This reduces silliness in Dolphin ubershaders by eliminating the double
lowering. It also makes the GLES shader assembly nicer to read.
Dolphin ubershader performance at 4K on MMG improved by about 0.5%. Not massive,
but definitely noticeable and reduces the delta to macOS.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25052>
While desktop GL supports sampler LOD bias, GLES does not. To support the GL use
case, all Gallium drivers are expected to handle sampler LOD bias. However, this
may require shader code to implement (lowering tex to txb, txl to fadd+txl) and
cost resources to push the LOD bias constants into the shader. The issue is
compounded with something like Dolphin's GLES renderer, which does this LOD bias
emulation itself -- meaning that LOD bias is lowered twice when using Dolphin
with GLES! As such, this commit adds a context flag for frontends to communicate
that they will never use sampler LOD bias, allowing the driver to omit the
lowering as a GLES fast path (or, for Dolphin, for performance parity between
GLES and GL).
This will be used on Asahi. It could also be used to optimize a path on
Mali-T720 supported in Panfrost, though I don't intend to write that patch.
Originally https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25034
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25052>
With =deqp. I don't want this exposed before geometry shaders since we run dEQP
(GLES) far more than Piglit (GL), and we need geometry shaders to get adequate
regression testing via dEQP-GLES.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25052>
When rendering to a layered depth/stencil attachment, we specify the layer
stride in pages. That means that depth/stencil targets must be page-aligned to
be rendered to correctly.
If we're merely sampling, not rendering, we do not need the extra alignment. So
we add a flag to handle this case so we keep passing the generated ail tests.
Fixes KHR-GLES31.core.texture_cube_map_array.color_depth_attachments
Similarly, we page-align colour attachments. I don't have a good theoretical
justification for this part, but it seems to be necessary and layered rendering
fails otherwise. Possibly the PBE requires page-aligned layers unconditionally?
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25052>
The debug flags are already plumbed into driver_flags for the disk
cache, so we just need to actually allow some flags instead of bailing
out of the disk cache init.
We only care about no16 for production right now, and it's probably a
good idea to disable disk caching during most debug sessions, so
allowlist only that one.
Signed-off-by: Asahi Lina <lina@asahilina.net>
Reviewed-by: Eric Engestrom <eric@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25052>
This is the driconf equivalent of our debug no16 flag, which disables
fp16 support to work around apps using bad GLSL precision qualifiers.
Signed-off-by: Asahi Lina <lina@asahilina.net>
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Eric Engestrom <eric@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25052>
It's time to start using some of these, so add the required scaffolding
to be able to have driver-specific driconf handling for us.
Signed-off-by: Asahi Lina <lina@asahilina.net>
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Eric Engestrom <eric@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25052>
Some frontends differentiate between textures and images more explicitly
than st/mesa. So we might end up with PIPE_BIND_SHADER_IMAGE but not
PIPE_BIND_SAMPLER_VIEW in is_format_supported.
Signed-off-by: Karol Herbst <git@karolherbst.de>
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25052>
Frontends might try to allocate linear textures or images, we should
gracefully return NULL so frontends can do fallback paths.
Signed-off-by: Karol Herbst <git@karolherbst.de>
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25052>
the vbo index is used to set the stride, so it needs to be updated
affects dEQP-VK.pipeline.pipeline_library.bind_buffers_2.single.stride_0_4_offset_1_0.count_2
Fixes: 7672545223 ("gallium: move vertex stride to CSO")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24954>
Issue: For texture with multiple planes, the planes will point to the
same BO with the total size, so current vcn dt_size is incorrect.
(gdb) p/x *((struct si_resource *)(((struct vl_video_buffer *)out_surf)->resources[0]))
...
buf = 0x5555558daa30,
gpu_address = 0xffff800101000000,
bo_size = 0xa2000,
...
}
(gdb) p/x *((struct si_resource *)(((struct vl_video_buffer *)out_surf)->resources[1]))
...
buf = 0x5555558daa30,
gpu_address = 0xffff800101000000,
bo_size = 0xa2000,
...
}
This is because: in function static struct si_texture *si_texture_create_object(),
if (plane0) {
/* The buffer is shared with the first plane. */
resource->bo_size = plane0->buffer.bo_size;
...
radeon_bo_reference(sscreen->ws, &resource->buf, plane0->buffer.buf);
resource->gpu_address = plane0->buffer.gpu_address;
}
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/9728
Cc: mesa-stable
Signed-off-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25013>
When MSAA is enabled, instead of using BLENDFACTOR_ZERO use CONST_COLOR,
CONST_ALPHA and supply zero by using blend constants.
We need info on blend state entries in the CSO so that we can set them
up properly.
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/24714>
The opcodes write to w by default so using anything else means we can't
schedule anything in the rbg slot anyway becasue we have to replicate the
result from w. We already attempt to do this during the scheduling, but
at that point it is more tricky, so doing it early leads to much better
code. Performance++
RV530 benchmarks:
Lightsmark, 1280x800, fullscreen
before:
N Min Max Median Avg Stddev
x 5 27.32 27.36 27.34 27.34 0.015811388
after:
N Min Max Median Avg Stddev
x 5 27.53 27.61 27.59 27.576 0.034351128
Unigine Sanctuary, 1280x800, fullscreen, medium shaders
before:
N Min Max Median Avg Stddev
x 5 10.1211 10.1238 10.1214 10.12192 0.0011211601
after:
N Min Max Median Avg Stddev
x 5 10.4607 10.4637 10.4619 10.46206 0.0012441865
RV530 shader-db:
total instructions in shared programs: 129643 -> 128038 (-1.24%)
instructions in affected programs: 45415 -> 43810 (-3.53%)
helped: 514
HURT: 43
total presub in shared programs: 4912 -> 5201 (5.88%)
presub in affected programs: 752 -> 1041 (38.43%)
helped: 40
HURT: 30
total omod in shared programs: 381 -> 383 (0.52%)
omod in affected programs: 6 -> 8 (33.33%)
helped: 1
HURT: 3
total temps in shared programs: 16904 -> 16841 (-0.37%)
temps in affected programs: 1377 -> 1314 (-4.58%)
helped: 81
HURT: 52
total lits in shared programs: 3555 -> 3550 (-0.14%)
lits in affected programs: 294 -> 289 (-1.70%)
helped: 13
HURT: 11
total cycles in shared programs: 194771 -> 193734 (-0.53%)
cycles in affected programs: 79079 -> 78042 (-1.31%)
helped: 452
HURT: 84
GAINED: shaders/glamor/82.shader_test FS
RV370 shader-db:
total instructions in shared programs: 82116 -> 81600 (-0.63%)
instructions in affected programs: 11888 -> 11372 (-4.34%)
helped: 273
HURT: 40
total temps in shared programs: 12438 -> 12441 (0.02%)
temps in affected programs: 692 -> 695 (0.43%)
helped: 36
HURT: 39
total cycles in shared programs: 128140 -> 127630 (-0.40%)
cycles in affected programs: 25838 -> 25328 (-1.97%)
helped: 266
HURT: 41
GAINED: shaders/0ad/12.shader_test FS
GAINED: shaders/CC3-tiberium-wars/314.shader_test FS
GAINED: shaders/lightsmark/16.shader_test FS
GAINED: shaders/sanctuary/159.shader_test FS
GAINED: shaders/sanctuary/162.shader_test FS
GAINED: shaders/sanctuary/51.shader_test FS
GAINED: shaders/sanctuary/54.shader_test FS
GAINED: shaders/trine/fp-422.shader_test FS
Partial fix for: https://gitlab.freedesktop.org/mesa/mesa/-/issues/6661
Reviewed-by: Filip Gawin <filip.gawin@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24889>
Arm hdlcd display units do exist on Juno SoC's. This is the
first time Mesa has had to deal with panfrost working on these SoC's,
thus have to add hdlcd support.
Signed-off-by: Carsten Haitzler <carsten.haitzler@foss.arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25027>
This fixes a regression with context loss hardened compositors such as
wlroots or kwin where instead of continuing execution in a reset
situation, the process would be aborted. Although these applications set
their notification strategy to lose context on reset, radeonsi also
creates auxiliary contexts for its own use observed when
`egl_init_display` and `gbm_create_device` are called from these
compositors. Fix this by allowing a context loss on reset for these
auxiliary contexts.
Note: It seems this has been attempted before for another call site
creating auxiliary contexts, but this location was missed, hence the
fixed commit hash below.
Fixes: #9672
Fixes: 591aaea648
Signed-off-by: Alexander Orzechowski <alex@ozal.ski>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25023>
Ys & Yf are both implemented in ISL now, we still have some Yf issues
to investigate. Instead of disabling them in ISL, we disable them in
the two drivers.
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23620>
It didn't do any of the error checking, but it was supposed to be. Also
the error checking was slightly wrong and we should return
CL_INVALID_QUEUE_PROPERTIES instead of CL_INVALID_VALUE for unsupported
properties.
Signed-off-by: Karol Herbst <git@karolherbst.de>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24991>
