-13/+54
2011-12-22sna: flatten source alphamapsChris Wilson1-0/+6
2011-12-22sna/gen2+: Prefer to use the CPU if we have a source alphamap and CPU picturesChris Wilson1-1/+7
2011-12-20sna: Implement extended fallback handling for src == dst copiesChris Wilson1-10/+5
2011-12-18sna/gen5: Tidy checking against hardcoded maximum 3D sizeChris Wilson1-19/+22
2011-12-18sna/gen2+: If we use the BLT to prepare the target, try using BLT for opChris Wilson1-0/+9
2011-12-18sna/gen5: If we need to flush the composite op, check to see if we can blitChris Wilson1-1/+12
2011-12-18sna/gen5+: First try a blt composite if the source/dest are too largeChris Wilson1-3/+13
2011-12-17sna/gen4+: disable the blend unit for PictOpSrcChris Wilson1-1/+2
2011-12-17src/gen4+: Add support for depth 15 render copies/fillsChris Wilson1-1/+4
2011-12-10sna/gen5: Remove a redundant format checkChris Wilson1-5/+1