We could probably support some strides if we tried hard enough but the
whole point of this opcode is to accelerate things with crazy Align16 or
crazy regions. It's ok if we have to emit an extra MOV to get a packed
source.
Fixes: 8b4a5e641b "intel/fs: Add support for subgroup quad operations"
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7329>
(cherry picked from commit 58bcb5401d)
Previously, we were returning 2 whenever the source was a Q type. As
far as I can tell, the only reason why this hasn't blown up before is
that it was only ever used for VGRFs until the SWSB pass landed which
uses it for everything. This wasn't a problem because Q types generally
aren't a thing on TGL. However, they are for a small handful of
instructions.
Cc: mesa-stable@lists.freedesktop.org
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7329>
(cherry picked from commit 4c8cbe9b13)
We enable the KHR_vulkan_memory_model extension whenever we use
tesselation, so right now this is a defacto requirement. So let's make
this requirement explicit.
Fixes: f815b87e18 ("zink: export tess shader pipe caps")
Reviewed-by: Hoe Hao Cheng <haochengho12907@gmail.com>
Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8655>
We used to select the stencil layout even if we should have selected
the depth/stencil one.
Fixes: e4c8491bdf ("radv: implement VK_KHR_separate_depth_stencil_layouts")
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8552>
(cherry picked from commit 3ef89b245e)
Without this, we'll expose GL_ARB_transform_feedback2 and
GL_ARB_transform_feedback3 even without VK_EXT_transform_feedback,
because these caps are directly wired up without checking the pervious
extensions.
Fixes: e8ad52f7b0 ("zink: enable xfb extension in screen creation")
Reviewed-by: Hoe Hao Cheng <haochengho12907@gmail.com>
Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8640>
(cherry picked from commit 855370bb62)
Even in the presence of VK_KHR_draw_indirect_count, we still technically
need to respect the feature-cap when using a Vk 1.0 core-function.
Fixes: cef876910a ("zink: enable PIPE_CAP_MULTI_DRAW_INDIRECT(_PARAMS) caps")
Reviewed-by: Hoe Hao Cheng <haochengho12907@gmail.com>
Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8640>
(cherry picked from commit c9340744a3)
Vulkan has a cap to enable this, we should check that one rather than
always claiming support.
Fixes: 0c70268ff7 ("zink: mark ARB_sample_shading as supported")
Reviewed-by: Hoe Hao Cheng <haochengho12907@gmail.com>
Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8640>
(cherry picked from commit 6f6941e2dd)
Vulkan has a cap to enable this, we should check that one rather than
always claiming support.
Fixes: 8d46e35d16 ("zink: introduce opengl over vulkan")
Reviewed-by: Hoe Hao Cheng <haochengho12907@gmail.com>
Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8640>
(cherry picked from commit 612169859a)
With RADV_THREAD_TRACE_BUFFER_SIZE=1073741824, the computed size
will overflow and be 4096 instead of 4294967296.
Cc: <mesa-stable@lists.freedesktop.org>
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8616>
(cherry picked from commit c40ea24ee0)
For example:
s2: %688:s[32-33] = p_linear_phi %3:s[10-11], %688:s[32-33]
would have been considered trivial.
This might happen due to parallelcopies when assigning phi registers.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Fixes: 69b6069dd2 ("aco: refactor try_remove_trivial_phi() in RA")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8645>
(cherry picked from commit 824eba2148)
The intention of IRIS_DIRTY_{RENDER,COMPUTE}_RESOLVES_AND_FLUSHES
is to avoid considering resolves/flushes on back to back draw calls
where nothing of significance has changed with the resources. When
anything changes that could require a resolve, we must flag those.
Those situations are:
1. Texture/image/framebuffer bindings change
(as the set of images we need to look at is now different)
2. Depth writes are enabled/disabled (the resolve code uses this)
3. The aux state for a currently bound resource changes.
We were missing this last case. In particular, one example where
we missed this was:
1. Bind a texture.
2. Clear that texture (likely blits/copies/teximage would work too)
3. Draw and sample from that texture
Clear-then-Bind would work, as binding would flag resolves as dirty.
But Bind-then-Clear doesn't work, as clear can change the aux state
of the bound texture, but wasn't flagging that anything had changed.
Technically, we could consider whether the resource whose aux state
is changing is bound for compute (and only flag COMPUTE_RESOLVES),
or bound for a 3D stage (and only flag RENDER_RESOLVES), and flag
nothing at all if it isn't bound. But we don't track that well,
and it probably isn't worth bothering. So, flag unconditionally
for now.
This does not appear to impact Piglit's drawoverhead scores.
Cc: mesa-stable
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3994
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/4019
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8603>
(cherry picked from commit e2500c02cc)
The spec calls to always use sample 0 in this case, whereas we can do
undefined things for invalid sample id's in the MSAA case.
Fixes
dEQP-GLES31.functional.shaders.multisample_interpolation.interpolate_at_sample.non_multisample_buffer.sample_n_*
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8574>
(cherry picked from commit 245a696741)
Fixes some assertion failures in the GM107 emitter with the game
'tansei', noticed while debugging gitlab issue 4101.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8534>
(cherry picked from commit 6638b58ccf)
These ops just put out mov's directly, which screws up the assignment
logic -- it just tries to only process the "last" mov. Don't try to do
the more optimized thing for 64-bit types, where this is just much
trickier.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8463>
(cherry picked from commit 55c42b7885)
Because Gallium and Vulkan disagree on what kind of state strides is, we
need to wrangle this state a bit, and up until now, we've been simply
fixing this up while binding the vertex-buffers.
But this isn't robust, because the vertex element state might be bound
after the vertex-buffer state was bound. We also need to take
binding-map into account, which we're currently missing as well.
Instead, w need to deal with this at a place where we know what's being
used for both of these. So let's do this during draw instead.
Ideally, we'd also do some dirty-tracking to know if this is needed or
not, but I believe Mike has some patches in this areas lined up, so it
might be easier to wait for those.
Fixes: 8d46e35d16 ("zink: introduce opengl over vulkan")
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3661
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/4125
Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8588>
(cherry picked from commit d74b012260)
When NGG is used, the hw can't know the number of geometry shader
primitives. To fix that, the NGG geometry shader accumulates itself
the number of primitives by using an atomic operation directly to GDS.
Then, begin/query copy the start/stop values from GDS to the
query pool buffer using a PS_DONE event. This was actually wrong
because PS_DONE is completely asynchronous to everything and executed
when the preceding draws finish pixel shaders.
Fix this by using a COPY_DATA packet which is synced with CP. This
fixes random failures on Sienna Cichlid with
dEQP-VK.query_pool.statistics_query.*.geometry_shader_primitives.*.
Cc: <mesa-stable@lists.freedesktop.org>
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8590>
(cherry picked from commit 085e2ce3d4)
We incorrectly utilize the stencil layouts structures even if we
should stick to the depth_stencil ones if the layout includes stencil.
v2: Don't forget stencil only layout (Nanley)
Simplify callers of new helper functions (Nanley)
v3: Store VK_IMAGE_LAYOUT_UNDEFINED when no stencil is available (Nanley)
Use a switch statement (Nanley)
v4: Consider all layouts but depth only to be potential stencil layouts (Lionel)
v5: Refactor helper in vk_image_layout_depth_only() and discard
VkAttachmentDescriptionStencilLayoutKHR in
VkAttachmentDescription2KHR if format is not depth/stencil.
v5: s/LAYOUT_COLOR_ATTACHMENT_OPTIMAL/LAYOUT_DEPTH_ATTACHMENT_OPTIMAL/ (Nanley)
v6: Fix overly harsh assert()
Fixes: c1c346f166 ("anv: implement VK_KHR_separate_depth_stencil_layouts")
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/4084
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8475>
(cherry picked from commit 28207669d0)
Fixes several dEQP-VK.robustness.robustness2.* tests on GFX8. Generations
other than GFX8 don't fail the tests because bounds-checking is done using
the index (making it per-vertex).
fossil-db (Polaris):
Totals from 1387 (0.99% of 140385) affected shaders:
(no statistics affected)
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Fixes: 03a0d39366 ("aco: use MUBUF in some situations instead of splitting vertex fetches")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7834>
(cherry picked from commit 914c61d6c0)
This reverts commit aca67a555c, which
regressed the following Piglit test on i915 (and presumably r200):
piglit/spec/!opengl 1.1/sized-texture-format-channels
Specifically, it begins testing glTexImage2D with format GL_RGBA,
type GL_FLOAT, and internalFormat GL_RGB16F, which leads to the
following error:
Mesa 21.0.0-devel implementation error: unexpected format GL_RGB16F in _mesa_choose_tex_format()
Please report at https://gitlab.freedesktop.org/mesa/mesa/-/issues
sized-texture-format-channels: ../../src/mesa/main/teximage.c:2836: _mesa_choose_texture_format: Assertion `f != MESA_FORMAT_NONE' failed.
i915 and r200 unconditionally support ARB_half_float_pixel, but neither
support RGB16F as an internal format. According to Ian's rationale
in the commit message for 1edca151a0
(which enabled that extension for all drivers):
"This extension only adds data types that can be passed to, for
example, glTexImage2D. It does not add internal formats. Since
you can already pass GL_FLOAT to glTexImage2D this shouldn't pose
any additional issues with those drivers. Note that r200 and i915
already supported this extension, and they don't support
floating-point textures either."
So, commit aca67a55c011 enabled half-float internal formats on hardware
that cannot support them. We should revert the change.
v2: Don't reintroduce the _mesa_is_gles3() condition, as that shouldn't
be necessary (feedback from Erik Faye-Lund).
Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Reviewed-by: Erico Nunes <nunes.erico@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Adam Jackson <ajax@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8458>
(cherry picked from commit 07473321a2)
_tnl_draw_prims loops over the prims, and for each one, maps the VBOs,
draws, and unmaps them. But it failed to reset nr_bos = 0 between each
loop iteration, which meant that when processing prim[n], the BO list
had all BOs for prior primitives too. Assuming each primitive used the
same VBOs, that means the same VBO would appear in the list multiple
times, and it would try to unmap the same BO multiple times. This
triggered asserts on the second unmap, as it had already been unmapped.
Fixes Piglit's oes_draw_elements_base_vertex-multidrawelements on i915.
Fixes: e99e7aa4c1 ("mesa: switch Draw(Range)Elements(BaseVertex) calls to DrawGallium")
Acked-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8522>
(cherry picked from commit 9fb5d7acbb)
Prior to commit e99e7aa4c1 (mesa: switch
Draw(Range)Elements(BaseVertex) calls to DrawGallium), the indices
parameter of glDrawElements (an offset into the VBO) was handled by
setting ib->ptr. With that commit, it instead began binding the
index buffer with offset 0, and adding the offset to draw->start,
which eventually becomes prim->start.
t_draw.c's bind_indices() was trying to convert the relevant section of
the index buffer to GLuints, but was failing to account for start, so
it nabbed the wrong portion of the index buffer.
Fixes: e99e7aa4c1 ("mesa: switch Draw(Range)Elements(BaseVertex) calls to DrawGallium")
Acked-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8522>
(cherry picked from commit 376c8f750b)
Commit 4c751ad67a (vbo/dlist: use a shared
index buffer) caused multiple draws to use the same index buffer, and
began setting the primitive's `start` field to the offset needed to
access the right portion of the index buffer.
Unfortunately, t_rebase_prims completely botches handling this case.
Say for example we had start = 40, min_index = 6, max_index = 11.
The actual indexes in the buffer are ib[40..45]. t_rebase_prims,
however, would allocate an index buffer containing only 6 elements,
and populate them with <ib[0..5] - min_index>. For one, this reads
the wrong source data, leading to garbage index values. For another,
it stores the new index buffer in the wrong spot, so drawing will try
and read elements [40..45] of an array of length 6, and crash.
This patch makes t_rebase_prims allocate a larger index buffer, with
the blank space at the beginning, and try to copy the correct section
of index buffer data over. This only works if `start` is the same for
all primitives, however, so if we detect different ones, we recurse
to rebase and call draw() separately for each different start value.
Fixes: 4c751ad67a ("vbo/dlist: use a shared index buffer")
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/4082
Acked-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8522>
(cherry picked from commit bd6120f562)
We only convert line strips to lines in certain cases, but were flagging
node->merged.prim as GL_LINES even if we simply copied a GL_LINE_STRIP
prim[0] over without modifying it.
Fixes Piglit's lineloop test (which triggers loop -> strip conversion
earlier in this path, then was incorrectly triggering strip -> list
mode modification with no changes to the underlying data).
Fixes: 310991415e ("vbo/dlist: implement primitive merging")
Reviewed-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/8522>
(cherry picked from commit 14ae5069da)
I'm can't see why this is necessary. There are already new fields
(node->merged.{min,max}_index) for the new values in the merged case.
But in vbo_save_draw.c, in the !draw_using_merged_prim case, we would
try and use the original node...with the now destroyed min/max index.
Fixes some assert failures when running with swtnl and forcing the
non-merged path (though it takes the merged path by default).
Fixes: 4c751ad67a ("vbo/dlist: use a shared index buffer")
Reviewed-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/8522>
(cherry picked from commit 44bdd5225c)
In some rare cases, L2 needs to be flushed if an image is affected
by the pipe misaligned issue. This is roughly based on AMDVLK.
I confirmed that disabling TC-compat HTILE, and respectively DCC,
for the relevant images also fixes the regressions below.
This fixes some regressions introduced with L2 coherency for
dEQP-VK.renderpass2.depth_stencil_resolve.image_2d_* and for
dEQP-VK.renderpass2.suballocation.multisample_resolve.*.
Fixes: 4a783a3c78 ("radv: Use L2 coherency on GFX9+.")
Co-Authored-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8557>
(cherry picked from commit 4c99d6ff54)
The driver used to invalidate the vector cache for meta operations
but this has been removed and I think it should be restored to fix
a bunch of regressions on GFX8.
This probably needs to be cleaned up but this is a hotfix.
This fixes a bunch of regressions and flakes on GFX8 like
dEQP-VK.pipeline.multisample.sample_locations_ext.draw.color.samples_4.*.
Fixes: 8f8d72af55 ("radv: Use access helpers for flushing with meta operations.")
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8573>
(cherry picked from commit 8882abe47e)
v_or_b32 with a v2b definition should use SDWA if is_partial=true.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Fixes: 56345b8c61 ("aco: allow reading/writing upper halves/bytes when possible")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8577>
(cherry picked from commit fcda9b6737)
This restores the previous logic because L2 coherency was fully
implemented. It appears that flushing L2 metadata with a CS_DONE
event hangs.
This fixes GPU hangs with Monster Hunter World.
Fixes: 4a783a3c ("radv: Use L2 coherency on GFX9+.")
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8566>
(cherry picked from commit c3ac6f7cd7)
If software decompression is used for ETC2, the alpha channel
for sRGB8 textures would be set only if BGRA is true.
Fixes: e5604ef78b "st/mesa/i965: Allow decompressing ETC2 to GL_RGBA"
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Adam Jackson <ajax@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8529>
(cherry picked from commit 290dcb26ae)
