Avoiding NaNs should have the same effect but it's good practice to not
rely on float OPs for correctness.
Fixes: 95a89f7 ("radv: Report smaller bvh sizes when possible")
Reviewed-by: Natalie Vock <natalie.vock@gmx.de>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39640>
(cherry picked from commit 24a1e3d8c2)
As seen in the Vivante kernel driver function gckHARDWARE_Flush(),
GPUs without gcvFEATURE_TEX_CACHE_FLUSH_FIX, which translates to
all GPUs before halti5, need a full stall of the GPU pipeline
before flushing the texture caches.
This fixes sporadic GPU hangs observed in use-cases where texture
data updates are intermixed with draws without any state changes
that might necessitate a stall.
Cc: mesa-stable
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Reviewed-by: Christian Gmeiner <cgmeiner@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39673>
(cherry picked from commit 643ba9a784)
When you get UnexpectedResult(skip), that means take your xfail out
because it's now skipping. Which is the fix, instead of "take the xfail
out and add it to manual skips".
Fixes: e54440d15e ("Uprev Piglit to a3826de3c26a279599d15b018a9a3e75ca46f4f8")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39568>
(cherry picked from commit 42e17a948e)
The generation version for V3D XML package was marked as 3.3, but
actually we removed all the code supporting this generation, and the
generations we support now are from 4.2 onwards.
So we bump up the generation version.
Fixes: 9c4829473a ("broadcom/cle: remove v33 and v41 from xml definition")
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Signed-off-by: Juan A. Suarez Romero <jasuarez@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39577>
(cherry picked from commit 5a85b3d9f4)
Mesh shader uses store per vertex output for point size
and store per primitive output for layer id.
This fixes gpu-ratemeter run slow for kill point size
and layer id cases when mono shader is used which expect
to kill these outputs.
Also gather fragment shader per primitive input info
to kill mesh shader per primitive output.
Fixes: e6e21dfbf2 ("radeonsi: kill outputs for mesh shader")
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39644>
(cherry picked from commit f20cd07e21)
For non-WSI images, explicitly map VK_IMAGE_LAYOUT_PRESENT_SRC_KHR to
VK_IMAGE_LAYOUT_TRANSFER_SRC_OPTIMAL in anv_layout_to_aux_state().
Before this patch, the function passed PRESENT_SRC into
vk_image_layout_to_usage_flags() and got a return value of 0 from it
(that function expects that layout to be explicitly handled by the
caller). This caused the logic dependent on the return value to be
unreliable.
Fixes: c5cad407f8 ("anv: handle non-wsi images in anv_layout_to_aux_state")
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39618>
(cherry picked from commit f616d4fb2a)
Don't return early from anv_layout_to_fast_clear_type() for Xe2+. We'll
need to make more use of the function for some MCS changes in later
commits.
Reviewed-by: Jianxun Zhang <jianxun.zhang@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37660>
(cherry picked from commit 811c413f98)
This change updates the vs_as_ls switch logic to make it
reliable. It resets the dirty flag when the switch is
happening. It uses also evergreen_emit_vs_constant_buffers()
to try to update again some of the states which could be
lost otherwise.
This change fixes some "flakes". These tests needed previously
to be executed twice to set the hardware in the proper state
for the test to pass. It also fixes the main issue of the
texture_view.view_sampling test.
This change was tested on palm and cayman. Here are the tests
which are now utterly fixed:
khr-gl4[3-6]/stencil_texturing/functional: fail pass
khr-gl4[4-6]/texture_cube_map_array/texture_size_tesselation_ev_sh: fail pass
khr-gles31/core/texture_cube_map_array/texture_size_tesselation_ev_sh: fail pass
khr-glesext/texture_cube_map_array/texture_size_tesselation_ev_sh: fail pass
Fixes: 25f96c1120 ("r600: hook up constants/samplers/sampler view for tessellation")
Signed-off-by: Patrick Lerda <patrick9876@free.fr>
Acked-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39269>
(cherry picked from commit 9c5e15e6f5)
The empty .clang-format file in the project root is required for meson
to generate the clang-format target. It was accidentally deleted.
Fixes: efe60d2940 ("intel: remove unused show_shader_stage debug option")
Signed-off-by: Christian Gmeiner <cgmeiner@igalia.com>
Acked-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39648>
(cherry picked from commit 449261b6ba)
It was incorrect to mark chit/miss arguments as discardable without
the equivalent in the traversal shader. Also, tail calls with modified
parameters that aren't marked discardable are incorrect.
This could lead to random corruption by clobbering parameter values
across two levels of nested calls: A Raygen shader calls traversal,
expecting e.g. the ray tMax parameter to be preserved. Traversal
overwrites the parameter's register with the hit t and tail-calls chit,
which immediately returns to raygen. Now the raygen shader still has the
clobbered tMax (which is actually the ray hit t) - if it calls traversal
multiple times, the second traversal iteration may use the previous
ray's hit t as tMax instead of the intended value.
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39579>
(cherry picked from commit 3275be503c)
There were two issues here:
1. Tail calls where the tail-callee receives modified parameters are
hazardous and only work if the parameter is return or discardable.
Otherwise, the caller of the function that executes the tail-call may
not expect some of the parameters to be clobbered.
2. There was also an indexing confusion with the call instruction vs.
call signature parameters. The call instruction has not been adapted
to the new lowered signatures, where the system args are prepended. To
make things clearer, split the loop into two, one iterating over
parameters in the call signature and one for parameters of the call
instruction.
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39579>
(cherry picked from commit 0d7705c206)
The original semantic of discardable parameters was "okay, nothing
actually uses this parameter, feel free to clobber it", but we were
only using it with tail calls from a function without discardable
parameters, which was broken.
Instead, slightly change the use-case and utilize the "discardable"
attribute to mark parameters that the callee will clobber in a tail
call. This makes doing tail calls safe when the tail callee receives a
modified set of parameters.
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39579>
(cherry picked from commit ad23e02a28)
This matches the initialization that the proprietary driver does.
Fixes dEQP-VK.query_pool.discard.*.alpha_to_coverage* on vk cts 1.4.5
Cc: mesa-stable
Reviewed-by: Mary Guillemard <mary@mary.zone>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39621>
(cherry picked from commit 8d7f14620b)
Expose DRM format modifiers via VkDrmFormatModifierPropertiesList2EXT.
VVL is one notable user.
This is required for VK_EXT_image_drm_format_modifier when
VK_KHR_format_feature_flags2 is supported.
Cc: mesa-stable
Signed-off-by: Valentine Burley <valentine.burley@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39600>
(cherry picked from commit e185f40fc3)
In case of texel buffers that are read in the shader, but not bound by
the application, the current implementation would incorrectly try to
read from non-existent buffers.
To ensure this does not happen, this change sets the format for any
unbound attributes to CONST_0000, which will kill any actual
reads/writes and always return zeroes.
This fixes the following two tests:
- spec@arb_shading_language_420pack@active sampler conflict
- spec@arb_texture_buffer_object@render-no-bo
Fixes: a21ee564e2 ("pan/bi: Make texel buffers use Attribute Buffers")
Acked-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39431>
(cherry picked from commit aec8132b8b)
Also change to use H265 constant for maxDpbSlots (both values for H264 and H265
are the same).
Fixes: ee535aa039 ("radv: video: rework maxActiveReferenceSlot/MaxDpbSlots")
Reviewed-by: Benjamin Cheng <benjamin.cheng@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39609>
(cherry picked from commit 7607aeefa6)
This is just wrong if the secondary uses ESO because the emitted
pipelines would be NULL in the secondary, but if the app re-binds
the same pipeline in the primary it would consider it as already
emitted. A sequence like this would break:
CmdBindPipeline(compute)
CmdDispatch()
CmdExecuteCommands() --> with ESO compute
CmdBindPipeline(compute)
CmdDispatch()
This tracking is probably useless anyways because it's unlikely that
apps will rebind the same pipeline right after CmdExecuteCommands() but
let's keep it because this is a bugfix.
Fixes
dEQP-VK.api.command_buffers.pipeline_shader_object_mix_with_secondaries.
Cc: mesa-stable
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39587>
(cherry picked from commit 9ad02b5724)
The pMiColStarts/pMiRowStarts arrays from applications may have
incorrect units. Instead of using them directly, compute the tile
start positions in superblock units internally based on the tile
dimensions.
Cc: mesa-stable
Signed-off-by: Hyunjun Ko <zzoon@igalia.com>
Acked-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39471>
(cherry picked from commit 8e9fec8e40)
It might be that the radv_pipeline_cache_lookup_nir_handle() in
radv_ray_tracing_pipeline_cache_search() fails but we will later need the
NIR. If rt_stages[i].shader was non-NULL, then we would not have created
the NIR.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Backport-to: 25.2
Reviewed-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38263>
(cherry picked from commit 89eefdcadb)
The non-dynamic members of xfb_info are already included in
sizeof(hk_passthrough_gs_key), so adding nir_xfb_info_size counts them
twice. Because of this we were including uninitialized memory in the key
in hk_handle_passthrough_gs, which is undefined behavior.
Fixes: 5bc8284816 ("hk: add Vulkan driver for Apple GPUs")
Signed-off-by: Olivia Lee <olivia.lee@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39574>
(cherry picked from commit d6745b358d)
This fixes bunch of cts tests hitting issues when attempting
anv_image_mcs_op with compute.
Fixes: ab9d3528dc ("anv: fix queue check in anv_blorp_execute_on_companion on xe3")
Signed-off-by: Tapani Pälli <tapani.palli@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39581>
(cherry picked from commit 85978ccd28)
When proceeding with rendering, any transient attachment that will be used
as LRZ buffer should also be allocated. With GMEM rendering, these
attachments otherwise remained unloaded and subsequent LRZ clears produced
GPU faults.
Signed-off-by: Zan Dobersek <zdobersek@igalia.com>
Fixes: 764b3d9161 ("tu: Implement transient attachments and lazily allocated memory")
Fixes: #14604
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39535>
(cherry picked from commit b6a049ea4b)
The samples per tile calculation was incorrect for sample count 4 and 8.
Fix:
dEQP-VK.pipeline.monolithic.multisample.std_sample_locations.draw.depth.samples_4.*
dEQP-VK.pipeline.monolithic.multisample.std_sample_locations.draw.stencil.samples_4.*
Backport-to: 26.0
Signed-off-by: Nick Hamilton <nick.hamilton@imgtec.com>
Reviewed-by: Frank Binns <frank.binns@imgtec.com>
Reviewed-by: Simon Perretta <simon.perretta@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39580>
(cherry picked from commit 9f9788330e)
Within the driver buffers are treated as 2D as sampling them as 1D
will run into HW restrictions on max size.
The compiler does the same however for atomic image ops the address
is manually calculated and doing this via the 2D path leads to
incorrect offsets.
The fix is to treat buffers as 1D for atomic ops which calculates
the correct offsets for the operations.
Fix deqp:
dEQP-VK.image.atomic_operations.add.buffer.*
dEQP-VK.image.atomic_operations.and.buffer.*
dEQP-VK.image.atomic_operations.compare_exchange.buffer.*
dEQP-VK.image.atomic_operations.dec.buffer.*
dEQP-VK.image.atomic_operations.exchange.buffer.*
dEQP-VK.image.atomic_operations.inc.buffer.*
dEQP-VK.image.atomic_operations.max.buffer.*
dEQP-VK.image.atomic_operations.min.buffer.*
dEQP-VK.image.atomic_operations.or.buffer.*
dEQP-VK.image.atomic_operations.sub.buffer.*
dEQP-VK.image.atomic_operations.xor.buffer.*
Fixes: 6dc5e1e109 ("pco: fully support Vulkan 1.2 image atomics")
Signed-off-by: Nick Hamilton <nick.hamilton@imgtec.com>
Reviewed-by: Simon Perretta <simon.perretta@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39521>
(cherry picked from commit 079377c767)
This reverts commit 6eadcaa851.
VK_EXT_primitives_generated_query has a dependency on
VK_EXT_transform_feedback, which we do not implement yet. This is
breaking the android CTS. It will be reenabled once transform feedback
is in.
Signed-off-by: Olivia Lee <olivia.lee@collabora.com>
Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Reviewed-by: Valentine Burley <valentine.burley@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39547>
(cherry picked from commit 4959f45e99)
For mesh/task shaders, the thread payload provides a local invocation
index, but it's always linear so it doesn't give the correct value when
quad derivatives are in use.
The lowering pass where all of this is done correctly for compute
shaders assumes load_local_invocation_index will be lowered in the
backend for mesh/task, calculates the values for the quads correctly but
then avoid replacing the original intrinsic and we remain with the wrong
results.
Add an intel specific intrinsic and always lower the generic one to that
(or whatever else was calculated) to avoid ambiguities and fix the value
for quad derivatives.
Fixes future CTS tests using mesh/task shaders under:
dEQP-VK.spirv_assembly.instruction.compute.compute_shader_derivatives.*
Fixes: d89bfb1ff7 ("intel/brw: Reorganize lowering of LocalID/Index to handle Mesh/Task")
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39276>
(cherry picked from commit 5b48805b42)
