summaryrefslogtreecommitdiffstats
path: root/src/gallium
Commit message (Expand)AuthorAgeFilesLines
* gallium: add PIPE_SHADER_CAP_MAX_UNROLL_ITERATIONS_HINTMarek Olšák2015-10-2115-1/+42
* st/omx/dec/h264: fix field picture type 0 poc disorderLeo Liu2015-10-211-4/+8
* st/va: Used correct parameter to derive the value of the "h" variable in vlVa...Indrajit Das2015-10-211-1/+1
* radeonsi: fix a GS copy shader leakMarek Olšák2015-10-211-1/+3
* freedreno/a3xx: cache-flush is needed after MEM_WRITERob Clark2015-10-213-5/+14
* nv30: include the header of ffs prototypeChih-Wei Huang2015-10-211-0/+1
* nv50/ir: use C++11 standard std::unordered_map if possibleChih-Wei Huang2015-10-211-3/+17
* u_vbuf: fix vb slot assignment for translated buffersNicolai Hähnle2015-10-211-0/+1
* nouveau: make sure there's always room to emit a fenceIlia Mirkin2015-10-218-41/+32
* Revert "nouveau: make sure there's always room to emit a fence"Emil Velikov2015-10-104-8/+2
* st/dri: Use packed RGB formatsMichel Dänzer2015-10-072-17/+17
* nouveau: make sure there's always room to emit a fenceIlia Mirkin2015-10-074-2/+8
* nv30: always go through translate module on big-endianIlia Mirkin2015-10-071-0/+4
* nv30: pretend to have packed texture/surface formatsIlia Mirkin2015-10-071-12/+12
* st/dri: don't use _ctx in client_wait_syncMarek Olšák2015-10-071-2/+5
* radeon/llvm: Initialize gallivm targets when initializing the AMDGPU target v2Tom Stellard2015-10-071-0/+2
* gallivm: Allow drivers and state trackers to initialize gallivm LLVM targets v2Tom Stellard2015-10-073-8/+34
* gallium/radeon: Use call_once() when initailizing LLVM targetsTom Stellard2015-10-071-13/+12
* nouveau: wait to unref the transfer's bo until it's no longer usedIlia Mirkin2015-10-071-2/+3
* nouveau: delay deleting buffer with unflushed fenceIlia Mirkin2015-10-072-2/+10
* nouveau: be more careful about freeing temporary transfer buffersIlia Mirkin2015-10-075-4/+30
* radeonsi: add scratch buffer to the buffer list when it's re-allocatedMarek Olšák2015-10-071-0/+1
* radeon/vce: fix vui time_scale zero errorLeo Liu2015-10-071-0/+3
* gallium/u_blitter: handle allocation failuresMarek Olšák2015-10-071-0/+6
* radeonsi: handle dummy constant buffer allocation failureMarek Olšák2015-10-071-0/+2
* radeonsi: don't forget to update scratch relocations for LS, HS, ES shadersMarek Olšák2015-10-071-2/+6
* radeonsi: skip drawing if updating the scratch buffer failsMarek Olšák2015-10-071-14/+49
* radeonsi: skip drawing if PS fails to compile or uploadMarek Olšák2015-10-071-12/+3
* radeonsi: skip drawing if VS, TCS, TES, GS fail to compile or uploadMarek Olšák2015-10-071-7/+23
* radeonsi: handle fixed-func TCS shader create failureMarek Olšák2015-10-071-2/+5
* radeonsi: handle shader precompile failuresMarek Olšák2015-10-071-1/+6
* radeonsi: skip drawing if GS ring allocations failMarek Olšák2015-10-071-1/+16
* radeonsi: skip drawing if the tess factor ring allocation failsMarek Olšák2015-10-073-5/+18
* radeonsi: add malloc fail paths to si_create_shader_stateMarek Olšák2015-10-071-0/+8
* radeonsi: report alloc failure from si_shader_binary_readMarek Olšák2015-10-071-1/+4
* gallium/radeon: add a fail path for depth MSAA texture readbackMarek Olšák2015-10-071-0/+5
* gallium/radeon: handle buffer alloc failures in r600_draw_rectangleMarek Olšák2015-10-071-0/+3
* gallium/radeon: handle buffer_map staging buffer failures betterMarek Olšák2015-10-071-4/+3
* radeonsi: handle constant buffer alloc failuresMarek Olšák2015-10-071-1/+7
* radeonsi: handle index buffer alloc failuresMarek Olšák2015-10-071-0/+6
* radeonsi: load fmask ptr relative to the resources arrayIlia Mirkin2015-09-231-1/+1
* nv50,nvc0: flush texture cache in presence of coherent bufsIlia Mirkin2015-09-232-0/+39
* nv50,nvc0: detect underlying resource changes and update ticIlia Mirkin2015-09-232-0/+43
* freedreno/a3xx: fix blending of L8 formatIlia Mirkin2015-09-231-0/+2
* nv50, nvc0: fix max texture buffer size to 128M elementsIlia Mirkin2015-09-232-2/+2
* r600g: use pipe_resource::width0 instead pb_buffer::sizeMarek Olšák2015-09-112-6/+6
* radeonsi: enable VGPR spilling on VIMarek Olšák2015-09-111-3/+1
* winsys/amdgpu: calculate the maximum number of compute unitsMarek Olšák2015-09-111-2/+13
* clover: Avoid using typename to allow compilation of clover by clangAlbert Freeman2015-09-111-1/+1
* nv50/ir: don't fold immediate into mad if registers are too highIlia Mirkin2015-09-111-0/+4