Lines Matching full:radv
34 - VK_KHR_maintenance5 on RADV
46 - VK_KHR_cooperative_matrix on RADV/GFX11+
54 - [RADV] War Thunder has some grass flickering.
55 - radv: satisfactory broken shader
56 - RADV problem with R7 M440 in some games
60 - RADV: trunc_coord breaks ambient occlusion in Dirt Rally and other games
61 - radv: Mass Effect Legendary Edition: a line going across the screen is visible in some areas with…
64 - [RADV][TONGA] - BeamNG.drive (284160) - Artifacts are present when looking at the skybox.
66 - [radv] Crypt not rendering properly
70 - RADV: Visual glitches in Unreal Engine 5.2.1 when using material with anisotropy and light channe…
71 - radv: Regression with UE5 test
94 - RADV: regression in 23.2.1 causing GPU hang with RDNA1 in various UE5 games
134 - radv: Counter Strike 2 has multiple bugs while rendering smoke grenade effect
138 - RADV: Randomly dissapearing objects in Starfield with RX 5xx and Vega graphics
140 - radv: Star Wars The Old Republic hang when DCC is enabled
141 - radv: Resident Evil 6 hangs 7900XTX GPU when DCC is enabled if in Options go to Display settings
142 - radv: Resident Evil 6 Benchmark Tool hangs 7900 XTX GPU when DCC is enabled immediately after spl…
152 - [radv] [Path Of Exile] - one setting in the workaround file breaks shadows/lighting rendering. Ot…
153 - radv: images don't always have extents in RGP
163 - radv: Regression from 266b2cfe5bf3feda16747c50c1638fb5a0426958
179 - [RADV] Dead by Daylight memory leak (shader-related?) on 23.1.6
191 - radv: commit 81641b01555faa4dd1dfc7de2513ad8d63e77ab7 leaded to artifacts in Quake II RTX
192 - [radv] Colors are distorted in Cyberpunk 2077 with ray tracing enabled
197 - [RADV] red and pink tinted shadows in Overwatch 2 on 7900 XTX
214 - aco, radv Rage 2 menu corruption - bisected
215 - radv, aco: World War Z character texture regression on 7900xtx
363 - radv: Rely on workgroup_size initialization
656 - radv: Use before/after_cf_list for entrypoints
835 - radv: Expose VK_EXT_external_memory_acquire_unmodified.
841 - radv: Use a double jump to limit nops in DGC for dynamic sequence count.
845 - radv: Don't transparently use wave32 with cooperative matrices.
846 - radv: Add cooperative matrix lowering.
847 - radv: Expose VK_KHR_cooperative_matrix.
851 - radv/video: use app provided hevc scaling list order
852 - radv/video: copy from correct H264 scaling lists
855 - radv/video: use vk_video_derive_h264_scaling_list
858 - radv/video: send h264 scaling list in raster order
860 - radv/video: find SPS with pps_seq_parameter_set_id
868 - radv/video: Match function definitions to declarations
886 - radv: Use nir_opt_reuse_constants()
1039 - radv: fix separate depth/stencil layouts in fb state
1040 - radv: fix separate depth/stencil layouts in resolve meta
1041 - radv: refactor depth clear in clear meta
1042 - radv: fix separate depth/stencil layouts in clear meta
1043 - amd/ci: update radv-stoney-aco-fails.txt for depth/stencil clear
1044 - radv: disable tc-compat htile for layered images on gfx8
1045 - amd/ci: update radv-stoney-aco-fails.txt for depth/stencil resolve
1050 - radv: use vk_tecompress_etc2 from the runtime
1053 - vulkan/runtime, radv: remove 1D support from ETC2 emulation
1054 - radv: add radv_is_format_emulated
1055 - radv: simplify view format override for emulated formats
1056 - radv: hard code format features for emulated formats
1058 - radv, drirc: rename radv_require_{etc2,astc}
1076 - radv: fix image view extent override for astc
1080 - radv: initialize result when pipeline cache creation fails
1088 - radv/video: use correct enum value for max level IDC
1305 - radv: fix unused non-xfb shader outputs not being removed
1307 - radv: Use common nir_vk_is_not_xfb_output
1494 - radv: don't emit event code on video queues.
1497 - radv/video: take db alignment into account when allocating images.
1736 - ci/radv: Clarify when the ANGLE GS failures started happening.
1919 - docs/radv: mark VK_EXT_tooling_info as implemented
1920 - docs/radv: mark VK_INTEL_shader_integer_functions2 as implemented
1922 - git-blame-ignore-revs: add radv formatting commit
1928 - ci/zink+radv: set a timeout of 2x the normal runtime
1981 - ci/zink+radv: specify that zink-radv-navi10-valve should run in the mupuf farm
1982 - ci/zink+radv: bump the timeout of zink-radv-navi10-valve by 10 minutes
1987 - ci/zink+radv: document flake
2985 - radv/ci: Set DRIVER_NAME in LAVA raven vkcts jobs
2986 - radv: Handle VK_SUBOPTIMAL_KHR in trace layers
2988 - ac/sqtt,radv: Split internal and API hash in PSO correlations
2991 - radv/sqtt: Move record filling to helper function
2992 - radv/sqtt: Unregister records based on hash
2993 - radv/sqtt: Write LDS size metadata in code objects
2994 - radv/sqtt: Handle separately-compiled RT pipelines
2995 - ac/sqtt,radv/sqtt: Add and use marker for separate RT compilation
2997 - radv/rt: Pre-initialize instance address
2998 - radv: Initialize shader freelist on allocation
2999 - radv: Fix check in insert_block
3000 - radv/rt: Reject hits within 10ULP of previous hits in emulated RT
3001 - radv/rra: Recognize LPDDR memory
3002 - radv/rmv: Recognize LPDDR memory
3897 - radv: fix buffers in vkGetDescriptorEXT with size not aligned to 4
3944 - radv: Stop using the misleading round_up_u* functions
3945 - radv/meta_buffer: Stop setting RADV_META_SAVE_DESCRIPTORS
3946 - radv/meta_buffer: Rename size_minus16 to max_offset
3960 - radv: Use common physical device properties
3966 - radv/rt: Rename shader_pc and next_shader
3967 - radv/rt: Rename traversal_shader to traversal_shader_addr
3980 - radv: Add internal_nodes_offset to scratch_layout
3981 - radv: Remove leaf_args::dst_offset
3982 - radv/rt: Remove some dead code
3983 - radv/rt: Do not apply stack_ptr for non-recursive stages
3984 - radv/rt: Add and use radv_build_traversal
3985 - radv/rt: Insert rt_return_amd before lowering shader calls
3986 - radv/rt: Split stage initialization and hashing
3988 - radv: Stop updating the stack_size in insert_rt_case
3998 - radv: Only generate debug info if required
4000 - radv: Don't use the depth image view for depth bias emission
4001 - radv/rt: Store NIR shaders separately
4002 - radv/rt: Add monolithic raygen lowering
4003 - radv/rt: Enable monolithic pipelines
4004 - radv/ci: Document new flake
4006 - radv: Remove dead radix_sort_vk_get_memory_requirements call
4007 - radv/radix_sort: Vendor the radix sort dispatch code
4008 - radv: Perform multiple sorts in parallel
4009 - radv/ci: Improve ray tracing skips
4013 - radv: Don't advertise features requiring PS epilogs with LLVM
4014 - radv: Update navi21 llvm fails
4015 - radv/rt: Handle stages without nir properly
4016 - radv: Remove ray tracing shader module identifier skips
4017 - radv/bvh: Treat instances with mask == 0 as inactive
4018 - radv/ray_queries: Skip cull_mask handling if it is FF
4019 - radv/rt: Skip cull_mask handling if it is FF
4029 - radv/bvh/ploc: Load child bounds from LDS
4030 - radv: Merge the sync_data and header initialization
4031 - radv: Do not sync after radv_update_buffer_cp
4037 - radv/rt: Use nir_shader_instructions_pass for lower_rt_instructions
4038 - radv/sqtt: Fix tracing acceleration structure commands
4493 - Revert "radv/amdgpu: fix alignment of command buffers"
4494 - Revert "radv: fix alignment of DGC command buffers"
4552 - radv/ci: drop the auto-reboot-on-hang for vkcts-navi10
4553 - radv/ci: use the default kernel on vkcts-navi10
4556 - radv/ci: move vkcts-navi10 testing to KWS
4557 - radv/ci: add more tests to the navi10 vkcts flake list
4558 - radv/ci: increase the parallelism of the vkcts-navi21 job
4559 - radv/ci: add more tests to the navi21 vkcts flake list
4560 - radv/ci/vkcts-navi21: catch all the line_stipple_(enable|params) flakes
4561 - radv/ci/vkcts-navi21: document more flakes
4562 - radv/ci/vkcts-navi10: catch all the line-related flakes
4563 - radv/ci: update the vkcts gfx1100 flake/fail lists
4564 - radv/ci: add a manual job to run vkcts on navi31
4565 - radv/ci: add a manual job for vkd3d-proton on navi31
4569 - zink/ci: remove 19 tests from the zink-radv-polaris10-fails list
4571 - zink/ci: remove 42 tests from the zink-radv-polaris10-fails list
4572 - radv/ci: tighten the vkcts-navi21 timeouts
4573 - zink/ci: tighten the zink-radv-vangogh timeouts
4661 - radv: bump max xfb output to 128
4877 - radv: fix external handle type queries for dmabuf/fd
4935 - radv: correctly return oom from the device when failing to create a cs
5081 - radv/sdma: use multiple commands if required
5082 - radv/sdma: use correct limits for gfx10.3
5106 - aco,radv: replace tess_input_vertices shader info param
5155 - aco,radv,radeonsi: rename is_monolithic to merged_shader_compiled_separately
5162 - aco,radv: remove unused ps epilog info fields
5163 - aco,radv: rename ps epilog info inputs to colors
5165 - aco,radv: add radeonsi spec ps epilog code
5167 - aco,radv,radeonsi: pass spi ps input ena and addr
5222 - radv: fix radv_get_ballot_bit_size with CS
5225 - radv: add conformant_trunc_coord to cache UUID
5226 - radv: don't unset TRUNC_COORD if conformant_trunc_coord=true
5234 - radv: workaround WWZ exporting index=1 through location=1
5235 - radv: correctly skip MRT output NaN fixup for meta shaders
5236 - radv: don't set vertex_attribute_strides on GFX8+
5237 - radv/ci: skip some mesh shader tests on GFX1100
5240 - radv: disable 64-bit color attachments
5241 - radv: fix 128bpp comp-to-single clears
5242 - radv: support 128bpp comp-to-single with all colors
5243 - radv/gfx11: re-enable 0001/1110 clear values
5246 - radv: vectorize RT stack access
5247 - radv: vectorize scratch access
5255 - radv: optimize mesh workgroup ID using ts_mesh_dispatch_dimensions
5256 - radv: use shortcut_1d_workgroup_id
5261 - radv: disable mesh dispatch XYZ_DIM when possible
5283 - radv: skip zero-sized memcpy
5285 - radv: fix signed integer overflow
5286 - Revert "radv: pre-init surface info"
5294 - radv: implement mesh shader gs_fast_launch=2
5296 - ac/nir,radv: pass workgroup size to ac_nir_lower_ngg_ms
5298 - radv: implement mesh shader multi-row export
5299 - radv: enable mesh shader gs_fast_launch=2 and multi-row export
5303 - radv: call lower_array_deref_of_vec before lower_io_arrays_to_elements
5304 - radv: skip radv_remove_varyings for mesh shaders
5305 - radv: disable gs_fast_launch=2 by default
5307 - radv: add radv_disable_trunc_coord option
5308 - radv: enable radv_disable_trunc_coord for vkd3d-proton/DXVK
5518 - radv: remove support for VK_INDIRECT_COMMANDS_TOKEN_TYPE_STATE_FLAGS_NV
5519 - radv: make radv_get_pa_su_sc_mode_cntl() static
5521 - radv: stop using a pipeline for emitting VGT_VERTEX_REUSE_BLOCK_CNTL
5522 - radv: remove unused param in radv_pipeline_emit_vgt_gs_out()
5523 - radv: pass a shaders array for computing ia_multi_vgt_param
5524 - radv: bind the pre-compiled PS epilog to the cmdbuf state
5525 - radv: stop using an array of binaries when compiling a compute shader
5526 - radv: add radv_compile_cs() to compile a compute shader
5527 - radv: remove the pipeline dependency for creating a GS copy shader
5528 - radv: add a helper to compute the ESGS itemsize
5529 - radv: use the number of GS linked inputs to compute the ESGS itemsize
5530 - radv: determine ES info for VS/TES with GS earlier
5531 - radv: determine as_ls earlier by using the next stage
5532 - radv: simplify getting next VS stage for VS prologs
5533 - radv: use next_stage for determining the stage to lower NGG
5534 - radv/amdgpu: fix dumping CS with the chained IBs path
5535 - radv/amdgpu: rename old_ib to ib in radv_amdgpu_winsys_cs_dump()
5536 - radv: pass submit info to radv_check_gpu_hangs()
5537 - radv: initialize stage/next_stage earlier
5538 - radv: set next_stage to MESA_SHADER_NONE if there is no FS
5539 - radv: rework considering force VRS without relying on graphics pipeline
5540 - radv: stop passing radv_graphics_pipeline to radv_fill_shader_info()
5541 - radv: move removing all varyings when the FS is a noop
5542 - radv: rename graphics pipeline linking helpers
5543 - radv: simplify lowering NGG GS intrinsics
5544 - radv: rework determining the NGG stage without a graphics pipeline
5545 - radv: cleanup pipeline compute emit helpers
5546 - radv: rename radv_pipeline_stage to radv_shader_stage
5547 - radv: rename NGG query state to be more generic
5548 - radv: declare the shader query user SGPR for emulating GS counters
5549 - radv: enable pipelinestat query emulation for legacy GS
5550 - radv: simplify the NGG vs legacy pipelinestat query path
5551 - radv: rename RADV_SHADER_QUERY_PIPELINE_STAT_OFFSET
5552 - radv: implement nir_intrinsic_atomic_add_gs_invocation_count_amd
5553 - radv: emulate GEOMETRY_SHADER_INVOCATIONS query on RDNA1-2
5554 - radv: track whether inputs/outputs are linked per shader stage
5555 - radv: add support for VS/TES as ES without shaders IO linking
5556 - radv: use next_stage to determine if the layer should be exported
5557 - radv: use next stage to determine if primID/clip dist should be exported
5558 - radv: compute the legacy GS info earlier
5559 - radv: stop copying some NIR info fields from TES to TCS
5560 - radv: stop lowering patch vertices for TES
5561 - radv: do not always copy the number of tess patches to TES
5562 - radv: initialize tcs.tes_{patch}_inputs_read to a default value
5563 - radv: prevent linking TCS<->TES when TES is NULL
5564 - radv: use a packed user SGPR for the TES state
5565 - radv: stop checking if patch control points is dynamic everywhere
5566 - radv: copy the number of TCS vertices out to TES shader info
5567 - radv: add support for dynamic TCS vertices out for TES
5568 - radv: remove radv_shader_info::tes::num_linked_patch_inputs
5570 - radv: allow to use fixed IO locations for VS<->TCS<->TES without linking
5573 - radv,aco: move has_epilog to radv_shader_info
5574 - radv: assume a TCS needs an epilog unless it's linked with a TES
5575 - radv: do not write tess factors in main TCS when it has an epilog
5576 - radv: track if TES reads tess factors differently
5577 - radv: declare new argument for the TCS epilog PC
5578 - radv: add radv_tcs_epilog_key
5579 - radv: add infra for creating TCS epilogs
5580 - radv: add support for a TCS epilogs cache in the device
5581 - radv: add support for emitting TCS epilogs in cmdbuf
5582 - radv: remove unnecessary check in radv_pipeline_nir_to_asm()
5583 - radv: stop passing a graphics pipeline to radv_pipeline_nir_to_asm()
5584 - radv: inline radv_pipeline_get_nir() in radv_graphics_pipeline_compile()
5585 - radv: add a struct for the retained shaders and GPL
5586 - radv: add radv_graphics_shaders_compile() to compile graphics shaders
5587 - radv: remove redundant check in radv_cmd_buffer_after_draw()
5588 - radv: track if patch control points is dynamic from the cmdbuf state
5589 - radv: re-emit binning state if the framebuffer is dirty
5590 - radv: track if vertex binding stride is dynamic from the cmdbuf state
5594 - radv: use the RT prolog scratch size directly for tracing rays
5595 - radv: add a helper to get the maximum number of scratch waves per shader
5596 - radv: update the number of scratch waves for RT prolog at bind time
5597 - radv: update cmdbuf scratch size info when shaders are bound
5599 - radv: use vk_buffer_view
5600 - radv: use vk_sampler
5601 - radv: use common vkCmdBegin/EndQuery wrappers
5602 - radv: use vk_query
5604 - radv/rt: fix capture/replay support
5606 - radv: implement vkCmdBindIndexBuffer2KHR()
5607 - radv: allow VK_WHOLE_SIZE for pSizes in vkCmdBindVertexBuffers2()
5608 - radv/rmv: remove unused pipeline create flags when logging pipelines
5609 - radv: store pipeline create flags to radv_pipeline::create_flags
5610 - radv: add support for VkPipelineCreateFlags2CreateInfoKHR
5611 - radv: add support for VkBufferUsageFlags2CreateInfoKHR
5612 - radv: allow VK_REMAINING_ARRAY_LAYERS with VkImageSubresourceLayers
5613 - radv: implement radv_Get{Device}ImageSubresourceLayout2KHR()
5614 - radv: advertise VK_KHR_maintenance5
5615 - radv: remove useless NULL for pipeline layout during shader info pass
5616 - radv: introduce radv_shader_layout for per-stage descriptor layout
5617 - radv: stop passing redundant stage to radv_shader_stage_init()
5618 - radv: re-introduce radv_pipeline_stage_init()
5619 - radv: add support for loading the LSHS vertex stride from a SGPR
5620 - radv: use the number of VS outputs for computing the tessellation info
5622 - radv: reduce TCS_OFFCHIP_LAYOUT_NUM_PATCHES to 6-bits
5623 - radv: add missing comment about TCS_OFFCHIP_LAYOUT_LSHS_VERTEX_STRIDE
5624 - radv: fix emitting TCS epilogs for GFX6-9
5625 - radv: remove radv_cmd_buffer::cached_vertex_formats
5626 - radv: remove unused param from radv_pipeline_init_multisample_state()
5627 - radv: simplify declaring VS specific input SGPRs
5628 - radv: stop copying if VS or TES uses the InvocationID built-in
5629 - Revert "radv/amdgpu: workaround a kernel bug when replacing sparse mappings"
5630 - Revert "radv/amdgpu: skip adding per VM BOs for sparse during CS BO list build"
5631 - radv/amdgpu: allow to execute external IBs on the compute queue
5632 - radv/amdgpu: add support for submitting external IBs with the chained path
5634 - radv: use the maximum possible workgroup size for TCS epilogs
5635 - radv: stop declaring the scratch offset argument for TCS epilogs
5636 - radv: declare shader arguments for TCS epilogs
5637 - radv: add tcs_out_patch_fits_subgroup to radv_tcs_epilog_key
5639 - aco: adjust TCS epilogs for RADV
5642 - radv: track the pipeline bind point for indirect commands layout
5643 - radv: prepare radv_get_sequence_size() for DGC compute
5644 - radv: prepare radv_prepare_dgc() for DGC compute
5645 - radv: implement NV_device_generated_commands_compute
5646 - radv: allow DGC on the compute queue
5647 - radv: advertise NV_device_generated_commands_compute
5649 - radv: fix the per-patch data offset when TES isn't linked with TCS
5650 - radv: stop declaring unused SGPR arguments for PS epilogs
5651 - radv: add radv_shader_info::is_monolithic
5652 - radv: use info->uses_view_index directly when declaring shader arguments
5653 - radv: do not inline push constants for non-monolithic shaders
5654 - radv: force indirect descriptor sets for non-monolithic shaders
5655 - radv: always declare some arguments for non-monolithic VS/TCS shaders
5656 - radv: add a new shader argument for non-monolithic shaders PC
5658 - radv: preserve shader arguments for non-monolithic VS/TCS on GFX9+
5662 - radv: always declare some arguments for non-monolithic {VS,TES}/GS shaders
5663 - radv: preserve shader arguments for non-monolithic {VS,TES}/GS on GFX9+
5666 - radv,aco: remove unused clip/cull distances variables
5667 - radv: rename tcs_shader to tcs in radv_emit_tcs_epilog_state()
5668 - radv: small cleanups in radv_emit_patch_control_points()
5669 - radv: fix emitting TCS epilogs if TES and GS are linked on GFX9+
5670 - radv: remove the pipeline dependency for emitting VGT_GS_MODE
5672 - radv: re-order IO slot layout for stages that aren't linked
5677 - radv: preserve shader argument for separate compilation of NGG shaders
5681 - zink/ci: add zink-radv-polaris10-valve
5682 - radv/ci: re-enable vkcts-polaris10-valve
5683 - radv: fix capturing indirect dispatches with SQTT
5684 - radv/ci: re-enable vkd3d-polaris10-valve
5686 - radv/amdgpu: fix executing secondaries without IB2
5687 - radv/amdgpu: do not copy the original chain link for IBs
5688 - radv: avoid emitting SQTT markers for DGC calls
5689 - radv: add support for DGC with SQTT
5690 - zink/ci: merge GLCTS testing with GLESx for RADV
5691 - zink/ci: merge piglit testing with deqp-runner for RADV
5692 - radv: fix interactions with primitives generated queries and pipeline stats
5693 - radv: skip DGC calls when the indirect sequence count is zero with a predicate
5694 - radv: avoid emitting THREAD_TRACE_MARKER for predicated draws/dispatches
5695 - radv: adjust next stage for VS prologs and merged shaders compiled separately
5696 - radv: adjust emitted prolog regs for merged shaders compiled separately
5697 - radv: do not use pre-compiled prologs when VS is compiled separately
5698 - radv: remove useless PIPELINE_CREATE_2_LIBRARY_BIT check for retained shaders
5699 - radv: fix enabling DGCC
5700 - radv: fix emitting SQTT userdata when CAM is needed
5701 - radv: fix capturing RGP on RDNA3 with more than one Shader Engine
5703 - radv: set THREAD_TRACE_TOKEN_MASK.BOP_EVENTS_TOKEN_INCLUDE on GFX10.3+
5704 - radv: disable unsupported hw shader stages for RGP on GFX11+
5705 - radv: fix instruction timing on GFX11
5707 - radv: set THREAD_TRACE_MARKER_ENABLE for mesh/task draws
5708 - radv: emit relocation for mesh/task shaders
5710 - ac,radv,radeonsi: rework SPM counters configuration and share it
5713 - radv: enable the PKT3 CAM bit for some SPM register writes
5714 - radv,radeonsi: use AC_SPM_SEGMENT_TYPE_xxx instead of magic values
5723 - radv: reserve more CS space in SQTT/SPM paths
5726 - radv,radeonsi: make sure to emit GRBM_GFX_INDEX before SQ select registers
5728 - ac,radv,radeonsi: prepare support for multi-instance SPM SQ counters
5729 - ac,radv,radeonsi: prepare support for multi-instance SPM generic counters
5732 - radv: fix checking if RGP is enabled with others tracing tools
5733 - radv: fix missing ISA with RGP and GPL
5737 - radv: remove drirc workarounds for Path Of Exile
5738 - radv: remove absolute_depth_bias workaround
5742 - radv: add SPM support for GFX11
5743 - radv: enable cache counters for RGP on GFX11
5745 - radv/ci: skip dEQP-VK.robustness.* on Vangogh due to weird GPU hangs
5749 - radv: add GDS counters offset for mesh/task queries
5750 - radv: adjust lowering of intrinsic queries for mesh/task shaders
5751 - radv: enable lowering of mesh/task shader queries when enabled
5752 - radv: declare shader_query_state for mesh/task shaders
5753 - radv: stop skip emitting CB states when there is no color attachment
5754 - radv: re-enable DCC with mipmaps on GFX11
5755 - radv: fix COMPUTE_SHADER_INVOCATIONS query on compute queue
5756 - radv: emit missing PA_{SC,SU}_LINE_STIPPLE_xxx regs in gfx preamble
5757 - radv: fix alignment of DGC command buffers
5758 - radv/ci: update list of expected failures on PITCAIRN
5759 - radv/ci: update list of flakes for NAVI10/VEGA10
5760 - radv/amdgpu: fix alignment of command buffers
5761 - radv: enable DCC for MSAA images on GFX11
5764 - radv/ci: rename GFX1100 lists to NAVI31
5765 - radv: fix emulated geometry shader primitives/invocations queries
5766 - radv/ci: remove duplicate skipped tests for RAVEN/STONEY
5767 - radv/ci: exclude dEQP-VK.texture.explicit_lod.2d.sizes.128x128_* for all jobs
5768 - radv: fix synchronization with emulated GS primitives/invocations queries
5769 - radv/ci: remove no longer existing test for VANGOGH
5770 - radv/ci: cleanup list of expected failures for NAVI10/NAVI21/VEGA10
5771 - radv: always write the sample positions when a new descriptor BO is created
5772 - radv: fill the scratch BO in radv_fill_shader_rings()
5773 - radv: fix gang submissions with chaining
5774 - radv: fix re-emitting streamout descriptors for NGG streamout
5775 - radv: fix IB alignment
5777 - radv: fix destroying GDS/OA BOs
5778 - radv: allocate only 1 GDS OA counter for gfx10 NGG streamout
5780 - radv/ci: update list of expected failures on RAVEN
5781 - radv/ci: update list of flakes for VANGOGH
5782 - radv/ci: update list of flakes for STONEY
5783 - radv: disable primitive restart for non-indexed draws on GFX11
5784 - radv: enable radv_disable_aniso_single_level=true for Zink too
5785 - amd/llvm,aco,radv: implement NGG streamout with GDS_STRMOUT registers on GFX11
5786 - radv: mark GDS as needed for XFB queries with NGG streamout on GFX11
5787 - radv: skip GDS allocation for NGG streamout on GFX11
5788 - zink/ci: remove expected failures that are skipped for RADV
5792 - radv: set ENABLE_PING_PONG_BIN_ORDER for GFX11.5
5793 - radv: initialize video decoder for GFX11.5
5795 - Revert "radv: fix finding shaders by PC"
5796 - radv: fix missing predicate bit for WRITE_DATA helper
5798 - radv: remove outdated RADV_DEBUG=vmfaults support
5801 - radv/amdgpu: add support quering the last GPUVM fault
5802 - radv: query and report the last GPUVM fault with RADV_DEBUG=hang
5803 - radv: report the last GPUVM fault when a device lost is detected
5805 - radv: fix a synchronization issue with primitives generated query on RDNA1-2
5806 - radv: bind the non-dynamic graphics state from the pipeline unconditionally
5807 - radv: fix compute shader invocations query on compute queue on GFX6
5808 - radv: emit COMPUTE_PIPELINESTAT_ENABLE for CS invocations on ACE
5810 - radv: fix registering queues for RGP with compute only
5811 - radv: set radv_zero_vram=true for Unreal Engine 4/5
5812 - radv: fix a descriptor leak with debug names and host base descriptor set
5813 - radv: add a missing async compute workaround for Tonga/Iceland
5814 - radv: disable TC-compatible HTILE on Tonga and Iceland
5815 - radv: set radv_invariant_geom=true for War Thunder
5816 - radv: do not set OREO_MODE to fix rare corruption on GFX11
5880 - radv/winsys: check amdgpu_create_bo_from_user_mem() for EINVAL
5956 - radv/amdgpu: Remove unused bo_list variable from cs_submit.
5957 - radv/winsys: Remove unused struct radv_winsys_bo_list.
5958 - radv/amdgpu: Do not pass in a BO handle when clearing PRT VA region.
5959 - radv: Fix IB size for RADV_DEBUG=hang.
5960 - radv: Fix dumping vertex descriptors with RADV_DEBUG=hang.
5961 - radv/amdgpu: Use rwlock to protect access to virtual BOs.
6074 - radv: Move radv_select_hw_stage to radv_shader_info.
6075 - radv: Use ac_nir_lower_intrinsics_to_args.
6094 - radv: Rename SDMA file to radv_sdma.c
6095 - radv: Use const device argument in radv_sdma_copy_buffer.
6096 - radv: Use const on vi_alpha_is_on_msb arguments.
6097 - radv: Only call si_cp_dma_wait_for_idle on GFX and ACE queues.
6098 - radv: Move radv_cp_wait_mem to radv_cs.h and add queue family argument.
6099 - radv: Refactor WRITE_DATA helper function.
6100 - radv: Use new WRITE_DATA helper in more places.
6101 - radv: Add queue family argument to some functions.
6102 - radv: Wait for bottom of pipe in ACE gang wait postamble.
6103 - radv: Simplify gang CS and semaphore initialization.
6104 - radv: Allow gang submit use cases other than task shaders.
6105 - radv: Slightly refactor gang semaphore functions.
6106 - radv: Add gang follower semaphore functions.
6107 - radv: Support SDMA in radv_cs_write_data_head.
6108 - radv: Support SDMA in radv_cp_wait_mem.
6109 - radv: Support SDMA in si_cs_emit_write_event_eop.
6218 - radv: integrate meta astc compute decoder to radv
6248 - ac/radv: decouple radv vulkan driver and compiler from gallium
6260 - radv: Fixes mingw linkage error undefined reference to \`radv_GetCalibratedTimestampsEXT'