Ryujinx/src/Ryujinx.Graphics.Vulkan/BufferUsageBitmap.cs
riperiperi 492a046335
Vulkan: Buffer Mirrors for MacOS performance (#4899)
* Initial implementation of buffer mirrors

Generally slower right now, goal is to reduce render passes in games that do inline updates

Fix support buffer mirrors

Reintroduce vertex buffer mirror

Add storage buffer support

Optimisation part 1

More optimisation

Avoid useless data copies.

Remove unused cbIndex stuff

Properly set write flag for storage buffers.

Fix minor issues

Not sure why this was here.

Fix BufferRangeList

Fix some big issues

Align storage buffers rather than getting full buffer as a range

Improves mirrorability of read-only storage buffers

Increase staging buffer size, as it now contains mirrors

Fix some issues with buffers not updating

Fix buffer SetDataUnchecked offset for one of the paths when using mirrors

Fix buffer mirrors interaction with buffer textures

Fix mirror rebinding

Move GetBuffer calls on indirect draws before BeginRenderPass to avoid draws without render pass

Fix mirrors rebase

Fix rebase 2023

* Fix crash when using stale vertex buffer

Similar to `Get` with a size that's too large, just treat it as a clamp.

* Explicitly set support buffer as mirrorable

* Address feedback

* Remove unused fragment of MVK workaround

* Replace logging for staging buffer OOM

* Address format issues

* Address more format issues

* Mini cleanup

* Address more things

* Rename BufferRangeList

* Support bounding range for ClearMirrors and UploadPendingData

* Add maximum size for vertex buffer mirrors

* Enable index buffer mirrors

Enabled on all platforms for the IbStreamer.

* Feedback

* Remove mystery BufferCache change

Probably macos related?

* Fix mirrors not creating when staging buffer is empty.

* Change log level to debug
2023-08-14 14:18:47 -03:00

82 lines
2.5 KiB
C#

namespace Ryujinx.Graphics.Vulkan
{
internal class BufferUsageBitmap
{
private readonly BitMap _bitmap;
private readonly int _size;
private readonly int _granularity;
private readonly int _bits;
private readonly int _writeBitOffset;
private readonly int _intsPerCb;
private readonly int _bitsPerCb;
public BufferUsageBitmap(int size, int granularity)
{
_size = size;
_granularity = granularity;
// There are two sets of bits - one for read tracking, and the other for write.
int bits = (size + (granularity - 1)) / granularity;
_writeBitOffset = bits;
_bits = bits << 1;
_intsPerCb = (_bits + (BitMap.IntSize - 1)) / BitMap.IntSize;
_bitsPerCb = _intsPerCb * BitMap.IntSize;
_bitmap = new BitMap(_bitsPerCb * CommandBufferPool.MaxCommandBuffers);
}
public void Add(int cbIndex, int offset, int size, bool write)
{
if (size == 0)
{
return;
}
// Some usages can be out of bounds (vertex buffer on amd), so bound if necessary.
if (offset + size > _size)
{
size = _size - offset;
}
int cbBase = cbIndex * _bitsPerCb + (write ? _writeBitOffset : 0);
int start = cbBase + offset / _granularity;
int end = cbBase + (offset + size - 1) / _granularity;
_bitmap.SetRange(start, end);
}
public bool OverlapsWith(int cbIndex, int offset, int size, bool write = false)
{
if (size == 0)
{
return false;
}
int cbBase = cbIndex * _bitsPerCb + (write ? _writeBitOffset : 0);
int start = cbBase + offset / _granularity;
int end = cbBase + (offset + size - 1) / _granularity;
return _bitmap.IsSet(start, end);
}
public bool OverlapsWith(int offset, int size, bool write)
{
for (int i = 0; i < CommandBufferPool.MaxCommandBuffers; i++)
{
if (OverlapsWith(i, offset, size, write))
{
return true;
}
}
return false;
}
public void Clear(int cbIndex)
{
_bitmap.ClearInt(cbIndex * _intsPerCb, (cbIndex + 1) * _intsPerCb - 1);
}
}
}