Some games benefit from skipping caches (Pokémon Sword), and others
don't (Animal Crossing: New Horizons). Add an heuristic to decide this
at runtime.
The cache hit ratio has to be ~98% or better to not skip the cache.
There are 16 frames of buffer.
Reimplement the buffer cache using cached bindings and page level
granularity for modification tracking. This also drops the usage of
shared pointers and virtual functions from the cache.
- Bindings are cached, allowing to skip work when the game changes few
bits between draws.
- OpenGL Assembly shaders no longer copy when a region has been modified
from the GPU to emulate constant buffers, instead GL_EXT_memory_object
is used to alias sub-buffers within the same allocation.
- OpenGL Assembly shaders stream constant buffer data using
glProgramBufferParametersIuivNV, from NV_parameter_buffer_object. In
theory this should save one hash table resolve inside the driver
compared to glBufferSubData.
- A new OpenGL stream buffer is implemented based on fences for drivers
that are not Nvidia's proprietary, due to their low performance on
partial glBufferSubData calls synchronized with 3D rendering (that
some games use a lot).
- Most optimizations are shared between APIs now, allowing Vulkan to
cache more bindings than before, skipping unnecesarry work.
This commit adds the necessary infrastructure to use Vulkan object from
OpenGL. Overall, it improves performance and fixes some bugs present on
the old cache. There are still some edge cases hit by some games that
harm performance on some vendors, this are planned to be fixed in later
commits.
The current texture cache has several points that hurt maintainability
and performance. It's easy to break unrelated parts of the cache
when doing minor changes. The cache can easily forget valuable
information about the cached textures by CPU writes or simply by its
normal usage.The current texture cache has several points that hurt
maintainability and performance. It's easy to break unrelated parts
of the cache when doing minor changes. The cache can easily forget
valuable information about the cached textures by CPU writes or simply
by its normal usage.
This commit aims to address those issues.
Now that the GPU is initialized when video backends are initialized,
it's no longer needed to query components once the game is running: it
can be done when yuzu is booting.
This allows us to pass components between constructors and in the
process remove all Core::System references in the video backend.
NV_shader_buffer_{load,store} is a 2010 extension that allows GL applications
to use what in Vulkan is known as physical pointers, this is basically C
pointers. On GLASM these is exposed through the LOAD/STORE/ATOM
instructions.
Up until now, assembly shaders were using NV_shader_storage_buffer_object.
These work fine, but have a (probably unintended) limitation that forces
us to have the limit of a single stage for all shader stages. In contrast,
with NV_shader_buffer_{load,store} we can pass GPU addresses to the
shader through local parameters (GLASM equivalent uniform constants, or
push constants on Vulkan). Local parameters have the advantage of being
per stage, allowing us to generate code without worrying about binding
overlaps.
After marking buffers as resident, Nvidia's driver seems to take a
slow path. To workaround this issue, copy to a STREAM_READ buffer and
then call GetNamedBufferSubData on it.
This is a temporary solution until we have asynchronous flushing.
Make stream buffer and cached buffers as resident and query their
address. This allows us to use GPU addresses for several proprietary
Nvidia extensions.
Instead of using as template argument a shared pointer, use the
underlying type and manage shared pointers explicitly. This can make
removing shared pointers from the cache more easy.
While we are at it, make some misc style changes and general
improvements (like insert_or_assign instead of operator[] + operator=).
Instead of using boost::icl::interval_map for caching, use
boost::intrusive::set. interval_map is intended as a container where the
keys can overlap with one another; we don't need this for caching
buffers and a std::set-like data structure that allows us to search with
lower_bound is enough.
Drop MemoryBarrier from the buffer cache and use Maxwell3D's register
WaitForIdle.
To implement this on OpenGL we just call glMemoryBarrier with the
necessary bits.
Vulkan lacks this synchronization primitive, so we set an event and
immediately wait for it. This is not a pretty solution, but it's what
Vulkan can do without submitting the current command buffer to the queue
(which ends up being more expensive on the CPU).
The original idea of returning pointers is that handles can be moved.
The problem is that the implementation didn't take that in mind and made
everything harder to work with. This commit drops pointer to handles and
returns the handles themselves. While it is still true that handles can
be invalidated, this way we get an old handle instead of a dangling
pointer.
This problem can be solved in the future with sparse buffers.
Nvidia's OpenGL driver maps gl(Named)BufferSubData with some requirements
to a fast. This path has an extra memcpy but updates the buffer without
orphaning or waiting for previous calls. It can be seen as a better
model for "push constants" that can upload a whole UBO instead of 256
bytes.
This path has some requirements established here:
http://on-demand.gputechconf.com/gtc/2014/presentations/S4379-opengl-44-scene-rendering-techniques.pdf#page=24
Instead of using the stream buffer, this commits moves constant buffers
uploads to calls of glNamedBufferSubData and from my testing it brings a
performance improvement. This is disabled when the vendor is not Nvidia
since it brings performance regressions.
Quite a few unused includes have built up over time, particularly on
core/memory.h. Removing these includes means the source files including
those files will no longer need to be rebuilt if they're changed, making
compilation slightly faster in this scenario.
Rather than have a transparent dependency, we can make it explicit in
the interface. This also gets rid of the need to put the core include in
a header.
* get rid of boost::optional
* Remove optional references
* Use std::reference_wrapper for optional references
* Fix clang format
* Fix clang format part 2
* Adressed feedback
* Fix clang format and MacOS build
The idea of this cache is to avoid redundant uploads. So we are going
to cache the uploaded buffers within the stream_buffer and just reuse
the old pointers.
The next step is to implement a VBO cache on GPU memory, but for now,
I want to check the overhead of the cache management. Fetching the
buffer over PCI-E should be quite fast.