| Commit message (Expand) | Author | Age | Files | Lines |
* | r600g: use HTILE allocator from SI | Marek Olšák | 2014-09-01 | 3 | -47/+23 |
* | r600g: set DB_DEPTH_SIZE.HEIGHT_TILE_MAX for EG/CM, inline other fields | Marek Olšák | 2014-09-01 | 1 | -9/+12 |
* | radeonsi: set DB_DEPTH_SIZE.HEIGHT_TILE_MAX, inline other fields | Marek Olšák | 2014-09-01 | 1 | -9/+8 |
* | r600g: Implement sm5 geometry shader instancing | Glenn Kennard | 2014-09-01 | 3 | -2/+14 |
* | glsl_to_tgsi: allocate and enlarge arrays for temporaries on demand | Marek Olšák | 2014-09-01 | 1 | -18/+33 |
* | gallium/pb_bufmgr_cache: limit the size of cache | Marek Olšák | 2014-09-01 | 4 | -8/+30 |
* | pipe-loader: use the correct screen index | Marek Olšák | 2014-09-01 | 1 | -2/+18 |
* | egl/dri2: use the correct screen index | Marek Olšák | 2014-09-01 | 2 | -10/+30 |
* | i965/fs: don't use ir->shadow_comparitor in emit_texture_* | Connor Abbott | 2014-09-01 | 2 | -7/+5 |
* | i965/fs: don't pass ir_variable * to emit_samplepos_setup() | Connor Abbott | 2014-09-01 | 3 | -5/+4 |
* | i965/fs: don't pass ir_variable * to emit_frontfacing_interpolation() | Connor Abbott | 2014-09-01 | 4 | -6/+6 |
* | i965: Fix GPU hangs when INTEL_DEBUG=no16 is set. | Kenneth Graunke | 2014-08-31 | 1 | -1/+2 |
* | mesa: fix make tarballs | Emil Velikov | 2014-09-01 | 1 | -1/+2 |
* | i965/vec4: Remove try_emit_saturate | Abdiel Janulgue | 2014-08-31 | 2 | -22/+0 |
* | i965/fs: Refactor try_emit_saturate | Abdiel Janulgue | 2014-08-31 | 1 | -15/+8 |
* | ir_to_mesa, glsl_to_tgsi: Remove try_emit_saturate | Abdiel Janulgue | 2014-08-31 | 2 | -99/+0 |
* | i965/vec4: Allow propagation of instructions with saturate flag to sel | Abdiel Janulgue | 2014-08-31 | 1 | -27/+58 |
* | i965/fs: Allow propagation of instructions with saturate flag to sel | Abdiel Janulgue | 2014-08-31 | 1 | -1/+17 |
* | glsl: Optimize clamp(x, b, 1.0), where b > 0.0 as max(saturate(x),b) | Abdiel Janulgue | 2014-08-31 | 1 | -0/+23 |
* | glsl: Optimize clamp(x, 0.0, b), where b < 1.0 as min(saturate(x),b) | Abdiel Janulgue | 2014-08-31 | 1 | -0/+39 |
* | glsl: Optimize clamp(x, 0, 1) as saturate(x) | Abdiel Janulgue | 2014-08-31 | 1 | -0/+36 |
* | glsl: Implement saturate as ir_unop_saturate | Abdiel Janulgue | 2014-08-31 | 1 | -5/+1 |
* | yi965/vec4: Add support for ir_unop_saturate | Abdiel Janulgue | 2014-08-31 | 1 | -0/+4 |
* | i965/fs: Add support for ir_unop_saturate | Abdiel Janulgue | 2014-08-31 | 2 | -0/+5 |
* | ir_to_mesa, glsl_to_tgsi: Add support for ir_unop_saturate | Abdiel Janulgue | 2014-08-31 | 2 | -0/+12 |
* | ir_to_mesa, glsl_to_tgsi: lower ir_unop_saturate | Abdiel Janulgue | 2014-08-31 | 2 | -2/+9 |
* | glsl: Add a pass to lower ir_unop_saturate to clamp(x, 0, 1) | Abdiel Janulgue | 2014-08-31 | 2 | -0/+30 |
* | glsl: Add constant evaluation of ir_unop_saturate | Abdiel Janulgue | 2014-08-31 | 1 | -0/+6 |
* | glsl: Add ir_unop_saturate | Abdiel Janulgue | 2014-08-31 | 3 | -0/+4 |
* | i965/vec4/fs: Count loops in shader debug | Abdiel Janulgue | 2014-08-31 | 2 | -4/+8 |
* | i965/vec4: inline generate_vec4_instruction() within generate_code() | Abdiel Janulgue | 2014-08-31 | 2 | -316/+296 |
* | i965: Add 2x MSAA support to Broadwell fast clear code. | Kenneth Graunke | 2014-08-31 | 1 | -0/+1 |
* | i965/vec4: Update register coalescing test. | Matt Turner | 2014-08-30 | 1 | -4/+1 |
* | i965: Use unreachable() to silence warning. | Matt Turner | 2014-08-30 | 1 | -2/+1 |
* | ilo: set INTEL_RELOC_GGTT only on GEN6 | Chia-I Wu | 2014-08-31 | 1 | -7/+17 |
* | ilo: fix bound check for 3DSTATE_URB_VS | Chia-I Wu | 2014-08-31 | 1 | -3/+3 |
* | ilo: replace cmd by dw0 in GPE | Chia-I Wu | 2014-08-31 | 2 | -167/+236 |
* | st/hgl: Move st_visual create/destroy into hgl state_tracker | Alexander von Gluck IV | 2014-08-30 | 4 | -100/+111 |
* | st/hgl: Move st_manager create/destroy into hgl state_tracker | Alexander von Gluck IV | 2014-08-30 | 3 | -29/+58 |
* | freedreno/ir3: fix potential null ptr deref | Rob Clark | 2014-08-30 | 1 | -1/+2 |
* | freedreno/ir3: add TXB | Rob Clark | 2014-08-30 | 1 | -0/+5 |
* | freedreno/ir3: detect scheduler fail | Rob Clark | 2014-08-30 | 3 | -4/+21 |
* | glsl: Use bit-flags image attributes and uint16_t for the image format | Ian Romanick | 2014-08-29 | 6 | -43/+42 |
* | glsl: Use a single bit for the dual-source blend index | Ian Romanick | 2014-08-29 | 1 | -5/+9 |
* | glsl: Eliminate ir_variable::data.atomic.buffer_index | Ian Romanick | 2014-08-29 | 5 | -6/+7 |
* | mesa: Delete ctx->GeometryProgram.Cache. | Kenneth Graunke | 2014-08-29 | 2 | -5/+0 |
* | gallivm: fix somewhat broken NaN behavior for exp2 | Roland Scheidegger | 2014-08-30 | 2 | -13/+25 |
* | softpipe: handle vertex texture sampling when using llvm for draw | Roland Scheidegger | 2014-08-30 | 9 | -36/+209 |
* | llvmpipe: (trivial) enable cube map arrays | Roland Scheidegger | 2014-08-30 | 1 | -1/+2 |
* | gallivm: handle cube map arrays for texture sampling | Roland Scheidegger | 2014-08-30 | 5 | -44/+107 |