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

53
tests/TLASHighWaterMark/main.cpp
View file

@ -50,6 +50,14 @@ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
// — the strongest check that feeding an oversized instance buffer to the
// AS build (with tlasRangeInfo.primitiveCount < capacity) is spec-correct.
//
// Issue #65: this test also guards the instance buffer's memory-type request —
// HOST_VISIBLE (required) with a best-effort DEVICE_LOCAL preference and no
// mandatory HOST_COHERENT, so the per-frame GPU accesses stay in local VRAM
// (BAR) rather than crossing PCIe. See the assertion block after the first
// build. The zero-validation-errors check below also covers the dropped
// HOST_COHERENT: the FlushDevice(cmd, ...) in BuildTLAS gates on the chosen
// type's coherency flag, so a non-coherent BAR type still flushes correctly.
//
// Validation layers are required for the last check to be meaningful; the build
// marks this test as needing the SDK layers.
@ -207,6 +215,51 @@ int main() {
Check(RenderingElement3D::tlases[0].builtInstanceCount == 4,
"builtInstanceCount == 4 after first build");
// ── Issue #65: the instance buffer is allocated HOST_VISIBLE (required,
// mappable) with a best-effort DEVICE_LOCAL preference (BAR/VRAM) and the
// mandatory HOST_COHERENT dropped — so the per-frame compute-write of the
// transform field and the AS build's read of the instances both stay in
// local VRAM instead of crossing PCIe. The chosen type must match exactly
// what GetMemoryType resolves for this buffer's memoryTypeBits with that
// prefer-but-don't-require request: DEVICE_LOCAL when a host-visible
// device-local type is reachable (resizable BAR), plain HOST_VISIBLE
// otherwise. Asserting equality with the recomputed selection makes the
// check device-independent — it tracks the call-site request, not the
// particular GPU this runs on. ────────────────────────────────────────────
{
auto& ib = RenderingElement3D::tlases[0].instanceBuffer;
VkMemoryRequirements req{};
vkGetBufferMemoryRequirements(Device::device, ib.buffer, &req);
std::uint32_t expectIdx = Device::GetMemoryType(
req.memoryTypeBits,
VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT,
VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT);
VkMemoryPropertyFlags expectFlags =
Device::memoryProperties.memoryTypes[expectIdx].propertyFlags;
Check((ib.memoryPropertyFlagsChosen & VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT) != 0,
"instance buffer memory is HOST_VISIBLE (mappable — the required flag)");
Check(ib.memoryPropertyFlagsChosen == expectFlags,
"instance buffer memory matches the HOST_VISIBLE | prefer-DEVICE_LOCAL request (#65)");
bool barReachable = false;
constexpr VkMemoryPropertyFlags kBar =
VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT | VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT;
for (std::uint32_t i = 0; i < Device::memoryProperties.memoryTypeCount; ++i) {
if ((req.memoryTypeBits & (1u << i))
&& (Device::memoryProperties.memoryTypes[i].propertyFlags & kBar) == kBar) {
barReachable = true;
break;
}
}
if (barReachable) {
Check((ib.memoryPropertyFlagsChosen & VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT) != 0,
"instance buffer landed on a DEVICE_LOCAL (BAR/VRAM) type where one is reachable");
} else {
std::println("INFO no host-visible device-local type reachable — "
"fell back to plain HOST_VISIBLE (expected on non-BAR GPUs)");
}
}
// ── 2. Grow to 16 (past capacity) → REALLOCATES. ────────────────────────
SetCount(pool, 16);
BuildOnce();