8235d3aa19
radeonsi: preserve NaNs in draw-based resource_copy_region
...
Gfx copies are faster sometimes, so they should be able to copy anything.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28725 >
2024-04-24 19:17:10 +00:00
a03df53d3b
radeonsi: move blitter clear_render_target impl into si_gfx_clear_render_target
...
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28725 >
2024-04-24 19:17:10 +00:00
82e63db91f
radeonsi: move blitter resource_copy_region implementation to si_gfx_copy_image
...
for a new performance test.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28725 >
2024-04-24 19:17:10 +00:00
e94813204a
radeonsi: allow input NIR to use descriptors in image opcodes
...
Skip lowering because there is nothing to lower.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28725 >
2024-04-24 19:17:10 +00:00
30fab15f39
radeonsi: don't expose samples_identical and don't lower FMASK if it's disabled
...
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28725 >
2024-04-24 19:17:10 +00:00
dab4295cd5
radeonsi: fix initialization of occlusion query buffers for disabled RBs
...
GFX9+ should assume the enabled RB results are packed (no holes).
Same as PAL.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28725 >
2024-04-24 19:17:10 +00:00
aad2302cf5
radeonsi: move TCS epilog key bits to the key->ge.opt section
...
Since the TCS epilog is no more, this is required to apply those bits
to monolithic shaders.
tessfactors_are_def_in_all_invocs was unused.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28725 >
2024-04-24 19:17:10 +00:00
d29d215df7
radeonsi: check has_stable_pstate in the winsys
...
so that we don't duplicate the condition everywhere
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28725 >
2024-04-24 19:17:10 +00:00
a094339d64
radeonsi: add the radeonsi_optimize_io option into the shader cache key
...
otherwise the options would be ignored if the shader cache had already
cached the same shader with the option inverted.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28725 >
2024-04-24 19:17:10 +00:00
3630c11c3b
radeonsi: use the same nir_lower_subgroups_options as RADV
...
Some FREE calls are removed because nir_options is always NULL there.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28725 >
2024-04-24 19:17:10 +00:00
adde1dbae5
radeonsi/gfx11: enable DCC fast clears for 8-bit and 16-bit formats
...
They seem to work fine.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28725 >
2024-04-24 19:17:10 +00:00
d478693dc6
radeonsi/gfx11: don't prefetch constants in binaries into the instruction cache
...
Only prefetch shader instructions. There will be more GFX versions
in that list.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28725 >
2024-04-24 19:17:10 +00:00
71ae7b85ed
radeonsi/ci: update gfx11 failures
...
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28725 >
2024-04-24 19:17:10 +00:00
665df08af4
ac/surface: constify and reindent NIR meta address-from-coord function params
...
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28725 >
2024-04-24 19:17:09 +00:00
cce1aa4766
ac/llvm: always trim components of texture instructions, trim DMASK
...
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28725 >
2024-04-24 19:17:09 +00:00
83a601d420
ac/llvm: fix assertions for texture instructions with 16-bit LOD bias
...
A16 dictates the type.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28725 >
2024-04-24 19:17:09 +00:00
708b0a7c23
intel/dev: Read GFX IP version during runtime
...
Starting from MTL there is registers in HW to read the IP version of
graphics, media and display IPs, those registers are called GMD.
IPs can be used in any combination to form a SOC/platform and each IP
has it own stepping/revision, making complex to track each IP stepping
using just PCI revision.
Since MTL will be supported by default by i915 KMD that don't have
a uAPI fetch IP versions, this feature will only be supported in LNL
and newer that are backed by Xe KMD.
Signed-off-by: José Roberto de Souza <jose.souza@intel.com >
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26908 >
2024-04-24 18:06:04 +00:00
4d3fee0b40
intel: Sync xe_drm.h
...
Sync xe_drm.h with 31ced035ecde ("drm/xe/uapi: Restore flags VM_BIND_FLAG_READONLY and VM_BIND_FLAG_IMMEDIATE").
Signed-off-by: José Roberto de Souza <jose.souza@intel.com >
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26908 >
2024-04-24 18:06:04 +00:00
a78e98f18e
etnaviv/nn: Keep track of the sign bit when decrementing to zero
...
To avoid underflow.
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28879 >
2024-04-24 17:47:44 +00:00
9bac40b796
etnaviv/nn: Don't shortcut ZRL bits calculation
...
In some (probably malformed) cases, even weights BOs for strided or depthwise
convolutions can become bigger when using ZRL compression.
To avoid running out of space in the BO, play safe and calculate the
actual optimum ZRL bit count. This does slow compilation for quite a
bit, though (2x slower for MobileNetV1).
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28879 >
2024-04-24 17:47:44 +00:00
d46e68c89a
etnaviv/nn: Enable image cache
...
By using the on-chip SRAM to cache the input image we can save some more
bandwidth and increase the utilization of the NN cores, with the
following improvements:
MobileNetV1: 9.991ms -> 6.2ms
SSDLite MobileDet: 27ms -> 24.3ms
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28879 >
2024-04-24 17:47:44 +00:00
d6045ca502
etnaviv/nn: Move unused field to its right place in the struct
...
The blob sets it in some cases, but doesn't seem to make any difference.
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28879 >
2024-04-24 17:47:44 +00:00
c75b512673
etnaviv/nn: Fix calculation of remaining out channels
...
We were wrongly counting the remaining number of output channels in the
last superblock, when the former isn't divisible by the latter.
MobileNetV1: 9.991ms -> 9.991ms
SSDLite MobileDet: 32.692ms -> 27ms
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28879 >
2024-04-24 17:47:44 +00:00
baebd6f43d
etnaviv/nn: Ensure tile_y is > 0
...
A zero tile dimension doesn't make sense.
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28879 >
2024-04-24 17:47:44 +00:00
e70ea63a17
teflon: Enable convolutions with number of output channels not divisible by 8
...
This was an old restriction during initial development which isn't
needed any more, and gives us a speed bump.
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28879 >
2024-04-24 17:47:44 +00:00
b143823727
intel/tools: Parse INSTDONE registers in Xe KMD error dump
...
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Signed-off-by: José Roberto de Souza <jose.souza@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28722 >
2024-04-24 17:07:50 +00:00
c221ba6f75
intel/decoder: Add intel_print_group_custom_spacing()
...
This function has 2 additional parameters to set spacing before
printing register group dword or individual registers.
intel_print_group() is keept with the same spacing as before so no
changes on decoder output is expected here.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Signed-off-by: José Roberto de Souza <jose.souza@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28722 >
2024-04-24 17:07:50 +00:00
94deb24e2b
intel/tools/aubinator_error_decode: Move definition of option_color to header
...
Xe parser will also need to use the option_color parameter.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Signed-off-by: José Roberto de Souza <jose.souza@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28722 >
2024-04-24 17:07:50 +00:00
7e5628749c
anv: use u_foreach_bit to iterate over the the view mask like we do for transition_clear_color
...
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/28629 >
2024-04-24 16:42:07 +00:00
5efecc9782
anv: Enable HiZ on multi-LOD depth buffers.
...
Initial work by Rafael Antognolli <rafael.antognolli@intel.com >
Reworks
- Rebase to main
- Emit the right hiz op for higher mip levels when transitioning the
depth buffer
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/28629 >
2024-04-24 16:42:06 +00:00
599e8bf921
ci/valve: remove the traces runner
...
This script is severely outdated and has had no use in literal years.
Signed-off-by: Martin Roukala (né Peres) <martin.roukala@mupuf.org >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28902 >
2024-04-24 15:46:32 +00:00
a589225827
ci/b2c: allow setting the DTB to be used
...
This will be used by upcoming new CI jobs.
Signed-off-by: Martin Roukala (né Peres) <martin.roukala@mupuf.org >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28902 >
2024-04-24 15:46:32 +00:00
2d442fc014
ci/b2c: rename .deqp-test-valve into .b2c-deqp-test
...
Let's remove the mention of Valve and instead focus on the b2c/ci-tron
origin.
Signed-off-by: Martin Roukala (né Peres) <martin.roukala@mupuf.org >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28902 >
2024-04-24 15:46:32 +00:00
b084dbd44f
ci/b2c: rename .b2c-test-{vk,gl} to .b2c-x86_64-test-{vk,gl}
...
This will allow us to introduce non-x86_64 testing using CI-tron.
Signed-off-by: Martin Roukala (né Peres) <martin.roukala@mupuf.org >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28902 >
2024-04-24 15:46:32 +00:00
e2444ad6c1
etnaviv/nn: Extend post-multiplier for v8 architecture
...
The post-multiplier was extended by 8 bits for improved precision.
The shift offset appears to have changed as well.
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de >
Reviewed-by: Tomeu Vizoso <tomeu@tomeuvizoso.net >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28878 >
2024-04-24 15:26:37 +00:00
c2290843df
etnaviv: Add nn_core_version field to etna_specs
...
Use the NN_XYDP0 and NN_VIP7 feature flags to determine the NN core
version [1] and store it in etna_specs.
[1] https://github.com/nxp-imx/linux-imx/blob/lf-6.1.36-2.1.0/drivers/mxc/gpu-viv/hal/kernel/arch/gc_hal_kernel_hardware_func.c#L5464-L5465
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de >
Reviewed-by: Christian Gmeiner <cgmeiner@igalia.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28878 >
2024-04-24 15:26:37 +00:00
db2d5a0103
etnaviv: hwdb: Add VIP_V7 and NN_XYDP0 feature bits
...
These can be used to detect the NN core architecture version [1].
[1] https://github.com/nxp-imx/linux-imx/blob/lf-6.1.36-2.1.0/drivers/mxc/gpu-viv/hal/kernel/arch/gc_hal_kernel_hardware_func.c#L5464-L5465
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de >
Reviewed-by: Christian Gmeiner <cgmeiner@igalia.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28878 >
2024-04-24 15:26:37 +00:00
588c762936
zink: preserve/merge variable names when generating new variables
...
in the case where multiple variables get merged into one, try to use
all the names when creating new vars
Acked-by: Marek Olšák <marek.olsak@amd.com >
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28814 >
2024-04-24 12:36:00 +00:00
cb597cb85e
nir/print: print io instr->name if available
...
this will always be more accurate than trying to find the name from
a variable
Acked-by: Marek Olšák <marek.olsak@amd.com >
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28814 >
2024-04-24 12:35:59 +00:00
948126368a
nir/clone: preserve intrinsic name field across clones
...
Acked-by: Marek Olšák <marek.olsak@amd.com >
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28814 >
2024-04-24 12:35:59 +00:00
5303785bb9
nir/lower_io_to_scalar: preserve variable names when splitting io
...
Acked-by: Marek Olšák <marek.olsak@amd.com >
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28814 >
2024-04-24 12:35:59 +00:00
3541ed8502
nir: store variable names to io instrs during io lowering
...
this creates a reference between variables and their access instrs
before the variables are deleted, which improves debugging
Acked-by: Marek Olšák <marek.olsak@amd.com >
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28814 >
2024-04-24 12:35:59 +00:00
dbe2927472
etnaviv: Avoid duplicate query of ETNA_GPU_FEATURES_0 parameter
...
With the new hwdb, ETNA_GPU_FEATURES_0 were already queried inside
etna_gpu_new(). Use the stored PIPE_3D feature bit to determine
compatible cores.
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de >
Reviewed-by: Christian Gmeiner <cgmeiner@igalia.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28877 >
2024-04-24 12:13:49 +00:00
4f123a7951
etnaviv: common: Add PIPE_3D feature bit
...
With this, we can drop the duplicated ETNA_GPU_FEATURES_0 query in
screen_create().
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de >
Reviewed-by: Christian Gmeiner <cgmeiner@igalia.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28877 >
2024-04-24 12:13:49 +00:00
ff155f46a3
freedreno/a7xx: Register updates from kgsl
...
Will be necessary for kernel changes to match kgsl.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28883 >
2024-04-24 11:29:01 +00:00
59d3a8ea07
ci: uprev CTS to 1.3.8.2
...
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28871 >
2024-04-24 10:48:11 +00:00
cd5c9870ea
rusticl/program: handle -cl-no-subgroup-ifp
...
As per spec we don't have to do anything with that flag.
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28873 >
2024-04-24 10:25:41 +00:00
ca861e8f75
ci: Add zink-venus-lvp job
...
Test Zink on Venus on Lavapipe.
Acked-by: Gert Wollny <gert.wollny@collabora.com >
Reviewed-by: David Heidelberg <david.heidelberg@collabora.com >
Reviewed-by: Yiwei Zhang <zzyiwei@chromium.org >
Signed-off-by: Corentin Noël <corentin.noel@collabora.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27790 >
2024-04-24 09:01:15 +00:00
e9dacca3f7
ci: Allow to pass LIBGL_ALWAYS_SOFTWARE to the guest environment
...
Acked-by: Gert Wollny <gert.wollny@collabora.com >
Reviewed-by: David Heidelberg <david.heidelberg@collabora.com >
Reviewed-by: Yiwei Zhang <zzyiwei@chromium.org >
Signed-off-by: Corentin Noël <corentin.noel@collabora.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27790 >
2024-04-24 09:01:15 +00:00
708a635902
broadcom/ci: document external causes for some CTS 1.3.8 failures
...
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28891 >
2024-04-24 06:59:53 +00:00
Marek Olšák