If we have a host_memory_base pointer it means that we are handling
the pool memory as a whole, so each set is a sub-slice of the memory
pool. In this case we can't just free the individual set. In other
words, VK_DESCRIPTOR_POOL_CREATE_FREE_DESCRIPTOR_SET_BIT is not set.
Note tha at that point we were able to sub-allocate an set, and we are
failing to sub-allocate the pool bo for the descripto bo. So
technically we could try to return that set to the pool (so undo the
change on host_memory_ptr before), that I assume was my intention when
(wrongly) calling vk_free there. But in practice, at that point we are
already on a out of descriptor pool situation, so in the end it
doesn't even matter.
This fixes a double free crash with the UE4 VehicleGame demo.
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9640>
This pass splits writemaks with non-consecutive bits into multiple
store operations ensuring that each store only has consecutive
writemask bits set.
We can use this to simplify writemask handling in our backend removing
a loop solely intended to handle this case.
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9619>
This will make it so we pack consecutive scalar operations into a vector
operation, reducing the amount of load/store operations in the NIR program.
Our backend can handle vector load/stores, and doing so may be more efficient
since we don't need to setup individual load/stores all the time.
A pathological case is:
dEQP-VK.spirv_assembly.instruction.compute.opcopymemory.array
which goes from 862 instructions to only 573 by converting
all scalar SSBO load/store operations to vec4 operations.
total instructions in shared programs: 13752607 -> 13733627 (-0.14%)
instructions in affected programs: 367117 -> 348137 (-5.17%)
helped: 1168
HURT: 371
Instructions are helped.
total threads in shared programs: 412230 -> 412272 (0.01%)
threads in affected programs: 54 -> 96 (77.78%)
helped: 23
HURT: 2
Threads are helped.
total uniforms in shared programs: 3790248 -> 3784601 (-0.15%)
uniforms in affected programs: 57417 -> 51770 (-9.84%)
helped: 1420
HURT: 19
Uniforms are helped.
total max-temps in shared programs: 2322170 -> 2322714 (0.02%)
max-temps in affected programs: 14353 -> 14897 (3.79%)
helped: 185
HURT: 306
Max-temps are HURT.
total spills in shared programs: 5940 -> 6010 (1.18%)
spills in affected programs: 65 -> 135 (107.69%)
helped: 0
HURT: 11
total fills in shared programs: 13372 -> 13494 (0.91%)
fills in affected programs: 75 -> 197 (162.67%)
helped: 0
HURT: 11
total sfu-stalls in shared programs: 31505 -> 31521 (0.05%)
sfu-stalls in affected programs: 751 -> 767 (2.13%)
helped: 210
HURT: 246
Inconclusive result (value mean confidence interval includes 0).
total inst-and-stalls in shared programs: 13784112 -> 13765148 (-0.14%)
inst-and-stalls in affected programs: 360283 -> 341319 (-5.26%)
helped: 1125
HURT: 366
Inst-and-stalls are helped.
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9619>
Otherwise, gl_SampleMask[] writes are ignored and the stencil test works like
if all samples were enabled.
Fixes: dEQP-VK.renderpass.suballocation.multisample.*s8*
Signed-off-by: Samuel Iglesias Gonsálvez <siglesias@igalia.com>
Reviewed-by: Hyunjun Ko <zzoon@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9478>
v2: link libvulkan_util with libglsl so it can find the glsl singleton symbols.
v3: link with libcompiler instead of libglsl (Jason)
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Dylan Baker <dylan.c.baker@intel.com>
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com> for the v3dv bits.
Reviewed-by: Samuel Iglesias Gonsálvez <siglesias@igalia.com> for the turnip bits.
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> for the radv bits.
Acked-by: Dave Airlie <airlied@redhat.com> for the lvp bits.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9457>
This gets rid of unused variable warnings on genX_thing, because
now the compiler will think that the unknown hardware generation
case is unreachable.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9634>
This should make both GCC and clang happy and make them believe that
the array bounds are not exceeded.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9634>
this really just means to nuke the counter buffer, and this can be done
by using a special bind_history bit that can be unset when the buffer has
been rebound
Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9546>
this creates new backing objects for the invalidated resource and, if
needed, rebinds it to any descriptor sets it might be used in by invalidating
the descriptor state and creating new view objects
Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9546>
this moves tracking onto the surface/bufferview, which is more accurate
and allows the removal of a temporary hack in resource invalidation
Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9546>
gallium rewrites all the ubo/ssbo instructions to use the buffer index as
the instruction src. the nir variables which are passed to zink after that
point are completely worthless, and it's impossible to accurately determine
which one corresponds to which buffer
thus, deleting all the variables and creating new ones based on the buffers
that are used is the best option, and it also enables simplifying a ton
of code as well as doing even better improvements in the future
Reviewed-by: Adam Jackson <ajax@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9624>
now that descriptor types are split, we can just use the type-max values
per stage as the increment instead of all type max values
Reviewed-by: Adam Jackson <ajax@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9624>
By keeping track of nonuniform access from nir and storing it to ir3.
Signed-off-by: Hyunjun Ko <zzoon@igalia.com>
Reviewed-by: Danylo Piliaiev <dpiliaiev@igalia.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9125>
This seems to be originally introduced from 2a0d45ae6c, and 562aaea07c
misused the method.
Fixes: 2a0d45ae6c "freedreno/ir3: Add a NIR pass to select tex instructions eligible for pre-fetch"
Fixes: 562aaea07c "freedreno/ir3: respect tex prefetch limits"
Signed-off-by: Hyunjun Ko <zzoon@igalia.com>
Reviewed-by: Danylo Piliaiev <dpiliaiev@igalia.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9125>
Alejandro Piñeiro
Iago Toral Quiroga
Samuel Pitoiset
Samuel Iglesias Gonsálvez
Lukas Feller
Timur Kristóf
Daniel Stone
Mike Blumenkrantz
Hyunjun Ko