summaryrefslogtreecommitdiff
path: root/src
AgeCommit message (Collapse)Author
2010-01-19r600: prepare for some code sharingMaciej Cencora
2010-01-19r300: check if blitting for given format is supported earlierMaciej Cencora
Prevents failing assertions at later stage.
2010-01-19r300: use nearest texture filtering for accelerated blitsMaciej Cencora
2010-01-19r300: fix Y coord flipping in accelerated blitsMaciej Cencora
2010-01-19radeon: use mesa provided _mesa_tex_target_to_face functionMaciej Cencora
2010-01-19r300: prepare for texcopy code sharingMaciej Cencora
2010-01-19radeon: add blit function to vtblMaciej Cencora
2010-01-19intel: Remove dead note_fence vtbl hook.Eric Anholt
2010-01-19i965: Improve the hashing of brw_state_cache keys to include the cache_id.Eric Anholt
No measurable difference on cairoperf.
2010-01-19i965: Remove obsolete comment about the state atoms.Eric Anholt
2010-01-19i965: Upload as many VS constants as possible through the push constants.Eric Anholt
The pull constants require sending out to an overworked shared unit and waiting for a response, while push constants are nicely loaded in for us at thread dispatch time. By putting things we access in every VS invocation there, ETQW performance improved by 2.5% +/- 1.6% (n=6).
2010-01-19i965: Allow for variable-sized auxdata in the state cache.Eric Anholt
Everything has been constant-sized until now, but constant buffer handling changes will make us want some additional variable sized array.
2010-01-19intel: Use the new DRI2 flush invalidate entrypoint to signal frame done.Eric Anholt
Previously for frame throttling we would wait on the first batch after a swap before emitting another swap, because we had no hook after a swap was emitted. This meant that if an app managed to squeeze everything it for a frame had into one batch, it would lock-step with the GPU. With the swapbuffers changes, we now have the entrypoint we want. This takes the WoW intro screen from 25% GPU idle and visibly jerky to 4-5% GPU idle and rather smooth. Other apps such as OpenArena have run into this problem as well.
2010-01-19Sun compilers now support some gcc __attribute__ valuesAlan Coopersmith
Sun cc 5.9 and later (__SUNPRO_C >= 0x590) support __attribute__ calls for aligned, always_inline, noinline, pure, const, and malloc. This commit includes updates to files that were regenerated by gl_XML.py after adding the __SUNPRO_C checks to it Signed-off-by: Alan Coopersmith <alan.coopersmith@sun.com> Signed-off-by: Brian Paul <brianp@vmware.com>
2010-01-19softpipe: remove redundant assignmentsBrian Paul
We initialized width/height/depth from pt->width0/height0/depth0 above.
2010-01-19r100/r200/r600: fix typo in 2b1d5ea4f0250a6a7fa312ced0a7af85e909381bAlex Deucher
2010-01-19r100/r200/r600: check if blitting for given format is supported earlierAlex Deucher
based on Maciej's r300 patch.
2010-01-19r100/r200: add blit support for ARGB4444Alex Deucher
2010-01-18r60: Add relocs for CB_TILE/FRAGAlex Deucher
as per 46dc6fd3ed5ef96cda53641a97bc68c3bc104a9f
2010-01-18docs: Clarify PIPE_TEXTURE_USAGE_DYNAMIC.Corbin Simpson
2010-01-18docs: Use proper XOR symbol.Corbin Simpson
2010-01-18r100: add blit supportAlex Deucher
Only enabled with KMS.
2010-01-18r200: add blit supportAlex Deucher
Only enabled with KMS.
2010-01-18docs: Spacing in TGSI formulae.Corbin Simpson
Some of those still look atrocious. :T
2010-01-18docs: Grammar and refs in Rasterizer.Corbin Simpson
2010-01-18docs: Cleanup Rasterizer a bit.Corbin Simpson
I'm getting better at this, I think.
2010-01-18docs: Fix terms and refs.Corbin Simpson
I fail at Sphinx-style ReST.
2010-01-18docs: Slowly keep fleshing out more info.Corbin Simpson
2010-01-18docs: PIPE_TEXTURE_USAGE info.Corbin Simpson
From IRC with Jakob.
2010-01-18i965: Clean up constbuf handling by splitting reladdr/non-reladdr loads.Eric Anholt
The codepaths in the function were almost entirely different.
2010-01-18i965: Only set up the stack register if it's going to get used.Eric Anholt
2010-01-18i965: Fix loads of non-relative-addr constants after a reladdr load.Eric Anholt
Fixes piglit vp-arl-constant-array-huge-overwritten.
2010-01-18nv50: fix constant vtxattr methodsChristoph Bumiller
This function was untested, sorry.
2010-01-18nv50: make instanced drawing work with edge flagsChristoph Bumiller
And fix some obvious mistakes introduced in the previous instancing commit.
2010-01-18nv50: cannot exit shaders on a control flow instructionChristoph Bumiller
Fixes lockup triggered by this ingenious shader: 1: CALL :3 2: END 3: BGNSUB ...
2010-01-18nv50: fix nv50_program->immd memory leakMarcin Slusarz
2010-01-18tgsi: Fix behaviour of dimension index.Michal Krol
The dimension index always addresses the second-dimension axis.
2010-01-18tgsi: Allow TEMPORARY registers as indirect address into source operands.Michal Krol
2010-01-18tgsi: Add ureg_DECL_immediate_block_uint().Michal Krol
Allows declaring a contiguous block of immediates. Useful for relative indexing.
2010-01-18glsl: remove __inline directiveBrian Paul
It makes no difference with gcc -O3, for example.
2010-01-18st/mesa: updated comments and whitespaceBrian Paul
2010-01-18st/mesa: fix memory leak in st_translate_mesa_programMarcin Slusarz
Signed-off-by: Brian Paul <brianp@vmware.com>
2010-01-18r600: fix some warningsAlex Deucher
2010-01-18r600: Update default state size to account for the new relocationJerome Glisse
the new relocation for CB_COLOR0_FRAG & CB_COLOR0_TILE add 4 dwords to the default command stream. Increase the prediction default size to take this into account
2010-01-18r6xx/r7xx: emit relocation for FRAG & TILE bufferJerome Glisse
FRAG & TILE buffer are unused but still they need to be associated with a valid relocation so that userspace can't try to abuse them to overwritte GART and then try to write anywhere in system memory.
2010-01-18r600: fix shadow_ambient shaderAndre Maasikas
rtype enums are different, DST_REG_OUTPUT got SRC_REG_CONSTANT in some shaders and produced invalid output/hang as TEX output is temp register always set out src to SRC_REG_TEMPORARY
2010-01-18radeong: Don't allocate HW BOs for constantbufs.Corbin Simpson
We have broken 1000 FPS. Hell yes. Heavily inspired by Marek's patch, but using pipebuffer instead of a roll-your-own malloc.
2010-01-18r300g: fix polygon offsetMarek Olšák
As per classic r300. Not sure why glean/polygonOffset still fails, but we do emit the same register values as in classic.
2010-01-18r300g: fix vertex data swizzleMarek Olšák
2010-01-18r300g: do not align compressed textures to a tile sizeMarek Olšák
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-09 17:30:30 +0000