summaryrefslogtreecommitdiff
path: root/src/sna/gen4_render.c
AgeCommit message (Expand)Author
2012-12-04sna/gen4: Special case solids through the general vertex emitterChris Wilson
2012-12-04sna/gen4: Remove unused CC viewportChris Wilson
2012-12-04sna/gen4: Avoid emitting URB_FENCE across a cache-lineChris Wilson
2012-11-30sna: Unify gen4 acceleration againChris Wilson
2012-11-30Convert generation counter to octalChris Wilson
2012-11-25sna: Exploit the alpha-fixup of the BLT for texture format conversionsChris Wilson
2012-11-23sna/gen4: Revert changes to 965g[m]Chris Wilson
2012-11-23sna/gen4: Don't force a flush for the dirty target if the we do not read backChris Wilson
2012-11-23sna/gen4: Set composite op before testing for a BLT compatible opChris Wilson
2012-11-23sna/gen4: Pass the mask channel explicitly rather than through a dummy maskChris Wilson
2012-11-23sna/gen4: Reduce the flush before performing the CA passChris Wilson
2012-11-23sna/gen4: Update render fill routines to use the dummy maskChris Wilson
2012-11-23sna/gen4: Move the flush from inside the spans to emit_state()Chris Wilson
2012-11-23sna/gen4: Backport the more efficient composite box emittersChris Wilson
2012-11-23sna/gen4: Use a dummy white mask to avoid the flush w/a when compositingChris Wilson
2012-11-21sna/gen3+: Clear the render.vbo when replacing it for vertex uploadChris Wilson
2012-11-13sna/gen4: Tidy emission of opacity vertex attributeChris Wilson
2012-11-13sna/gen4: Do not prefer inplace non-rectilinear spansChris Wilson
2012-11-13sna/gen4: Always initialise redirectChris Wilson
2012-11-09sna/gen4: Only 965gm suffers the !snoop restrictionChris Wilson
2012-11-06sna/gen4: opacity spans requires the per-rectangle flush w/aChris Wilson
2012-11-06sna/gen4: Remove a couple of old, now redundant, w/a flushesChris Wilson
2012-11-06sna/gen4: Flush after pipelined pointer updates (inverted logic!)Chris Wilson
2012-11-02sna/gen4+: Prefer GPU spans if the destination is activeChris Wilson
2012-11-01sna: Try to reduce ping-pong migration for intermixed render/legacy code pathsChris Wilson
2012-10-18sna/gen4: Presume we need a flush upon state change similar to gen5+Chris Wilson
2012-09-13sna: Fix analysis of source extents for BLT compositeChris Wilson
2012-09-01sna/gen2+: Add the missing assertions in case the drawrect is invalidChris Wilson
2012-08-27Revert "sna: Cleanup composite redirection after substituting the BLT"Chris Wilson
2012-08-26sna: Cleanup composite redirection after substituting the BLTChris Wilson
2012-08-26sna/gen4+: Check for allocation failure for the clear solid boChris Wilson
2012-08-20sna: Trim a parameter from kgem_bo_mark_dirty() and add some assertionsChris Wilson
2012-08-20sna: Remove confusing is_cpu()Chris Wilson
2012-08-18sna: Avoid forcing an upload for an unblittable bo unless on a fallback pathChris Wilson
2012-08-11sna/gen2-5: Substitute an equivalent BLT composite operationChris Wilson
2012-08-04sna/gen4: Restore the w/a flush for fill/copy as wellChris Wilson
2012-08-04sna/gen4: Restore w/a flush for videoChris Wilson
2012-08-01sna/gen4: Flush not required between fill vertices, only nomaskcompositeChris Wilson
2012-08-01sna/gen6+: Reduce floats-per-vertex for spansChris Wilson
2012-08-01sna/gen4+: Implement an opacity shaderChris Wilson
2012-07-31sna/gen4: Tidy debugging codeChris Wilson
2012-07-30sna/gen4: Compile basic kernels at runtimeChris Wilson
2012-07-27sna/gen4: Move the common vertex_offset==0 check into the flush()Chris Wilson
2012-07-27sna/gen4: Further refinement to the GT allocationChris Wilson
2012-07-26sna/gen4: Tweak heuristics for render/blt usageChris Wilson
2012-07-26sna/gen4: Bump thread countsChris Wilson
2012-07-21sna: s/vmap/snoop/ since we use the flag more genericallyChris Wilson
2012-07-21sna: Only update a buffer when it becomes dirtyChris Wilson
2012-07-19sna/gen4: Hookup composite spansChris Wilson
2012-07-18sna/gen4+: Drop unsupported source formatsChris Wilson
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-26 01:22:50 +0000