If depth bias is enabled but zero values used, they were never
emitted to the command buffer because they are equal to the default
values.
Previously, they were always emitted when the bound DS attachment
changed.
This should fix some sort of Z fighting with Dota2 on all GPUs.
This also fixes a different issue (ie. some occlusion queries failures)
on GFX6 because CLEAR_STATE is not used on that chip.
Fixes: 8a47422d97 ("radv: do not scale the depth bias for D16_UNORM depth surfaces")
Cc: 21.1 mesa-stable
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/10310>
The global VRS image is created on-demand to avoid wasting space.
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/10187>
When a subpass uses a VRS attachment without binding a depth/stencil
attachment (yes, this is allowed by the Vulkan spec), we have to bind
our internal depth buffer that contains the VRS data.
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/10187>
The retile map is removed and replaced by direct DCC address computations
in the retile shader using the new function ac_nir_dcc_addr_from_coord.
The RADV code is disabled.
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/10003>
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>
In case we don't have DCC, we can still predicate FCE with CMASK.
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/8332>
GFX10+ supports compressed writes to HTILE, so it should just work
to skip decompressions when transitioning from/to GENERAL.
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/8039>
Otherwise it's useless because we are unlikely to perform a
fast depth stencil clear.
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/8039>
We can only use the entire HTILE buffer if TILE_STENCIL_DISABLE is
TRUE. On GFX8+, this is only true if the depth image has no stencil
and if it's not TC-compatible because of the ZRANGE_PRECISION issue.
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/8039>
To make sure the stencil compare state is properly initialized and
cleared when the driver performs a fast depth clear.
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/8039>
Not doing this for APUs because spilling is quite likely, due to
overall VRAM pressure.
Also adding a flag to disable for performance debugging.
Finally adds some memset for places where we depended on the memory
being initialized to zero, which we won't get with VRAM anymore.
(I think these places should stop depending on it since it hides
issues with executing the cmdbuffer multiple times, but this
preserves behavior)
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7979>
Fixes dEQP-VK.api.copy_and_blit.*.4_bit. I think the MSAA2x and
MSAA8x just passed by luck.
Fixes: 7b21ce401f ("radv: disable FMASK compression when drawing with GENERAL layout")
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/7915>
This can result in meaningful compression changes so we shouldn't skip.
Fixes: 66131ceb8b "radv: Pass through render loop detection to internal layout decisions."
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7004>
Only supported on GFX10.3+. Attachment Fragment Shading Rate is
for later.
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/7837>
It might be useful to know if the VA is valid and if other info
like the stride seems correct.
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/7753>
This workaround fixes a hang while loading a renderdoc trace for me.
Since the workload does 1 mip per cmdbuffer it is quite hard to confirm
what exactly the conditions for the hang are but this is the most
restrictive set I found and it corresponds to a workaround in AMDVLK as
well.
CC: mesa-stable
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7210>
It's expected to be 0.
Fixes: 62d9ca696e ("radv: use 32-bit predication for conditional rendering on GFX10.3+")
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/7789>
It seems that only gfx queue doesn't support it, except on GFX10.3
which supports all queues.
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/7732>
The fce metadata can always be set to false as we don't care about
the compressed clear color.
Avoiding useless fast clear eliminates improves basemark performance by
1%-1.5%.
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7005>
Not doing the EOP TS cacheflush event because that break wave counting
in RGP for some reason. But the rest looks to be all there.
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6550>
Since the flushes really happen on the next draw delay the barrier
end to include the flushes.
This fixes the barrier duration in RGP.
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6550>
From the Vulkan 1.2.154 spec:
"If pCounterBufferOffsets is NULL, then it is assumed the
offsets are zero."
Fix new CTS
dEQP-VK.transform_feedback.simple.backward_dependency_no_offset_array.
CC: mesa-stable
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/6798>
If radv_layout_can_fast_clear() is false, 028C70_COMPRESSION is unset when
the image is rendered to and CMASK isn't updated. This appears to cause
FMASK to be ignored and the 0th sample to always be used.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3449
Fixes: 7b21ce401f
('radv: disable FMASK compression when drawing with GENERAL layout')
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6745>
Because the driver now waits for idle after every draw/dispatch
calls, we shouldn't report gfx pipelines when the GPU hang happens
after a dispatch (or the opposite).
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/6471>
It reduces traffic between CB, DB and TCP blocks if buffers
respect a certain alignment.
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/6482>
Fixes some dEQP-VK.renderpass2.* flakes. Valgrind:
Test case 'dEQP-VK.renderpass2.dedicated_allocation.attachment.8.724'..
==754520== Conditional jump or move depends on uninitialised value(s)
==754520== at 0x575B21C: radv_layout_is_htile_compressed (radv_image.c:1690)
==754520== by 0x572F470: radv_handle_depth_image_transition (radv_cmd_buffer.c:5855)
==754520== by 0x572F2F2: radv_handle_image_transition (radv_cmd_buffer.c:6123)
==754520== by 0x572EEC6: radv_handle_subpass_image_transition (radv_cmd_buffer.c:3385)
==754520== by 0x572A104: radv_cmd_buffer_begin_subpass (radv_cmd_buffer.c:4843)
==754520== by 0x572A007: radv_CmdBeginRenderPass (radv_cmd_buffer.c:4913)
==754520== by 0x572A197: radv_CmdBeginRenderPass2 (radv_cmd_buffer.c:4921)
Why false?
A renderloop happens when the same attachment is both used as input
attachment and output (color, ds) attachment in a subpass. Of course
this doesn't happen outside of a renderpass and hence we can initialize
it to false at the start of the renderpass.
Fixes: 66131ceb8b "radv: Pass through render loop detection to internal layout decisions."
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3074
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6068>
AMDGPU_GEM_CREATE_CPU_GTT_USWC should be faster when CPU reads
are unexpected (because they aren't cached).
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/5978>
Out-of-order rasterization is disabled if a pipeline uses an
extended dynamic depth/stencil state because the driver doesn't
support enabling/disabling out-of-order dynamically.
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/5718>
The number of viewports/scissors is currently static because it can
only be specified at pipeline creation, but it doesn't hurt to
assume it's dynamic. Will help for supporting setting the number
of viewports/scissors dynamically.
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/5718>
From the Vulkan spec 1.2.146:
"VK_ACCESS_MEMORY_READ_BIT specifies all read accesses. It is
always valid in any access mask, and is treated as equivalent
to setting all READ access flags that are valid where it is
used."
"VK_ACCESS_MEMORY_WRITE_BIT specifies all write accesses.
It is always valid in any access mask, and is treated as
equivalent to setting all WRITE access flags that are valid
where it is used."
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3241
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/5807>
We have an issue with early depth testing and discard, where
non-perfect counts count the tile if the early depth test succeeds.
We could spend a lot of effort to set this conditionally based
on the presence of the two conditions, but in the presence of
inherited queries let's try this first.
Changing PERFECT_ZPASS_COUNTS since I'm pretty sure this has a lower
performance impact than always using late depth testing.
CC: <mesa-stable@lists.freedesktop.org>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3218
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5757>
The maximum value for both points and lines is 65536. This doesn't
fix anything known (just found this while looking in that area).
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/5696>
With VK_EXT_robustness2, an element of pBuffers can be NULL.
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/4775>
Use the f variants of the math functions if the input parameter is a
float, saves converting from float to double and running the double
variant of the math function for gaining no precision at all
Reviewed-by: Matt Turner <mattst88@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3969>
The other pixels in the grid might have samples with a larger
distance than the (0,0) pixel.
Fixes dEQP-VK.pipeline.multisample.sample_locations_ext.verify_location.samples_8_packed
when CTS is compiled with clang.
CC: <mesa-stable@lists.freedesktop.org>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4480>
The goal of this function was to return whether a depth-stencil image
has HTILE, in comparison to radv_layout_is_htile_compressed() which
is used to know whether a depth-stencil image has HTILE compressed.
These two functions are actually similar and they have never been
used for what they were supposed to. Remove radv_layout_has_htile()
in favour of radv_layout_is_htile_compressed() for now. If it's
needed in the future, I will re-introduce this concept properly.
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/4389>
The Vulkan spec 1.2.135 says:
"pSizes is an optional array of buffer sizes, specifying the maximum
number of bytes to capture to the corresponding transform feedback
buffer. If pSizes is NULL, or the value of the pSizes array element
is VK_WHOLE_SIZE, then the maximum bytes captured will be the size
of the corresponding buffer minus the buffer offset."
Closes: https://gitlab.freedesktop.org/mesa/mesa/issues/2650
Fixes: b4eb029062 ("radv: implement VK_EXT_transform_feedback")
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4232>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4232>
Thread trace markers (also called events in Radeon GPU Profiler)
should be emitted after every draw/dispatch calls to collect data.
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/3900>
The extra bits in CB_SHADER_MASK break dual source blending in
SkQP on a Stoney device. However:
- As far as I can tell, some other dual source blend tests are passing
before and after the change.
- A hacked around skqp passes on my Vega desktop and Raven laptop
- Getting Skqp to give any useful info or to run it outside of Android
on ChromeOS is proving difficult.
I have confirmed 3 strategies that seem to work:
- The old radv behavior of setting CB_SHADER_MASK to 0xF
- AMDVLK: CB_SHADER_MASK = 0xFF, and the 3 RB+ regs
are 0.
- radeonsi: CB_SHADER_MASK = 0xFF, but does not set DISABLE
bits in SX_BLEND_OPT_CONTROL for CB 1-7.
Let us use the radeonsi solution as that solution also seems like the correct
thing to do for holes. I have tested on my Raven laptop that setting the high
surfaces to not disabled and downconvert to 32_R does not imply a performance
penalty.
Fixes: e9316fdfd4 "radv: fix setting CB_SHADER_MASK for dual source blending"
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3670>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3670>
The number of generated primitives is only counted by the hardware
if GS uses the legacy path. For NGG GS, we need to accumulate that
value in the NGG GS itself. To achieve that, we use a plain GDS
atomic operation.
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/3380>
For implementing NGG GS queries, we decided to use GDS but GDS OA
is only required for NGG streamout.
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/3380>
Promoted to Vulkan 1.2 with the KHR suffix omitted.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Promoted to Vulkan 1.2 with the KHR suffix omitted.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Promoted to Vulkan 1.2 with the KHR suffix omitted.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Fixes a hang on Raven with Resident Evil 2.
I did not find anything more restricted to fix it:
- Setting persistent_states_per_bin to 1 fixes it too,
but likely does an internal break on any descriptor set changes
too.
- Only breaking the batch when cb_target_mask changes does not fix
it (and looking at AMDVLK comments, I suspect the code in radeonsi
should really be doing a FLUSH_DFSM).
- Always doing a FLUSH_DFSM on shader switch helps, but that is more
often than this and I don't think we should be doing that when DFSM
is disabled.
- Also emitting the existing break on framebuffer change when DFSM is
disabled does not fix the issue.
Closes: https://gitlab.freedesktop.org/mesa/mesa/issues/2315
CC: <mesa-stable@lists.freedesktop.org>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
I don't think this makes much differences and a potential clear
following the initialization will overwrite HTILE anyways.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
PA_SC_AA_CONFIG might be updated when conversative rasterization is
enabled. Because the driver only re-emits the multisample state if
the number of samples is different, that register value might not
be updated correctly.
Found by inspection, doesn't fix anything known.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
They don't have to be updated dynamically.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
No functional changes because the aspect mask is still not used
during image transitions but it will be needed for the separate
depth/stencil aspects logic.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
When the scratch ringbuffer settings are changed, the shader unit has
to be idle or we will have shaders using old and new settings.
That combination is not supported on the HW (likely the offset is
ringbuffer idx * WAVESIZE * 1024).
CC: <mesa-stable@lists.freedesktop.org>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
This will allow to change wavesize on-demand.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
On GFX8 the number of records is in bytes while on other chips
it's in units of "stride".
Fixes dEQP-VK.robustness.vertex_access.*.draw.vertex_* on RAVEN.
Tested on GFX6, GFX8, GFX10 and RAVEN.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Fixes some crashes with dEQP-VK.geometry.layered.*.secondary_cmd_buffer
on Raven and other chips that allow rbplus.
This just prevents a crash and rbplus probaby needs more work.
Cc: 19.2 <mesa-stable@lists.freedesktop.org>
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
On GFX9, the driver is able to do an optimized fast depth/stencil
clear with only one aspect (ie. clear the stencil part of a
depth/stencil image). When this happens, the driver should only
update the clear values of the given aspect.
Note that it's currently only supported on GFX9 but I have some
local patches that extend this optimized path for other gens.
Closes: https://gitlab.freedesktop.org/mesa/mesa/issues/1967
Cc: 19.2 <mesa-stable@lists.freedesktop.org>
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
e.g. a VERTEX only flush with tess on Vega should look at the TCS
to see which bits are needed.
CC: <mesa-stable@lists.freedesktop.org>
Closes: https://gitlab.freedesktop.org/mesa/mesa/issues/1953
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
uintptr_t is 32 bits in a 32-bits build, resulting in shifting out
of bounds.
Reviewed-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
The buffer isn't necessarily used before.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
LLVM remains default and ACO can be enabled with RADV_PERFTEST=aco.
Co-authored-by: Daniel Schürmann <daniel@schuermann.dev>
Co-authored-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Use the fastest way only if both aspects are used. Oops.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111728
Fixes: 218ce34962 ("radv: add mipmap support for the clear depth/stencil values")
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Otherwise the next streamout operation will overwrite GDS. This
can be improved by tracking if there is a streamout operation in
flight. Currently the driver unconditionally flushes but that
doesn't matter much as NGG streamout is disabled by default.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
NGG streamout uses GDS and we have to make sure that another
process isn't going to overwrite GDS while our shaders are busy.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
It's used to determined the max emit per buffer.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
This allocates two BOs for GFX10 NGG streamout.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
This internal option is turned off by default because NGG streamout
still hangs. It seems like it's related to GDS as RadeonSI.
That option will be turned on once all issues are resolved.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Having two different structs is useless.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
16-bit and 32-bit values match hardware values but 8-bit doesn't.
This fixes dEQP-VK.pipeline.input_assembly.* with 8-bit index.
Fixes: 372c3dcfdb ("radv: implement VK_EXT_index_type_uint8")
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl
Test that found this: dEQP-VK.geometry.layered.1d_array.secondary_cmd_buffer
Fixes: 49e6c2fb78 "radv: Store color/depth surface info in attachment info instead of framebuffer."
Reviewed-by: Dave Airlie <airlied@redhat.com>