summaryrefslogtreecommitdiffstats
path: root/src/amd
Commit message (Expand)AuthorAgeFilesLines
* radv: Add debug option to dump meta shaders.Timur Kristóf2019-09-263-2/+6
* amd/common: Introduce ac_get_fs_input_vgpr_cnt.Timur Kristóf2019-09-263-33/+60
* radv: Set shared VGPR count in radv_postprocess_config.Timur Kristóf2019-09-262-2/+18
* amd/common: Add num_shared_vgprs to ac_shader_config for GFX10.Timur Kristóf2019-09-262-0/+20
* amd/common: Extract some helper functions to ac_shader_util.Timur Kristóf2019-09-265-117/+131
* amd/common: Move ac_export_mrt_z to ac_llvm_build.Timur Kristóf2019-09-264-75/+76
* aco: CSE readlane/readfirstlane/permute/reduce with the same exec maskRhys Perry2019-09-262-9/+37
* aco: don't CSE v_readlane_b32/v_readfirstlane_b32Rhys Perry2019-09-261-0/+4
* aco,radv: rename record_llvm_ir/llvm_ir_string to record_ir/ir_stringRhys Perry2019-09-266-18/+18
* radv/aco: return a correct name and description for the backend IRRhys Perry2019-09-263-2/+9
* aco: store printed backend IR in binaryRhys Perry2019-09-261-4/+21
* aco,radv/aco: get dissassembly for release builds if requestedRhys Perry2019-09-262-10/+2
* radv/aco: actually disable ACO when unsupportedRhys Perry2019-09-261-1/+0
* aco: check for duplicate opcode numbersRhys Perry2019-09-251-0/+25
* aco: fix opcode for s_mul_hi_i32Rhys Perry2019-09-251-1/+1
* aco: fix v_subrev_co_u32_e64 opcodeRhys Perry2019-09-251-1/+1
* aco: fix GFX9 opcode for v_xad_u32Rhys Perry2019-09-251-1/+1
* aco: implement 64-bit inegRhys Perry2019-09-252-2/+17
* aco: run nir_lower_int64() before nir_lower_idiv()Rhys Perry2019-09-251-3/+3
* radv: fix s/load/store/ copy-paste typoEric Engestrom2019-09-241-1/+1
* radv: Add workaround for hang in The Surge 2.Bas Nieuwenhuizen2019-09-241-0/+8
* ac/nir: force unnormalized coordinates for RECTMarek Olšák2019-09-231-1/+3
* ac/nir: port Z compare value clamping from radeonsiMarek Olšák2019-09-231-9/+25
* ac: stop using PCI IDs for chip identificationMarek Olšák2019-09-231-15/+58
* ac/addrlib: fix chip identification for Vega10, Arcturus, Raven2, RenoirMarek Olšák2019-09-231-10/+5
* aco: only emit waitcnt on loop continues if we there was some load or exportDaniel Schürmann2019-09-231-1/+1
* amd: Build aco only if radv is enabledBas Nieuwenhuizen2019-09-211-1/+1
* radv: remove dead shared variablesDaniel Schürmann2019-09-191-1/+1
* radv/aco: enable VK_EXT_shader_demote_to_helper_invocationDaniel Schürmann2019-09-193-0/+8
* radv: enable clustered reductionsDaniel Schürmann2019-09-191-0/+1
* radv/aco: Setup alternate path in RADV to support the experimental ACO compilerDaniel Schürmann2019-09-1911-103/+205
* aco: Initial commit of independent AMD compilerDaniel Schürmann2019-09-1931-0/+25572
* radv: Add DFSM support.Bas Nieuwenhuizen2019-09-181-5/+17
* radv: Disable dfsm by default even on Raven.Bas Nieuwenhuizen2019-09-182-3/+4
* radv: Only break batch on framebuffer change with dfsm.Bas Nieuwenhuizen2019-09-181-1/+1
* radv: never kill a NGG GS shaderRhys Perry2019-09-181-1/+3
* radv/gfx10: fix VK_KHR_pipeline_executable_properties with NGG GSSamuel Pitoiset2019-09-181-4/+13
* ac: move ac_get_num_physical_vgprs into radeon_infoMarek Olšák2019-09-182-10/+2
* ac: move ac_get_num_physical_sgprs into radeon_infoMarek Olšák2019-09-184-15/+15
* ac: move ac_get_max_wave64_per_simd into radeon_infoMarek Olšák2019-09-183-17/+5
* ac: move num_sdp_interfaces into radeon_infoMarek Olšák2019-09-183-15/+16
* ac: move PBB MAX_ALLOC_COUNT into radeon_infoMarek Olšák2019-09-183-31/+34
* radv: fix loading 64-bit GS inputsSamuel Pitoiset2019-09-181-0/+35
* radv: fix writing depth/stencil clear values to imageSamuel Pitoiset2019-09-181-3/+4
* ac: Remove DEBUG workaroundMichel Dänzer2019-09-171-6/+0
* radv: always emit a position export in gs copy shadersRhys Perry2019-09-161-1/+1
* radv: keep GS threads with excessive emissions which could write to memoryRhys Perry2019-09-163-4/+16
* radv/gfx10: disable unsupported transform feedback features for NGGSamuel Pitoiset2019-09-161-3/+3
* radv/gfx10: implement NGG streamoutSamuel Pitoiset2019-09-161-7/+514
* radv/gfx10: make sure to wait for idle before clearing GDSSamuel Pitoiset2019-09-161-0/+8
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-26 19:01:22 +0000