Not correct, will need spec additions to handle it properly.
Fixes ground rendering in DIRT 5.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
- Honor resource barriers for resource states which cannot automatically
decay or promote. This includes COLOR_ATTACHMENT, UNORDERED_ACCESS and
VRS image. If SIMULTANEOUS_ACCESS is used, we can still promote, and
we handle that by setting common layout to GENERAL for these resources.
- Avoid redundant barriers in render passes since normal resource
barriers will always make sure we are already in
COLOR_ATTACHMENT_OPTIMAL.
- Do not force GENERAL layout if resource has UNORDERED_ACCESS flag set.
As this is not a promotable state, we have to explicitly transition
into it. I tested this on validation layers, where even COMMON state
refuses to promote to UAV state. The exception here of course is
SIMULTANOUS_ACCESS, but we handle that properly now.
- Verify that UAV or SIMULTANEOUS access is not used together with DSV
state. This is explicitly banned in the API docs.
- Actually emit image barriers. Batch the image transitions as that's
what D3D12 docs encourage app developers to do, and it also expects
that drivers can optimize this. Ensure that we respect the in-order
resource barrier rules by splitting batches if there are overlaps in
the transitions.
- Ensure that correct image layout is used when clearing a suspended
render pass attachment.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
Avoid using the separate layouts if we're only using formats with one
aspects. This makes it more likely to match layouts with common layout,
and we can avoid awkward transition barriers.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
Some games end up writing the wrong descriptor type when using null
descriptors, and to be robust against that, we have to clear out
all descriptors when creating null descriptors.
If we copy a null descriptor, we will also have to copy from all sets.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
Needed so we can switch between having a VRS and non-VRS attachment on the fly.
Extensible enough for this to work for other things down the line also.
Signed-off-by: Joshua Ashton <joshua@froggi.es>
C is fun, yo. Returned data from dead stack variable, also triggered
overflow in some cases.
Uncalled in release mode, but can crash debug builds.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
Otherwise we can do an alligned_malloc with a non-aligned size as the descriptor size is 48 for a d3d12_rtv_desc otherwise.
Signed-off-by: Joshua Ashton <joshua@froggi.es>
Increment physical value one by one, find the exact timeline value we're
supposed to signal and perform the update.
Select lowest physical timeline value correctly.
Array can be reordered now, so lowest value isn't necessarily first.
Fixes some super weird hangs in Control DXR.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
Rather than one per device. This solves issues with D3D12 fences
being signalled too late because the fence worker is waiting on
a different set of semaphores while the fence is being enqueued.
Greatly increases performance in Horizon Zero Dawn and Death
Stranding with multi-queue mode enabled.
Signed-off-by: Philip Rebohle <philip.rebohle@tu-dortmund.de>
This will be necessary once we introduce fence workers per
command queue, since we cannot reliably store pointers to
queues.
Signed-off-by: Philip Rebohle <philip.rebohle@tu-dortmund.de>
Replaces d3d12_device_get_vkd3d_queue when mapping D3D12
command queues to Vulkan device queues.
Signed-off-by: Philip Rebohle <philip.rebohle@tu-dortmund.de>
The implemnentation is not complete enough to safely enable it, since
some games will try to create RTPSOs by default, leading to crashes.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
Compacts ranges and only issues one bind for buffer ranges and
full subresource updates, rather than one bind per tile.
Signed-off-by: Philip Rebohle <philip.rebohle@tu-dortmund.de>
Bindless CBV is *pretty* bad on NVIDIA, so add a code path which can
promote descriptor table CBVs into push descriptors.
We can safely do this with Root Signature 1.1 STATIC or
the somewhat obscure STATIC_KEEPING_BUFFER_BOUNDS_CHECKS.
With VOLATILE, which basically all titles are using,
we can still force this behavior through a config flag,
but this is an incorrect speed hack. It works in most
titles however, since bindless CBV is exceptionally rare.
We only hoist descriptors when the root signature range has 1 descriptor
anyway, so we should avoid any reasonable bindless scenario.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
There is no need to scan through the Vulkan format list,
especially since texel buffer creation happens in the hot path
in cases where we know we need to create R32UI texel buffer views.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
Refactor push constant invalidation to SetPipelineState,
it is technically more correct to only invalidate when actually pushing
constants, but we need to do full state invalidation when transitioning
between RT pipelines and non-RT pipelines due to bind point aliasing
shenanigans in D3D12, so it makes more sense to invalidate state based
on active bind point there.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
Enabling VK_EXT_debug_utils comes at some overhead in Wine due to the object tracking required. There is also likely a non-zero overhead in some native implementations also.
By enabling this conditionally, we can also avoid additional overhead from apps that set debug labels on both the Vulkan and front-end side.
The default condition is to enable it when building with Renderdoc integration or in debug builds.
Signed-off-by: Joshua Ashton <joshua@froggi.es>
Gives a massive boost on NVIDIA for some reason.
RADV defers push constant update, so ALL_STAGES doesn't have
that much of a perf hit.
~20% uplift in RE2, ~5% uplift in CP77 from some quick and dirty testing.
Seems to be heavily content dependent either way.
Also a bug fix, since we would clobber graphics push constants from
compute and vice versa if both graphics and compute used the same root
signature.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
As per MSDN, SetName is just a wrapper around SetPrivateData and a specific GUID.
Some apps and tools will use this to retrieve their name back.
So instead, just forward the name to Vulkan in the SetPrivateData call.
Signed-off-by: Joshua Ashton <joshua@froggi.es>
Can only support a subset in Vulkan without extra heroics. The DXR API
lets you query things that you technically should know apriori in the
application. We might need to allocate some side-channel buffers on
demand, but let's defer that until actually needed ... :\
DXR is also very awkward in that we have a query which is resolved in
UNORDERED_ACCESS state instead of COPY_DEST state, so we'll have to
ping-pong through some barriers redundantly.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
When building acceleration structures, we need to have an
VkAccelerationStructureKHR object, but the D3D12 API just uses a plain
VA = ID3D12Resource::GetGPUVA() + offset.
For this to work, we need to resolve the VA back to VkBuffer + offset.
The only VkBuffer we can lookup is the original backing memory
allocation in the VA map, and that allocation itself must own a view
map, since we cannot tie the VA to any specific ID3D12Resource.
Since creating an RTAS is not the common path, we allocate the view map
on-demand with CAS.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
RTAS must stay in this resource state forever. The only way to
synchronize them is UAV barriers.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
Allows local root signatures to work correctly and is also a good
optimization since we no longer need to dereference memory (potentially
cold cache lines) to figure out heap offset in command buffer.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
If we're signalling and waiting on same physical queue (always true for
current SINGLE_QUEUE define), we can rely on submission boundary
synchronization which doesn't require any extra submissions to resolve.
Avoids awkward GPU driver bubbles with back to back signal -> wait pairs
with timeline.
Observed 2% GPU uplift on RE2 on AMD.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
Otherwise, when suballocating memory, GetHeapProperties may
not return the exact same set of flags if we ignore flags
when looking up suitable chunks.
Signed-off-by: Philip Rebohle <philip.rebohle@tu-dortmund.de>
This is still useful as a low-level memory allocation function when
we don't want to bother with buffer offsets or D3D12 validation.
Signed-off-by: Philip Rebohle <philip.rebohle@tu-dortmund.de>
Has one bit set for each vkd3d_queue_family that points to a
unique queue. This can be used to iterate over device queues
without having to check for duplicates manually.
Signed-off-by: Philip Rebohle <philip.rebohle@tu-dortmund.de>
This is necessary to keep the amount of allocated memory manageable
in games that allocate a lot of small heaps or committed resources.
Signed-off-by: Philip Rebohle <philip.rebohle@tu-dortmund.de>
This is designed to work with actual device addresses if supported by
the Vulkan implementation.
Signed-off-by: Philip Rebohle <philip.rebohle@tu-dortmund.de>
Apparently the docs are lying and RTPSO does not hold references to the
root signatures after all.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
Need it here since local root signatures need to know
the physical layout of the record buffer up front.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
We will use the same pointer buffer to handle acceleration structures,
so unify this buffer under a new name. Simplifies some of the binding
code since SRV path and UAV path looks more similar now.
Only difference is that UAV path uses BDA -> uint32_t,
and SRV uses BDA -> RTAccelerationStructure.
RT requires BDA, so the fallback descriptor set (storage texel buffer) is never used for RT.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
We will need separate descriptor sets to be able to handle typed vs
untyped buffer workarounds.
Also writes multiple descriptors for buffers views to make sure MUTABLE
and SSBO sets are filled (or TEXEL_BUFFER + SSBO for non-mutable).
Applications often get this wrong and use raw buffer in shader where
typed view was written and vice versa.
To mitigate this, just write a typed and untyped view together.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
The first range will store the byte offset, the second one will
be the typed buffer range. Typed descriptors should write both.
Signed-off-by: Philip Rebohle <philip.rebohle@tu-dortmund.de>
Co-authored-by: Hans-Kristian Arntzen <post@arntzen-software.no>
This begins the refactor toward letting us to use both texel buffer and
SSBO descriptors for typed buffers, which is a better workaround than
force_bindless_texel_buffers.
In this new approach, we store a mask in metadata instead of
set/binding.
When copying a descriptor, we will iterate over the masks and look up
binding directly from device->bindless_state.set_info[].
The mask is represented in terms of info index rather than set index to
avoid needless lookups. Add some new helpers to make this process
easier.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
Unnecessary because the UAV counter buffer is a host memory
allocation anyway in case of host-only descriptor heaps, so
we will not read from uncached memory.
Signed-off-by: Philip Rebohle <philip.rebohle@tu-dortmund.de>
When reading GPU hang dumps, we can figure out what happened to
descriptor types along the way.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
Caused crash when using a driver that did not support
mutable_descriptor_type.
Was using the wrong enum bitfields ... Sigh, type safe enums would be nice.
Regression caused during refactor in review most likely.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
The common case is that we find an entry, so taking a writer lock should
be the rare case. We need to optimize for the case where the application
hammers the view map with e.g. buffers.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
Official AMD drivers do not support VK_EXT_conditional_rendering,
so we'll use indirect draws instead to emulate the feature.
This also handles 64-bit predicates in combination with the
Vulkan extension, which was not possible previously.
Signed-off-by: Philip Rebohle <philip.rebohle@tu-dortmund.de>
The idea is to use indirect draws and dispatches to implement
predication. For predicated indirect draws, we'll use indirect
count.
Signed-off-by: Philip Rebohle <philip.rebohle@tu-dortmund.de>
Potentially avoids some unnecessary host memory access. Use BDA for
the compute shader so that we can ignore alignment restrictions on
some GPU architectures.
Signed-off-by: Philip Rebohle <philip.rebohle@tu-dortmund.de>
Command lists may need to allocate temporary device memory for
certain operations. In order to avoid frequent alloc/free calls,
we'll recycle these scratch buffers until a certain threshold.
Signed-off-by: Philip Rebohle <philip.rebohle@tu-dortmund.de>
Realign VBO strides and offsets if we have to, for sake of
robustness. Violating these rules is against D3D12 spec, but it does not
cause crashes on native drivers. On RDNA we can hit hangs with unaligned
vertex attributes. It appears that native drivers apply some kind of
fixup here to avoid the crash, even if the result is not what we expect.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
Ensures that queries are always available and initialized
in the correct order on the GPU timeline.
Signed-off-by: Philip Rebohle <philip.rebohle@tu-dortmund.de>
Game renders the map with wrong descriptor type, which means we must
implement everything as texel buffers to make this work.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
We have observed a lot of large GPU bubbles when using back-to-back
timeline semaphores to synchronize GPU submissions. Use prebaked
pipeline barrier command buffers instead.
To resolve queue sparse serialization, use two binary semaphore pairs to
resolve this. There is no need to use timeline semaphores in this case.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
USE_PUSH_DESCRIPTORS may be misleading since it would be set even when
we're not using push descriptors at all due to root descriptors being
passed in via VAs. Instead, make the flag represent whether or not we
use a regular descriptor set for root parameters.
Signed-off-by: Philip Rebohle <philip.rebohle@tu-dortmund.de>
The packed descriptor index is no longer needed, and causes issues in
case a game sets a root signature, then binds a root descriptor, and
then sets a different root signature which maps the given root parameter
index to a different descriptor since we may now read undefined data
when updating push descriptors.
Fixes#366.
Signed-off-by: Philip Rebohle <philip.rebohle@tu-dortmund.de>
MSDN states that root signatures across multiple stages in a graphics
pipeline must be identical, but the D3D12 runtime does not validate
this and mixing different root signatures results in undefined
behaviour, so just taking this from the VS should be safe.
Signed-off-by: Philip Rebohle <philip.rebohle@tu-dortmund.de>
We only need to know the pipeline layout for pipeline variant
creation. We are not holding a strong reference to the root
signature anyway, which may be problematic, but this should
not introduce a regression.
Signed-off-by: Philip Rebohle <philip.rebohle@tu-dortmund.de>
The struct definitions were identical anyway, and unifying
these will prevent unnecessary code duplication.
Signed-off-by: Philip Rebohle <philip.rebohle@tu-dortmund.de>
Version string is used in logging for information purposes, but pipelines blobs and libraries use uint64_t–based commit hash. Using fixed–size integer silences warnings about string length and makes storing build info a little more efficient.
The hash is obtained separately from version string and is shifted to the left by 4 bits if the working tree is dirty.
Signed-off-by: Krzysztof Bogacki <krzysztof.bogacki@leancode.pl>
We will not have offset information for root descriptors, so
we can still only use them with four-byte aligned SSBOs.
Signed-off-by: Philip Rebohle <philip.rebohle@tu-dortmund.de>
Introduces 'extra' bindings to bindless sets which can be used to
bind additional storage buffers to the pipeline, which will occur
before the bindless descriptor array in the descriptor set.
Signed-off-by: Philip Rebohle <philip.rebohle@tu-dortmund.de>
We cannot rely on alignment analysis since games are buggy and screw up
RAW vs structured on occasion.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
It is broken by design and won't be needed by a swapchain
implementation which uses user buffers.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
This will allow us to use the same bindless descriptor set for
different types of descriptor ranges.
Signed-off-by: Philip Rebohle <philip.rebohle@tu-dortmund.de>
This is no longer performance-critical, so in order to simplify changing
the binding model, remove hard-coded descriptor set numbers and instead
look them up based on the requested descriptor properties.
Signed-off-by: Philip Rebohle <philip.rebohle@tu-dortmund.de>
Ignore any indexed draw calls which uses a NULL index buffer.
This is not fully correct, but there is no easy way to emulate D3D12
behavior exactly.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
We cannot compare resource pointers or view pointers,
since the pointers might have been recycled.
This leads to a scenario where we're not updating descriptors we're
supposed to, and the GPU reads a stale descriptor.
Fixes a GPU hang in Death Stranding (and possibly lots of other weird
crashes as well).
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
For correctness, we will need to defer any initial resource state
handling to the queue timeline. Here, we will build an UNDEFINED ->
common layout barrier if (and only if):
- The resource is marked to care about initial layout transition.
- We are the first queue thread to observe that initial_transition
member is 1 (atomic exchange).
- The first use of the resource was not marked to be a discard.
E.g., if the first use of the resource is an alias barrier, we must
not emit an early barrier. The only we should do here is to clear the
initial_transition member, and leave it like that.
A command list maintains a list of d3d12_resources which *might* need a
transition. For the first frame a resource is used (or so), it will not
have the flag cleared yet, so multiple command lists might add the
d3d12_resource to its own transition list. This is fine, as the queue
will resolve it.
If multiple queues see the same initial transition, there might be
shenanigans, but the application must ensure there is either a
submission boundary or fence boundary between the uses. Any initial
layout transition will only be submitted after a Wait() is observed, as
submission of the transition command buffer will be in-order with other
submissions.
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
Hans-Kristian Arntzen
Georg Lehmann
Philip Rebohle
rochaudhari
David McCloskey
Joshua Ashton
Krzysztof Bogacki