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

Merge pull request 'perf(rt): high-water-mark growth for TLAS host-input buffers (#64)' (#98) from claude/issue-64 into master

Browse source
This commit is contained in:
catbot 2026-06-16 20:24:48 +02:00
commit 00b84dd301
3 changed files with 339 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

25
implementations/Crafter.Graphics-RenderingElement3D.cpp
View file

@ -88,12 +88,29 @@ void RenderingElement3D::BuildTLAS(VkCommandBuffer cmd, std::uint32_t index, RTB
}
if (topologyChanged) {
// Resize the host-visible inputs to match the new count.
// Grow the host-visible inputs on a high-water mark rather than
// resizing to the exact count every topology change. These buffers
// only need to hold *at least* primitiveCount entries — the AS build
// reads exactly primitiveCount of them via tlasRangeInfo, and the
// copy loop below writes [0, primitiveCount) — so an allocation left
// over from a larger earlier frame is reused as-is. This drops the
// two host-buffer reallocations on a count decrease (and on an
// increase that still fits the previous high-water capacity),
// leaving only the AS storage + scratch rebuild below, which is tied
// to the AS itself and dominates this path regardless.
//
// instanceBuffer and metadataBuffer grow in lockstep (always resized
// together to the same entry count), so one capacity check covers
// both. size is only meaningful once buffer is non-null, so the
// null check must short-circuit before the division.
// STORAGE_BUFFER_BIT is required because the application's compute
// shaders bind this buffer as a storage SSBO (e.g. to write
// shaders bind these buffers as storage SSBOs (e.g. to write
// per-instance transforms directly into the TLAS instance data).
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.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);
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.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);
}
}
for(std::uint32_t i = 0; i < primitiveCount; i++) {