There are a lot of places where we add 0 to an offset. Avoiding
generating this can save us algebraic + copy_propagation later.
Cuts compile time in Borderlands 3 by -0.590631% +/- 0.170108% (n=25).
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29849>
Instead of replicating the whole thing in macros, just make an alu2()
function and use that in the wrappers. It ought to get inlined anyway.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29849>
Wait and see if we actually have a candidate for saturate propagation
before requesting liveness info. Saves the calculation in the case
where we have nothing to do.
Cuts compile time in Borderlands 3 by -0.304754% +/- 0.194162% (n=25).
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29849>
When I wrote sparse resources support for Anv we didn't have TileYs
support so I made non-opaque binds work even for non-standard block
shapes, which meant the block size could be either 64k or 4k. Since
then we merged TileYs support and changed our sparse resources
implementation to treat all the non-standard block shape cases as
"everything is the miptail", which means non-opaque binds are not
possible. So here we adjust the code to more explicitly represent
that.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29337>
There are 3 different places in our code where we calculate the tile
size and until recently the 3 implementations were different and with
slight bugs. Unify everything and also change the calculation to use
tile_info->phys_extent_B.
While doing this we move the isl_surf_get_tile_info() calls from
anv_sparse_calc_block_shape() to its callers so we total amount of
times we call it doesn't change.
v2: Adjust the patch now that tile_info is not part of isl_surf
anymore.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> (v1)
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29337>
The code that tries to create a "pretend block shape" for linear
tiling surfaces was necessary back when we were going to support
sparse residency (non-opaque binds) for non-standard block shapes
(since there was uncertainty about TileYs support). That hasn't been
the case since before we merged sparse resources upstream, so remove
the code and leave an assertion instead, just in case.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29337>
Since commit 18d8c3ca33 we were allocating a little more than what
we were actually using (2621440 bytes instead of 2097152, aka 0x280000
instead of 0x200000), and we were not properly marking the BO as
internal. No applications should be misbehaving because of this.
Fixes: 18d8c3ca33 ("anv: Add missing ANV_BO_ALLOC_INTERNAL")
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29337>
I've found myself adding this piece of code to our codebase when
debugging some Zink sparse failures recently, so let's upstream it.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29337>
Pass struct isl_tile_info to isl_choose_image_alignment_el() and its
subfunctions. We already compute isl_tile_info at isl_surf_init_s(),
don't make the subfunctions compute it again, just reuse the results.
Other subfunctions of isl_surf_init_s() also take the tile info as an
argument instead of recomputing it.
v2: Rebase after the gen20 version was added.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> (v1)
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com> (v2)
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29337>
This calculation was wrong for both compressed formats and
multi-sampled images. As a result, we misreported the image as having
a single miptail.
No Vulkan or GL CTS tests were tripping on this bug. I found this
while looking for tile size calculations after fixing a similar bug
elsewhere in the code.
The calculation should now match what we have in
anv_sparse_bind_image_memory(), which is widely tested.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29337>
We have to take the number of samples into account when calculating
the tile size. If we don't do this, multi-sampled images may end up
falling in the "goto out_everything_is_miptail" case, while in reality
multi-sampled images don't even have miptails.
Also assert that the value is one of the only two values we expect
this to be. This assert would have been useful to catch this issue,
since with multi-sampled images we were getting values like 16k or 32k
depending on the number of samples.
This helps move forward progress in some Zink tests, but does not
make them fully pass yet, as those tests are full of sub-cases and
this only helps some of them:
KHR-GL46.sparse_texture2_tests.UncommittedRegionsAccess
KHR-GL46.sparse_texture2_tests.SparseTexture2Commitment
KHR-GL46.sparse_texture2_tests.SparseTexture2Lookup
Fixes: 7ef3d652b2 ("anv/sparse: enable MSAA for Sparse when applicable")
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29337>
The Vulkan spec splits sparse resources in two different features:
sparse binding and sparse residency.
Sparse binding is much simpler. It requires the resources to be fully
bound before being used and it treats them as a black box. We're
required to support sparse binding for all the formats that are
supported by non-sparse, but that's easy beacause this feature is
simpler.
Now sparse residency is the one where we're allowed to partially bind
resources, and the one that comes with more complicated features such
as block shapes and non-opaque binding of images. This feature is
subdivided into:
- sparseResidencyBuffer
- sparseResidencyImage2D
- sparseResidencyImage3D
- sparseResidency{2,4,8,16}Samples (which refers to 2D images)
Notice that there's no sparseResidencyImage1D. And if you read the
specs it's clear that sparse residency is meant for non-1D images.
Still, supporting it didn't require any extra effort in Anv so we just
did it.
That's until we started running GL CTS tests on Zink. There's a CTS
test that checks for the standard block shapes. It creates 1D images
and expects the block shapes for them to be the standard 2D block
shapes. While we could very well just patch
anv_sparse_calc_image_format_properties() to return the standard 2D
block shapes for 1D images, that's just wrong (block shapes for 1D
images are just line segments, not rectangles!) so let's just reject
this all until maybe one day Vulkan defines sparseResidencyImage1D and
we get GL_ARB_sparse_texture3 to match it, or somebody decides to
change the GL CTS test.
Testcase: KHR-GL46.sparse_texture2_tests.StandardPageSizesTestCase
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29337>
InternalBufferSubDataCopyMESA is required for
PIPE_CAP_ALLOW_GLTHREAD_BUFFER_SUBDATA_OPT.
Signed-off-by: Zack Middleton <zack@cloemail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29795>
Export functions for GL_OES_vertex_array_object through GetProcAddress
on gles1.
Signed-off-by: Zack Middleton <zack@cloemail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29794>
Otherwise the assert in si_set_shader_buffer could trigger for blits
through clear_buffer on user resources.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29867>
No Turnip or ir3 changes required, this was implemented in NIR by Intel.
Passes dEQP-VK.spirv_assembly.instruction.*.float_controls2.*
Signed-off-by: Valentine Burley <valentine.burley@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29866>
I got the image alignment requirements for CPCB surfaces from Bspec
authors. The vertical alignment value of 8 was confirmed through the
Vulkan CTS test group, dEQP-VK.fragment_shading_rate*layered*. It also
happens to match the QPitch alignment requirement documented in the
Bspec. Hopefully the CTS will add tests for LOD2+ in order to exercise
the horizontal alignment value.
With this in place, we can start using Tile4.
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/10784
Reviewed-by: Rohan Garg <rohan.garg@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29355>
Some applications may benefit from this while some can get a performance
hit. Default to false and make it possible to toggle only for selected
workloads.
See workaround 14022483228 for some measurements.
Signed-off-by: Tapani Pälli <tapani.palli@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29760>
This will disable cases with 2D array views (which could be views to 3D
texture) but enables on regular 2D surfaces which seems to work fine.
Fixes: 70382f7f06 ("intel/isl/xe2: Enable route of Sampler LD message to LSC")
Signed-off-by: Tapani Pälli <tapani.palli@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29760>
DGC IBs are considered external IBs because they aren't managed by
the winsys and the BO itself isn't really useful. Passing a VA instead
will help for future work.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29600>
This wasn't needed in practice because DGC NV is only enabled for
vkd3d-proton and it always uses the global BO list but better to add it
anyways.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29600>
This will prevent the dynamic loader to pick the wrong function once we
rename things to the proper API names.
In any case, this should have been done all along anyway.
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29855>
Compiler can't know that array_size() of the offsets parameter in
textureGatherOffsets is (at most) 4, so use a MIN2() to make the limit
visible. Just adding an assert() gets ignored in Release builds.
This fixes the following warning in Release compilation:
```
../src/compiler/glsl/glsl_to_nir.cpp: In member function ‘virtual void {anonymous}::nir_visitor::visit(ir_texture*)’:
../src/compiler/glsl/glsl_to_nir.cpp:2453:41: warning: writing 1 byte into a region of size 0 [-Wstringop-overflow=]
2453 | instr->tg4_offsets[i][j] = val;
| ~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~
In file included from ../src/compiler/glsl/glsl_to_nir.h:31,
from ../src/compiler/glsl/glsl_to_nir.cpp:29:
../src/compiler/nir/nir.h:2470:11: note: at offset 8 into destination object ‘nir_tex_instr::tg4_offsets’ of size 8
2470 | int8_t tg4_offsets[4][2];
| ^~~~~~~~~~~
../src/compiler/glsl/glsl_to_nir.cpp:2453:41: warning: writing 1 byte into a region of size 0 [-Wstringop-overflow=]
2453 | instr->tg4_offsets[i][j] = val;
| ~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~
../src/compiler/nir/nir.h:2470:11: note: at offset 9 into destination object ‘nir_tex_instr::tg4_offsets’ of size 8
2470 | int8_t tg4_offsets[4][2];
| ^~~~~~~~~~~
```
This is from: `gcc (GCC) 14.1.1 20240522 (Red Hat 14.1.1-4)`.
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29508>
First argument for qsort() is declared to be never NULL, so ensure NULL
is never passed.
This has been detected by Undefined Behaviour Sanitizer (UBSan).
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Signed-off-by: Juan A. Suarez Romero <jasuarez@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29772>
Ensure unsigned integers are used instead of signed ones when performing
left bit shifts.
This has been detected by the Undefined Behaviour Sanitizer (UBSan).
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Signed-off-by: Juan A. Suarez Romero <jasuarez@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29772>
Check if the structure is NULL before trying to get access to its
members.
This has been detected by the Undefined Behaviour Sanitizer (UBSan).
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Signed-off-by: Juan A. Suarez Romero <jasuarez@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29772>
