Currently we heavily thrash the heap each draw, with malloc/free taking up about 10% of GPFIFOs execution time. Using a linear allocator for the main offenders of buffer usage callbacks and index/vertex state helps to reduce this to about 4%
After the introduction of workahead a system to hold a single large megabuffer per submission was implemented, this worked fine for most cases however when many submissions were flight at the same time memory usage would increase dramatically due to the amount of megabuffers needed. Since only one megabuffer was allowed per execution, it forced the buffer to be fairly large in order to accomodate the upper-bound, even further increasing memory usage.
This commit implements a system to fix the memory usage issue described above by allowing multiple megabuffers to be allocated per execution, as well as reuse across executions. Allocations now go through a global allocator object which chooses which chunk to allocate into on a per-allocation scale, if all are in use by the GPU another chunk will be allocated, that can then be reused for future allocations too. This reduces Hollow Knight megabuffer memory usage by a factor 4 and SMO by even more.
Since we don't call `SynchronizeHost` on source buffers which are GPU dirty, their mirrors will be out of date. The backing contents of this source buffer's region in the new buffer will be incorrect. By copying from the backing directly, we can ensure that no writes are lost and that if the newly created buffer needs to turn GPU dirty during recreation no copies need to be done since the backing is as up to date as the mirror at a minimum.
Buffer lookups are a fairly expensive operation that we currently spend `O(log n)` on the simplest and most frequent case of which is a direct match, this is a very frequent operation where that may be insufficient. This commit optimizes that case to `O(1)` by utilizing a `RangeTable` at the cost of slightly higher insertion/deletion costs for setting ranges of values but these are minimal in frequency compared to lookups.
Having a single variable denoting the exact state of a buffer and the operations that could be performed on it was found to be too restrictive, it's now been expanded into an additional `BackingImmutability` variable but due to these two. We can no longer use atomics without significant additional complexity so all accesses to the state are now mediated through `stateMutex`, a mutex specifically designed for tracking the state.
While designing the system around `stateMutex` it was determined to be more efficient than atomics as it would enforce blocking far less than it would generally have been compared to if the regular atomic fallback of locking the main resource lock which is locked for significantly longer generally.
Co-authored-by: PixelyIon <pixelyion@protonmail.com>
The lifetime of the `this` pointer in the trap callbacks could be invalid as the lifetime of the underlying `Buffer`/`Texture` object wasn't guaranteed, this commit fixes that by passing a `weak_ptr` of the objects into the callbacks which is locked during the callbacks and ensures that a destroyed object isn't accessed.
Co-authored-by: Billy Laws <blaws05@gmail.com>
`FindOrCreate` ended up being monolithic function with poor readability, this commit addresses those concerns by refactoring the function to split it up into multiple member functions of `BufferManager`, while some of these member functions may only have a single call-site they are important to logically categorize tasks into individual functions. The end result is far neater logic which is far more readable and slightly better optimized by virtue of being abstracted better.
It was determined that `FindOrCreate` has several issues which this commit fixes:
* It wouldn't correctly handle locking of the newly created `Buffer` as the constructor would setup traps prior to being able to lock it which could lead to UB
* It wouldn't propagate the `usedByContext`/`everHadInlineUpdate` flags correctly
* It wouldn't correctly set the `dirtyState` of the buffer according to that of its source buffers
`ContextLock` had unoptimal semantics in the form of direct access to the `isFirst` member which wasn't clearly defined, it's now been broken up into function calls `IsFirstUsage` and `OwnsLock` with explicit move semantics and a function for releasing the lock.
Co-authored-by: PixelyIon <pixelyion@protonmail.com>
A buffer that's attached to a context could be coalesced into a larger buffer which isn't attached, this would break as it wouldn't keep the buffer alive till the end of the associated context. To fix this if any source buffers are attached then the resulting coalesced buffer is also attached now.
Certain submissions might not utilize megabuffering but reserve a `MegaBuffer` regardless, this is not optimal since it can inflate the allocations and waste memory. This commit addresses the issue by eliding the allocation given the current submission doesn't utilize them.
An atomic transactional loop was performed on the backing `std::shared_ptr` inside `BufferView`/`TextureView`'s `lock`/`LockWithTag`/`try_lock` functions, these locks utilized `std::atomic_load` for atomically loading the value from the `shared_ptr` recursively till it was the same value pre/post-locking.
This commit abstracts the locking functionality of `TextureView`/`BufferDelegate` into `LockableSharedPtr` to avoid code duplication and removes the usage of `std::atomic_load` in either case as it is not necessary due to the implicit memory barrier provided by locking a mutex.
Multiple threads concurrently accessing the `TextureManager`/`BufferManager` (Referred to as "resource managers") has a potential deadlock with a resource being locked while acquiring the resource manager lock while the thread owning it tries to acquire a lock on the resource resulting in a deadlock.
This has been fixed with locking of resource manager now being externally handled which ensures it can be locked prior to locking any resources, `CommandExecutor` provides accessors for retrieving the resource manager which automatically handles locking aside doing so on attachment of resources.
Resources on the GPU can be fairly convoluted and involve overlaps which can lead to the same GPU resources being utilized with different views, we previously utilized fences to lock resources to prevent concurrent access but this was overly harsh as it would block usage of resources till GPU completion of the commands associated with a resource.
Fences have now been replaced with locks but locks run into the issue of being per-view and therefore to add a common object for tracking usage the concept of "tags" was introduced to track a single context so locks can be skipped if they're from the same context. This is important to prevent a deadlock when locking a resource which has been already locked from the current context with a different view.
We need move-assignment semantics to viably utilize these objects as class members, they cannot be replaced without move-assign (or copy-assign but that is undesirable here). This commit fixes that by introducing a move assignment operator to them while making the `slot` a pointer which has the necessary nullability semantics.
This commit implements several key optimisations in megabuffering that are all inherently interlinked.
- Megabuffering is moved from per-buffer to per-view copies, this makes megabuffering possible for small views into larger underlying buffers which is often the case with even the simplest of games,
- Megabuffering is no longer the default option, it is only enabled for buffer views that have had inline GPU writes applied to them in the past as that is the only case where they are beneficial. In any other case the cost of copying, even with a 128KiB limit can be significant.
- With both of these changes, there is now possibility for overlapping views where one uses megabuffering and one does not. In order to allow GPU inline writes to work consistently in such cases a system of 'host immutability' has been implemented, when a buffer is marked as host immutable for a given cycle, all writes to the buffer from that point to the point the cycle is signalled will be performed on the GPU, ensuring that the backing contents are correctly sequenced
Has the same guarantees of pointer stabilty while also being significantly faster in cases where a buffer has thousands of views. This is the case in RE4 and this change leads to an almost 1000% performance improvement in that game.
We currently have a global `MegaBuffer` instance that is shared across all channels, this is very problematic as `MegaBuffer` fundamentally works like a state machine with allocations (especially resetting/freeing) and is thread-specific. Therefore, we now have a pool of several `MegaBuffer`s which is allocated from by the `CommandExecutor` and kept channel specific as a result which also limits its usage to a single thread, this allows for individually resetting or freeing any allocations.
Previously constant buffer updates would be handled on the CPU and only the end result would be synced to the GPU before execute. This caused issues as if the constant buffer contents was changed between each draw in a renderpass (e.g. text rendering) the draws themselves would only see the final resulting constant buffer.
We had earlier tried to fix this by using vkCmdUpdateBuffer however this caused significant performance loss due to an oversight in Adreno drivers. We could have worked around this simply by using vkCmdCopy buffer however there would still be a performance loss due to renderpasses being split up with copies inbetween.
To avoid this we introduce 'megabuffers', a brand new technique not done before in any other switch emulators. Rather than replaying the copies in sequence on the GPU, we take advantage of the fact that buffers are generally small in order to replay buffers on the GPU instead. Each write and subsequent usage of a buffer will cause a copy of the buffer with that write, and all prior applied to be pushed into the megabuffer, this way at the start of execute the megabuffer will hold all used states of the buffer simultaneously. Draws then reference these individual states in sequence to allow everything to work without any copies. In order to support this buffers have been moved to an immediate sync model, with synchronisation being done at usage-time rather than execute (in order to keep contents properly sequenced) and GPU-side writes now need to be explictly marked (since they prevent megabuffering). It should also be noted that a fallback path using cmdCopyBuffer exists for the cases where buffers are too large or GPU dirty.
We require certain buffers to only be on the host while being accessible through the same abstractions as a guest buffer as they must be interchangeable in usage.
We have support for overlapping buffers which allows us to merge a lot of smaller buffers located on a single page into a single larger buffer which allows for better performance. It additionally ensures that all host buffers match the alignment guarantees of the guest and adequately fulfill host alignment requirements.
This commit encapsulates a complex sequence of cascading changes in the process of supporting overlaps for buffers:
* We determined that it is impossible to resolve overlaps with multiple intervals per buffer within the constraints of each overlap being a contiguous view, support for multiple intervals was therefore dropped. The older buffer manager code was entirely reworked to be simpler due to only handling one interval per buffer with code now being based off `IntervalMap` but tailored specifically for buffers.
* During overlap resolution, the problem of how existing views into the buffer being recreated would be updated, it had to be replaced with a larger buffer that could contain all overlaps and all existing views would need to be repointed to it. This was addressed by a buffer owning all views to itself, we could automatically recalculate the offset of all views and update the buffers with it.
* We still needed to update usage of existing views which was done by handling all access (such as inside a recorded draw) to buffer view properties via `BufferView::RegisterUsage` which dispatches a callback with the view and the corresponding backing buffer. This callback can be stored and called during overlap resolution with the new buffer.
* We had issues with lifetime of the buffer with the handle-like semantics of `BufferView` introduced in the last buffer-related commit, if we updated the view to be owned by a new buffer we'd need to extend the lifetime of the new buffer not the older one and the only way to do this was a proxy owner object `BufferDelegate` which holds a shared pointer to the real `Buffer` which in-turn holds a pointer to all `BufferDelegate` objects to update on repointing. A `BufferView` is effectively just a wrapper around `std::shared_ptr<BufferDelegate>` with more favorable semantics but generally just forwarding calls.
It should be additionally noted that to support usage of `RegisterUsage` the code around buffers in `GraphicsContext` was refactored to defer truly binding till the recording phase.
We wanted views to extend the lifetime of the underlying buffers and at the same time preserve all views until the destruction of the buffer to prevent recreation which might be costly in the future when we need `VkBufferView`s of the buffer but also require a centralized list of all views for recreation of the buffer. It also removes the inconsistency between `BufferView*` being returned in `GetXView` in `GraphicsContext`.
Buffers generally don't have formats that are fundamentally associated with them unless they're texel buffers, if that is the case it can be manually set in `BufferView`.
The Buffer Manager handles mapping of guest buffers to host buffer views with automatic handling of sub-buffers and eventually supporting recreation of overlapping buffers to create a single larger buffer.
