Objective

Improve CPU-side rendering performance.

Solution

Create BufferPool variants of DynamicBuffer, StorageBuffer, BatchedUniformBuffer, and GpuArrayBuffer. They do not have a system RAM side buffer of any kind, but rely on Queue::write_buffer_with to directly write values into a staging buffer. As Queue::write_buffer with operates with a &Queue, it's possible to parallelize down to a view level when batching.

The downside is that these buffers are not resizable after being mapped, so these types must reserve fixed sized slices from the buffer ahead of time. The data flow runs as follows:

1. clear_batch_buffer clears the buffer pool.
2. reserve_batch_buffer mutably grabs the buffer pool and reserves a range for every RenderPhase<T> and saves the reserved in the RenderPhase. This is a very fast O(1) operation that does not require allocation or IO of any kind. These must run sequentially due to needing to grab the pool and render phases in parallel.
3. allocate_batch_buffer allocates the actual GPU-side buffer.
4. batch_and_prepare_render_phase then runs on each of them in parallel and parallelizes individual views with Query::par_iter_mut.

NOTE: I'm likely getting something wrong with the indices, which is causing mesh draw calls to be mismatched, causing them to be rendered randomly, which can be potentially seizure inducing depending on the scene. Please be aware of this while testing this change.

Performance

Tested against many_foxes, this nets a rough 4% improvement in render schedule timings.

TODO: Test this against heavier scenes.

Changelog

TODO

Migration Guide

TODO