- 1535b75 nv50/ir/tgsi: Exclude local declarations from function prototypes. by Francisco Jerez · 12 years ago
- 9b563ef nv50/ir/opt: try to make use of SUCLAMP addend by Christoph Bumiller · 12 years ago
- a788be1 nv50/ir: don't assert on type in Modifier.applyTo if it is 0 by Christoph Bumiller · 12 years ago
- c3a5bc0 nv50/ir: add support for barriers by Christoph Bumiller · 12 years ago
- a0a2519 nv50/ir/tgsi: add support for atomics by Christoph Bumiller · 12 years ago
- c2dfcd7 nv50/ir/tgsi: handle TGSI_OPCODE_LOAD,STORE by Christoph Bumiller · 12 years ago
- d105b3d nvc0/ir: don't replace load from input in COMPUTE progs with VFETCH by Christoph Bumiller · 12 years ago
- 4506ed2 nvc0/ir: implement lowering of surface ops for nve4 by Christoph Bumiller · 12 years ago
- 8ac68b0 nvc0/ir: add formatted surface load lib code, move to extra header by Christoph Bumiller · 12 years ago
- ce1951d nv50/ir: extend moveSources for delta < 0 by Christoph Bumiller · 12 years ago
- c0fc346 nvc0/ir: lower atomics in s[] by Christoph Bumiller · 12 years ago
- 9c19677 nvc0/ir/emit: implement INSBF, EXTBF, PERMT and ATOM by Christoph Bumiller · 12 years ago
- c8f0c43 nv50/ir/emit: handle OP_ATOM by Christoph Bumiller · 12 years ago
- d6c95f6 nvc0/ir/target: some ops can't be predicated, e.g. CALL by Christoph Bumiller · 12 years ago
- 1ed507c nv50/ir/opt: CALLs cannot load by Christoph Bumiller · 12 years ago
- c893b94 nv50/ir: add support for indirect BRA,CALL by Christoph Bumiller · 12 years ago
- efe5507 nvc0/ir/emit: implement move to and logic ops on predicates by Christoph Bumiller · 12 years ago
- ce7610f nvc0/ir/emit: implement surface related ops by Christoph Bumiller · 12 years ago
- 3741b7d nv50/ir: initialize CodeEmitters' specialized target fields by Christoph Bumiller · 12 years ago
- b0fc2f1 nv50/ir/opt: make optimization aware of atomics, barriers, surface ops by Christoph Bumiller · 12 years ago
- 22b762f nv50/ir: add various new OPs that will be needed for compute by Christoph Bumiller · 12 years ago
- c82714c nv50/ir: Rename "mkLoad" to "mkLoadv" for consistency. by Francisco Jerez · 12 years ago
- cc30ce8 nv50/ir: fix comparison of system values by Christoph Bumiller · 12 years ago
- 4ddfdce nv50/ir/tgsi: Translate grid-related system parameters. by Francisco Jerez · 13 years ago
- 8446c31 nv50/ir/tgsi: Accept COMPUTE programs. by Francisco Jerez · 13 years ago
- e9294e1 nv50/ir/ra: make sure all used function inputs get assigned a reg by Christoph Bumiller · 12 years ago
- ee431b1 nv50/ir/ra: also add pre-existing MERGE,SPLIT to constraint list by Christoph Bumiller · 12 years ago
- f1dfa41 nv50/ir/ra: fix confusion with conditional RegisterSet::occupy by Christoph Bumiller · 12 years ago
- d995f44 nv50/ir/ra: swap copyCompound args if src is compound and dst isn't by Christoph Bumiller · 12 years ago
- 95ad9bc nv50/ir/ra: Fix maxGPR calculation for programs with multiple functions. by Francisco Jerez · 12 years ago
- ca04e71 nv50/ir/ra: Fix traversal before the beginning of the active list in buildRIG. by Francisco Jerez · 12 years ago
- fe17d8a nv50/ir/ra: Fix RegisterSet::occupy(const Value *v). by Francisco Jerez · 12 years ago
- 49ded0e nv50/ir/ra: Fix argument const-ness in RegisterSet::idToUnits and idToBytes by Francisco Jerez · 12 years ago
- 5959d42 nv50/ir/opt: Fix tryPropagateBranch for BBs with several exit branches. by Francisco Jerez · 12 years ago
- 572bf83 nv50/ir: Clean up references to function values before destroying them. by Francisco Jerez · 12 years ago
- 12f65e3 nouveau: Bail out from nouveau_fence_wait if flushing the pushbuf fails. by Francisco Jerez · 13 years ago
- 543d032 mesa: Use correct functions for enum conversion. by Vinson Lee · 12 years ago
- 6173cc1 freedreno: gallium driver for adreno by Rob Clark · 12 years ago
- 44a8e51 d3d1x: Remove. by José Fonseca · 12 years ago
- 7db60f0 nv50: Remove nv0_ir_from_sm4.* by José Fonseca · 12 years ago
- 5c41d1c gallivm: clean up passing derivatives around by Roland Scheidegger · 12 years ago
- b7262ac i965: Fix typo in doxygen hyperlink by Chad Versace · 12 years ago
- 11b8df0 mesa: Reduce memory usage for reg alloc with many graph nodes (part 2). by Eric Anholt · 12 years ago
- 6aa3afb mesa: Reduce the memory usage for reg alloc with many graph nodes (part 1) by Eric Anholt · 12 years ago
- 5daf867 i965/fs: Improve CSE performance by expiring some available expressions. by Eric Anholt · 12 years ago
- f179f41 i965/fs: Improve live variables calculation performance. by Eric Anholt · 12 years ago
- 4dc7e6d i965/fs: Also do the gen4 SEND dependency workaround against other SENDs. by Eric Anholt · 12 years ago
- 4c1fdae i965/fs: Switch to using sampler LD messages for uniform pull constants. by Eric Anholt · 12 years ago
- 1323772 i965/fs: Fix broken rendering in large shaders with UBO loads. by Eric Anholt · 12 years ago
- c588cd2 i965/fs: Add a comment about about an implementation detail. by Eric Anholt · 12 years ago
- f10f5e4 i965/fs: Fix register allocation for uniform pull constants in 16-wide. by Eric Anholt · 12 years ago
- f09a8e1 intel: Remove some unused debug flags. by Eric Anholt · 12 years ago
- 7295fad draw/gs: Correctly iterate the emitted primitives by Zack Rusin · 12 years ago
- e5406f7 tgsi/exec: Correctly reset NumOutputs before parsing the shader by Zack Rusin · 12 years ago
- 9060c83 draw/llvm: another quick hack for drawing with no position output by Roland Scheidegger · 12 years ago
- ef17cc9 softpipe: don't use samplers with prebaked sampler and sampler_view state by Roland Scheidegger · 12 years ago
- f33c744 tgsi: emit code for SVIEWINFO and SAMPLE_I by Roland Scheidegger · 12 years ago
- 7b3a0bb tgsi: fix wrong reg used for unit for TGSI_OPCODE_TXF by Roland Scheidegger · 12 years ago
- a067696 r600g/llvm: Fix build by Tom Stellard · 12 years ago
- e4e655f r600g: add debug options disabling various copy-buffer-related features by Marek Olšák · 12 years ago
- 4b69c1a mesa: don't allocate a texture if width or height is 0 in CopyTexImage by Marek Olšák · 12 years ago
- 68ed4c9 gallium/util: attempt to fix blitting multisample texture arrays by Marek Olšák · 12 years ago
- 52efa01 r600g: allocate FMASK right after the texture, so that it's aligned with it by Marek Olšák · 12 years ago
- 2c339f8 r600g: remove r600.h, move the stuff elsewhere (mostly to r600_pipe.h) by Marek Olšák · 12 years ago
- ec7d775 r600g: remove r600_hw_context_priv.h, move the stuff to r600_pipe.h by Marek Olšák · 12 years ago
- 1724ef8 r600g: remove deprecated state management code by Marek Olšák · 12 years ago
- 65cbf89 r600g: atomize pixel shader by Marek Olšák · 12 years ago
- 63042af r600g: atomize vertex shader by Marek Olšák · 12 years ago
- 167263e r600g: inline r600_pipe_shader function by Marek Olšák · 12 years ago
- 65b2a44 r600g: dump vertex elements state along with the fetch shader by Marek Olšák · 12 years ago
- 3f0a51d gallium/util: dump instance_divisor by Marek Olšák · 12 years ago
- 3832059 r600g: remove bytecode dumping by Marek Olšák · 12 years ago
- 4bf0ebd r600g: use a single env var R600_DEBUG, disable bytecode dumping by Marek Olšák · 12 years ago
- 2ca73bc r600g: cleanup #include recursion between r600_pipe.h and evergreen_compute.h by Marek Olšák · 12 years ago
- 43d3e0c r600g: don't check for R600_ENABLE_S3TC env var by Marek Olšák · 12 years ago
- b21a9d4 glapi/gen: Remove duplicate PYTHON_FLAGS by Stefan Brüns · 12 years ago
- 89559c5 i965: Link i965_dri.so with C++ linker. by Frank Henigman · 12 years ago
- ba588dd gallium/util: Correct shift value for TSC feature detection. by Maxence Le Doré · 12 years ago
- 07f2dee configure.ac: Build dricommon for DRI gallium drivers by Matt Turner · 12 years ago
- 7de78ce5 configure.ac: Remove redundant checks of enable_dri. by Matt Turner · 12 years ago
- 79a0977 mesa: Allow ETC2/EAC formats with ARB_ES3_compatibility. by Matt Turner · 12 years ago
- 1662178 i915g: Use PIPE_FLUSH_END_OF_FRAME to trigger throttling by Stéphane Marchesin · 12 years ago
- d815e8a i915g: Update TODO by Stéphane Marchesin · 12 years ago
- 728240b docs: document another Viewperf bug by Brian Paul · 12 years ago
- 17f1cb1 dri/nouveau: fix crash in nouveau_flush by Jan de Groot · 12 years ago
- 057c46d draw: add const qualifier to silence compiler warning by Brian Paul · 12 years ago
- 9915636 llvmpipe: remove the power of two sizeof(struct cmd_block) assertion by Brian Paul · 12 years ago
- c2665aa vbo: fix crash found with shared display lists by Brian Paul · 12 years ago
- 5984a91 mesa: fix glGetInteger*(GL_SAMPLER_BINDING). by Alan Hourihane · 12 years ago
- eddf33f radeon/llvm: document LLVM commit by Christian König · 12 years ago
- a7a8995 radeon/llvm: enable LICM and DCE pass v2 by Christian König · 12 years ago
- e4188ee radeonsi: add LLVMNoUnwindAttribute to intrinsic by Christian König · 12 years ago
- 0666ffd radeonsi: rework input interpolation by Christian König · 12 years ago
- c497321 radeonsi: remove SI.vs.load.buffer.index by Christian König · 12 years ago
- 55fe5cc radeon/llvm: make SGPRs proper function arguments v2 by Christian König · 12 years ago
- b8f4ca3 radeon/llvm: replace shader type intrinsic with function attribute by Christian König · 12 years ago
- de80e56 radeonsi: switch to v*i8 for resources and samplers v2 by Christian König · 12 years ago
- 2cb5483 r600g/llvm: Update CONSTANT_BUFFER address space definition by Christian König · 12 years ago
- 2532147 draw/llvm: fix inputs to the geometry shader by Zack Rusin · 12 years ago
- 8c74380 draw: use geometry shader info in clip_init_state if appropriate by Bryan Cain · 12 years ago