We can drop RT flush and PS Scoreboard stall if state cache perf fix
disabled is set to 1. If bit is set RCC uses the sum of Binding Table
Pointer and Binding Table Index as tag in state cache instead of just
Binding Table Index.
On DX12 this is a performance win on all workloads we've tested.
On DX11 there are a bunch of performance of regression. We think this
is due to the fact that to avoid trashing the RCC, we need to remove
all but render targets from the binding table, meaning all shader
resource accesses have to go through the bindless HW heap. This leads
to additional register usage due to the need to push the base offset
of descriptor sets. Improvement in the compiler would likely mitigate
this.
This change introduce a DRIRC key we only turn on for DX12.
Also platforms prior to DG2/LSC have a really small bindless heap that
leads to additional register usage, so this optimization is completely
disable there.
Signed-off-by: Sagar Ghuge <sagar.ghuge@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/10872
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/10873
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/14075
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39982>
The current tracking seems to have hidden issues related to MCS
ambiguate that are currently hidden by the fact that we're inserting
pb-stall+RT-flush on BTI changes which we're going to be remove in the
next commits.
The issues appear to be related to a missing pb-stall+RT-flush between
MCS ambiguate and fast-clear causing failures on the following tests
once BTP+BTI RCC caching is enabled :
dEQP-VK.pipeline.*.multisample.misc.*multi*
dEQP-VK.pipeline.*.framebuffer_attachment.diff_attachments_2d_32x32_39x41_ms
dEQP-VK.pipeline.*.framebuffer_attachment.diff_attachments_2d_32x32_48x48_ms
Here we rework the tracking with a new enum to track 3 classes of
operations.
Signed-off-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/39982>
Instead of :
foreach color attachment
transition layout
fast clear
slow clear
do this :
foreach color attachment
transition layout
foreach color attachment
fast clear
foreach color attachment
slow clear
Signed-off-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/39982>
When rendering only has depth/stencil, we need to look at the
depth/stencil view size to generate a dummy null color attachments. So
do that first, so we don't have to iterate color attachments once more
with the final size.
This change also has the nice impact of removing a BTI change flush
due to the sequence moving from :
- before blorp BTI-flush
- color fast-clear
- after blorp BTI-flush
- depth fast-clear
- change RT due to shader outputs (BTI-flush)
- draw call
to :
- depth fast-clear
- before blorp BTI-flush
- color fast-clear
- combined after blorp BTI-flush (pending)
- change RT due to shader outputs (BTI-flush, combined with above)
- draw call
Signed-off-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/39982>
Simulator is crashing when receiving GPGPU + Pixel as resource barrier signal
stage, what according to spec is invalid.
So here replacing the pixel stage by color, over synchronizing it a bit but
keeping it functional.
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/14641
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Suggested-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/40516>
Simulator hangs if a resource barrier has wait stage = None, HW seens
to don't care but something bad could be happning internaly.
So here making sure Wait stage is set to TOP when it is None.
Simulator hangs if a resource barrier has wait stage = None.
The HW seems to ignore it, but something bad could be happening internally.
So here I'm making sure the wait stage is set to TOP when it is None.
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40516>
When there is no trace pointer, there is usually a another tracepoint
being emitted (see STATE_BASE_ADDRESS,
3DSTATE_BINDING_TABLE_POOL_ALLOC emission).
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Sagar Ghuge <sagar.ghuge@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40503>
In commit 10b5b279a4 ("anv: Fix CmdResetEvent2() with RESOURCE_BARRIER::Wait stage == none")
I haved added assert to catch invalid cases but looks like we have several tests
affected by that problem causing crashes in debug builds.
So here I'm removing those asserts(), will then work on all the fixes and bring
it back.
Acked-by: Ivan Briano <ivan.briano@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40476>
On integrated platforms, we have issue where L3 cache not being coherent
with CS and it forces us to push data out L3.
To avoid data cache flush, let's write the IR header with BLORP shader.
There is a small shader launch latency but eventually that should not
matter because writing data with CS (MI_STORE) commands is slower than
shader execution when we consider large number of BVH tree getting
built.
Signed-off-by: Sagar Ghuge <sagar.ghuge@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39971>
CmdResetEvent2() was calling anv_add_pending_pipe_bits() with no dst_stages
stages causing RESOURCE_BARRIER::Wait stage == none, what causes a GPU hang in
NVL-P simulator.
So here setting dst_stages to VK_PIPELINE_STAGE_2_TOP_OF_PIPE_BIT and adding
an assert in resource_barrier_wait_stage() to catch hw_stage == 0.
This fixes crucible func.event.cmd_buffer.q0 in simulator.
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/40445>
Fixes new CTS tests.
Similar to a previous change : 5bf3546cc6 ("anv: Use companion cmd
buffer for CCS and MCS image barriers")
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Acked-by: Ivan Briano <ivan.briano@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40332>
blorp_copy() will soon gain the ability to increase the format bpb.
Prepare anv by replicating the clear color pixel on gfx12.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39974>
Shaders are allocated from anv_shader_heap, which is backed by the
util_vma_heap. Rename the VA range field to shader_heap to match current
usage and avoid confusion.
Signed-off-by: Michael Cheng <michael.cheng@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40131>
For Gfx125 workloads that use systolic mode, this might mean
an extra PIPELINE_SELECT when flipping between a compute shader
that use the mode and another that doesn't use the mode
(or vice-versa).
Reviewed-by: Iván Briano <ivan.briano@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40014>
With perfetto that string is processed later leading to
use-after-free.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Cc: mesa-stable
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39405>
The previous commit enable different command buffers to program the
same 3DSTATE_BINDING_TABLE_POOL_ALLOC instruction even though they
allocated different chunks of binding tables.
Now we can just predicate this programming and skip the stalling,
flushing & invalidation.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39527>
We currently allocate 64KiB chunks of binding table pools for each
command buffers and program the 3DSTATE_BINDING_TABLE_POOL_ALLOC
instruction accordingly.
But 3DSTATE_BINDING_TABLE_POINTERS_* instructions can address 2^20
bytes. So it's possible to have 2 command buffers share the same
programming if they just add some offsets to their
3DSTATE_BINDING_TABLE_POINTERS_* programming and round down
3DSTATE_BINDING_TABLE_POOL_ALLOC addresses to 2^20.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39527>
If we have extended bindless surface offset (ExBSO) support, we want to
use it. Consolidate the anv_physical_device and brw_compiler bits into
a single static inline that take devinfo.
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@intel.com>
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39839>
Having the named field allowed us to indicate that our code conditions
are referring to the specific decision about how we handle indirect
UBOs, rather than some other arbitrary hardware change.
Still, there's no need to store this in a singleton struct - we can
easily have a static inline bool that does the devinfo check for us.
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@intel.com>
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39839>
A descriptor buffer promoted to push constants requires a constant
cache invalidation if it is modified on the device.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Cc: mesa-stable
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35160>
Given a situation like this :
- CB_A: begin, renderDepthA, end
- CB_B: begin, computeA, barrier (depth), computeB, end
The depth cache is not being flushed between renderDepthA & computeB
because :
- it's not flushed at the end of CB_A (it's not required)
- when CB_B starts, we're still on GFX pipeline mode but do not
flush render caches because pipeline mode is unknown
- when barrier is CB_B is executed, we're already in compute
pipeline mode and HW cannot flush depth.
The fix is to flush RT/depth cached when switching from unknown
pipeline mode any pipeline mode.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes: e6dae6ef5f ("vulkan: Optimize implicit end_subpass barrier")
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/14816
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Tested-by: David Gow <david@davidgow.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39824>
This bit is set in mocs for other protected attachment types by
anv_image_fill_surface_state() however was ommited for depth/stencil
attachments here.
Without the protected bit set, it causes heavy black artifacting when
attaching a protected depth attachment image to a framebuffer.
Fixes: 794b0496e9 ("anv: enable protected memory")
Signed-off-by: Juston Li <justonli@google.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39818>
On Xe2+, support multi-layer and non-zero-layer CCS fast-clears. To do
this in a simple manner, drop the code which splits multi-layer clears
into fast clears and slow clears. The performance CI reports no
regressions nor improvements on BMG.
For MCS on all platforms and for CCS on prior platforms, use a new
heuristic. Instead of only allowing fast clears on the first
slice/layer, do the following:
For 3D images, only fast-clear if all slices are cleared. Enables
fast-clearing every slice of 3D textures in:
* Terminator Resistance - 480x270x128.
* Ghostrunner 2 - 320x180x128.
For 2D arrays, match the Xe2+ behavior and allow clearing to any layer.
This is possible because we only allow fast-clearing if the clear color
matches the default value. Enables fast-clearing every layer of 2D array
textures in:
* Assassin's Creed - 128x128, 6-layers.
* Blackops 3 - 1024x1024, 6-layers.
* Borderlands 3 - 128x128, 6-layers.
* Cyberpunk - 1024x1024, 10-layers.
* Unigine Superposition - 4K, 2-layers.
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/11893
Reviewed-by: Jianxun Zhang <jianxun.zhang@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37660>
A future commit will enable clearing to more than the first layer of 2D
array images. To ensure consistency for the clear color, require the
ANV_FAST_CLEAR_DEFAULT_VALUE for such images if they make use of
ISL_AUX_STATE_CLEAR. Also, use a non-zero default value for some image
formats.
I tested the majority of workloads in the performance CI. This will
cause those which clear to 2D array layers to gain clears on more than
just the first layer. At the moment, we still only support clearing the
first layer, so there should be no change in performance. Affected games
are documented in the code.
Acked-by: Jianxun Zhang <jianxun.zhang@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37660>
Now that hasvk is the driver for supporting HSW and BDW, we no longer
need to convert CCS_D partial resolves to full resolves to avoid an
assert-failure in BLORP.
Reviewed-by: Jianxun Zhang <jianxun.zhang@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37660>
This will make handling fast-clears on multiple layers simpler by saving
us from having to pass more parameters into fast-clear state setting
functions.
It also allows us to set more complex fast-clear state for FCV_CCS_E
without marking the image as compressed.
Reviewed-by: Jianxun Zhang <jianxun.zhang@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37660>
Enables more support for FCV_CCS_E partial resolves if we ever need it.
Also enables support for multiple layers being fast cleared and needing
resolves. Support for that will arrive in several commits.
Reviewed-by: Jianxun Zhang <jianxun.zhang@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37660>
We started allowing non-default clear colors with FCV in commit
cd8e120b97. When rendering to an image with FCV, set the fast-clear
type to ANV_FAST_CLEAR_ANY if the image properties allow such
fast-clears.
Fixes: cd8e120b97 ("anv: Allow more single subresource fast-clears with FCV")
Reviewed-by: Jianxun Zhang <jianxun.zhang@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37660>
This appears to be needed to guarantee that a resolved depth surface
has no remaining fast-cleared blocks on DG2 as well as MTL. After
this series this should no longer be hit in practice since we'll be
doing partial resolves in most cases, but it seems sensible to keep
and correct the workaround for our peace of mind to make sure that
full resolves are truly resolving the main surface.
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31139>
Issue a partial resolve instead of a full resolve from
transition_depth_buffer() when the final usage requires the
CCS-compressed surface to provide a complete representation of the
image.
This significantly improves performance of applications that
frequently interleave depth rendering and sampling on non-WT surfaces
(e.g. MSAA surfaces). Nba2K23-trace-dx11-2160p-ultra improves
performance by about 260% with this on MTL, DG2 shows a similar
benefit.
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31139>
For transitions to a state that requires the image to be fully defined
by the primary+CCS surface without necessarily requiring a valid
primary we have to perform a resolve if the initial state was
ISL_AUX_STATE_COMPRESSED_HIER_DEPTH, which isn't fully defined by its
primary+CCS surface. This full resolve will be replaced with a more
efficient partial resolve in a future commit, but we have to do this
up front in order to avoid breaking bisectability.
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31139>
We can end up in this situation in cases where the application uses a
layout that allows both rendering and sampling from a depth surface,
since in such cases we will attempt to render with HIZ CCS WT usage as
a side effect of using ISL_AUX_USAGE_HIZ_CCS_WT for all layouts that
allow the image to be sampled from.
Disabling fast clears for that case isn't expected to cause
performance regression since before this series for HiZ CCS non-WT
images transitioning to such a layout we would have issued a full
resolve and used ISL_AUX_USAGE_NONE, which also doesn't support fast
clears.
Multisample depth images should still get fast clears after this
commit in cases where the rendering and sampling is split into
separate render pasess with a layout transition between them that
transitions the image from a W/O layout into a R/W one -- Such
transitions will be handled with a relatively cheap partial resolve in
a subsequent commit.
v2: Add details of additional findings about these hardware issues in
comment.
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
v3: Pass aspect bit consistent with layout to
anv_layout_to_aux_usage() instead of defaulting to
VK_IMAGE_ASPECT_DEPTH_BIT.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31139>
Currently anv_fast_clear_depth_stencil() doesn't know the correct
layout of the depth and stencil images, instead it uses
ANV_IMAGE_LAYOUT_EXPLICIT_AUX to force the base AUX usage of each
plane, which can be inconsistent with the VkImageLayout currently in
use. Plumb the correct depth and stencil layouts.
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31139>
Disable RHWO by default for singlesample draws and for MSAA
draws if a drirc key is set (avoid perf hit if not needed).
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/39404>
Fixes a crash with:
dEQP-VK.api.external.semaphore.opaque_fd.signal_export_import_wait_temporary
when driver calls genX(CmdSetEvent2) -> emit_apply_pipe_flushes with
having NULL in emitted_flush_bits.
Fixes: 8834ef8bcd ("anv: use flushing PIPE_CONTROL for event signaling")
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/39343>
