Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | Merge remote branch 'origin/mesa_7_6_branch' | Eric Anholt | 2009-11-13 | 10 | -46/+81 |
|\ | |||||
| * | i965: Fix Ironlake shadow comparisons. | Eric Anholt | 2009-11-12 | 1 | -7/+17 |
| | | | | | | | | The cube map array index arg is always present. | ||||
| * | i965: Fix VBO last-valid-offset setup on Ironlake. | Eric Anholt | 2009-11-12 | 1 | -10/+3 |
| | | | | | | | | | | Instead of doing math based on the (broken for VBO && offset != 0) input->count number, just use the BO size. Fixes assertion failure in ETQW. | ||||
| * | i965: fix EXT_provoking_vertex support | Roland Scheidegger | 2009-11-11 | 8 | -29/+61 |
| | | | | | | | | | | | | | | | | This didn't work for quad/quadstrips at all, and for all other primitive types it only worked when they were unclipped. Fix up the former in gs stage (could probably do without these changes and instead set QuadsFollowProvokingVertexConvention to false), and the rest in clip stage. | ||||
* | | i965: Flag BRW_NEW_CONTEXT on some context state. | Eric Anholt | 2009-11-13 | 2 | -6/+6 |
| | | | | | | | | | | | | Fixing this is a prereq for avoiding flagging all state at new batch time. Eliminating that still causes problems, though (notably glean logicOp fails on my GM965). | ||||
* | | intel: Remove some dead context structure fields. | Eric Anholt | 2009-11-13 | 1 | -2/+0 |
| | | |||||
* | | i965: Remove an unused cache_item field. | Eric Anholt | 2009-11-13 | 3 | -3/+1 |
| | | |||||
* | | i965: Remove long dead structures for ffvertex_prog.c. | Eric Anholt | 2009-11-13 | 1 | -17/+0 |
| | | |||||
* | | i965: Use bo_map instead of subdata to upload the bits of constant buffer. | Eric Anholt | 2009-11-13 | 2 | -2/+26 |
| | | | | | | | | Saves CPU time, resulting in a 2.5% FPS win on ETQW. | ||||
* | | i965: Validate the number of URB entries selected for the VS. | Eric Anholt | 2009-11-13 | 1 | -4/+33 |
| | | |||||
* | | intel: When subdataing a busy buffer, use a temporary and blit in. | Eric Anholt | 2009-11-13 | 1 | -3/+16 |
| | | | | | | | | | | | | This cuts a massive number of waits in ET:QW, which uses a VBO ringbuffer. Unfortunately it doesn't BufferData when wrapping back to 0, so we can't be clever with tracking what's been initialized. | ||||
* | | i965: Clean up Ironlake sampler type definitions. | Eric Anholt | 2009-11-13 | 3 | -18/+10 |
| | | | | | | | | They're the same regardless of execution width for 8, 4x2, and 16. | ||||
* | | i965: Avoid moving the current value back into the accumulator for MAD. | Eric Anholt | 2009-11-13 | 1 | -1/+34 |
| | | | | | | | | | | This is a 2.9% (+/-.3%) performance win for my GL demo, which hits MAD sequences for matrix transforms. | ||||
* | | mesa: Improve the eliminate-move-use to work across multiple instructions. | Eric Anholt | 2009-11-13 | 1 | -41/+85 |
| | | | | | | | | | | | | This shaves more instructions off of the VS of my GL demo, but no performance difference this time at n=6. This also fixes a regression that was in this path, which is now piglit's glsl-vs-mov-after-deref. | ||||
* | | intel: Don't check for context pointer to be NULL during extension init | Ian Romanick | 2009-11-12 | 1 | -7/+6 |
| | | | | | | | | | | | | | | | | | | | | Thanks to Chia-I Wu's changes to the extension function infrastructure, we no longer have to tell the loader which extensions the driver might enable. This means that intelInitExtensions will never be called with a NULL context pointer. Remove all the NULL checks. Signed-off-by: Ian Romanick <ian.d.romanick@intel.com> Reviewed-by: Eric Anholt <eric@anholt.net> | ||||
* | | intel: Remove unused enable_imaging parameter to intelInitExtensions | Ian Romanick | 2009-11-12 | 3 | -6/+4 |
| | | |||||
* | | swrast: handle additional Z24 formats in read_depth_pixels() | Brian Paul | 2009-11-11 | 1 | -5/+18 |
| | | |||||
* | | r300, r300g: Add missing registers. | Corbin Simpson | 2009-11-11 | 1 | -0/+2 |
| | | |||||
* | | swrast: update renderbuffer format assertions | brian | 2009-11-10 | 1 | -3/+4 |
| | | |||||
* | | mesa: fix some begin/end render-to-texture logic | brian | 2009-11-10 | 1 | -21/+38 |
| | | | | | | | | | | | | | | | | | | Before, we weren't aggressive enough in checking for the start or end of render-to-texture. In particular, if only the ctx->ReadBuffer had texture attachments, we were treating that as a render-to-texture case. This fixes a regression from commit 75bdbdd90b15c8704d87ca195a364ff6a42edbb1 "intel: Don't validate in a texture image used as a render target." | ||||
* | | mesa: move check_begin/end_texture_render() calls | brian | 2009-11-10 | 1 | -9/+11 |
| | | |||||
* | | mesa: new vars: oldDrawFb, oldReadFb in _mesa_BindFramebufferEXT() | brian | 2009-11-10 | 1 | -3/+7 |
| | | |||||
* | | mesa: rename vars in _mesa_BindFramebufferEXT() | brian | 2009-11-10 | 1 | -22/+21 |
| | | |||||
* | | mesa: added comment for check_begin_texture_render() | brian | 2009-11-10 | 1 | -0/+5 |
| | | |||||
* | | Merge remote branch 'origin/mesa_7_6_branch' | Eric Anholt | 2009-11-10 | 3 | -8/+77 |
|\ \ | |/ | |||||
| * | i965: Fix VS constant buffer value loading. | Eric Anholt | 2009-11-10 | 1 | -1/+11 |
| | | | | | | | | | | | | | | | | | | | | Previously, we'd load linearly from ParameterValues[0] for the constants, though ParameterValues[1] may not equal ParameterValues[0] + 4. Additionally, the STATE_VAL type paramters didn't get updated. Fixes piglit vp-constant-array-huge.vpfp and ET:QW object locations. Bug #23226. | ||||
| * | i965: Unalias src/dst registers for SGE and friends. | Eric Anholt | 2009-11-10 | 1 | -19/+21 |
| | | | | | | | | | | | | | | Fixes piglit vp-sge-alias test, and the googleearth ground shader. \o/ Bug #22228 (cherry picked from commit 56ab92bad8f1d05bc22b8a8471d5aeb663f220de) | ||||
| * | i965: Allow use of PROGRAM_LOCAL constants in ARB_vp. | Eric Anholt | 2009-11-10 | 1 | -1/+1 |
| | | | | | | | | | | Fixes piglit arl.vp. (cherry picked from commit d52d78b4bcd6d4c0578f972c0b8ebac09e632196) | ||||
| * | r600: don't emit htile regs | Alex Deucher | 2009-11-09 | 1 | -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. | ||||
| * | prog parse: Handle GL_VERTEX_PROGRAM_ARB in glLoadProgramNV | Ian Romanick | 2009-11-07 | 1 | -1/+13 |
| | | |||||
| * | prog parse: Handle GL_VERTEX_PROGRAM_NV in glProgramStringARB | Ian Romanick | 2009-11-07 | 1 | -1/+23 |
| | | | | | | | | | | Handle both NV vertex programs and NV vertex state programs passed to glProgramStringARB. | ||||
| * | prog parse: Handle GL_FRAGMENT_PROGRAM_ARB in glLoadProgramNV | Ian Romanick | 2009-11-07 | 1 | -0/+15 |
| | | |||||
| * | prog parse: Handle GL_FRAGMENT_PROGRAM_NV in glProgramStringARB | Ian Romanick | 2009-11-07 | 1 | -5/+15 |
| | | |||||
* | | i965: avoid memsetting all the BRW_WM_MAX_INSN arrays for every compile. | Eric Anholt | 2009-11-10 | 4 | -4/+23 |
| | | | | | | | | | | | | | | | | | | For an app that's blowing out the state cache, like sauerbraten, the memset of the giant arrays ended up taking 11% of the CPU even when only a "few" of the entries got used. With this, the WM program compile drops back down to 1% of CPU time. Bug #24981 (bisected to BRW_WM_MAX_INSN increase). | ||||
* | | i965: Add a note explaining the data cache domain. | Eric Anholt | 2009-11-10 | 1 | -1/+4 |
| | | |||||
* | | i965: Unalias src/dst registers for SGE and friends. | Eric Anholt | 2009-11-10 | 1 | -19/+21 |
| | | | | | | | | | | | | Fixes piglit vp-sge-alias test, and the googleearth ground shader. \o/ Bug #22228 | ||||
* | | i965: Allow use of PROGRAM_LOCAL constants in ARB_vp. | Eric Anholt | 2009-11-10 | 1 | -1/+1 |
| | | | | | | | | Fixes piglit arl.vp. | ||||
* | | slang: Fix return value check. | Michal Krol | 2009-11-10 | 1 | -1/+1 |
| | | |||||
* | | slang: Check OOM conditions for alloc_node_storage(). | Michal Krol | 2009-11-10 | 1 | -4/+15 |
| | | |||||
* | | slang: Check return value from new_instruction(). | Michal Krol | 2009-11-10 | 1 | -1/+3 |
| | | |||||
* | | slang: Fix signed/unsigned int handling in _slang_free_temp(). | Michal Krol | 2009-11-10 | 1 | -2/+2 |
| | | |||||
* | | slang: Handle OOM condition in new_instruction(). | Michal Krol | 2009-11-10 | 1 | -20/+81 |
| | | |||||
* | | r600/r700: typo, fix mask of DB_ALPHA_TO_MASK | Jerome Glisse | 2009-11-09 | 1 | -3/+3 |
| | | |||||
* | | r600: rework DB render setup | Alex Deucher | 2009-11-09 | 4 | -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 regs | Alex Deucher | 2009-11-09 | 1 | -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 Deucher | 2009-11-09 | 2 | -0/+6 |
| | | |||||
* | | mesa: move code after decl | brian | 2009-11-07 | 1 | -1/+2 |
| | | | | | | | | Fixes bug 24967. | ||||
* | | i965: Use Compr4 instruction compression mode on G4X and newer. | Eric Anholt | 2009-11-06 | 3 | -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.c | Eric Anholt | 2009-11-06 | 3 | -60/+72 |
| | | |||||
* | | i965: Share emit_fb_write() between brw_wm_emit.c and brw_wm_glsl.c | Eric Anholt | 2009-11-06 | 4 | -127/+40 |
| | | | | | | | | This should fix issues with antialiased lines in GLSL. |