This generally works well.
There are new cases that select Wave32, and there are shader profiles
which adjust that.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13966>
This capability is enabled for drivers supporting formatless image
writing in shader.
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Signed-off-by: Juan A. Suarez Romero <jasuarez@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13409>
egl-copy-buffers test has been fixed for dri3. So remove
it from broadcom and freedreno ci fail list to prevent the
gitlab ci test fail:
spec@egl 1.4@egl-copy-buffers,UnexpectedPass
Also remove it from radeonsi ci fail list since I verified
on radeonsi.
Acked-by: Daniel Stone <daniels@collabora.com>
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Signed-off-by: Qiang Yu <yuq825@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13868>
The big comment was not really true.
The other debug options are unused right now, but will be used again
in the future.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13878>
We don't set them and we don't read them if they are disabled, so don't
print them either. This silences valgrind warnings.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13878>
It already does compaction, so we just need to load vertex positions
and cull. This was easier than expected.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13829>
si_llvm_translate_nir() changes ctx.stage, so the outside code shouldn't
use it. This hasn't caused any issues yet. Since ctx.stage starts as 0,
the first use in this commit was a tautology.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13829>
use a user SGPR instead. This will be needed in the future.
Also don't upload small_prim_precision because it's passed via
VS_STATE_BITS.
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13811>
The downside is that this duplicates shader code for clip/cull distances
in both the position and parameter portions of the shader.
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13811>
This is more correct because we are loading constants into an SGPR even
though there is no effect on behavior in this case.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13700>
fma32 only round once so has 0.5UP accuracy. mad32 round twice so
has 1UP accuracy. This accuracy difference sometimes make the result
different at the last bit.
Applications like META need more accuracy for display right result.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Qiang Yu <yuq825@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13686>
shader_stages_mask and others expect MESA_SHADER_* based values,
not PIPE_SHADER_*...
Without this the fragment shader wouldn't appear in the "Pipelines"
pane of RGP.
Fixes: c276bde34a ("radeonsi/sqtt: export shader code to RGP")
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13696>
- Unset depth_cleared_level_mask for non-clear blits. Set the flag after
the clear, so that we don't have to check blitter_running.
- Set depth_cleared_level_mask only when we set depth_clear_value.
Fixes: ff8a930cf7 - radeonsi: add _once suffix to depth_cleared_level_mask
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13603>
It returned false when a render condition was not bound, but it should
have returned true.
The bool stuff is random and incomplete, but that's life.
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13602>
si_update_ps_colorbuf0_slot used blitter_running as a way to detect
recursive calls.
Unfortunately this catch too many cases; for instance a backtrace
like:
#0 si_update_ps_colorbuf0_slot
#1 si_set_framebuffer_state
#2 do_blits
[...]
#5 si_blit
#6 si_copy_region_with_blit
Would end-up not updating ps_uses_fbfetch; so if the new fb_state is
something like:
cbufs = {0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0}, zsbuf = 0x55b8987545e0}
We can have ps_uses_fbfetch=true but cbufs[0] = NULL, which causes a
crash later in si_ps_key_update_framebuffer.
This commit fixes intermittent crashes in KHR-GL46.stencil_texturing.functional.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13550>
src can use dcc even for non sdma v5 variants because si_decompress_dcc
is called in si_sdma_copy_image.
Fixes: 46c95047bd ("radeonsi: implement si_sdma_copy_image for gfx7+")
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13550>
This eliminates the overhead of invoking si_decompress_depth.
The complication here is that we need to update needs_depth_decompress_mask
every time we update dirty_level_mask.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13492>
It was mistakenly disabled, decreasing performance a lot.
Only valid for Mesa 21.3.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Cc: 21.3 <mesa-stable@lists.freedesktop.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13539>
We've noticed issues with these tests when uprevving Mesa in Chrome OS.
This CI catches some existing failures, and some debug-build assertion
failures as well.
To do this, uprev deqp-runner for its new gtest-runner command. This
runner is not as efficient as I would hope, due to some expensive code in
gtest. I've reported the issue to gtest and it should be easily fixable,
but for now it at least means we get to use the same baseline/skip/flake
handling we have from deqp and piglit runners.
I also fixed build-libdrm for our rootfses to not throw away libdrm's
share directory, which was causing a bunch of test-time spam from radeon's
libdrm when trying to look up its marketing name tables (not that big of a
deal for deqp-runner, but really noisy for piglit and libva-utils which
make gallium screens approximatly per-test).
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13419>
The test names are definitely unique (deqp has specific prefixes, piglit
uses '@' as a separator instead of '.'), so we can just have a single file
regardless of test type. Merges the two groups of xfails together so you
can't mix up which file to edit (I certainly have), and so that we don't
need to introduce yet another set of files when we add gtest for libva.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Acked-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Acked-by: Daniel Stone <daniels@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13517>
We have two testsuites with the same format for fails/flakes/skips files,
and test names that are definitely unique. As I'm about to add a third
testsuite (gtest for libva-utils), so let's have just one file each for
fails/flakes/skips instead of one per type of testsuite. This starts the
move with just the bulk rename of deqp.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Acked-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Acked-by: Daniel Stone <daniels@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13517>
This should make it easier to tune the runtime, and enable KHR-GL* tests
in the future. (Not done currently because something in KHR-GL* causes
oomkiller).
This drops the redundant FDO_CI_CONCURRENT settings, since the default on
these boards is 4 anyway.
Reviewed-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13504>
We can use the general "how parallel should we go on this runner?" env var
and save a bunch of massaging env var names. Fixes how PIGLIT_PARALLEL
looked like it was useful but actually wasn't passed through to HW
runners.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13372>
This removes resource_copy_region for BufferSubData. Drivers have to opt in
to use this.
See the comment in the header file.
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13399>
This uses a C++ template to compute the memcmp size at compile time,
which is important for getting inlined memcmp.
There are 4 different key sizes now:
GE with inlined uniforms: 68 bytes
GE without inlined uniforms: 52 bytes
PS with inlined uniforms: 28 bytes
PS without inlined uniforms: 12 bytes
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13285>
ps is for the pixel shader, while ge is for VS, TCS, TES, and GS.
si_shader_key: 68 bytes
si_shader_key_ge: 68 bytes
si_shader_key_ps: 28 bytes
The only notable change is that si_shader_select_with_key is changed
to a C++ template. Other changes are trivial.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13285>
This is to fix serious performance drop of texture_upload/
texture_resue relative items in chromeos glbench test.
Staging texture is not efficient for CPU uploading.
Signed-off-by: Jasber Chen <yipeng.chen@amd.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13306>
This patch is to to remove PKT3_CONTEXT_REG_RMW from radeonsi.
and avoid multiple command buffer(PM4 packet)creation for R_02881C_PA_CL_VS_OUT_CNTL.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Signed-off-by: Arvind Yadav <arvind.yadav@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12789>
It eliminates "False Sharing" for atomic operations. (see wikipedia)
Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11618>
DCN only supports an extent < 4K on !64B && 128B.
Signed-off-by: Joshua Ashton <joshua@froggi.es>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13056>
It regresses the first snx test because it adds CPU overhead, and there is
no way to work around it. The average effect on viewperf is 0, meaning that
a few cases improve, while a few others regress.
Acked-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13279>
Rather than having an ever increasing list of parameters to
threaded_context_create(), split out a struct for optional
flags and parameters. This should reduce churn in adding
new options.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13207>
Doing this copy using SDMA frees up the dGPU to do more
interesting things while the copy is happening; for instance
the rendering of the next frame.
hw queue activity before:
------------------------
dGPU:
gfx: [renderframe 1][copy->iGPU][renderframe 2][copy->iGPU]...
iGPU:
gfx: [Xorg] [Xorg]
hw queue activity before after:
------------------------------
dGPU:
gfx: [renderframe 1][renderframe 2][renderframe 3]....
sdma: [copy->iGPU] [copy->iGPU] [copy->iGPU]
iGPU:
gfx: [Xorg] [Xorg] ...
If SDMA isn't available or can't do the copy, use an async compute
context instead.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12763>
SDMA support was dropped in 1f31a21664 mainly because the
advantages of delegating some copy/clear operations to the
SDMA hw came with large drawbacks: CPU overhead due to the
sdma/gfx synchronization and hangs.
This commit restores SDMA support for all gfx7+ chips but
only for the image copy operations.
SDMA operations won't be intertwined with gfx operations
like before. Instead, a SDMA IB will contain a single copy
at a time and the synchronization will be handled by the
winsys (based on the used buffers).
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12763>
GPU hangs are asynchronous already, there should not be an expectation
that this is synchronized with driver thread.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13163>
We need to keep RADV and RadeonSI on the same page about this due to modifiers.
Signed-off-by: Joshua Ashton <joshua@froggi.es>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13153>
This helps some viewperf subtests.
Only view XY culling is done. Edgeflags are always disabled with lines.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13048>
This improves viewperf performance on Navi1x.
All Navi1x fast launch workarounds are removed and all fast launch
codepaths are disabled.
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13048>
When it's enabled, it stays enabled until the next shader change
or an incompatible primitive type, etc.
This improves performance for viewperf/snx.
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13048>