Samuel Pitoiset [Thu, 25 May 2023 13:04:56 +0000 (15:04 +0200)]
amd: add has_gpuvm_fault_query
Whether the kernel allows to query the last GPUVM fault.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23238>
Samuel Pitoiset [Tue, 10 Oct 2023 08:37:16 +0000 (10:37 +0200)]
amd: update amdgpu_drm.h
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23238>
Samuel Pitoiset [Tue, 24 Oct 2023 07:29:41 +0000 (09:29 +0200)]
radv: remove outdated RADV_DEBUG=vmfaults support
It's been a very long time since this was useless because dmesg
required sudo access for a while.
This will be replaced by the new GPUVM fault interface which allows
to query from the kernel directly instead of trying to parse dmesg.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23238>
Seppo Yli-Olli [Wed, 25 Oct 2023 11:55:47 +0000 (11:55 +0000)]
zink: Fix SyntaxWarning in zink_extensions script
Fix regex pattern in zink_extensions to use proper escaping. While the original
code works, it relies on Python ignoring incorrect syntax and fallbacking to
passing through the escape. Current behaviour results in SyntaxWarning
whenever the code is used.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25881>
Louis-Francis Ratté-Boulianne [Thu, 21 Sep 2023 15:19:23 +0000 (11:19 -0400)]
panfrost: Add env variable for max AFBC packing ratio
Add `PAN_MAX_AFBC_PACKING_RATIO` variable. If the ratio (size of the
packed resource) / (size of the sparse resource) * 100 is above that
value, we don't care about packing it.
Signed-off-by: Louis-Francis Ratté-Boulianne <lfrb@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25012>
Louis-Francis Ratté-Boulianne [Fri, 1 Sep 2023 17:34:28 +0000 (13:34 -0400)]
panfrost: Add some debug utility methods for resources
Add a method to dump a specific superblock given its index (header
and few first bytes from the body) and a method to dump a resource
to a ppm file.
Signed-off-by: Louis-Francis Ratté-Boulianne <lfrb@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25012>
Louis-Francis Ratté-Boulianne [Fri, 1 Sep 2023 17:31:19 +0000 (13:31 -0400)]
panfrost: Add debug flag to force packing of AFBC textures on upload
Add `forcepack` flag that will force conversion to AFBC-packed right
after a texture is uploaded when possible. We only pack 2D resources
larger than 32x32 as of now.
Signed-off-by: Louis-Francis Ratté-Boulianne <lfrb@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25012>
Louis-Francis Ratté-Boulianne [Fri, 1 Sep 2023 15:26:02 +0000 (11:26 -0400)]
panfrost: Don't force constant modifier after converting
After converting a texture from one modifier to another, there is
no reason to force the modifier to stay constant afterwards. Set
back `modifier_constant` to false because it is changed by
`resource_setup` as it is causing issues when implementing AFBC
packing.
Signed-off-by: Louis-Francis Ratté-Boulianne <lfrb@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25012>
Louis-Francis Ratté-Boulianne [Fri, 1 Sep 2023 15:22:05 +0000 (11:22 -0400)]
panfrost: Legalize resource when attaching to a batch
Make sure we don't convert the texture for nothing by only
legalizing when creating a batch instead of on surface creation.
Also, to avoid recursive blit, we need to legalize the destination
resource before blitting.
Finally, make sure the resource has a sparse memory layout if
AFBC compressed. The GPU doesn't support rendering to a AFBC-packed
texture.
Signed-off-by: Louis-Francis Ratté-Boulianne <lfrb@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25012>
Louis-Francis Ratté-Boulianne [Fri, 1 Sep 2023 03:33:45 +0000 (23:33 -0400)]
panfrost: Add support for AFBC packing
When the GPU is converting a texture from linear/tiled to compressed
AFBC, it uses a sparse memory layout. That means that the
superblocks are stored starting at intervals equal to the size of an
uncompressed superblock. When memory usage needs to be optimized, it
is possible to pack the resource by trimming each superblock as much
as possible. The GPU will still be able to read from these packed
textures, but won't be able to write directly to them. If the
layout is AFBC-tiled, the packing process will also de-tile as
tiled+packed is not supported by Mali GPUs.
No new modifier flag has been added as the absence of the
`AFBC_FORMAT_MOD_SPARSE` flag means the resource will be packed.
Signed-off-by: Louis-Francis Ratté-Boulianne <lfrb@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25012>
Louis-Francis Ratté-Boulianne [Mon, 11 Sep 2023 06:52:16 +0000 (02:52 -0400)]
panfrost: Add method to get size of AFBC superblocks valid data
The compute shader is going through all the AFBC header blocks and
calculating the size of valid data by summing up the subblock
sizes (and taking into account solid color, uncompressed mode and
copy blocks). The result is written into the given buffer (array
of `pan_afbc_block_info`).
The size is rounded up to the alignment parameter directly in the
shader.
Signed-off-by: Louis-Francis Ratté-Boulianne <lfrb@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25012>
Louis-Francis Ratté-Boulianne [Sat, 7 Oct 2023 01:19:45 +0000 (21:19 -0400)]
panfrost: Add infrastructure for internal AFBC compute shaders
A few compute shaders are needed to support AFBC-packing. Here is
just the boilerplate to create, compile and retrieve the shaders.
Signed-off-by: Louis-Francis Ratté-Boulianne <lfrb@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25012>
Louis-Francis Ratté-Boulianne [Sat, 7 Oct 2023 01:19:10 +0000 (21:19 -0400)]
panfrost: Split out internal of `panfrost_launch_grid`
For an upcoming feature (AFBC packing), we're gonna run internal
compute shaders on resources. This commit just split the internal
of `panfrost_launch_grid` so we can run the shader on a given
batch.
Signed-off-by: Louis-Francis Ratté-Boulianne <lfrb@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25012>
Louis-Francis Ratté-Boulianne [Thu, 31 Aug 2023 16:18:46 +0000 (12:18 -0400)]
panfrost: Make panfrost_resource_create_with_modifier public
It allows creating a resource when we already know which modifier
we're gonna use.
Signed-off-by: Louis-Francis Ratté-Boulianne <lfrb@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25012>
Louis-Francis Ratté-Boulianne [Thu, 31 Aug 2023 15:47:48 +0000 (11:47 -0400)]
panfrost: Add panfrost_batch_write_bo
Needed when writing to a BO from a compute shader when the BO isn't
assigned to a resource yet.
Signed-off-by: Louis-Francis Ratté-Boulianne <lfrb@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25012>
Louis-Francis Ratté-Boulianne [Thu, 31 Aug 2023 15:33:39 +0000 (11:33 -0400)]
panfrost: Precalculate stride and nr of blocks for AFBC layouts
For AFBC packing, we will need to have the stride of the resource
in terms of superblocks and the total number of blocks. It is
easier to pre-calculate once when initializing the resource layout.
Signed-off-by: Louis-Francis Ratté-Boulianne <lfrb@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25012>
Louis-Francis Ratté-Boulianne [Thu, 31 Aug 2023 15:31:42 +0000 (11:31 -0400)]
panfrost: Add method to get size of AFBC subblocks
Each AFBC superblock is subdivised into subblocks that are
compressed individually. For all formats that we currently support,
the subblocks are 4x4 pixels.
Signed-off-by: Louis-Francis Ratté-Boulianne <lfrb@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25012>
Louis-Francis Ratté-Boulianne [Thu, 31 Aug 2023 15:19:45 +0000 (11:19 -0400)]
panfrost: Add methods to determine slice and body alignment
Those methods are needed to have the same alignment everywhere
without hard-coding the values
Signed-off-by: Louis-Francis Ratté-Boulianne <lfrb@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25012>
Louis-Francis Ratté-Boulianne [Thu, 31 Aug 2023 15:17:45 +0000 (11:17 -0400)]
panfrost: Fix error in comment
"linear" -> "tiled"
Signed-off-by: Louis-Francis Ratté-Boulianne <lfrb@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25012>
Tapani Pälli [Mon, 23 Oct 2023 05:01:31 +0000 (08:01 +0300)]
egl: fix leaking drmDevicePtr in _eglFindDevice
Fixes:
3a9e1014e13 ("egl: Rename _eglAddDevice() to _eglFindDevice()")
Signed-off-by: Tapani Pälli <tapani.palli@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25524>
Lionel Landwerlin [Tue, 24 Oct 2023 20:06:01 +0000 (23:06 +0300)]
anv: fixup 32bit build of internal shaders
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes:
11b4c23d19 ("anv: add ring buffer mode to generated draw optimization")
Fixes:
db335d9b73 ("anv: factor out host/gpu internal shaders interfaces")
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/10037
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25870>
Christian Gmeiner [Wed, 25 Oct 2023 08:10:41 +0000 (10:10 +0200)]
etnaviv: Don't leak disk_cache
Fixes:
77af1ca690f ("etnaviv: add disk cache")
Signed-off-by: Christian Gmeiner <cgmeiner@igalia.com>
Reviewed-by: Tomeu Vizoso <tomeu@tomeuvizoso.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25877>
Christian Gmeiner [Wed, 25 Oct 2023 08:35:47 +0000 (10:35 +0200)]
ci: Bump PyYAML to 6.0.1
Fixes an issue I am seeing on Fedora 39. For more details
about the upstream fix see https://github.com/yaml/pyyaml/pull/702
Signed-off-by: Christian Gmeiner <cgmeiner@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25878>
Tapani Pälli [Mon, 23 Oct 2023 11:47:58 +0000 (14:47 +0300)]
intel/dev: expand existing fix for all gfx12 with small EU count
Commit
7db1b94e07f added a fix for ADL-N but this issue has been
reproduced also on RPL-S and is likely common with all gfx12 variants
with a small EU count.
cc: mesa-stable
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/25861>
Caio Oliveira [Fri, 8 Sep 2023 21:55:58 +0000 (14:55 -0700)]
compiler/types: Move comments and reorganize declarations
Move comments from C++ member functions to the C functions. In
some cases just delete comments or consolidate them together.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Fri, 8 Sep 2023 19:29:54 +0000 (12:29 -0700)]
compiler/types: Remove warnings about potential fallthrough
None of those cases are expected to fallthrough, but should be unreachable.
Just break them so they get to the unreachable entry at the end.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Fri, 8 Sep 2023 18:45:43 +0000 (11:45 -0700)]
compiler/types: Rename glsl_types.cpp to glsl_types.c
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Fri, 8 Sep 2023 18:20:43 +0000 (11:20 -0700)]
compiler/types: Annotate extern "C" only once in glsl_types.cpp
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Fri, 8 Sep 2023 17:04:43 +0000 (10:04 -0700)]
compiler/types: Remove usages of C++ members in glsl_types.cpp
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Fri, 8 Sep 2023 17:46:11 +0000 (10:46 -0700)]
compiler/types: Use C instead of C++ constants for builtin types
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Fri, 8 Sep 2023 16:50:45 +0000 (09:50 -0700)]
compiler/types: Add remaining type extraction functions and use them in C++
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Fri, 8 Sep 2023 15:42:31 +0000 (08:42 -0700)]
compiler/types: Add glsl_simple_explicit_type() and simplify glsl_simple_type()
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Fri, 8 Sep 2023 03:15:35 +0000 (20:15 -0700)]
compiler/types: Implement glsl_type::field_type() in terms of existing functions
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Fri, 8 Sep 2023 03:35:31 +0000 (20:35 -0700)]
compiler/types: Add glsl_get_explicit_*() functions and use them in C++
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Fri, 8 Sep 2023 03:20:53 +0000 (20:20 -0700)]
compiler/types: Add glsl_get_std430_array_stride() and use it in C++
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Fri, 8 Sep 2023 03:08:37 +0000 (20:08 -0700)]
compiler/types: Add glsl_type_uniform_locations() and use it in C++
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Fri, 8 Sep 2023 03:03:57 +0000 (20:03 -0700)]
compiler/types: Add glsl_type_compare_no_precision() and use it in C++
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Fri, 8 Sep 2023 02:50:36 +0000 (19:50 -0700)]
compiler/types: Add glsl_get_mul_type() and use it in C++
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Fri, 8 Sep 2023 02:35:54 +0000 (19:35 -0700)]
compiler/types: Add more glsl_contains_*() functions and use them in C++
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Sat, 16 Sep 2023 17:19:22 +0000 (10:19 -0700)]
rusticl: Add bindings for glsl_vector_type()
This is going to become inline functions, so add the corresponding
Rust bindings for it first.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Fri, 8 Sep 2023 00:47:32 +0000 (17:47 -0700)]
compiler/types: Move remaining code from nir_types to glsl_types
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Thu, 7 Sep 2023 03:34:49 +0000 (20:34 -0700)]
compiler/types: Flip wrapping of numeric type conversion functions
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Sun, 3 Sep 2023 01:29:09 +0000 (18:29 -0700)]
compiler/types: Flip wrapping of remaining small data getters
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Sun, 3 Sep 2023 01:09:17 +0000 (18:09 -0700)]
compiler/types: Flip wrapping of remaining non-trivial type getters
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Sun, 3 Sep 2023 01:00:42 +0000 (18:00 -0700)]
compiler/types: Flip wrapping of get row/column type helpers
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Sun, 3 Sep 2023 00:53:34 +0000 (17:53 -0700)]
compiler/types: Flip wrapping of various get instance functions
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Sun, 3 Sep 2023 00:20:29 +0000 (17:20 -0700)]
compiler/types: Flip wrapping of texture/sampler/image get instance functions
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Sun, 3 Sep 2023 00:12:56 +0000 (17:12 -0700)]
compiler/types: Flip wrapping of get_instance()
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Sat, 2 Sep 2023 20:01:52 +0000 (13:01 -0700)]
compiler/types: Flip wrapping of record_compare
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Sat, 2 Sep 2023 19:53:32 +0000 (12:53 -0700)]
compiler/types: Flip wrapping of layout related functions
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Sat, 2 Sep 2023 19:19:39 +0000 (12:19 -0700)]
compiler/types: Flip wrapping of interface related functions
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Sat, 2 Sep 2023 18:39:23 +0000 (11:39 -0700)]
compiler/types: Flip wrapping of struct related functions
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Sat, 2 Sep 2023 18:25:49 +0000 (11:25 -0700)]
compiler/types: Flip wrapping of size related functions
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Sat, 2 Sep 2023 18:04:49 +0000 (11:04 -0700)]
compiler/types: Flip wrapping of CL related functions
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Thu, 28 Sep 2023 19:17:45 +0000 (12:17 -0700)]
compiler/types: Flip wrapping of cmat related functions
Also add a missing `struct` related to cmat.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Sat, 2 Sep 2023 17:53:02 +0000 (10:53 -0700)]
compiler/types: Flip wrapping of array related functions
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Caio Oliveira [Sat, 2 Sep 2023 17:25:37 +0000 (10:25 -0700)]
compiler/types: Flip wrapping of "type contains?" predicate functions
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25129>
Eric Anholt [Fri, 20 Oct 2023 10:11:13 +0000 (12:11 +0200)]
ci_run_n_monitor: Always resolve --rev arguments for looking up pipelines.
Otherwise you'd loop forever never finding it with --rev <paste from
gitlab UI> or --rev <branch name>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25824>
David Rosca [Wed, 4 Oct 2023 14:55:47 +0000 (16:55 +0200)]
radeonsi/vcn: Add encode support for H264 B-frames
Tested with ffmpeg and gstreamer vah264enc.
References to B-frames (b_depth/b-pyramid) not supported.
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25565>
David Rosca [Thu, 5 Oct 2023 14:47:21 +0000 (16:47 +0200)]
frontends/va: Fix parsing packed headers without emulation bytes
Don't try to handle emulation bytes and only parse first NAL unit
if the packed header has no emulation bytes.
This fixes parsing packed headers from gstreamer.
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25565>
David Rosca [Thu, 5 Oct 2023 14:41:33 +0000 (16:41 +0200)]
util/vl: Fix vl_rbsp parser with bitstreams without emulation bytes
This is used for parsing VA packed headers and those can be without
emulation prevention bytes.
Add emulation_bytes argument to vl_rbsp_init and skip all emulation
bytes handling when set.
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25565>
David Rosca [Wed, 4 Oct 2023 14:51:05 +0000 (16:51 +0200)]
frontends/va: Parse H264 SPS for max_num_reorder_frames
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25565>
Chia-I Wu [Tue, 17 Oct 2023 19:25:20 +0000 (12:25 -0700)]
anv: add gen9 astc workaround
gen9 does not handle denorms in void extent blocks correctly. We need
to flush them to zero.
Signed-off-by: Chia-I Wu <olvaffe@gmail.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25800>
Chia-I Wu [Wed, 18 Oct 2023 15:59:28 +0000 (08:59 -0700)]
anv: prep for gen9 astc workaround
We will reuse astc emu for gen9 astc workaround. This commit contains
minor cleanups and has no functional change.
Signed-off-by: Chia-I Wu <olvaffe@gmail.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25800>
Timur Kristóf [Fri, 20 Oct 2023 20:16:16 +0000 (22:16 +0200)]
radv: Support SDMA in si_cs_emit_write_event_eop.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Tatsuyuki Ishi <ishitatsuyuki@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25833>
Timur Kristóf [Fri, 20 Oct 2023 20:12:43 +0000 (22:12 +0200)]
radv: Support SDMA in radv_cp_wait_mem.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Tatsuyuki Ishi <ishitatsuyuki@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25833>
Timur Kristóf [Fri, 20 Oct 2023 20:10:50 +0000 (22:10 +0200)]
radv: Support SDMA in radv_cs_write_data_head.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Tatsuyuki Ishi <ishitatsuyuki@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25833>
Mary Guillemard [Fri, 22 Sep 2023 16:30:51 +0000 (18:30 +0200)]
nir: Add NVIDIA-specific geometry shader opcodes
Signed-off-by: Mary Guillemard <mary.guillemard@collabora.com>
Reviewed-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25000>
Faith Ekstrand [Sat, 30 Sep 2023 07:16:51 +0000 (02:16 -0500)]
nir: Add NVIDIA-specific I/O intrinsics
NVIDIA hardware doesn't take a vertex index for per-vertex I/O.
Instead, it takes an offset into the primitive. This has to be fetched
using a combination of SR_INVOCATION_INFO and the ISBERD instruction.
To keep things simple and allow for maximum CSE, we do the lowering in
NIR and patch the load/store_per_vertex_input/output intrinsic.
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25000>
Faith Ekstrand [Tue, 26 Sep 2023 20:01:03 +0000 (15:01 -0500)]
nir: Add a range to most I/O intrinsics
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25000>
Faith Ekstrand [Fri, 15 Sep 2023 22:22:52 +0000 (17:22 -0500)]
nir: Add an load_barycentric_at_offset_nv intrinsic
NVIDIA hardware takes the offset as two 4.12 fixed-point values packed
into a single 32-bit value.
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25000>
Faith Ekstrand [Mon, 10 Apr 2023 22:23:32 +0000 (17:23 -0500)]
nir: Add NV-specific texture opcodes
These are for implementing various texture queries.
Acked-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25000>
Faith Ekstrand [Tue, 19 Sep 2023 02:14:35 +0000 (21:14 -0500)]
nir: Add a load_sysval_nv intrinsic
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25000>
Faith Ekstrand [Mon, 10 Apr 2023 22:23:32 +0000 (17:23 -0500)]
nir/lower_tex: Add a lower_txd_clamp option
Some of us want to lower all TXD with min_lod regardless of whether or
not it's shadow or cube or whatever.
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25000>
Faith Ekstrand [Mon, 10 Apr 2023 22:23:30 +0000 (17:23 -0500)]
nir: Add convert_alu_types to divergence analysis
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25000>
Faith Ekstrand [Fri, 28 Apr 2023 23:44:55 +0000 (18:44 -0500)]
nir: Add a nir_ssa_def_all_uses_are_fsat() helper
Extracted from nir_lower_to_source_mods, this is useful for back-ends
which don't want to rely on NIR source and destination modifiers.
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25000>
Rhys Perry [Fri, 1 Sep 2023 10:27:39 +0000 (11:27 +0100)]
radv: enable mesh shader gs_fast_launch=2 and multi-row export
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25040>
Rhys Perry [Fri, 1 Sep 2023 16:15:49 +0000 (17:15 +0100)]
radv: implement mesh shader multi-row export
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25040>
Rhys Perry [Thu, 19 Oct 2023 18:27:07 +0000 (19:27 +0100)]
ac/nir: implement mesh shader multi-row export
Unlike AMDVLK, this has separate loops for attribute stores and exports,
so that the stores from different rows can overlap.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25040>
Rhys Perry [Thu, 19 Oct 2023 18:27:07 +0000 (19:27 +0100)]
ac/nir,radv: pass workgroup size to ac_nir_lower_ngg_ms
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25040>
Rhys Perry [Fri, 1 Sep 2023 16:13:20 +0000 (17:13 +0100)]
ac/nir: add emit_ms_outputs helper
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25040>
Rhys Perry [Fri, 1 Sep 2023 10:25:00 +0000 (11:25 +0100)]
radv: implement mesh shader gs_fast_launch=2
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25040>
Rhys Perry [Thu, 7 Sep 2023 16:01:14 +0000 (17:01 +0100)]
ac/nir: optimize mesh shader local_invocation_index
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25040>
Rhys Perry [Fri, 1 Sep 2023 10:24:56 +0000 (11:24 +0100)]
ac/nir: implement mesh shader gs_fast_launch=2
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25040>
Rhys Perry [Fri, 1 Sep 2023 10:22:42 +0000 (11:22 +0100)]
ac/nir: refactor mesh vertex/primitive export
To prepare for row export, move them into helpers with index and row
parameters.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25040>
Rhys Perry [Fri, 1 Sep 2023 10:29:57 +0000 (11:29 +0100)]
ac/nir: remove dead code
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25040>
Rhys Perry [Fri, 1 Sep 2023 10:18:38 +0000 (11:18 +0100)]
ac/nir: add row parameter to helpers
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25040>
Rhys Perry [Fri, 1 Sep 2023 10:16:29 +0000 (11:16 +0100)]
aco,nir: add export_row_amd intrinsic
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25040>
Rhys Perry [Thu, 31 Aug 2023 19:35:25 +0000 (20:35 +0100)]
nir: improve ms_cross_invocation_output_access with local_invocation_id
Since GFX11, RADV doesn't need to lower local_invocation_id.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25040>
Caio Oliveira [Sun, 22 Oct 2023 21:36:03 +0000 (14:36 -0700)]
intel/compiler: Don't emit calls to validate() in release build
While the fs_visitor::validate() implementation is empty in release
build, we still emit calls to it since it is defined in a separate
compilation unit than its callers. To fix this, just expose an inline
empty function in the header for the release mode.
Fossil run time differences in TGL laptop (difference at 95.0% confidence):
```
Rise of The Tomb Rider (Native) [n=7]
-0.482857 +/- 0.010932
-1.60608% +/- 0.0363621%
Cyberpunk 2077 (DXVK) [n=7]
-0.987143 +/- 0.0904516
-0.82996% +/- 0.076049%
Batman Arkham City (DXVK) [n=7]
-7.74857 +/- 0.329561
-1.46298% +/- 0.0622231%
```
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25847>
Samuel Pitoiset [Tue, 24 Oct 2023 14:52:41 +0000 (16:52 +0200)]
ac/gpu_info: fix querying the maximum number of IBs per ring
The kernel uses 32-bit and Mesa was using 8-bit...
Fixes:
96345ae2ed3 ("ac/gpu_info: query the maximum number of IBs per submit from the kernel")
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25867>
Rohan Garg [Mon, 23 Oct 2023 10:02:32 +0000 (12:02 +0200)]
anv: selectively enable FCV optimization for DG2
Enabling FCV on MTL breaks a number of games and benchmarks. Let's
disable it for now till we can root cause the issue.
Closes: #9987
Fixes: 26c2c9 ('anv: enable FCV for Gen12.5')
Signed-off-by: Rohan Garg <rohan.garg@intel.com>
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25863>
Rohan Garg [Wed, 11 Oct 2023 10:30:58 +0000 (12:30 +0200)]
anv: turn off non zero fast clears for CCS_E
This helps fix a performance regression on games such as F1 22 and RDR2.
Turning on non zero fast clears causes additional partial resolves for
these games that degrades performance. Let's turn off non zero fast
clears till we can eliminate the partial resolves.
Signed-off-by: Rohan Garg <rohan.garg@intel.com>
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25863>
Boyuan Zhang [Mon, 23 Oct 2023 20:22:42 +0000 (16:22 -0400)]
radeonsi/vcn: disable tmz ctx buffer for VCN_2_2_0
VCN_2_2_0 should not use tmz context buffer.
Fixes:
ffbbf23e
A minor fix for above commit to use the original comparison logic "<"
instead of "<="
Cc: mesa-stable
Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25856>
Juan A. Suarez Romero [Tue, 24 Oct 2023 11:54:37 +0000 (13:54 +0200)]
v3d/vc4/ci: add new fails/timeout
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25868>
Timur Kristóf [Fri, 20 Oct 2023 17:55:38 +0000 (19:55 +0200)]
radv: Add gang follower semaphore functions.
These functions implement the possibility to have the
gang leader wait for its follower.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25796>
Timur Kristóf [Fri, 20 Oct 2023 16:48:47 +0000 (18:48 +0200)]
radv: Slightly refactor gang semaphore functions.
This is in preparation for adding some new ones.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25796>
Timur Kristóf [Sat, 14 Oct 2023 15:17:07 +0000 (17:17 +0200)]
radv: Allow gang submit use cases other than task shaders.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25796>
Timur Kristóf [Mon, 16 Oct 2023 09:42:42 +0000 (11:42 +0200)]
radv: Simplify gang CS and semaphore initialization.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25796>
Samuel Pitoiset [Mon, 23 Oct 2023 11:32:41 +0000 (13:32 +0200)]
radv: fix missing predicate bit for WRITE_DATA helper
Fixes:
12a753f8d2c ("radv: Use new WRITE_DATA helper in more places.")
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25850>