implementations/Crafter.Graphics-RenderingElement3D.cpp

@@ -121,10 +121,23 @@ void RenderingElement3D::BuildTLAS(VkCommandBuffer cmd, std::uint32_t index, RTB
         // 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.
+        //
+        // metadataBuffer (#75) gets the same HOST_VISIBLE | prefer-DEVICE_LOCAL
+        // upgrade: it is CPU-written every frame (the copy loop below) and read
+        // by the ray shaders as a STORAGE_BUFFER every frame, so it has the same
+        // per-frame-shader-read-over-PCIe cost. Unlike instanceBuffer there is
+        // no GPU co-write, so the direct upgrade is unconditional — but staging
+        // is still wrong here: a per-frame-rewritten buffer would pay a stage+
+        // copy+barrier every frame, defeating the point. HOST_COHERENT is
+        // likewise dropped; the FlushDevice() after the copy loop makes the host
+        // writes available before the consuming submit on a non-coherent type
+        // (no-op when the chosen type is coherent — the previous behaviour),
+        // and the queue submit carries the host-write -> shader-read ordering as
+        // it always has.
         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, 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);
+            tlas.metadataBuffer.Resize(VK_BUFFER_USAGE_STORAGE_BUFFER_BIT | VK_BUFFER_USAGE_SHADER_DEVICE_ADDRESS_BIT, VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT, primitiveCount, VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT);
         }
     }
 
@@ -147,6 +160,18 @@ void RenderingElement3D::BuildTLAS(VkCommandBuffer cmd, std::uint32_t index, RTB
 
     tlas.instanceBuffer.FlushDevice(cmd, VK_ACCESS_MEMORY_READ_BIT, VK_PIPELINE_STAGE_ACCELERATION_STRUCTURE_BUILD_BIT_KHR);
 
+    // Make the per-frame metadata host writes available before the consuming
+    // submit. metadataBuffer is not an AS build input (the build never reads it)
+    // and has no GPU co-write — only the ray shaders read it, in a later pass —
+    // so it needs neither the build-stage barrier instanceBuffer takes above nor
+    // a HOST->shader command barrier: the queue submit already orders host
+    // writes made available before it against every command in the submission,
+    // exactly as it did when this buffer was HOST_COHERENT. This plain host
+    // flush is what now makes those writes available on a non-coherent
+    // (BAR/VRAM) type; it self-gates to a no-op on a coherent type (#60),
+    // preserving the previous behaviour where the type ends up coherent.
+    tlas.metadataBuffer.FlushDevice();
+
     VkAccelerationStructureGeometryInstancesDataKHR instancesData {
         .sType = VK_STRUCTURE_TYPE_ACCELERATION_STRUCTURE_GEOMETRY_INSTANCES_DATA_KHR,
         .arrayOfPointers = VK_FALSE,

tests/TLASHighWaterMark/main.cpp

@@ -58,6 +58,15 @@ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301 USA
 // HOST_COHERENT: the FlushDevice(cmd, ...) in BuildTLAS gates on the chosen
 // type's coherency flag, so a non-coherent BAR type still flushes correctly.
 //
+// Issue #75: the metadata buffer gets the identical upgrade — it is CPU-written
+// every frame and read by the ray shaders as a STORAGE_BUFFER every frame, so
+// the same HOST_VISIBLE | prefer-DEVICE_LOCAL, no-mandatory-HOST_COHERENT
+// request keeps those per-frame shader reads in local VRAM. A second assertion
+// block after the first build checks its chosen memory type the same way. The
+// dropped HOST_COHERENT is covered by the zero-validation-errors check: the
+// FlushDevice() added after the copy loop in BuildTLAS makes the host writes
+// available on a non-coherent type and self-gates to a no-op on a coherent one.
+//
 // Validation layers are required for the last check to be meaningful; the build
 // marks this test as needing the SDK layers.
 
@@ -260,6 +269,49 @@ int main() {
         }
     }
 
+    // ── Issue #75: the metadata buffer carries the same memory-type request as
+    // the instance buffer — HOST_VISIBLE (required, mappable) with a best-effort
+    // DEVICE_LOCAL preference (BAR/VRAM) and the mandatory HOST_COHERENT dropped.
+    // It is CPU-written every frame and read by the ray shaders every frame, so
+    // landing it in local VRAM keeps those per-frame storage-buffer reads off
+    // PCIe. Same device-independent check: assert the recorded chosen flags equal
+    // what GetMemoryType resolves for this buffer's memoryTypeBits with that
+    // request, and that DEVICE_LOCAL is chosen wherever a host-visible
+    // device-local type is reachable. ───────────────────────────────────────────
+    {
+        auto& mb = RenderingElement3D::tlases[0].metadataBuffer;
+        VkMemoryRequirements req{};
+        vkGetBufferMemoryRequirements(Device::device, mb.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((mb.memoryPropertyFlagsChosen & VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT) != 0,
+              "metadata buffer memory is HOST_VISIBLE (mappable — the required flag)");
+        Check(mb.memoryPropertyFlagsChosen == expectFlags,
+              "metadata buffer memory matches the HOST_VISIBLE | prefer-DEVICE_LOCAL request (#75)");
+
+        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((mb.memoryPropertyFlagsChosen & VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT) != 0,
+                  "metadata buffer landed on a DEVICE_LOCAL (BAR/VRAM) type where one is reachable");
+        } else {
+            std::println("INFO  no host-visible device-local type reachable — "
+                         "metadata fell back to plain HOST_VISIBLE (expected on non-BAR GPUs)");
+        }
+    }
+
     // ── 2. Grow to 16 (past capacity) → REALLOCATES. ────────────────────────
     SetCount(pool, 16);
     BuildOnce();