summaryrefslogtreecommitdiff
path: root/src/sna/kgem.c
AgeCommit message (Expand)Author
2012-12-20sna/gen4+: Amalgamate all the gen4-7 vertex buffer emissionChris Wilson
2012-12-20sna: Ignore throttling during vertex closeChris Wilson
2012-12-17sna: Untangle the confusion of caching large LLC boChris Wilson
2012-12-17sna: Promote pinned-batches to run-time detectionChris Wilson
2012-12-17sna: Limit the default upload buffer size to half the cpu cacheChris Wilson
2012-12-16sna: Enable support for opting out of the kernel CS workaroundChris Wilson
2012-12-16sna: Try to reuse pinned batches by inspecting the kernel busy statusChris Wilson
2012-12-16sna: Precompute the base set of batch-flagsChris Wilson
2012-12-16sna: Only flush at the low fence wm if idleChris Wilson
2012-12-16sna/gen6+: Keep the bo on its current ringChris Wilson
2012-12-14sna: Reduce fence watermarksChris Wilson
2012-12-13sna/gen2: Align surface sizes to an even tileChris Wilson
2012-12-13sna: Fix typo for 830/845 genChris Wilson
2012-12-12sna: Improve the initialisation failure path for pinned batchesChris Wilson
2012-12-12sna: Fix the error path in kgem_init_pinned_batches() to use the right iterChris Wilson
2012-12-12sna: Pin some batches to avoid CS incoherence on 830/845Chris Wilson
2012-12-10sna: Avoid reusing the same 'busy' bit for two different meanings.Chris Wilson
2012-12-10sna: Compromise and only flush a split batch if writing to scanoutChris Wilson
2012-12-10sna: Immediately flush a split batchChris Wilson
2012-12-09sna: Replace remaining kgem_is_idle() with kgem_ring_is_idle()Chris Wilson
2012-12-08sna: Flush upon change of target if GPU is idleChris Wilson
2012-12-07sna: Only inspect the target ring for busynessChris Wilson
2012-12-07sna: Only flush before adding fresh surfaces to the batchChris Wilson
2012-12-07sna: Only flush at the low apeture watermark if idleChris Wilson
2012-12-07sna: Mark proxies as dirty on first relocationChris Wilson
2012-12-05sna: Assume that future hardware only gets more flexibleChris Wilson
2012-11-30Convert generation counter to octalChris Wilson
2012-11-30sna: Prevent gen4 from rendering to I915_TILING_YChris Wilson
2012-11-30sna: Increase tiling alignment to an even tileChris Wilson
2012-11-26sna: Use a single execobject flag to mark read/write domainsChris Wilson
2012-11-21sna: Remove the kgem_bo_is_mappable refcnt assertion from freed pathsChris Wilson
2012-11-21sna: Add a few refcnt assertionsChris Wilson
2012-11-10sna: Fix use of uninitialised value in DBGChris Wilson
2012-11-10sna: Specify read/write domains for no-relocation fastpathChris Wilson
2012-11-10sna: Allow snooped buffers to be retained (and reused) between batchesChris Wilson
2012-11-09sna: Mark no-reloc write buffersChris Wilson
2012-11-08sna: Experiment with using reloc.handle as an index into the execbufferChris Wilson
2012-11-08sna: Set the known offset for the batch as wellChris Wilson
2012-11-08sna: Support a fast no relocation changed pathChris Wilson
2012-11-07sna: Abandon kernels that do not support execbuffer2Chris Wilson
2012-10-23sna: Beware 16-bit overflow when computing sample areasChris Wilson
2012-10-17sna: secure batches accepted upstream, so simply use runtime detectionChris Wilson
2012-10-17sna: Enable support for SECURE batch buffersChris Wilson
2012-10-11sna: Limit available space for gen2Chris Wilson
2012-10-11sna: Use high/low watermarks for fenced aperture countingChris Wilson
2012-10-09sna: Check the map exists before trying to release itChris Wilson
2012-10-07sna: Only reduce the maximum batch size for old kernelsChris Wilson
2012-10-05sna: Do not create an unsnooped CPU mapping for readbacksChris Wilson
2012-10-04sna/gen2: Prevent using the GTT maps with I915_TILING_Y on 855gmChris Wilson
2012-10-03sna: Protect against undefined O_CLOEXECChris Wilson
generated by cgit v1.2.3 (git 2.25.1) at 2025-01-26 20:25:19 +0000