| Commit message (Expand) | Author | Age | Files | Lines |
* | i965: Skip update_texture_surface when the plane doesn't exist | Jordan Justen | 2016-06-24 | 3 | -29/+26 |
* | i965: Validate a few SEND-from-GRF requirements. | Kenneth Graunke | 2016-06-24 | 1 | -0/+18 |
* | i965: Delete send-from-GRF only opcodes from implied_mrf_writes(). | Kenneth Graunke | 2016-06-24 | 1 | -19/+0 |
* | i965: Drop unnecessary inst->base_mrf = -1 assignments. | Kenneth Graunke | 2016-06-24 | 2 | -16/+0 |
* | i965: Set fs_inst::base_mrf = -1 by default. | Kenneth Graunke | 2016-06-24 | 1 | -0/+1 |
* | i965: Drop unused return value from intel_finalize_mipmap_tree(). | Kenneth Graunke | 2016-06-24 | 2 | -7/+5 |
* | i965: Move contents of brw_tex.c into intel_tex_validate.c. | Kenneth Graunke | 2016-06-24 | 4 | -58/+20 |
* | radeonsi: fix fractional odd tessellation spacing for Polaris | Marek Olšák | 2016-06-24 | 4 | -1/+23 |
* | radeonsi: set some VGT context registers on SI-CI | Marek Olšák | 2016-06-24 | 1 | -0/+3 |
* | radeonsi: optimize rendering to linear color buffers | Marek Olšák | 2016-06-24 | 2 | -1/+12 |
* | radeonsi: set almost optimal settings in SC_MODE_CNTL_1 | Marek Olšák | 2016-06-24 | 1 | -1/+10 |
* | gallium/radeon: let drivers specify SC_MODE_CNTL_1 fields | Marek Olšák | 2016-06-24 | 4 | -10/+18 |
* | gallium/radeon: disable complicated point clipping against user clip planes | Marek Olšák | 2016-06-24 | 3 | -3/+0 |
* | radeonsi: fix a compute shader hang with big threadgroups on SI & CI | Marek Olšák | 2016-06-24 | 1 | -0/+18 |
* | nvc0: when mapping directly, provide accurate xfer info + start | Ilia Mirkin | 2016-06-24 | 1 | -5/+12 |
* | st/mesa: don't assume that the whole surface gets mapped | Ilia Mirkin | 2016-06-24 | 1 | -7/+6 |
* | radeonsi: drop the DRAW_PREAMBLE packet on Polaris | Nicolai Hähnle | 2016-06-24 | 2 | -1/+28 |
* | radeonsi: use DRAW_(INDEX_)INDIRECT_MULTI on Polaris | Nicolai Hähnle | 2016-06-24 | 1 | -10/+36 |
* | st/mesa: handle negative _ColorDrawBufferIndexes values correctly | Francesco Ansanelli | 2016-06-24 | 1 | -1/+1 |
* | winsys/radeon: add guard pages when R600_DEBUG=check_vm is enabled | Nicolai Hähnle | 2016-06-24 | 3 | -2/+7 |
* | winsys/amdgpu: add guard pages when R600_DEBUG=check_vm is enabled | Nicolai Hähnle | 2016-06-24 | 3 | -2/+8 |
* | radeonsi: report a failure to parse dmesg instead of asserting | Nicolai Hähnle | 2016-06-24 | 1 | -1/+6 |
* | radeon: check VM faults from DMA flush | Nicolai Hähnle | 2016-06-24 | 5 | -6/+68 |
* | radeonsi: move gfx fence wait out of si_check_vm_faults | Nicolai Hähnle | 2016-06-24 | 2 | -6/+7 |
* | radeonsi: extract IB and bo list saving into separate functions | Nicolai Hähnle | 2016-06-24 | 6 | -54/+88 |
* | st/mesa: fix readpixels regression with MESA_pack_invert | Nicolai Hähnle | 2016-06-24 | 1 | -1/+1 |
* | radeonsi: set LLVM denormal flags | Marek Olšák | 2016-06-24 | 1 | -2/+5 |
* | radeonsi: emit 1/sqrt for RSQ | Marek Olšák | 2016-06-24 | 1 | -2/+16 |
* | r600g: Enable FMA on chips that support it | Jan Vesely | 2016-06-24 | 2 | -5/+7 |
* | gallium/u_queue: allow the execute function to differ per job | Marek Olšák | 2016-06-24 | 6 | -15/+18 |
* | gallium/u_queue: reduce the number of mutexes by 2 | Marek Olšák | 2016-06-24 | 2 | -20/+35 |
* | gallium/u_queue: add an option to name threads | Marek Olšák | 2016-06-24 | 4 | -2/+13 |
* | gallium/u_queue: add an option to have multiple worker threads | Marek Olšák | 2016-06-24 | 8 | -23/+71 |
* | gallium/u_queue: rewrite util_queue_fence to allow multiple waiters | Marek Olšák | 2016-06-24 | 2 | -16/+43 |
* | gallium/u_queue: use a ring instead of a stack | Marek Olšák | 2016-06-24 | 4 | -20/+47 |
* | i965: Preserve the internal format of the dri image | Jordan Justen | 2016-06-23 | 1 | -3/+10 |
* | anv: Add anv_render_pass_attachment::store_op | Chad Versace | 2016-06-23 | 2 | -2/+2 |
* | gbm: Fix comments | Gurkirpal Singh | 2016-06-23 | 1 | -2/+2 |
* | gbm: doc fixes | Eric Engestrom | 2016-06-23 | 2 | -4/+4 |
* | Remove wrongly repeated words in comments | Giuseppe Bilotta | 2016-06-23 | 45 | -51/+51 |
* | svga: update some comments in svga_buffer_handle() | Brian Paul | 2016-06-23 | 1 | -10/+3 |
* | svga: add a const qualifier in svga_buffer_upload_piecewise() | Brian Paul | 2016-06-23 | 1 | -1/+1 |
* | svga: minor code refactor for svga_buffer_upload_command() | Brian Paul | 2016-06-23 | 1 | -5/+21 |
* | svga: minor code simplification in svga_context_finish() | Brian Paul | 2016-06-23 | 1 | -1/+1 |
* | i965: Implement rasterizer discard via SOL unless required for queries. | Kenneth Graunke | 2016-06-23 | 2 | -0/+21 |
* | i965: Combine 3DSTATE_STREAMOUT emitters and genX_sol_state atoms. | Kenneth Graunke | 2016-06-23 | 4 | -99/+37 |
* | glsl: Don't constant propagate arrays. | Kenneth Graunke | 2016-06-23 | 1 | -1/+1 |
* | glsl: Make lower_const_arrays_to_uniforms work directly on constants. | Kenneth Graunke | 2016-06-23 | 1 | -8/+3 |
* | i965: Copy propagate before doing variable index lowering. | Kenneth Graunke | 2016-06-23 | 1 | -0/+2 |
* | glsl: Propagate invariant/precise after lowering const arrays. | Kenneth Graunke | 2016-06-23 | 1 | -0/+1 |