It's always better if init/finish come in pairs.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Hyunjun Ko <zzoon@igalia.com>
Reviewed-by: David Rosca <david.rosca@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36646>
It was just a dummy wrapper around the runtime struct. We do, however,
have to keep at least the Create/Update entrypoints because RADV has to
do some patching for video encode. Since we're keeping Create, we keep
Destroy as well.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: David Rosca <david.rosca@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36646>
This also allows us to simplify the interface to
vk_video_session_parameters_create().
Reviewed-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Hyunjun Ko <zzoon@igalia.com>
Reviewed-by: David Rosca <david.rosca@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36646>
These are never created on the stack or deep inside other objects so it
makes sense to use create/destroy instead of init/finish.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Hyunjun Ko <zzoon@igalia.com>
Reviewed-by: David Rosca <david.rosca@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36646>
so that we can get rid of ac_get_ptr_args.
RADV uses AC_ARG_CONST_PTR for num_work_groups, which maps to i8, which
seems wrong.
No functional change.
Reviewed-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36696>
There seems to be a hardware bug that sometimes causes a GPU hang when
an alias...sam sequence crosses an instruction cache line boundary. This
commit adds a workaround pass that inserts padding nops to ensure no
such sequence cross a cache line. Until an alternative solution is
found, this is the best we can do.
While the number of nops we have to insert is fixed at this point, we
can try to minimize the number of nops executed at runtime by replacing
nops encoded in instructions by standalone nops. That is, if this pass
has to insert one nop, it will try to make one of the following
replacements:
- (rptN)nop -> (rptN-1)nop; nop
- (nopN)foo -> (nopN-1)foo; nop
It does so by keeping track of "insert points". Each insert point keeps
track of the instruction and the maximum number of nops that can be
inserted there without pushing any subsequent alias sequences over the
next cache line. Whenever we need to insert nops, we first try it at the
encountered insert points and only if that doesn't work, we insert them
right before the first alias. The pass makes sure the insert points are
only visited a bounded number of times in total to keep the whole pass
O(n).
Totals:
Instrs: 48207402 -> 48278230 (+0.15%)
CodeSize: 101907026 -> 102294524 (+0.38%)
NOPs: 8386320 -> 8457148 (+0.84%)
(ss)-stall: 4013046 -> 4012931 (-0.00%)
(sy)-stall: 16741190 -> 16741033 (-0.00%)
Preamble Instrs: 11506988 -> 11520671 (+0.12%)
Last helper: 11686328 -> 11701615 (+0.13%)
Cat0: 9241457 -> 9312285 (+0.77%)
Totals from 25237 (15.32% of 164705) affected shaders:
Instrs: 22172360 -> 22243188 (+0.32%)
CodeSize: 44372164 -> 44759662 (+0.87%)
NOPs: 4201698 -> 4272526 (+1.69%)
(ss)-stall: 1982473 -> 1982358 (-0.01%)
(sy)-stall: 7379552 -> 7379395 (-0.00%)
Preamble Instrs: 4552074 -> 4565757 (+0.30%)
Last helper: 6260280 -> 6275567 (+0.24%)
Cat0: 4616677 -> 4687505 (+1.53%)
Signed-off-by: Job Noorman <jnoorman@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36639>
We already have these two:
- dep_android comes from vulkan_lite_runtime_deps, through
idep_vulkan_runtime.
- VK_USE_PLATFORM_ANDROID_KHR comes from idep_vulkan_wsi_defines,
through idep_vulkan_runtime.
So let's remove these two, as they don't really add anything new.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36716>
There's two functions that use sysconf(), and they don't seem to agree
on what combination of platforms supports the function. Let's perform
proper function detection instead.
Acked-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Eric Engestrom <eric@igalia.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36621>
The POSIX spec says that_SC_PAGE_SIZE is a synonym for _SC_PAGESIZE, and
both will have the same value. Let's be consistent in which one we use,
and let's use the one that points directly to the authoritative
documentation.
Acked-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Eric Engestrom <eric@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36621>
This reorder things a bit, ensure we attempt more agressive vectorisation,
attempt to optimize cf and more.
Inspiration from NAK's optimize_nir function.
Signed-off-by: Mary Guillemard <mary.guillemard@collabora.com>
Acked-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Acked-by: Eric R. Smith <eric.smith@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36629>
We can end up with conversion instructions to the same type of integer
with nir_lower_bool_to_bitsize so let's make
bifrost_nir_lower_algebraic_late handle those cases.
Signed-off-by: Mary Guillemard <mary.guillemard@collabora.com>
Acked-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36629>
We can benifit from it, let's allow it when we aren't forced to follow
robustness2.
Signed-off-by: Mary Guillemard <mary.guillemard@collabora.com>
Acked-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36629>
Embrace modernity and consistency between alu and vectorization passes.
Signed-off-by: Mary Guillemard <mary.guillemard@collabora.com>
Acked-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36629>
We'll have to handle RT pipelines inside of Anv because the runtime
doesn't have support for that.
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/36711>
Previously we had 2 stages :
runtime -> precomputed values -> packing/emission
With this change we use 3 stages :
runtime -> precomputed values -> packing -> emission
Now blorp & other changes to the pipeline should not retrigger
repacking of instructions.
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/36711>
Since 4095fac72b ("loader: move some common dri3 functions out
of dri3 loader") the new folder has been created, and since
950dac6e6c ("x11: Add an x11_xlib_display_is_thread_safe()
helper") it's also used by vulkan x11, so adding it to the core rules.
Fixes: 4095fac72b ("loader: move some common dri3 functions out of dri3 loader")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36705>
Unless the command we're tracing produces the data we want to capture,
there is no need to wait for its timestamp write.
Currently, there is no such case, so make it the responsibility of the
caller instead of implicitly adding the wait.
Also remove and unnecessary wait for the LS scoreboard after the copy
buffer store.
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36519>
The buffer is only an IUB if it's within the size of the resource entry.
Otherwise, it might just be a buffer that landed just after the
descriptor allocation.
Fixes: fb38f10240 ("panvk: Handle IUBs in decoder")
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36519>
