aboutsummaryrefslogtreecommitdiffstats
path: root/src/gallium/drivers/radeonsi
Commit message (Collapse)AuthorAgeFilesLines
* radeonsi/gfx10: don't use NGG culling if compute-based culling is usedMarek Olšák2020-03-281-0/+1
| | | | | Acked-by: Pierre-Eric Pelloux-Prayer <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4269>
* radeonsi: add num_vbos_in_user_sgprs into the shader cache keyMarek Olšák2020-03-281-0/+3
| | | | | Acked-by: Pierre-Eric Pelloux-Prayer <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4269>
* radeonsi: always create wait_mem_scratch for compute-based cullingMarek Olšák2020-03-281-1/+2
| | | | | | | used by the primitive restart emulation Acked-by: Pierre-Eric Pelloux-Prayer <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4269>
* radeonsi: set amdgpu-gds-size for mode == 2 of compute-based cullingMarek Olšák2020-03-281-1/+4
| | | | | Acked-by: Pierre-Eric Pelloux-Prayer <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4269>
* radeonsi: fix incorrect ordered_wave_id initilization for compute-based cullingMarek Olšák2020-03-281-1/+2
| | | | | Acked-by: Pierre-Eric Pelloux-Prayer <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4269>
* radeonsi: remove obsolete TODO comment related to compute-based cullingMarek Olšák2020-03-281-1/+0
| | | | | Acked-by: Pierre-Eric Pelloux-Prayer <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4269>
* radeonsi: enable full out-of-order drawing when allow_draw_out_of_order is setMarek Olšák2020-03-261-2/+4
| | | | | | Reviewed-by: Pierre-Eric Pelloux-Prayer <[email protected]> Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4152> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4152>
* radeonsi: Stop exposing PIPE_SHADER_CAP_FP16Kristian H. Kristensen2020-03-251-1/+1
| | | | | | | Not fully supported. Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4321> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4321>
* radeonsi: clarify the conditions when FLUSH_AND_INV_DB is neededPierre-Eric Pelloux-Prayer2020-03-242-14/+7
| | | | | | | | | | | | | | | | FLUSH_AND_INV_DB should be done when we're changing surface state registers of a bound depth target. When depth_clear_value changes, si_state will modify S_028038_ZRANGE_PRECISION so we need to flush the DB caches. Verified with the captures from bugs cited below. Closes: https://gitlab.freedesktop.org/mesa/mesa/issues/1283 Closes: https://gitlab.freedesktop.org/mesa/mesa/issues/1330 Reviewed-by: Marek Olšák <[email protected]> Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4263> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4263>
* vbo,gallium: make glBegin/End buffer size configurable by driversMarek Olšák2020-03-211-0/+3
| | | | | | | | The default is 512 KB, but radeonsi wants 4 MB. Acked-by: Pierre-Eric Pelloux-Prayer <[email protected]> Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4154> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4154>
* Android.mk: Tweak MESA_ENABLE_LLVM checksJohn Stultz2020-03-191-0/+4
| | | | | | | | | | | | | | | Change the MESA_ENABLE_LLVM checks in Android.mk files in order to get mesa3d to build w/ AOSP using mmma. This tries to re-create a change that was introduced in the following merge in the AOSP branch: 69f2c0128d2b Merge branch 'aosp/upstream-18.0' Acked-by: Tapani Pälli <[email protected]> Acked-by: Mauro Rossi <[email protected]> Signed-off-by: John Stultz <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4175>
* ac: unify denorm setting enforcementMarek Olšák2020-03-171-18/+1
| | | | | | Acked-by: Pierre-Eric Pelloux-Prayer <[email protected]> Reviewed-by: Samuel Pitoiset <[email protected] Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4196>
* ac: add radeon_info::use_late_alloc to control LATE_ALLOC globallyMarek Olšák2020-03-122-6/+8
| | | | | Acked-by: Pierre-Eric Pelloux-Prayer <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4143>
* radeonsi: tune primitive binning for small chipsMarek Olšák2020-03-121-3/+9
| | | | | | | same as PAL Acked-by: Pierre-Eric Pelloux-Prayer <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4143>
* radeonsi: set better tessellation tunables on gfx9 and gfx10Marek Olšák2020-03-121-1/+8
| | | | | | | same as PAL Acked-by: Pierre-Eric Pelloux-Prayer <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4143>
* radeonsi/gfx10: cache metadata in L2 on small chipsMarek Olšák2020-03-121-8/+19
| | | | | | | same as PAL. Acked-by: Pierre-Eric Pelloux-Prayer <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4143>
* gallium: add PIPE_CAP_DRAW_INFO_START_WITH_USER_INDICESMarek Olšák2020-03-111-0/+1
| | | | | Reviewed-by: Pierre-Eric Pelloux-Prayer <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3591>
* Revert "gallium: make handles of set_global_binding 64 bit"Karol Herbst2020-03-101-3/+3
| | | This reverts commit e1ffb72a05f9b50ee47767aaadbab3e47896ee14
* gallium: make handles of set_global_binding 64 bitKarol Herbst2020-03-101-3/+3
| | | | | | | | | | needed by CL Signed-off-by: Karol Herbst <[email protected]> Reviewed-by: Marek Olšák <[email protected]> Reviewed-by: Alyssa Rosenzweig <[email protected]> Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4072> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4072>
* radeonsi: determine uses_bindless_samplers correctlyMarek Olšák2020-03-091-5/+6
| | | | | | Acked-by: Pierre-Eric Pelloux-Prayer <[email protected]> Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4079> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4079>
* radeonsi: add a bug workaround for NGG - LATE_ALLOC_GSMarek Olšák2020-03-091-0/+6
| | | | | | Cc: 19.3 20.0 <[email protected]> Acked-by: Pierre-Eric Pelloux-Prayer <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4079>
* radeonsi: enable EXT_texture_shadow_lodSonny Jiang2020-03-091-0/+1
| | | | | | | Signed-off-by: Sonny Jiang <[email protected]> Signed-off-by: Marek Olšák <[email protected]> Acked-by: Pierre-Eric Pelloux-Prayer <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4079>
* amd: join emit_kill() from radv and radeonsi in ac_nir_to_llvmDaniel Schürmann2020-03-091-9/+0
| | | | | | Reviewed-by: Marek Olšák <[email protected]> Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4047> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4047>
* radeonsi: lower discard to demote when FS_CORRECT_DERIVS_AFTER_KILL is enabledDaniel Schürmann2020-03-095-26/+7
| | | | | Reviewed-by: Marek Olšák <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4047>
* radeonsi: add 10-bit HEVC encode support for VCN2.0 devicesThong Thai2020-03-061-6/+9
| | | | | | Signed-off-by: Thong Thai <[email protected]> Reviewed-by: Leo Liu <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4033>
* radeonsi: remove AMD_DEBUG=sisched optionPierre-Eric Pelloux-Prayer2020-03-063-7/+1
| | | | | | | | | sisched is not maintained anymore in LLVM. Reviewed-by: Marek Olšák <[email protected]> Reviewed-by: Samuel Pitoiset <[email protected]> Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4059> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4059>
* ac: rename lds_size_per_cu to lds_size_per_workgroupSamuel Pitoiset2020-03-031-1/+1
| | | | | | | | | It's more accurate. Signed-off-by: Samuel Pitoiset <[email protected]> Reviewed-by: Marek Olšák <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3975>
* radeonsi: fix surf_pitch for subsampled surfacePierre-Eric Pelloux-Prayer2020-02-271-10/+10
| | | | | | | | | | | | | | gfx9.surf_pitch is supposed to be in blocks (or elements) but addrlib returns a pitch in pixels. This cause a mismatch between surface->bpe and surface.u.gfx9.surf_pitch. For subsampled formats like uyvy (bpe is 2) this breaks in various places: - sdma copy - video rendering (see issue https://gitlab.freedesktop.org/mesa/mesa/issues/2363) when the vl_compositor_gfx_render method is used Reviewed-by: Marek Olšák <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3738>
* radeonsi: test subsampled format in testdmaPierre-Eric Pelloux-Prayer2020-02-271-30/+31
| | | | | | Reviewed-by: Marek Olšák <[email protected]> Acked-by: Leo Liu <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3738>
* ac,radeonsi: add ac_gpu_info::lds_size_per_cuSamuel Pitoiset2020-02-261-7/+1
| | | | | | | | | Both RadeonSI and RADV use the WGP mode, so we can assume 128KB on GFX10. Signed-off-by: Samuel Pitoiset <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3899>
* radeonsi: Fix compute copies for subsampled formats.Bas Nieuwenhuizen2020-02-191-3/+18
| | | | | | | | | | | | | | | | | | | | | We cannot do image stores (or render) to subsampled formats. Reinterpret as R32_UINT instead. si_set_shader_image_desc already uses the blockwidth from the view formats, so the image width adjustments are already implemented. This is still icky with mipmapping on GFX9+ though, but since it is mostly a video format I don't think that will be much of an issue and broken mipmapping is still better than broken everything. Fixes: e5167a9276d "radeonsi: disable SDMA on gfx8 to fix corruption on RX 580" Closes: https://gitlab.freedesktop.org/mesa/mesa/issues/2535 Reviewed-by: Marek Olšák <[email protected]> Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3853> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3853>
* radeonsi: don't wait for shader compilation to finish when destroying a contextMarek Olšák2020-02-141-3/+0
| | | | | | | | | | | | This was a hack for glsl_types deinitialization and it predates the proper fix, which was the addition of glsl_type_singleton_decref. This fixes a crash when the context is destroyed via the atexit handler. Cc: 19.3 20.0 <[email protected]> Reviewed-by: Timothy Arceri <[email protected]> Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3800> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3800>
* radeonsi: make si_fence_server_signal flush pipe without workPeng Huang2020-02-121-0/+4
| | | | | | | | | | | glSignalSemaphoreEXT sometime doesn't signal the semaphore, it is because radeonsi doesn't flush if gl context doesn't have pending work. Fix the porblem by always submit ib. Reviewed-by: Marek Olšák <[email protected]> Cc: 19.3 20.0 <[email protected]> Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3779> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3779>
* radeonsi: don't update states for the DCC MSAA bug on GFX6-7Marek Olšák2020-02-101-2/+2
| | | | | | Reviewed-by: Bas Nieuwenhuizen <[email protected]> Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3646> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3646>
* radeonsi: fix the DCC MSAA bug workaroundMarek Olšák2020-02-101-1/+1
| | | | | | Cc: 19.3 20.0 <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3646>
* radeonsi: don't report that multi-plane formats are supportedMarek Olšák2020-02-071-7/+0
| | | | | | | | | Fixes: a554b45d - st/mesa: don't lower YUV when driver supports it natively Closes: #2376 Acked-by: Pierre-Eric Pelloux-Prayer <[email protected]> Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3632> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3632>
* radeonsi/ngg: add VGT_FLUSH when enabling fast launchPierre-Eric Pelloux-Prayer2020-02-051-0/+5
| | | | | | | | Closes: https://gitlab.freedesktop.org/mesa/mesa/issues/2418 Closes: https://gitlab.freedesktop.org/mesa/mesa/issues/2426 Closes: https://gitlab.freedesktop.org/mesa/mesa/issues/2434 Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3675> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3675>
* gallium: Add and use a helper for packing uc from a color_union.Eric Anholt2020-02-041-7/+1
| | | | | | | | The same pattern kept coming up, and we don't need to hit util_format_write_4* to do it when we have util_format_pack_rgba(). Reviewed-by: Marek Olšák <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/2744>
* util: Make helper functions for pack/unpacking pixel rows.Eric Anholt2020-02-041-9/+4
| | | | | | | | | Almost all users of the unpack functions don't have strides to plug in (and many are only doing one pixel!), and this will help simplify them. Reviewed-by: Marek Olšák <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/2744>
* radeonsi: Clear uninitialized variableDrew Davenport2020-01-281-1/+1
| | | | | | | | | | | |view| was not initialized leading to flaky test failures in SkQP test unitTest_ES2BlendWithNoTexture. Fixes: 029bfa3d253 "radeonsi: add ability to bind images as image buffers" Reviewed-by: Bas Nieuwenhuizen <[email protected]> Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3592> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3592>
* radeonsi: move AMD_DEBUG tests to AMD_TESTPierre-Eric Pelloux-Prayer2020-01-272-11/+23
| | | | | | | | AMD_DEBUG env var is stored in a 64 bits int and has 64 different values. This commit makes some space by moving the test* special values to AMD_TEST. Reviewed-by: Marek Olšák <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3492>
* radeonsi: fix a regression since the addition of si_shader_llvm_vs.cMarek Olšák2020-01-251-3/+4
| | | | | | | Fixes: cd5b99c541d241d - radeonsi: move VS shader code into si_shader_llvm_vs.c Closes: #2416 Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3561> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3561>
* radeonsi: make screen available to shader part compilationMarek Olšák2020-01-251-0/+4
| | | | | | | to fix a crash in is_multi_part_shader. Fixes: 1a0890dcf30 - radeonsi: change prototypes of si_is_multi_part_shader & si_is_merged_shader Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3561>
* radeonsi: expose shader cache stats to the HUDMarek Olšák2020-01-242-8/+46
| | | | | | Reviewed-by: Pierre-Eric Pelloux-Prayer <[email protected]> Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/2929> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/2929>
* radeonsi: print shader cache stats with AMD_DEBUG=cache_statsMarek Olšák2020-01-244-5/+24
| | | | | Reviewed-by: Pierre-Eric Pelloux-Prayer <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/2929>
* radeonsi: restructure si_shader_cache_load_shaderMarek Olšák2020-01-241-39/+31
| | | | | Reviewed-by: Pierre-Eric Pelloux-Prayer <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/2929>
* radeonsi: use the live shader cacheMarek Olšák2020-01-247-25/+46
| | | | | Reviewed-by: Pierre-Eric Pelloux-Prayer <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/2929>
* radeonsi: separate LLVM compilation from non-LLVM codeMarek Olšák2020-01-231-20/+38
| | | | | | Reviewed-by: Timothy Arceri <[email protected]> Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3421> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3421>
* radeonsi: change prototypes of si_is_multi_part_shader & si_is_merged_shaderMarek Olšák2020-01-233-16/+16
| | | | | Reviewed-by: Timothy Arceri <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3421>
* radeonsi: make si_compile_shader return boolMarek Olšák2020-01-233-21/+18
| | | | | Reviewed-by: Timothy Arceri <[email protected]> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3421>
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-05 07:02:38 +0000