Catcrafts/Crafter.Graphics
2
0
Fork 0
Code Issues 1 Pull requests Projects Releases Packages Wiki Activity Actions

Merge pull request 'perf(rt): allocate TLAS instance buffer in BAR/VRAM, not system RAM (#65)' (#105) from claude/issue-65 into master

Browse source
This commit is contained in:
catbot 2026-06-17 19:38:13 +02:00
commit 576a5eb717
2 changed files with 69 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

17
implementations/Crafter.Graphics-RenderingElement3D.cpp
View file

@ -106,9 +106,24 @@ void RenderingElement3D::BuildTLAS(VkCommandBuffer cmd, std::uint32_t index, RTB
// STORAGE_BUFFER_BIT is required because the application's compute
// shaders bind these buffers as storage SSBOs (e.g. to write
// per-instance transforms directly into the TLAS instance data).
//
// instanceBuffer prefers HOST_VISIBLE | DEVICE_LOCAL (BAR/VRAM) so the
// two per-frame GPU accesses stay on-chip instead of crossing PCIe: the
// compute shader writes the transform field in place, and the AS build
// reads the whole instance. The CPU still writes the host-authored
// fields below — those are write-only, sequential, never-read-back
// writes, the ideal write-combined BAR workload. DEVICE_LOCAL is a
// best-effort preference: GetMemoryType falls back to plain
// HOST_VISIBLE (the previous behaviour) when no combined type exists
// (no resizable BAR). HOST_COHERENT is intentionally dropped from the
// required set — the combined type may not be coherent, and the
// FlushDevice(cmd, ...) below already establishes host->build
// visibility, gating its flush-skip on the *chosen* type's flags. The
// single shared buffer is preserved: a whole-buffer copy would clobber
// the GPU-written transforms, so staging is deliberately avoided.
if (tlas.instanceBuffer.buffer == VK_NULL_HANDLE
|| primitiveCount > tlas.instanceBuffer.size / sizeof(VkAccelerationStructureInstanceKHR)) {
tlas.instanceBuffer.Resize(VK_BUFFER_USAGE_SHADER_DEVICE_ADDRESS_BIT | VK_BUFFER_USAGE_TRANSFER_DST_BIT | VK_BUFFER_USAGE_ACCELERATION_STRUCTURE_BUILD_INPUT_READ_ONLY_BIT_KHR | VK_BUFFER_USAGE_STORAGE_BUFFER_BIT, VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT | VK_MEMORY_PROPERTY_HOST_COHERENT_BIT, primitiveCount);
tlas.instanceBuffer.Resize(VK_BUFFER_USAGE_SHADER_DEVICE_ADDRESS_BIT | VK_BUFFER_USAGE_TRANSFER_DST_BIT | VK_BUFFER_USAGE_ACCELERATION_STRUCTURE_BUILD_INPUT_READ_ONLY_BIT_KHR | VK_BUFFER_USAGE_STORAGE_BUFFER_BIT, VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT, primitiveCount, VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT);
tlas.metadataBuffer.Resize(VK_BUFFER_USAGE_STORAGE_BUFFER_BIT | VK_BUFFER_USAGE_SHADER_DEVICE_ADDRESS_BIT, VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT | VK_MEMORY_PROPERTY_HOST_COHERENT_BIT, primitiveCount);
}
}