summaryrefslogtreecommitdiffstats
path: root/src/amd
Commit message (Collapse)AuthorAgeFilesLines
* radv: additional query fixesAndres Rodriguez2019-08-171-7/+8
| | | | | | | | | Make sure we read the updated data from the gpu in cases where WAIT_BIT is not set. Cc: 19.1 19.2 <[email protected] Reviewed-by: Samuel Pitoiset <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* ac/nir: Assert GS input index is constantConnor Abbott2019-08-231-0/+1
| | | | | | If it's not we silently ignore indir_index which is definitely a bug. Reviewed-by: Marek Olšák <[email protected]>
* ac/nir: Handle const array offsets in get_deref_offset()Connor Abbott2019-08-231-6/+11
| | | | | | | | | | | Some users of this function (e.g. GS inputs) currently only work with constant offsets. We got lucky since all the tests used an array index of 0, so the non-constant part was always 0. But we still need to handle this. This doesn't fix any CTS test, but was noticed while debugging one. Reviewed-by: Marek Olšák <[email protected]>
* radv/gfx10: do not use NGG with NAVI14Samuel Pitoiset2019-08-231-0/+1
| | | | | | Cc: 19.2 <[email protected]> Signed-off-by: Samuel Pitoiset <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* radv/gfx10: don't initialize VGT_INSTANCE_STEP_RATE_0Samuel Pitoiset2019-08-231-1/+2
| | | | | | | | | Only gfx9 and older use it to get InstanceID in VGPR1. Ported from RadeonSI. Cc: 19.2 <[email protected]> Signed-off-by: Samuel Pitoiset <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* ac,radv,radeonsi: remove LLVM 7 supportSamuel Pitoiset2019-08-2310-302/+62
| | | | | | | | Now that LLVM 9 will be released soon, we will only support LLVM 8, 9 and master (10). Signed-off-by: Samuel Pitoiset <[email protected]> Reviewed-by: Marek Olšák <[email protected]>
* radv: Disable NGG for geometry shaders.Bas Nieuwenhuizen2019-08-221-0/+20
| | | | | | | | A bunch of remaining issues including some that affect users. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111248 Fixes: ee21bd7440c "radv/gfx10: implement NGG support (VS only)" Reviewed-by: Samuel Pitoiset <[email protected]>
* ac: fix exclusive scans on GFX8-GFX9Samuel Pitoiset2019-08-221-4/+3
| | | | | | | | | | | | This fixes a regression introduced with scan&reduce operations on GFX10. Note that some subgroups CTS still fail on GFX10 but I assume it's a different issue. This fixes dEQP-VK.subgroups.arithmetic.*.subgroupexclusive*. Fixes: 227c29a80de "amd/common/gfx10: implement scan & reduce operations" Signed-off-by: Samuel Pitoiset <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* radv: add RADV_DEBUG=allentrypointsAndres Rodriguez2019-08-212-8/+20
| | | | | | | | | | | | This debug option allows vkGet[Instance/Device]ProcAddr() to succeed even if the extension associated with the requested entrypoint was not enabled. This has come in handy in a few instances when debugging VR applications, so I thought it would be good to have a cleaned up version upstreamed. Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* nir: Add explicit signs to image min/max intrinsicsJason Ekstrand2019-08-212-21/+38
| | | | | | | | | | | This better matches all the other atomic intrinsics such as those for SSBOs and shared variables where the sign is part of the intrinsic opcode. Both generators (GLSL and SPIR-V) know the sign from the type of the image variable or handle. In SPIR-V, signed min/max are separate opcodes from unsigned. Reviewed-by: Kenneth Graunke <[email protected]> Reviewed-by: Eric Anholt <[email protected]>
* radv: implement VK_AMD_shader_core_properties2Samuel Pitoiset2019-08-212-0/+10
| | | | | | | Trivial extension that matches PAL. Signed-off-by: Samuel Pitoiset <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* radv: force enable VK_AMD_shader_ballot for Wolfenstein YoungbloodSamuel Pitoiset2019-08-211-0/+8
| | | | | | | | | | | | | | This gives a nice boost, +20% at this time on my Vega 56. Shader ballot should be enabled by default at some point but it reduces performance a bit (-6%) with Wolfeinstein II. Enable it only for Youngblood at the moment, like what we did for Talos in the past. As a bonus point, it gets rid of some minor artifacts that only happens when ballot is disabled for some reasons. Cc: 19.2 <[email protected] Signed-off-by: Samuel Pitoiset <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* radv: add a new debug option called RADV_DEBUG=noshaderballotSamuel Pitoiset2019-08-212-0/+2
| | | | | | | | | Shader ballot will be enabled by default for Wolfenstein Youngblood. This follows what we did for sisched. Cc: 19.2 <[email protected] Signed-off-by: Samuel Pitoiset <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* radv: allow to enable VK_AMD_shader_ballot only on GFX8+Samuel Pitoiset2019-08-212-2/+3
| | | | | | | | Scans aren't implemented on SI/CIK. Cc: 19.2 <[email protected]> Signed-off-by: Samuel Pitoiset <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* radv: Emit VGT_GS_ONCHIP_CNTL for tess on GFX10.Bas Nieuwenhuizen2019-08-211-0/+8
| | | | | | | | Otherwise hangs are possible. This register was already set for GS and NGG. Fixes: 5eaed7ecfce "radv/gfx10: enable support for NAVI10, NAVI12 and NAVI14" Reviewed-by: Samuel Pitoiset <[email protected]>
* radv: Use correct vgpr_comp_cnt for VS if both prim_id and instance_id are ↵Bas Nieuwenhuizen2019-08-211-2/+4
| | | | | | | | | needed. Should take the max of the 2. Fixes: ea337c8b7e9 "radv/gfx10: fix VS input VGPRs with the legacy path" Reviewed-by: Samuel Pitoiset <[email protected]>
* radv/gfx10: hardcode some depth+stencil formats in the format tableSamuel Pitoiset2019-08-211-0/+5
| | | | | | | | | | | The script doesn't handle them correctly and D16_UNORM_S8_UINT isn't supported by the hardware, mark it as invalid. This fixes warning when generating gfx10_format_table.h. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111393 Signed-off-by: Samuel Pitoiset <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* radv/gfx10: tidy up gfx10_format_table.pySamuel Pitoiset2019-08-211-11/+9
| | | | | Signed-off-by: Samuel Pitoiset <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* radv/gfx10: do not emit PA_SC_TILE_STEERING_OVERRIDE twiceSamuel Pitoiset2019-08-201-2/+0
| | | | | | | CLEAR_STATE emits it for us. Signed-off-by: Samuel Pitoiset <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* radv: do not emit PKT3_CONTEXT_CONTROL with AMDGPU 3.6.0+Samuel Pitoiset2019-08-202-6/+12
| | | | | | | It's emitted by the kernel. Signed-off-by: Samuel Pitoiset <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* radv: Add Renoir support.Bas Nieuwenhuizen2019-08-192-3/+6
| | | | | | | | | Took the freedom to enable dfsm even though I don't have benchmark results yet, but it seems Raven-like. Rest is from radeonsi. Reviewed-by: Samuel Pitoiset <[email protected]>
* radeonsi/nir: always lower ballot masks as 64-bit, codegen handles itMarek Olšák2019-08-194-4/+14
| | | | | | This fixes KHR-GL45.shader_ballot_tests.ShaderBallotBitmasks. This solution is better, because the IR isn't dependent on wave32.
* ac/nir: set image=true when loading FMASK for imagesMarek Olšák2019-08-191-1/+1
| | | | Reviewed-by: Pierre-Eric Pelloux-Prayer <[email protected]>
* ac/nir: Fix store_scratch with a non-full writemaskConnor Abbott2019-08-183-5/+42
| | | | | | | | | | | | By adding one more helper to ac_llvm_build, we can also easily keep vector stores together. Fixes the tests/spec/glsl-1.30/execution/fs-large-local-array-vec4.shader_test piglit test. Fixes: 74470baebbd ("ac/nir: Lower large indirect variables to scratch") Reviewed-by: Marek Olšák <[email protected]
* Revert "radv/gfx10: Enable DCC for storage images."Bas Nieuwenhuizen2019-08-163-18/+4
| | | | | | | Quite useless without DCC for LAYOUT_GENERAL. Fixes: b4dad3afaa0 Revert "radv: Do not decompress on LAYOUT_GENERAL." Acked-by: Dave Airlie <[email protected]>
* Revert "radv: Do not decompress on LAYOUT_GENERAL."Bas Nieuwenhuizen2019-08-161-3/+3
| | | | | | | Causes issues with a bunch of games with DXVK. Fixes: 50add1b33ae "radv: Do not decompress on LAYOUT_GENERAL." Acked-by: Dave Airlie <[email protected]>
* radeonsi: add support for RenoirMarek Olšák2019-08-145-1/+11
| | | | Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* nir: merge and extend nir_opt_move_comparisons and nir_opt_move_load_uboRhys Perry2019-08-121-1/+1
| | | | | | | | | | v2: add to series v3: update Makefile.sources v4: don't remove a comment and break statement v4: use nir_can_move_instr Signed-off-by: Rhys Perry <[email protected]> Reviewed-by: Eric Anholt <[email protected]>
* radv: Enable VK_KHR_pipeline_executable_properties.Bas Nieuwenhuizen2019-08-122-1/+7
| | | | Reviewed-by: Dave Airlie <[email protected]>
* radv: Implement radv_GetPipelineExecutableStatisticsKHR.Bas Nieuwenhuizen2019-08-121-0/+103
| | | | Reviewed-by: Dave Airlie <[email protected]>
* radv: Implement radv_GetPipelineExecutableInternalRepresentationsKHR.Bas Nieuwenhuizen2019-08-121-5/+104
| | | | Reviewed-by: Dave Airlie <[email protected]>
* radv: Implement radv_GetPipelineExecutablePropertiesKHR.Bas Nieuwenhuizen2019-08-121-0/+111
| | | | Reviewed-by: Dave Airlie <[email protected]>
* radv: Keep shader info when needed.Bas Nieuwenhuizen2019-08-124-23/+36
| | | | | | | This allows enabling the shader info keeping on a per shader basis. Also disables the cache on a per shader basis. Reviewed-by: Dave Airlie <[email protected]>
* radv: Add VK_KHR_pipeline_executable_properties in disabled state.Bas Nieuwenhuizen2019-08-121-0/+1
| | | | | | So we can add the functions. Reviewed-by: Dave Airlie <[email protected]>
* radv: Use string for nir dumping.Bas Nieuwenhuizen2019-08-124-8/+29
| | | | | | Reviewed-by: Dave Airlie <[email protected]> Allows us to easily dump all nir shaders for combined variants in vega and simplifies ownership.
* radv: Get max workgroup size without nir.Bas Nieuwenhuizen2019-08-123-19/+28
| | | | Reviewed-by: Dave Airlie <[email protected]>
* radv: Add utility function to calculate max waves.Bas Nieuwenhuizen2019-08-122-8/+24
| | | | | | Not AC because a lot of it is data extraction out of radv structs. Reviewed-by: Dave Airlie <[email protected]>
* radeonsi/nir: implement default tess level system valuesMarek Olšák2019-08-122-3/+10
| | | | Reviewed-by: Connor Abbott <[email protected]>
* compiler: add SYSTEM_VALUE_USER_DATA_AMDMarek Olšák2019-08-122-0/+5
| | | | for internal radeonsi shaders
* compiler: add ACCESS_STREAM_CACHE_POLICYMarek Olšák2019-08-121-0/+3
| | | | | | radeonsi will use this. Reviewed-by: Connor Abbott <[email protected]>
* radv: Do not setup attachments without a framebuffer.Bas Nieuwenhuizen2019-08-121-3/+5
| | | | | | | Test that found this: dEQP-VK.geometry.layered.1d_array.secondary_cmd_buffer Fixes: 49e6c2fb78c "radv: Store color/depth surface info in attachment info instead of framebuffer." Reviewed-by: Dave Airlie <[email protected]>
* radv: Hash Wave32 settings in shader key.Bas Nieuwenhuizen2019-08-122-0/+9
| | | | | | | Can result in different shaders. Fixes: 8a86908e9a7 "radv/gfx10: add Wave32 support for vertex, tessellation and geometry shaders" Reviewed-by: Dave Airlie <[email protected]>
* radv: Properly use Wave64 for non-NGG GS and copy shader.Bas Nieuwenhuizen2019-08-121-1/+4
| | | | | Fixes: 8a86908e9a7 "radv/gfx10: add Wave32 support for vertex, tessellation and geometry shaders" Reviewed-by: Dave Airlie <[email protected]>
* radv: Put wave size in shader options/info.Bas Nieuwenhuizen2019-08-124-48/+38
| | | | | | | Instead of having the three values everywhere. This is also more future proof if we want the driver to make those decisions eventually. Reviewed-by: Dave Airlie <[email protected]>
* amd: prepare dropping include of p_compiler.hLionel Landwerlin2019-08-093-4/+5
| | | | | Signed-off-by: Lionel Landwerlin <[email protected]> Acked-by: Eric Engestrom <[email protected]>
* radv: Avoid VEGA/RAVEN scissor bug in binning.Bas Nieuwenhuizen2019-08-081-1/+2
| | | | | CC: <[email protected]> Reviewed-by: Dave Airlie <[email protected]>
* radv: Avoid binning RAVEN hangs.Bas Nieuwenhuizen2019-08-081-1/+2
| | | | | | | Mirroring radeonsi. CC: <[email protected]> Reviewed-by: Dave Airlie <[email protected]>
* radv: Fix off by one for S_028C48_MAX_ALLOC_COUNT.Bas Nieuwenhuizen2019-08-081-1/+1
| | | | Reviewed-by: Dave Airlie <[email protected]>
* radv/gfx10: Enable DCC for storage images.Bas Nieuwenhuizen2019-08-073-4/+18
| | | | | | v2: Hide it behind a perftest flag. Reviewed-by: Dave Airlie <[email protected]>
* radv: Add device argument for dcc compression check.Bas Nieuwenhuizen2019-08-075-18/+24
| | | | | | Because it is about to be generation dependent. Reviewed-by: Dave Airlie <[email protected]>
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-29 03:51:30 +0000