Starfield has a lot of empty ExecuteIndirect() calls. This optimizes
them by using the indirect sequence count as predicate.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25060>
Looks like indirect dispatches require an event marker instead of an
event marker with dims. That makes sense somehow given the blocks size
is not known at record time with indirect dispatches.
This allows RGP to report correct block sizes.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24994>
When TCS and TES aren't linked together and TCS exports unused outputs,
the per-patch data offset needs to be adjusted. This is similar to the
LS-HS vertex stride when VS and TCS aren't linked together.
This fixes a bunch of failures by forcing the driver to use TCS epilogs.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24776>
When TCS isn't linked with VS, the vertex stride should be computed
from vertex outputs. This is only for shader object and shouldn't
change anything right now.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24540>
With shader object, if VS and TCS aren't linked together, the LSHS
vertex stride should be computed from the vertex outputs. Otherwise,
if an output is unused, the stride is wrong in TCS.
This is currently for GFX8 only because for merged shaders this won't
be needed but shader object on GFX9+ isn't yet a thing.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24540>
The compute scratch size is computed later because the RT stack size
can be dynamic, but the number of waves shouldn't change.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24502>
This allows us to remove one more pipeline occurence during cmdbuf
recording. Note that shader object always uses dynamic vertex input.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24473>
This used to depend on the graphics pipeline, but now that everything
is dynamic it should be fine to trigger it on fb changes.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24473>
This allows us to remove one more pipeline occurence during cmdbuf
recording. Note that patch control points is always dynamic with
shader object.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24473>
RADV_CMD_FLAG_PS_PARTIAL_FLUSH is only used for draws with
RADV_DEBUG=syncshaders, which implies a valid graphics pipeline.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24473>
With shader object, if TES is compiled without a TCS, the number of
TCS vertices out might not be known at compile time and it needs to be
loaded from a user SGPR.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24346>
It only contains the number of tessellation patches for now, but it
will be used to pass the number of TCS vertices out for shader object.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24346>
The number of geometry shader invocations is correctly counted by the
hardware for both NGG and the legacy GS path but it increments for
NGG VS/TES because they are merged with GS, but it shouldn't. Fix this
by emulating the number of geometry shader invocations.
This fixes piglit/bin/arb_query_buffer_object-qbo and recent
dEQP-VK.query_pool.statistics_query.gs_invocations_no_gs.* failures
with NGG.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24231>
This user SGPR is only declared on chips that support NGG but might
fallback to legacy GS for some reasons, like XFB. It will be used to
emulate GS counters from shaders.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24231>
For PS epilogs we have two paths, the first one is to pre-compile PS
epilogs at pipeline creation time, while the second one is to compile
PS epilogs on-demand when some dynamic states are used.
Binding the pre-compiled PS epilog to the cmdbuf state allows us to
remove one more pipeline dependency when recording cmdbufs (for shader
objects).
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24254>
Move most of the DB_SHADER_CONTROL fields from the pipeline to the pixel
shader for preparation for shader objects.
Also, the GFX11 export conflict bug workaround doesn't need to be enabled
for non-1x sample counts or if blending is not enabled, so make the
application of DB_SHADER_CONTROL consider the current sample count and
blending state even if they're dynamic.
Having access to the exact sample count in DB_SHADER_CONTROL setup is also
necessary for good performance in SampleInterlock execution modes of
fragment shader interlock, for configuration of POPS_OVERLAP_NUM_SAMPLES
(GFX9-10.3) or OVERRIDE_INTRINSIC_RATE (GFX11), as PixelInterlock is
massively slower with multisampling due to overlap between adjacent
polygons sharing covered pixels among the common edge.
The name of the dynamic state controlling DB_SHADER_CONTROL is now
unambiguous - previously line rasterization mode had effect on attachment
feedback loop state emission.
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Signed-off-by: Vitaliy Triang3l Kuzmin <triang3l@yandex.ru>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23474>
