For MSAA storage images with DCC, we also need to perform a MSAA
color decompression.
Fixes dEQP-VK.pipeline.multisample.storage_image.* if DCC stores
is enabled.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9854>
To remove bubbles during layout transitions from UNDEFINED, especially
with MSAA because we might have all.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10004>
It was parsing it as SQ_WAVE_GPR_ALLOC instead of COMMAND.
Change the offset to an odd number to work around it.
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9795>
This should be equivalent without needed to force enable FMASK for
some specific internal pipelines.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9940>
This is no longer needed since FMASK is also compressed for
transfer dst operations.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9940>
The COMPRESSION bit is FMASK and this is much faster! Should
speedup transfer dst operations with MSAA images considerably.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9990>
this breaks up the monolithic draw path used for all draw calls into
pre/post functions to handle general setup and a couple helper functions
to more directly handle different draw modes in a way that's both more readable
and, potentially, more optimizable
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8788>
Since image stores can now compress and we can't track image stores
this also stops using predication for DCC decompression.
In GFX10 this was benchmarked to be faster. For GFX10.3 the microbenchmarks
are not as possible though I haven't tested any games, so this is not enabled
there yet.
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6796>
It ignored non-harvested chips with a non-power-of-two memory bus.
Fixes: abed921ce7 - amd: add support for Navy Flounder
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9568>
The Android ones we put in anv_android.c. Maybe one day we'll want a
vk_android.h to put some common Android stuff but, for now, let's keep
it contained to ANV's android code.
Reviewed-by: Eric Anholt <eric@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8857>
Scaling the depth bias doesn't seem correct with Vulkan. This is
probably the root cause of the shadow artifacts differences between
RADV and AMDVLK/AMDGPU-PRO.
Fix dEQP-VK.rasterization.depth_bias.d16_unorm.
Cc: mesa-stable
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/2217
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9249>
The loader_set_dispatch overwrites the magic with the dispatch
pointer, however when cmd buffers get recycled, and the loader
is in debug mode, it asserts that the magic isn't set anymore.
When recycling command buffers, reset the base object.
Cc: mesa-stable@lists.freedesktop.org
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9145>
RGP actually crashes if pipeline bind markers are emitted without
PSO correlation objects.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9097>
I suspect this marker to be useful for correlating pipeline shaders.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8995>
This saves a 64-bit pointer from radv_amdgpu_winsys_bo and it's
also common to pass a winsys pointer as the first parameter.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8859>
Vertex attribute bounds checking is supposed to be done per-attribute:
is_oob = index * stride + attrib_offset + attrib_size > buffer_size
but we were obtaining num_records by dividing the buffer size by the
stride, making it per-vertex:
is_oob = index * stride + (stride - 1) >= buffer_size
An example from Dead Cells (Wine) is:
attribute bindings: 0, 1, 2
attribute formats: r32g32, r32g32, r32g32b32a32
attribute offsets: 0, 0, 0
binding buffers: all the same buffer
binding offsets: 0, 8, 16
binding sizes: 128, 120, 112
binding strides: 32, 32, 32
Workaround this issue without switching to per-attribute descriptors by
rounding up the division. This is still incorrect, but it should now no
longer consider in-bounds attributes out-of-bounds.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3796
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/4199
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8835>
With HTILE mipmaps support, we should check if the base level
currently in use supports compression.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8124>
This is probably rarely used but it can be easily implemented now.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8650>
In some rare cases, L2 needs to be flushed if an image is affected
by the pipe misaligned issue. This is roughly based on AMDVLK.
I confirmed that disabling TC-compat HTILE, and respectively DCC,
for the relevant images also fixes the regressions below.
This fixes some regressions introduced with L2 coherency for
dEQP-VK.renderpass2.depth_stencil_resolve.image_2d_* and for
dEQP-VK.renderpass2.suballocation.multisample_resolve.*.
Fixes: 4a783a3c78 ("radv: Use L2 coherency on GFX9+.")
Co-Authored-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8557>
Especially on GFX10 we can avoid pretty much all L2 flushes.
However, instead of that we have to do L2_METADATA invalidations. We
do that every time we could possibly be reading new DCC/HTILE info
from the L2 cache in shaders.
Benchmark results, basemark on high preset with a navi10 on profile_standard
(which is slower than a navi10 on default settings, please don't compare
to random navi10 results you find)
before:
5932
5928
5937
after:
6011
6013
6009
So this looks like a >1% increase.
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7202>
This way we're properly using the vulkan barrier paradigm instead
of adhoc guessing what caches need to be flushed. This is more robust
for cache policy changes as we now don't have to revisit all the meta
operations all the time.
Note that a barrier has both a src and dst part though. So
barrier:
flush src
meta op
flush dst
becomes
barrier:
flush barrier src
flush meta op dst
meta op
flush meta op src
flush barrier dst
And there are some places where we've been able to replace a CB flush
with a shader flush because that is what we'd need according to vulkan rules
(and it turns out that in the cases the CB flush mattered the app will set the
bit in one of the relevant flushes or it was needed as a result of an optimization
that we counter-acted in the previous patch.)
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7202>
To cancel the optimization in radv_dst_access_flush if these helpers
get used by meta operations.
We could also remove that optimization but I think this triggers less
often as all SHADER_WRITE flushes on images not supporting STORAGE should
be meta
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7202>
