Unfortunately we have to disable concurrent binning by default
because it hurts performance in a number of desktop games without
any case where we know it helps.
There are less vertex fetch resource available in BV compared to BR,
so when binning runs in BV, there are many vertices, and vertices are
attribute heavy - BV has much worse performance than BR, sometimes more
than 50% worse.
Even with worse performance it won't be bad if concurrent binning
actually overlapped with other workload in those cases, but in case of
desktop games - there is almost never a chance for overlap.
However it's impossible to statically find out if binning on BV would
be much slower than on BR, and we also cannot statically predict if
there is enough overlap (if any) to cover for the performance penalty.
Given the above, I don't see a way out but to make concurrent binning
opt in via `tu_allow_concurrent_binning` driconf toggle.
Still allow concurrent binning in CI to catch issues early.
Signed-off-by: Danylo Piliaiev <dpiliaiev@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41394>
Add AtomicMemorySentinel for cross-platform atomic
memory synchronization. This provides a
platform-agnostic API over Linux futex syscalls,
allowing shared memory synchronization via
memory-mapped file descriptors.
Includes Linux futex implementation and stub
implementations for Windows and other platforms.
Signed-off-by: Dorinda Bassey <dbassey@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39653>
Apparently, this is a major footgun since it is not uncommon for apps to
enable all the features exposed by a driver. Having UBWC disabled for
D24S8 can result in a major performance loss, and the reason can be hard
for devs to spot. This footgun is already known to have happened a few
times. Furthermore, disabling UBWC depending on a Vulkan feature being
requested broke D24S8 sharing via external memory when only one device
was created with customBorderColorWithoutFormat.
Fortunately, there is the depthStencilSwizzleOneSupport feature, which
was added after the above hardware deficiency was found and, when false,
forbids the problematic state combination.
To prevent the footgun described above, we now set
depthStencilSwizzleOneSupport to false by default. This allows UBWC to be
enabled for D24S8 in all cases while remaining conformant. We also have
the tu_enable_d24s8_border_color_workaround driconf option, which enables
the previous workaround for apps that don't know about
depthStencilSwizzleOneSupport, which is currently only the ANGLE
translation layer.
One caveat is that we cannot use the fast border color HW feature for
D24S8+USAGE_SAMPLED+VK_FORMAT_UNDEFINED, so a new driconf toggle is
added. enable_fast_border_color_for_undefined_formats is set for DXVK and
vkd3d-proton since they are known not to use border colors with D24S8.
Lacking fast border colors is a much smaller penalty than not having UBWC
for D24S8.
For some context also see: https://gitlab.khronos.org/Tracker/vk-gl-cts/-/issues/4346
This partially reverts 36916949.
Signed-off-by: Danylo Piliaiev <dpiliaiev@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41514>
pre_chain.rp_trace usage relied on a bunch of bad assumptions
and together with u_trace_move didn't cause issues until
u_trace is started to be refactored. Fixing those bad assumptions
and correctly initializing and freeing pre_chain.rp_trace
also requires fixing u_trace_move at the same time.
u_trace_move fixes:
- If dst had trace chunks in it - we may have leaked them.
- The correct list move pattern is "list_replace -> list_inithead"
not "list_replace -> list_delinit"
Signed-off-by: Danylo Piliaiev <dpiliaiev@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41390>
When uncached memory type is used under emulation then most games have a
significant performance penalty due to accessing the buffer atomically.
Instead when this option is set, it will override uncached buffer
allocations to instead be cached+coherent if the host supports it. This
allows the atomic accesses to still be done but not have abysmal
performance.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41323>
If we're a bit clever with the bits, we can make one fixup helper that
works for all rounding modes. See the giant comment for details.
Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41295>
This makes the tests names a bit more consistent and takes advantage of
the namespacing that gtest already gives us. (There's no reason to put
the whole prefix in the test name again.)
Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41295>
Smashing bits is super sketchy. However, all the bits do is force the
test down the _slow path so let's explicitly test that instead.
Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41295>
The NDK api __android_log_write has been available since api level 3,
which is preferred since NDK api is more stable. Meanwhile, use write
instead of print to avoid extra internal copy/truncate involved in the
print helper.
Acked-by: Valentine Burley <valentine.burley@collabora.com>
Reviewed-by: Dhruv Mark Collins <mark@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41254>
According to ubsan shifting an int32_t by 31 bits to the left is undefined
behavior. So just declare it as uint32_t.
Backport-to: 26.1
Reviewed-by: Adam Jackson <ajax@redhat.com>
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41252>
__system_property_get is available since api level 3. There was a glitch
back in Android L, but the complete official supported was added back to
NDK immediately after the removal, and was patched into the same api
level 21. So it's safe to say this api is available all the time.
Our helper does not have a default prop value, so __system_property_get
is a better fit.
Reviewed-by: Dhruv Mark Collins <mark@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41222>
This checks that the subsampling is specified in the name of the
format.
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41151>
This applies to all subsampled layouts, including the planar ones.
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41151>
Instead of parsing the format name, let's make the subsampling explicit
in the format table.
This fixes the reported subsampling for Y8U8V8_420_UNORM_PACKED and
Y10U10V10_420_UNORM_PACKED, which didn't match because of the _PACKED
suffix.
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41151>
The definiton of Y8_UNORM and Y8_400_UNORM are already identical, with
the only real difference being that pipe_format_to_chroma_format() does
not return R8 for Y8_UNORM. But Y8_UNORM is only used by freedreno,
the intel drivers and virgl, none of which doesn't even call
pipe_format_to_chroma_format() in the first place, so this shouldn't
matter.
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41151>
The Vulkan spec says:
"VUID-vkCmdExecuteGeneratedCommandsEXT-None-11062
If a rendering pass is currently active, the view mask must be 0."
So, it's invalid with VK_EXT_device_generated_commands but it's allowed
in DX12, it seems we missed this during the spec review.
Crimson Desert uses this and emulating in vkd3d-proton would be complex,
so let's re-introduce this support only for vkd3d-proton.
Cc: mesa-stable
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41153>
For the future patches in Anv, we will be expanding the driconf enum to
have 19 entries, so extend array from 5 to 20 to account that.
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/40733>
This can be used to workaround problem cases with application
controlled subgroup size.
Signed-off-by: Tapani Pälli <tapani.palli@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40813>
CBV resources are supposed to be 256B aligned
(D3D12_CONSTANT_BUFFER_DATA_PLACEMENT_ALIGNMENT).
vkd3d-proton will puts CBV addresses in the push constant data and do
global loads on them. Unfortunately those loads don't have a 256B
alignment value on them. So when looking at what we can promote to HW
push buffers, we can't consider them.
This change introduces a detection pass for CBV resources (according
to vkd3d-proton devs those are 64KiB in size) and realign the loads to
be 256B aligned.
This is only enabled on DX emulation.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Felix DeGrood <felix.j.degrood@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39451>
This commit allows for overriding the normal u_stub's TAIL
implementation (returning -1) with a custom implementation, allowing for
different TAIL implementations to be added without having to create a
new TAIL+ in u_stub.h.
Signed-off-by: Thong Thai <thong.thai@amd.com>
Reviewed-by: David Rosca <david.rosca@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40493>
Move u_stub.h from amd/common, to util, so that it can be used in more
places.
Also, rename u_stub's PROC to MESAPROC, as it conflicts with the PROC
keyword and create a new TAILZ which returns 0.
Add u_stub_gfx_compute.h so that the following:
...can be a single-line:
Signed-off-by: Thong Thai <thong.thai@amd.com>
Reviewed-by: David Rosca <david.rosca@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40493>
The format has 4 x 16-bit words with 10-bit unorm values in bits [15:6]
and 6 padding bits in [5:0]. Since this requires 8 channel slots but the
format system only supports 4, use layout "other" with hand-written
pack/unpack conversion functions.
Signed-off-by: Christian Gmeiner <cgmeiner@igalia.com>
Reviewed-by: Lars-Ivar Hesselberg Simonsen <lars-ivar.simonsen@arm.com>
Acked-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40653>
runtime error: left shift of 65535 by 16 places cannot be represented in type 'int'
This fixes nir_opt_algebraic_pattern_test.bf2f.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Fixes: ecd2d2cf46 ("util: Add functions to convert float to/from bfloat16")
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40740>
It is sometimes useful to remove all elements of a bitset while retaining the
backing storage. With a dense bitset, we would just memset everything to 0,
which is O(capacity). With a sparse bitset, previously we would have to free and
reallocate, which is O(capacity) in the dense case and O(cardinality) in the
sparse case. That is the correct asymptoptic behaviour O(cardinality) in the
worst case, but there is an unfortunate constant-factor associated with the
redundant allocation & free in the dense case.
Therefore, we add a new helper to clear all elements of the sparse bitset in one
go, avoiding reallocation in the dense case.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@intel.com>
Reviewed-by: Natalie Vock <natalie.vock@gmx.de>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40806>
PC games tend to almost always run far better in SYSMEM due to the
high FS complexity, and so preferring SYSMEM tends to be a winning
policy until profiled mode reaches a state where it can surpass it.
Signed-off-by: Dhruv Mark Collins <mark@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37802>
The default ROUND_DOWN_TO only handles POT alignment values, so
an additional variant was added which handles NPOT alignment too.
Signed-off-by: Dhruv Mark Collins <mark@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37802>
drmGetNodeTypeFromFd and drmGetRenderDeviceNameFromFd will be used in
EGL.
Acked-by: Emma Anholt <emma@anholt.net>
Reviewed-by: Eric Engestrom <eric@igalia.com>
Signed-off-by: Valentine Burley <valentine.burley@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40302>
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Acked-by: Marek Olšák <marek.olsak@amd.com>
Acked-by: Emma Anholt <emma@anholt.net>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40318>
