summaryrefslogtreecommitdiff
AgeCommit message (Expand)AuthorFilesLines
7 daysradeonsi: handle PIPE_BIND_BLENDABLEMarek Olšák1-1/+5
11 daysradeonsi: add new SI pci idsAlex Deucher1-0/+4
11 daysradeonsi: add new CIK pci idsAlex Deucher1-0/+3
13 daysr600g: copy IA_MULTI_VGT_PARAM programming from radeonsi for CaymanMarek Olšák4-3/+36
13 daysradeonsi: bump PRIMGROUP_SIZE for some casesMarek Olšák1-1/+4
13 daysradeonsi: set PARTIAL_VS_WAVE(0) when appropriateMarek Olšák1-1/+6
13 daysradeonsi: set IA_MULTI_VGT_PARAM on SI the same as on CIK (v2)Marek Olšák2-46/+50
13 daysradeonsi: simplify si_num_banks functionMarek Olšák3-15/+13
13 daysradeonsi: use r600_draw_rectangle from r600gMarek Olšák9-75/+77
13 daysradeonsi: save scissor state and sample mask for u_blitterMarek Olšák3-8/+29
13 daysradeonsi: don't set CB_SHADER_MASK=1 if there are no color outputsMarek Olšák1-4/+0
2014-08-15gallium/r300/r600/radeonsi: handle query_renderer capsEmil Velikov3-0/+33
2014-08-15docs: document radeonsi BPTC support, sort extensions in 10.3 release notesMarek Olšák2-6/+6
2014-08-14radeonsi: implement BPTC texture supportGrigori Goronzy1-0/+20
2014-08-14radeonsi: fix buffer invalidation of unbound texture buffer objectsMarek Olšák3-7/+17
2014-08-13radeonsi/compute: Stop leaking the input bufferTom Stellard1-7/+14
2014-08-13radeonsi/compute: Whitespace fixesTom Stellard1-2/+1
2014-08-13radeonsi/compute: Call si_pm4_free_state() after emitting compute stateTom Stellard1-1/+1
2014-08-13radeonsi/compute: Update reference counts for buffers in si_set_global_binding()Tom Stellard1-2/+2
2014-08-12android: egl/main: resolve radeon linking issuesPaulo Sergio Travaglia1-4/+9
2014-08-10radeonsi: simplify constant buffer upload for big endianMarek Olšák1-18/+4
2014-08-09radeonsi: fix CMASK and HTILE allocation on TahitiMarek Olšák2-3/+56
2014-08-09radeonsi: use gpu_address from r600_resourceMarek Olšák6-56/+41
2014-08-09radeonsi: always prefer SWITCH_ON_EOP(0) on CIKMarek Olšák4-10/+46
2014-08-09radeonsi: fix a hang with instancing in Unigine Heaven/Valley on HawaiiMarek Olšák1-5/+2
2014-08-03st/dri: Fix driver loading if swrast isn't builtAaron Watry1-0/+4
2014-08-01r600g/radeonsi: Prefer VRAM for CPU -> GPU streaming buffersMichel Dänzer1-4/+11
2014-08-01r600g/radeonsi: Reduce or even drop special treatment of persistent mappingsMichel Dänzer1-4/+8
2014-07-28r600g,radeonsi: switch all occurences of array_size to util_max_layerMarek Olšák3-6/+10
2014-07-28radeonsi: fix occlusion queries on HawaiiMarek Olšák1-1/+7
2014-07-28radeonsi: fix a hang with streamout on HawaiiMarek Olšák2-1/+14
2014-07-28radeonsi: fix a hang with instancing on HawaiiMarek Olšák1-1/+15
2014-07-28radeonsi: fix CMASK and HTILE calculations for HawaiiMarek Olšák1-2/+2
2014-07-28r600g,radeonsi: add debug flags which disable tilingMarek Olšák3-13/+24
2014-07-28radeonsi: Use util_memcpy_cpu_to_le32()Tom Stellard2-19/+8
2014-07-23r600g/radeonsi: Use write-combined CPU mappings of some BOs in GTTMichel Dänzer17-26/+77
2014-07-21radeonsi/compute: Add support scratch buffer support v2Tom Stellard3-2/+85
2014-07-21radeonsi/compute: Bump number of user sgprs for LLVM 3.5Tom Stellard1-1/+6
2014-07-21radeonsi/compute: Share COMPUTE_DBG macro with r600gTom Stellard3-13/+10
2014-07-21radeonsi: Read rodata from ELF and append it to the end of shadersTom Stellard3-1/+22
2014-07-17radeonsi: only update vertex buffers when they need updatingMarek Olšák3-2/+22
2014-07-17radeonsi: remove nr_vertex_buffersMarek Olšák3-6/+23
2014-07-17radeonsi: move vertex buffer descriptors from IB to memoryMarek Olšák7-106/+133
2014-07-17radeonsi: add support for fine-grained sampler view updatesMarek Olšák3-30/+21
2014-07-17radeonsi: move si_set_sampler_views to si_descriptors.cMarek Olšák3-73/+68
2014-07-17radeonsi: move sampler descriptors from IB to memoryMarek Olšák5-82/+82
2014-07-17radeonsi: implement ARB_draw_indirectMarek Olšák7-20/+132
2014-07-17radeonsi: don't add info->start to the index buffer offsetMarek Olšák1-11/+25
2014-07-17radeonsi: use an SGPR instead of VGT_INDX_OFFSETMarek Olšák4-14/+23
2014-07-17radeonsi: assume LLVM 3.4.2 is always presentMarek Olšák6-56/+7