Fix typo in calculation of position of start of a row of tiles. This
could otherwise cause an out-of-bounds access in the next patch.
Fixes: 81d85be9a5 freedreno/gmem: Reverse order of alternative tile rows
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17888>
This is known to produce bogus results for certain combinations of
operands, so don't use it. See this issue for details:
https://gitlab.freedesktop.org/mesa/mesa/-/issues/6555
With this change, the idiv lowering will produce mul_high instructions,
so we need to instruct the compiler to lower those with the ALU lowering
right after the idiv lowering by adding the lower_mul_high option (we
only need to add this to V3D, since V3DV already had it set). This will
cause injection of uadd_carry instructions, for which we have backend
implementations that produce better code for us than the NIR lowering.
total instructions in shared programs: 12457692 -> 12463625 (0.05%)
instructions in affected programs: 23115 -> 29048 (25.67%)
helped: 0
HURT: 111
total threads in shared programs: 416372 -> 416368 (<.01%)
threads in affected programs: 8 -> 4 (-50.00%)
helped: 0
HURT: 2
total uniforms in shared programs: 3704067 -> 3704589 (0.01%)
uniforms in affected programs: 5804 -> 6326 (8.99%)
helped: 2
HURT: 109
total max-temps in shared programs: 2147845 -> 2148088 (0.01%)
max-temps in affected programs: 2456 -> 2699 (9.89%)
helped: 6
HURT: 91
Reviewed-by: Alyssa Rosenzweig <alyssa@collabora.com>
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17871>
Just got into a midnight discussion with a hw guy.
TC_ACTION_ENA apparently doesn't invalidate L1, so don't clear
the INV_VCACHE flag.
Fixes: 4056e953fe - radeonsi: move emit_cache_flush functions into si_gfx_cs.c
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17902>
Also while switching to GPGPU pipeline, make sure to flush the untyped
dataport cache. HDC pipeline flush bit must be set if we are flushing
untyped dataport L1 data cache.
v2: Add utrace support (Lionel)
Signed-off-by: Sagar Ghuge <sagar.ghuge@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/16905>
Set write back L1 cache policy in STATE_BASE_ADDRESS instruction for A64
messages.
Signed-off-by: Sagar Ghuge <sagar.ghuge@intel.com>
Suggested-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/16905>
This improves clover from crashing to just failing, but I mainly
want it this to cleanup the nir code first
It's also important the shaders coming from the state tracker
for feedback get images lowered when they are draw shaders now.
Reviewed-by: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10641>
if a texcoord input is read in a fragment shader but not written in
the previous stage, the texcoord variable must be preserved until
nir_lower_texcoord_replace has (possibly) run, and only then can it
be replaced with a 0000 read
Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17775>
nine uses this to pass unscaled units for depth bias, which means
the units must be scaled based on the format of the depth buffer
cc: mesa-stable
Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17775>
Provide a use flag to let the driver know that the allocated buffer will
be used for frontbuffer rendering. For example, bandwidth compressed
formats should usually be avoided for frontbuffer rendering to avoid the
visual corruption that results from this display racing with the GPU
writing header data vs. pixel data.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17799>
This is a workaround for #6753, without having to build and install a
custom xlib in our containers. Maybe some day debian will have a
backport?
Acked-by: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17549>
transfer_map (the only consumer of the flag now) was doing direct mapping
on resources with modifiers (UBWC compressed images on turnip) and
accessing them as linear. We definitely want the staging blit path
instead.
Fixes glReadPixels() from gbm surfaces on turnip.
Reviewed-by: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17549>
Also make the code cleaner and simplier.
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Acked-by: Jesse Natalie <jenatali@microsoft.com>
Reviewed-by: Jason Ekstrand <jason.ekstrand@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17334>
this shouldn't be writing undefs to pad out the clipdistance vec4,
it should just be doing the writes using the mask of the array size
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17770>
