summaryrefslogtreecommitdiffstats
path: root/src/amd
Commit message (Collapse)AuthorAgeFilesLines
* radv/vulkan: Move radv_get_driver_version to src/vulkan/utilAlex Smith2017-06-061-23/+1
| | | | | | | | | | | | This means it can be reused for other Vulkan drivers. Also fix up a typo, need to search for '.' in the version string rather than ','. v2: Remove unneeded temporary version variable (Emil, Eric) Signed-off-by: Alex Smith <[email protected]> Reviewed-by: Emil Velikov <[email protected]> Reviewed-by: Eric Engestrom <[email protected]> Reviewed-by: Jason Ekstrand <[email protected]>
* util/vulkan: Move Vulkan utilities to src/vulkan/utilAlex Smith2017-06-064-4/+5
| | | | | | | | | | | | | We have Vulkan utilities in both src/util and src/vulkan/util. The latter seems a more appropriate place for Vulkan-specific things, so move them there. v2: Android build system changes (from Tapani Pälli) Signed-off-by: Alex Smith <[email protected]> Reviewed-by: Emil Velikov <[email protected]> Reviewed-by: Eric Engestrom <[email protected]> Acked-by: Jason Ekstrand <[email protected]>
* radv: expose integrated device type for APUs.Dave Airlie2017-06-061-1/+1
| | | | | | | | This just sets the vulkan device type depending on whether this is an APU or GPU. Signed-off-by: Dave Airlie <[email protected]> Fixes: f4e499ec791 "radv: add initial non-conformant radv vulkan driver"
* ac/surface: Fix HTILE for radv.Bas Nieuwenhuizen2017-06-061-2/+1
| | | | | | | We always compute HTILE size using addrlib, even when not TC compatible. Signed-off-by: Bas Nieuwenhuizen <[email protected]> Reviewed-by: Dave Airlied <[email protected]>
* radv: fix write event eop on vega.Dave Airlie2017-06-061-1/+1
| | | | Typo here, fixes command submission hangs on vega
* radv: enable GFX9 on radvDave Airlie2017-06-061-2/+4
| | | | | | | | I'm open to reverting this closer to release if bad things happen, but it might be easier to debugging to leave it for now. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: turn off geom/tess for gfx9.Dave Airlie2017-06-061-4/+4
| | | | | | | We don't support these yet, and it'll take a bit of work to do so. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: misc GFX9 changes.Dave Airlie2017-06-063-6/+21
| | | | | | | These are just some register changes ported from radeonsi for gfx9. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: add some GFX9 specific events.Dave Airlie2017-06-061-0/+16
| | | | | | | | These are ported from radeonsi, don't know all the rules for when they should be inserted. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: add IA_MULTI_VGT_PARAM support for GFX9.Dave Airlie2017-06-063-5/+16
| | | | | Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: add rb+ support for GFX9Dave Airlie2017-06-065-1/+22
| | | | | | | | This adds some rb+ support, as on GFX9 we have to disable it as per radeonsi. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: add GFX9 cache flushing support.Dave Airlie2017-06-064-51/+145
| | | | | | | | | GFX9 needs to write event EOP to a fence buffer, allocate some space for this, and just write an ever increasing number to it, this isn't exactly what radeonsi does, but it seems to work. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: add texture descriptor/fmask/cmask support for GFX9Dave Airlie2017-06-061-31/+158
| | | | | | | | This adds gfx9 support for the texture descriptor along with the fmask/cmask allocation routines. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: add GFX9 to initialisation cmd buffer.Dave Airlie2017-06-062-16/+61
| | | | | | | | This just adds support for initialising some GFX9 registers, and handles the different init for the VGT reuse reg. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: don't setup raster_config on gfx9.Dave Airlie2017-06-061-12/+16
| | | | | Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: add gfx9 cp dma support.Dave Airlie2017-06-061-5/+16
| | | | | | | | This adds support to the CP dma code for GFX9, ported from radeonsi. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: add gfx9 depth/stencil surface support.Dave Airlie2017-06-063-15/+74
| | | | | | | This is ported from radeonsi. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: add GFX9 support for color surfaces.Dave Airlie2017-06-063-16/+69
| | | | | | | This is ported from radeonsi. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: add some misc gfx9 pieces.Dave Airlie2017-06-066-0/+13
| | | | | | | | This just adds the strings and includes the gfx9 register defs in some files that we need them in. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: set offchip hs param like radeonsi.Dave Airlie2017-06-061-3/+1
| | | | | | | radeonsi never uses 512 here anymore. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: fix typo in comment.Dave Airlie2017-06-061-1/+1
|
* radv: add a comment from radeonsi before cp dma function.Dave Airlie2017-06-061-0/+4
| | | | | | This is just copied over. Signed-off-by: Dave Airlie <[email protected]>
* radv: remove doubled up prototype.Dave Airlie2017-06-061-4/+0
| | | | Must have snuck in during a rebase.
* radv: split metadata struct into legacy/gfx9 parts.Dave Airlie2017-06-063-41/+58
| | | | | | | This is just ported from radeonsi. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: refactor some texture descriptor state.Dave Airlie2017-06-061-9/+17
| | | | | | | | This just splits out some non-gfx9 bits in advance to avoid regressions. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: refactor color surface init before gfx9.Dave Airlie2017-06-061-25/+35
| | | | | | | This just moves the code around in preparation for gfx9 support. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: refactor depth/stencil state setupDave Airlie2017-06-061-57/+62
| | | | | | | | In advance of GFX9 to reduce chances for regression, refactor this code out so adding the GFX9 changes will be more obvious. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: use radv_foreach_stage in a couple of places.Dave Airlie2017-06-061-46/+12
| | | | | | | | This just collapses a few per-stage things into a loop, shouldn't affect anything. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: use ac_compute_surfaceNicolai Hähnle2017-06-051-386/+6
| | | | Reviewed-by: Dave Airlie <[email protected]>
* radv: prepare fmask surface creationDave Airlie2017-06-052-7/+7
| | | | | | | | | | | | | | | | | The old code copied over all the surface info from the image surface, we only want some bits of it, and to modify the flags. This prevents a regression in dEQP-VK.api.copy_and_blit.resolve_image.* and others in the subsequent switch to ac_compute_surface. v2: - also disable opt4Space in radv_amdgpu_surface, so that we can apply this patch separately *before* switching to ac_compute_surface and hopefully avoid intermittent regressions (Nicolai) Signed-off-by: Dave Airlie <[email protected]> Reviewed-by: Dave Airlie <[email protected]> Signed-off-by: Nicolai Hähnle <[email protected]>
* radv: use amdgpu_addr_createNicolai Hähnle2017-06-054-158/+5
| | | | Reviewed-by: Dave Airlie <[email protected]>
* radv: stop using radv_amdgpu_winsys::familyNicolai Hähnle2017-06-052-2/+2
| | | | Reviewed-by: Dave Airlie <[email protected]>
* radv: use ac_gpu_infoNicolai Hähnle2017-06-055-229/+13
| | | | Reviewed-by: Dave Airlie <[email protected]>
* radv: remove radeon_info::nameNicolai Hähnle2017-06-053-30/+27
| | | | Reviewed-by: Dave Airlie <[email protected]>
* radv: use ac_surface data structuresNicolai Hähnle2017-06-058-153/+81
| | | | | | | | | This is mostly mechanical changes of renaming types and introducing "legacy" everywhere. It doesn't use the ac_surface computation functions yet. Reviewed-by: Dave Airlie <[email protected]>
* radv: rename radeon_surf::bo_{size,alignment} to surf_{size,alignment}Nicolai Hähnle2017-06-053-12/+13
| | | | | | To match radeonsi / ac_surface. Reviewed-by: Dave Airlie <[email protected]>
* radv: remove unused RADEON_SURF_HAS_SBUFFER_MIPTREENicolai Hähnle2017-06-052-3/+1
| | | | Reviewed-by: Dave Airlie <[email protected]>
* radv: remove radeon_surf_level::nblk_zNicolai Hähnle2017-06-053-6/+1
| | | | | | | We're not using thick tiling modes, so we can just derive the value ourselves. Reviewed-by: Dave Airlie <[email protected]>
* radv: remove radeon_surf_level::dcc_enabledNicolai Hähnle2017-06-055-6/+7
| | | | | | Like radeonsi; replace with radeon_surf::num_dcc_levels. Reviewed-by: Dave Airlie <[email protected]>
* radv: remove radeon_surf_level::pitch_bytesNicolai Hähnle2017-06-055-13/+3
| | | | | | | Like radeonsi. This saves memory, and the information can easily be recomputed on the fly where necessary. Reviewed-by: Dave Airlie <[email protected]>
* radv: add surface helper variable in radv_GetImageSubresourceLayoutNicolai Hähnle2017-06-051-6/+7
| | | | Reviewed-by: Dave Airlie <[email protected]>
* radv: fewer than 8 RBs are possibleNicolai Hähnle2017-06-051-2/+0
| | | | | | This fixes the subsequent assertion on Bonaire. Reviewed-by: Dave Airlie <[email protected]>
* ac/surface/gfx6: explicitly support S8 surfacesNicolai Hähnle2017-06-051-25/+50
| | | | | | This is needed by radv for dEQP-VK.renderpass.simple.stencil Reviewed-by: Dave Airlie <[email protected]>
* ac/nir: set workgroup size attribute to correct value.Dave Airlie2017-06-051-3/+32
| | | | | | | | | | | | This ports: 55445ff1891724c78e6573d2f8c721e14c0449fc from radeonsi radeonsi: tell LLVM not to remove s_barrier instructions LLVM 5.0 removes s_barrier instructions if the max-work-group-size attribute is not set. What a surprise. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* ac: add new helper function to add a integer target dependent function attr.Dave Airlie2017-06-052-0/+15
| | | | | | | This is needed to add the max workgroup size attribute. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: add external memory support.Dave Airlie2017-06-053-14/+183
| | | | | | | | | | | | | | | | | | | | | | | This adds support for exporting 2D images, to an opaque fd. This implements the: VK_KHX_external_memory_capabilities VK_KHX_external_memory VK_KHX_external_memory_fd extensions. These are used by SteamVR, we should work with anv to decide if we should ship these under an env var or something. v2 (Bas): - Don't expose the semaphore ext without implementing it. - Only export the capabilities ext as instance ext. - Implement radv_GetPhysicalDeviceExternalBufferPropertiesKHX. Signed-off-by: Dave Airlie <[email protected]> Signed-off-by: Bas Nieuwenhuizen <[email protected]>
* radv: Add VkPhysicalDeviceIDProperties support.Bas Nieuwenhuizen2017-06-052-2/+23
| | | | | Signed-off-by: Bas Nieuwenhuizen <[email protected]> Reviewed-by: Dave Airlie <[email protected]>
* radv: Add support for external queue family.Bas Nieuwenhuizen2017-06-051-1/+6
| | | | | Signed-off-by: Bas Nieuwenhuizen <[email protected]> Reviewed-by: Dave Airlie <[email protected]>
* radv/formats: reverse how the image format properties KHR2 is handledDave Airlie2017-06-051-30/+46
| | | | | | | This just aligns with how anv does it. Reviewed-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* radv: Dirty all descriptors sets when changing the pipeline.Bas Nieuwenhuizen2017-06-032-8/+14
| | | | | | | | | Sets could have been ignored during previous descriptor set flush due to the shader not using them and therefore no SGPR being assigned. Signed-off-by: Bas Nieuwenhuizen <[email protected]> Reviewed-by: Dave Airlie <[email protected]> Fixes: ae61ddabe8c "radv: move userdata sgpr ownership to compiler side."
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-22 16:05:16 +0000