When there are lots of inlined shaders, going over each one and checking
if the call index matches becomes expensive. Instead, use a
binary-search-like selection to skip most of the checks.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26380>
This lets us support multi-planar images properly on transfer queues.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Tatsuyuki Ishi <ishitatsuyuki@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26353>
This removes a bunch of redundant calculations, thus making the code
less error-prone.
Also move the row pitch calculation to a separate function.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Tatsuyuki Ishi <ishitatsuyuki@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26353>
This makes it possible to gather the surface information
only once and pass it to the various SDMA functions, therefore
the code can be less error-prone.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Tatsuyuki Ishi <ishitatsuyuki@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26353>
This makes it possible to call the function just once instead
of calling different functions repeatedly.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Tatsuyuki Ishi <ishitatsuyuki@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26353>
Using just one struct for both types of images (and buffers)
will simplify a lot of code.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Tatsuyuki Ishi <ishitatsuyuki@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26353>
Very few parts of RADV actually need the SDMA functions, so
moving them to a separate header makes the driver cleaner and
also improves compilation time when SDMA functions change.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Tatsuyuki Ishi <ishitatsuyuki@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26353>
Not expecting this to actually fix anything externally visible,
but reduces some invalid usage when the resulting vector is
not 16 elements long (e.g. the C/result matrix).
Fixes: 9df4703fbb ("radv: Add cooperative matrix lowering.")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26768>
Only shaders which explicitly allow shared memory are included for
now. The pass is very late to avoid optimizations removing the stores
and to ensure the clear gets added after MS outputs get loaded from LDS.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26679>
Doing it at bind-time causes a 1.4% overhead (among all driver calls) in
Overwatch 2. !24502 mentions that it can be precomputed in case overhead
is a concern, so do it here.
max_waves is stored directly in the radv_shader struct, because
ac_shader_config conforms to LLVM ABI and we cannot add anything custom,
and radv_shader_info needs to be determined from NIR only.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26692>
With dynamic rendering, it's allowed to begin rendering with depth or
stencil only but still with a depth/stencil format. The test below
checks that unbound part of ds isn't modified, if depth is bound and
stencil not and vice versa.
This fixes a recent CTS
dEQP-VK.dynamic_rendering.primary_cmd_buff.basic.partial_binding_depth_stencil.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25350>
Now that PS epilogs are always compiled during cmdbuf recording, we
have all information to enable MRT compaction, for optimal performance.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26667>
This has no effects because key->spi_shader_col_format isn't used when
the graphics pipeline needs to compile a PS epilog.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26663>
The only major change is the code removal of the legacy BO list path
in the winsys, which required switching "debug_all_bos" to the new path.
Reviewed-by: Yogesh Mohan Marimuthu <yogesh.mohanmarimuthu@amd.com>
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26547>
A BO can be always resident by two ways:
1. Through kernel bookkeeping. The BO is created with
AMDGPU_GEM_CREATE_VM_ALWAYS_VALID and bo->is_local gets set to true.
2. Through the driver global BO list. On every submission, the global
BO list is added to the CS's BO list.
Until now, use_global_list reflected either 1. or 2. . This commit
changes it to reflect 2. only, and update callsites that checks for
residency to use a new helper.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26591>
This is a promotion from the EXT, except the new property
supportsNonZeroFirstInstance which should already be supported.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26595>
TC-compat CMASK means Fmask decompression isn't needed because the hw
can read it directly from shaders, so this shouldn't have any effects.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26575>
