Another case of not clearing the metadata correctly.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes: c78be5da30 ("intel/fs: lower ray query intrinsics")
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/16970>
(cherry picked from commit 1ffd28149f)
There is some code that relies on TGSI here, and it has limits.
For now always just bind resources > 31.
Fixes
dEQP-VK.pipeline.pipeline_library.descriptor_limits*
Cc: mesa-stable
Reviewed-by: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18812>
(cherry picked from commit 16fd0c11c6)
This fixes a bunch of valgrind warnings in
dEQP-VK.pipeline.pipeline_library.descriptor_limits.fragment_shader.storage_images_63
Cc: mesa-stable
Reviewed-by: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18812>
(cherry picked from commit b144d3e6a7)
This makes the code more consistent with handling layers, but also
makes sure a new surface is created when the w/h/layers changes.
Fixes: 8a6160a354 ("lavapipe: VK_KHR_dynamic_rendering")
Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18811>
(cherry picked from commit 21d39dd1de)
Currently for GPUs which don't have a marketing name in libdrm,
RADV just prints "(null) (RADV ...)", which looks bad.
This commit replaces the "(null)" with "AMD Unknown".
Cc: mesa-stable
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18775>
(cherry picked from commit 25e1c3d5b3)
And run algebraic when either int64 for float64 are not supported so
those don't end up in the generated code.
Cc: mesa-stable
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Ivan Briano <ivan.briano@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17396>
(cherry picked from commit 139e8f4635)
Initially I tried to store ray query state in the RT scratch space but
got the offset wrong. In the end putting this in the scratch surface
makes more sense, especially for non RT stages.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes: c78be5da30 ("intel/fs: lower ray query intrinsics")
Reviewed-by: Ivan Briano <ivan.briano@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17396>
(cherry picked from commit 838bbdcf2e)
It's very unfortunate that we have the RT scratch being conflated with
the usual scratch. In our implementation those are 2 different buffers.
The usual scratch access are done through the scratch surface state
(delivered through thread payload), while RT scratch (which outlives
thread dispatch with shader calls) is its own buffer.
So checking the NIR scratch size makes no sense as we can have normal
scratch accesses completely unrelated to RT scratch accesses.
This change switches the validation by looking at whether the scratch
base pointer intrinsic is being used (which is what we use/abuse to
implement RT scratch).
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes: c78be5da30 ("intel/fs: lower ray query intrinsics")
Reviewed-by: Ivan Briano <ivan.briano@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17396>
(cherry picked from commit f7fab09a07)
Initially the level is world (top level), then it's whatever level the
potential hit is.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes: c78be5da30 ("intel/fs: lower ray query intrinsics")
Reviewed-by: Ivan Briano <ivan.briano@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17396>
(cherry picked from commit 259b1647e6)
We need the traversal stack to saved/restored along with mem hits.
Total spill/fill is 256bytes.
We can potentially optimize this but we have to be very careful about
what state the query is in.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes: c78be5da30 ("intel/fs: lower ray query intrinsics")
Reviewed-by: Ivan Briano <ivan.briano@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17396>
(cherry picked from commit f843bec7de)
This function copies the potential hit from its memory location to the
committed hit location. A couple of fields got their bit offset wrong.
Fixes some CTS tests in dEQP-VK.ray_query.*
v2: Copy primitive/instance leaf pointers
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes: 0465714790 ("intel/nir/rt: add more helpers for ray queries")
Reviewed-by: Ivan Briano <ivan.briano@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17396>
(cherry picked from commit a88f725eea)
I noticed that glmark2's glFinish()es in its offscreen rendering tests
under zink were spinning. When we passed -1 as the timeout for
drmSyncobjWait(), the kernel would immediately return ETIME.
Fixes: 0a82a26a18 ("turnip: Porting to common implementation for timeline semaphore")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18739>
(cherry picked from commit 5e39b52e6a)
Normalized samplers is the norm, and non-normalized samplers might cause
some drivers and hardware to have to bend over backwards a bit.
We're using TXF here anyway, so it doesn't really matter what we set
this state to. So let's always use normalized samplers instead of
always using non-normalized samplers. That makes things easier for
everyone.
Fixes: e7b9561959 ("gallium: implement compute pbo download")
Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17708>
(cherry picked from commit 37733c100d)
Normalized samplers is the norm, and non-normalized samplers might cause
some drivers and hardware to have to bend over backwards a bit.
We're using TXF here anyway, so it doesn't really matter what we set
this state to. So let's always use normalized samplers instead of
always using non-normalized samplers. That makes things easier for
everyone.
Fixes: 41e093fc98 ("st/pbo: add a fast pbo download code-path")
Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17708>
(cherry picked from commit 1a135bdd6c)
Normalized samplers is the norm, and non-normalized samplers might cause
some drivers and hardware to have to bend over backwards a bit.
We're using TXF here anyway, so it doesn't really matter what we set
this state to. So let's always use normalized samplers instead of
always using non-normalized samplers. That makes things easier for
everyone.
Fixes: ed0e9862c5 ("st/mesa: implement PBO downloads for ReadPixels")
Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17708>
(cherry picked from commit 484205b7eb)
This is likely required for OpenGL buffer texture allocations. It'll
also make buffer copies faster if things are generally nicely aligned.
It's definitely required for OpenCL.
Fixes: 32c5d6d1dc ("iris: Add an alignment parameter to iris_bo_alloc()")
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15811>
(cherry picked from commit 2984134395)
when running recent Mesa on i855 (gen 2) without amber drivers:
error: Kernel is too old for Iris. Consider upgrading to kernel v4.16.
libGL error: glx: failed to create dri3 screen
libGL error: failed to load driver: iris
error: Kernel is too old for Iris. Consider upgrading to kernel v4.16.
libGL error: glx: failed to create dri2 screen
libGL error: failed to load driver: iris
move the i915 feature check to after the hardware generation check
which results in:
MESA: warning: Driver does not support the 0x3582 PCI ID.
libGL error: glx: failed to create dri3 screen
libGL error: failed to load driver: iris
MESA: warning: Driver does not support the 0x3582 PCI ID.
libGL error: glx: failed to create dri2 screen
libGL error: failed to load driver: iris
Cc: mesa-stable
Reviewed-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18563>
(cherry picked from commit ed5d16cec1)
Change reset_block() so it only considers the logical
predecessors for VGPRs. Relevant for some optimizations
across loops.
This commit fixes an assertion failure which was triggered
by Zink in a piglit test.
Fossil DB stats unaffected on Navi 21.
Fixes: 2e56e23420
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18488>
(cherry picked from commit a8dd07518c)
This assumption is no longer true since the post-RA optimizer
can work across blocks. It is now possible that some control
flow paths overwrite some but not all registers of an operand.
This commit may prevent invalid optimizations and/or assertion
failures (on debug builds).
Fossil DB stats unaffected on Navi 21.
Fixes: 0e4747d3fb
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18488>
(cherry picked from commit 2eab413cf7)
Affects blocks whose some (but not all) predecessors overwrite a register.
This commit fixes glitches in some games which regressed because of the
improved SCC no-compare optimization.
Fossil DB stats on Navi 21:
Totals from 2816 (2.09% of 134906) affected shaders:
CodeSize: 24224276 -> 24241580 (+0.07%)
Instrs: 4570595 -> 4574921 (+0.09%)
Latency: 53680256 -> 53693655 (+0.02%); split: -0.00%, +0.02%
InvThroughput: 9829289 -> 9830573 (+0.01%)
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/7257
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/7305
Fixes: 2e56e23420
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18488>
(cherry picked from commit 63063dd5ce)
It's already called in brw_postprocess_nir and calling it the second time
actually breaks shading rate.
Initially, when I added this call here in 9acb30c8c4, I was testing it
on an internal tree, which didn't have brw_nir_lower_shading_rate_output call
in brw_postprocess_nir.
Fixes: 9acb30c8c4 ("intel/compiler: implement primitive shading rate for mesh")
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18702>
(cherry picked from commit cfd1e5a91e)
there's no requirement in the spec that the geometry for resolves must match,
only that the geometry must be positive (i.e., no flipped extents)
this avoids major perf issues for scaled resolves
cc: mesa-stable
Reviewed-by: Adam Jackson <ajax@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18364>
(cherry picked from commit 513fcb7936)
