summaryrefslogtreecommitdiffstats
path: root/src
Commit message (Collapse)AuthorAgeFilesLines
* slang: Handle OOM condition in new_instruction().Michal Krol2009-11-101-20/+81
|
* st/xorg: remove deprecated rendering codeZack Rusin2009-11-093-67/+0
|
* st/xorg: fix composite batchingZack Rusin2009-11-093-5/+18
| | | | quite a large performance optimization (text demo from 1.6fps to 9fps)
* r600/r700: typo, fix mask of DB_ALPHA_TO_MASKJerome Glisse2009-11-091-3/+3
|
* r600: rework DB render setupAlex Deucher2009-11-094-42/+73
| | | | | | | - consolidate DB render setup - only enable perfect ZPASS counts and cull disable when OQ is active - enable early Z
* r600: don't emit htile regsAlex Deucher2009-11-091-4/+2
| | | | | | These are needed for HiZ which is not currently used and the _BASE reg requires a reloc which is not currently supported in the drm.
* r600: add missing ZPASS setup bits for r7xx+Alex Deucher2009-11-092-0/+6
|
* llvmpipe: Ensure stack variables in unit tests are properly aligned.José Fonseca2009-11-093-12/+15
|
* nv50: clarify data for method 0x121cChristoph Bumiller2009-11-091-5/+6
|
* r300g: Fix up SW TCL rendering functions.Corbin Simpson2009-11-082-20/+53
| | | | They don't work, but at least they're clean now.
* r300g: Protect against possibly missing Draw pointer.Corbin Simpson2009-11-081-18/+29
| | | | Part of the SW TCL revival.
* r300g: Unify context names for counts.Corbin Simpson2009-11-086-14/+19
| | | | From the SW TCL fixups.
* r300g: Enable PSC/RS dump with new debugging flags.Corbin Simpson2009-11-081-12/+16
|
* r300g: Fix is_buffer_referenced.Corbin Simpson2009-11-081-2/+5
|
* r300g: Fix build error on old compilers.Corbin Simpson2009-11-081-3/+3
| | | | This dead code was still getting compiled, causing a bad ref in the lib.
* r300g: Organize inlined state.Corbin Simpson2009-11-071-36/+36
|
* r300g: DCE.Corbin Simpson2009-11-072-27/+2
| | | | This must never have been called before; it's completely wrong.
* r300g: Minor code cleanup to avoid confusion.Corbin Simpson2009-11-071-2/+1
|
* r300g: Remove do-nothing functions.Corbin Simpson2009-11-071-12/+0
|
* r300g: Remove faulty assert.Corbin Simpson2009-11-071-3/+1
|
* Merge branch 'r300g-vbo'Corbin Simpson2009-11-0713-113/+446
|\ | | | | | | | | | | This is an experimental HW TCL fastpath for r300g. It should run alright. Thanks to osiris for making this possible.
| * r300g: Be more verbose in what's killing us WRT vert formats.Corbin Simpson2009-11-071-4/+12
| |
| * r300g: Comments.Corbin Simpson2009-11-072-6/+11
| |
| * r300g: Don't assert on oversized VBOs, just return FALSE.Corbin Simpson2009-11-071-4/+12
| |
| * r300g: Moar vbo cleanup.Corbin Simpson2009-11-071-8/+12
| |
| * r300g: s/false/FALSE/Corbin Simpson2009-11-072-9/+9
| | | | | | | | Also s/true/TRUE/
| * r300g: Clean up indexbuf render, switch to RELOC macro.Corbin Simpson2009-11-071-15/+17
| |
| * r300g: Clean up r300_setup_vertex_buffers.Corbin Simpson2009-11-071-15/+13
| |
| * r300g: Don't pass hw_prim around in the context.Corbin Simpson2009-11-075-81/+74
| | | | | | | | And some other fixes.
| * r300g: Use common state funcs for translating vert formats.Corbin Simpson2009-11-071-72/+6
| |
| * r300g: don't hang GPU on misbehaving appsMaciej Cencora2009-11-071-0/+6
| |
| * r300g: VBOs WIPMaciej Cencora2009-11-0710-109/+477
| |
| * r300g: add missing flushMaciej Cencora2009-11-071-0/+2
| |
| * r300g: enable CS dumpingMaciej Cencora2009-11-071-2/+2
| |
| * r300g: move vborender context function to seperate fileMaciej Cencora2009-11-072-1/+6
| | | | | | | | | | | | r300g: Un-migrate r300_draw_render. It'll make maintaining the SW TCL path easier.
* | i915g: Fix comment in is buffer referencedJakob Bornecrantz2009-11-071-7/+3
|/
* mesa: move code after declbrian2009-11-071-1/+2
| | | | Fixes bug 24967.
* nv50: enable all 32 threads of a warpChristoph Bumiller2009-11-071-1/+3
| | | | | This should be the default setting. See also 7d967b9b7c08aea2a471c5bf6aced8bfafdae874.
* i965: Use Compr4 instruction compression mode on G4X and newer.Eric Anholt2009-11-063-17/+29
| | | | | | | No statistically significant performance difference at n=3 with either openarena or my GL demo, but cutting program size seems like a good thing to be doing for the hypothetical app that has a working set near icache size.
* i965: Share min/max between brw_wm_emit.c and brw_wm_glsl.cEric Anholt2009-11-063-60/+72
|
* i965: Share emit_fb_write() between brw_wm_emit.c and brw_wm_glsl.cEric Anholt2009-11-064-127/+40
| | | | This should fix issues with antialiased lines in GLSL.
* i965: Share most of the WM functions between brw_wm_glsl.c and brw_wm_emit.cEric Anholt2009-11-063-297/+109
| | | | | The PINTERP code should be faster for brw_wm_glsl.c now since brw_wm_emit.c's had been improved, and pixel_w should no longer stomp on a neighbor to dst.
* i965: Share math functions between brw_wm_glsl.c and brw_wm_emit.c.Eric Anholt2009-11-063-221/+111
|
* i965: Share the sop opcodes between brw_wm_glsl.c and brw_wm_emit.c.Eric Anholt2009-11-063-74/+29
|
* i965: Share OPCODE_MAD between brw_wm_glsl.c and brw_wm_emit.cEric Anholt2009-11-063-30/+13
|
* i965: Share the DP3, DP4, and DPH between brw_wm_glsl.c and brw_wm_emit.cEric Anholt2009-11-063-99/+33
|
* i965: Add generic GLSL code for unaliasing a 3-arg opcode, and share LRP code.Eric Anholt2009-11-063-45/+71
|
* i965: Use a normal alu1 emit for OPCODE_TRUNC.Eric Anholt2009-11-062-34/+2
|
* i965: Share basic ALU ops between brw_wm_glsl and brw_wm_emit.cEric Anholt2009-11-063-117/+38
| | | | | This drops support for get_src_reg_imm in these, but the prospect of getting brw_wm_pass*.c onto our GLSL path is well worth some temporary pain.
* i965: Collect GLSL src/dst regs up in generic code.Eric Anholt2009-11-062-7/+17
| | | | | | | | This matches brw_wm_emit.c, which we'll be using shortly. There's a possible penalty here in that we'll allocate registers for unused channels, since we aren't doing ref tracking like brw_wm_pass*.c does. However, my measurements on GM965 don't show any for either OA or UT2004 with the GLSL path forced.