summaryrefslogtreecommitdiffstats
path: root/src
Commit message (Collapse)AuthorAgeFilesLines
* freedreno/ir3: fix for load_front_face intrinsicRob Clark2016-03-281-1/+8
| | | | | | | Seems like trying to widen in the same instruction as the add.s does a non-sign-extending widen. Signed-off-by: Rob Clark <[email protected]>
* freedreno/ir3: fix compiler warnRob Clark2016-03-281-1/+1
| | | | Signed-off-by: Rob Clark <[email protected]>
* nvc0: make sure to disable fetches from previously-set VBOs when blittingIlia Mirkin2016-03-281-0/+2
| | | | | | | We disable the vertex attributes, but also disable the VBO fetch details as well, just in case. Not known to fix anything. Signed-off-by: Ilia Mirkin <[email protected]>
* nvc0: disable primitive restart and index bias during blitsIlia Mirkin2016-03-281-0/+11
| | | | | | | | | | | | | | | | Back in the dawn of time, we used to do immediate uploads for the vertex data, and all was well. However Maxwell dropped support for immediate vertex data, so we started feeding in a VBO (in all cases). But we forgot to disable some things that apply in such cases, specifically primitive restart and index bias. The latter was causing WoW and other Blizzard games trouble as they use a pattern where they draw with a base vertex (aka index bias), followed by texture uploads (aka blits, internally). Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=91526 Cc: "11.1 11.2" <[email protected]> Signed-off-by: Ilia Mirkin <[email protected]> Tested-by: Karol Herbst <[email protected]>
* nvc0/ir: fix picking of coordinates from tex instruction for textureGradIlia Mirkin2016-03-281-1/+11
| | | | | | | | | | | On Fermi, there's an argument in front of the coords that combines array and indirect handle, while on Kepler the array and the indirect handle are separate (and in front of the coords). We were previously only accounting for the array bit of it, if there were an indirect access it wouldn't be counted in the formula. Signed-off-by: Ilia Mirkin <[email protected]> Cc: "11.1 11.2" <[email protected]>
* nv50/ir: saturate depth writesIlia Mirkin2016-03-281-1/+4
| | | | | | | | | | | Apparently there's no post-FS clamping logic, so we have to do this by hand. The depth will never be outside of the 0..1 range, even on floating point zeta buffers, so this should be safe. Fixes dEQP-GLES3.functional.fbo.depth.*clamp.* which tests writing invalid values on various zeta buffer formats. Signed-off-by: Ilia Mirkin <[email protected]>
* gallium/util: fix up inaccurate behavior of util_framebuffer_state_equal (v2)Marek Olšák2016-03-281-5/+5
| | | | | | v2: move the nr_cbufs check above the loop Reviewed-by: Ilia Mirkin <[email protected]> (v1)
* st/mesa: only minify height if target != 1D array in st_finalize_textureMarek Olšák2016-03-281-1/+6
| | | | | | | | | | | The st_texture_object documentation says: "the number of 1D array layers will be in height0" We can't minify that. Spotted by luck. No app is known to hit this issue. Reviewed-by: Ilia Mirkin <[email protected]>
* mesa: optimize out the realloc from glCopyTexImagexD()Miklós Máté2016-03-271-0/+36
| | | | | | | | | | | v2: comment about the purpose of the code v3: also compare texFormat, add a perf debug message, formatting fixes Reviewed-by: Ian Romanick <[email protected]> Signed-off-by: Miklós Máté <[email protected]> Signed-off-by: Marek Olšák <[email protected]>
* st/mesa: fix handling the fallback textureMiklós Máté2016-03-271-3/+4
| | | | | | | | | | This fixes crash when post-processing is enabled in SW:KotOR. v2: fix const-ness v3: move assignment into the if() block Signed-off-by: Miklós Máté <[email protected]> Signed-off-by: Marek Olšák <[email protected]>
* st/mesa: enable GL_ATI_fragment_shaderMiklós Máté2016-03-271-0/+1
| | | | | Signed-off-by: Miklós Máté <[email protected]> Signed-off-by: Marek Olšák <[email protected]>
* st/mesa: implement GL_ATI_fragment_shaderMiklós Máté2016-03-2710-4/+1064
| | | | | | | | | | | | | v2: fix arithmetic for special opcodes, fix fog state, cleanup v3: simplify handling of special opcodes, fix rebinding with different textargets or fog equation, lots of formatting fixes v4: adapt to the compile early, fix later architecture, formatting fixes Signed-off-by: Miklós Máté <[email protected]> Signed-off-by: Marek Olšák <[email protected]>
* program: add ATI_fragment_shader to shader stages listMiklós Máté2016-03-271-0/+2
| | | | | Signed-off-by: Miklós Máté <[email protected]> Signed-off-by: Marek Olšák <[email protected]>
* mesa: optionally associate a gl_program to ATI_fragment_shaderMiklós Máté2016-03-275-2/+34
| | | | | | | | | the state tracker will use it Acked-by: Brian Paul <[email protected]> Reviewed-by: Ian Romanick <[email protected]> Signed-off-by: Miklós Máté <[email protected]> Signed-off-by: Marek Olšák <[email protected]>
* gallium/p_context.h: Make comment more readableEdward O'Callaghan2016-03-271-1/+1
| | | | | Signed-off-by: Edward O'Callaghan <[email protected]> Signed-off-by: Marek Olšák <[email protected]>
* mesa/st: Remove GLSLVersion clampingEdward O'Callaghan2016-03-271-10/+5
| | | | | | | While here, remove itermediate glsl_feature_level variable. Signed-off-by: Edward O'Callaghan <[email protected]> Signed-off-by: Marek Olšák <[email protected]>
* radeon/r600: Fix return type in failure branchEdward O'Callaghan2016-03-271-1/+1
| | | | | | | | Commit `d4e847ea` introduced a warning about making an integer from a pointer without a cast, fix it here. Signed-off-by: Edward O'Callaghan <[email protected]> Signed-off-by: Marek Olšák <[email protected]>
* radeon/r600_query.c: Minor style fixEdward O'Callaghan2016-03-271-1/+1
| | | | | | Signed-off-by: Edward O'Callaghan <[email protected]> Reviewed-by: Nicolai Hähnle <[email protected]> Signed-off-by: Marek Olšák <[email protected]>
* virgl: drop next shader property for now.Dave Airlie2016-03-261-0/+1
| | | | Signed-off-by: Dave Airlie <[email protected]>
* glsl: reduce buffer block duplicationTimothy Arceri2016-03-266-82/+57
| | | | | | | | | | | | | This reduces some of the craziness required for handling buffer blocks. The problem is each shader stage holds its own information about a block in memory, we were copying that information to a program wide list but the per stage information remained meaning when a binding was updated we needed to update all versions of it. This changes the per stage blocks to instead point to a single version of the block information in the program list. Acked-by: Kenneth Graunke <[email protected]>
* st/xa: emit sampler view declarations in shadersBrian Paul2016-03-251-0/+19
| | | | | | | Fixes recent regressions with the VMware gallium driver. Reviewed-by: Charmaine Lee <[email protected]> Tested-by: Charmaine Lee <[email protected]>
* swr: [rasterizer jitter] Fix MASKLOADD AVX prototype (float -> i32)Tim Rowley2016-03-251-1/+1
|
* swr: [rasterizer core] NUMA optimizations...Tim Rowley2016-03-255-65/+105
| | | | | - Affinitize hot-tile memory to specific NUMA nodes. - Only do BE work for macrotiles assoicated with the numa node
* swr: [rasterizer jitter] Fix logic bug for alpha-to-coverage.Tim Rowley2016-03-251-2/+11
|
* swr: [rasterizer core] Fix Compute workitem retirementTim Rowley2016-03-254-31/+22
|
* swr: [rasterizer core] Cleanup state ring arena after last draw that ↵Tim Rowley2016-03-253-2/+14
| | | | | | references it completes Rather than waiting for the API thread to re-use it.
* swr: [rasterizer jitter] add missing include for llvm jiteventsTim Rowley2016-03-251-0/+4
|
* swr: [rasterizer core] Reduce Arena blocksize to 128KB (from 1MB).Tim Rowley2016-03-251-3/+7
| | | | | With global allocator this doesn't seem to affect performance at all. Overall memory consumption drops by up to 85%.
* swr: [rasterizer core] One last pass at Arena optimizationsTim Rowley2016-03-251-15/+15
|
* swr: [rasterizer core] CachedArena optimizationsTim Rowley2016-03-253-210/+161
| | | | | | Reduce list traversal during Alloc and Free. Add ability to have multiple lists based on alloc size (not used for now)
* swr: [rasterizer jitter] support llvm-svnTim Rowley2016-03-256-12/+37
|
* swr: [rasterizer core] Globally cache allocated arena blocks for fast ↵Tim Rowley2016-03-258-46/+168
| | | | re-allocation.
* swr: [rasterizer] more arena workTim Rowley2016-03-255-10/+110
|
* swr: [rasterizer core] Add clipping against user clip distances in the ↵Tim Rowley2016-03-251-2/+12
| | | | NullPS backend.
* swr: [rasterizer core] Arena optimizations - preparing for global allocator.Tim Rowley2016-03-255-187/+131
|
* swr: [rasterizer core] Reset DrawContext arena at end of draw rather than ↵Tim Rowley2016-03-252-21/+4
| | | | | | | upon reclaim of DC Keeps overall memory consumption lower. Also, remove unused knobs.
* swr: [rasterizer core] Add clipping of user clip planes in clipper.Tim Rowley2016-03-251-0/+86
|
* swr: [rasterizer] Reduce max in-flight draws to 96 (by default)Tim Rowley2016-03-251-1/+1
|
* swr: [rasterizer] Fix run-time check assertsTim Rowley2016-03-252-8/+7
| | | | | One innocuous (uninitialized variable), and one not so innocuous (stack corruption).
* swr: [rasterizer jitter] signed immediate builderTim Rowley2016-03-252-0/+8
|
* swr: [rasterizer common] changes for cygwinTim Rowley2016-03-251-1/+4
|
* swr: [rasterizer] code styling and update copyrightsTim Rowley2016-03-2510-328/+328
|
* swr: [rasterizer core] Guard against enquing work to invalid hot tilesTim Rowley2016-03-251-0/+5
|
* swr: [rasterizer] Stop setting viewport size to larger than hottile arrayTim Rowley2016-03-251-0/+6
| | | | Guard against enquing work to invalid tiles
* swr: [rasterizer] Discard work + misc fixesTim Rowley2016-03-259-28/+119
|
* swr: [rasterizer] remove use of BYTE typeTim Rowley2016-03-2515-74/+65
|
* swr: [rasterizer core] Fix crash that can occur when switching contextsTim Rowley2016-03-253-1/+22
|
* swr: [rasterizer] remove unused knobTim Rowley2016-03-251-8/+0
|
* swr: [rasterizer core] subcontext reworkTim Rowley2016-03-257-52/+61
|
* swr: [rasterizer common] add _simd_s[rl]lv_epi32Tim Rowley2016-03-251-0/+115
|
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-28 01:39:59 +0000