我在Vulkan中使用光线追踪创建BLAS时遇到了一个问题。基本上，不总是，但经常当我发送命令"vkCmdBuildAccelerationStructuresKHR"通过计算队列中的commandBuffer, VkDevice变为VK_ERROR_DEVICE_LOST。vkqueuessubmit返回VK_SUCCESS，但是当我试图等待发送的命令完成vkDeviceWaitIdle返回VK_ERROR_DEVICE_LOST。所有使用的缓冲区都没有错误地分配，并且可以在设备上获得地址。我还使用VMA (Vulkan Memory Management)库来管理分配。缓冲区是用属性VK_SHARING_MODE_EXCLUSIVE创建的，但是只在Compute队列的commandBuffer中使用。真正的问题是验证层没有给出任何错误消息。
创建顶点缓冲区的代码:VkBufferCreateInfo vkVertexBufferCreateInfo{};
vkVertexBufferCreateInfo.sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO;
vkVertexBufferCreateInfo.size = vertexSize;
vkVertexBufferCreateInfo.usage = VK_BUFFER_USAGE_ACCELERATION_STRUCTURE_BUILD_INPUT_READ_ONLY_BIT_KHR
| VK_BUFFER_USAGE_TRANSFER_DST_BIT | VK_BUFFER_USAGE_SHADER_DEVICE_ADDRESS_BIT
| VK_BUFFER_USAGE_VERTEX_BUFFER_BIT | VK_BUFFER_USAGE_STORAGE_BUFFER_BIT;
vkVertexBufferCreateInfo.sharingMode = VK_SHARING_MODE_EXCLUSIVE;
vkVertexBufferCreateInfo.pQueueFamilyIndices = VK_NULL_HANDLE;
vkVertexBufferCreateInfo.queueFamilyIndexCount = 0;
VmaAllocationCreateInfo vmaVertexBufferAllocationCreateInfo{};
vmaVertexBufferAllocationCreateInfo.flags = VMA_ALLOCATION_CREATE_STRATEGY_MIN_MEMORY_BIT;
vmaVertexBufferAllocationCreateInfo.requiredFlags = VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT;
VkBufferCreateInfo vkIndexBufferCreateInfo{};
vkIndexBufferCreateInfo.sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO;
vkIndexBufferCreateInfo.size = faceSize;
vkIndexBufferCreateInfo.usage = VK_BUFFER_USAGE_ACCELERATION_STRUCTURE_BUILD_INPUT_READ_ONLY_BIT_KHR
| VK_BUFFER_USAGE_TRANSFER_DST_BIT | VK_BUFFER_USAGE_SHADER_DEVICE_ADDRESS_BIT
| VK_BUFFER_USAGE_INDEX_BUFFER_BIT | VK_BUFFER_USAGE_STORAGE_BUFFER_BIT;
vkIndexBufferCreateInfo.sharingMode = VK_SHARING_MODE_EXCLUSIVE;
vkIndexBufferCreateInfo.pQueueFamilyIndices = VK_NULL_HANDLE;
vkIndexBufferCreateInfo.queueFamilyIndexCount = 0;
VmaAllocationCreateInfo vmaIndexBufferAllocationCreateInfo = {};
vmaIndexBufferAllocationCreateInfo.flags = VMA_ALLOCATION_CREATE_STRATEGY_MIN_MEMORY_BIT;
vmaIndexBufferAllocationCreateInfo.requiredFlags = VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT;
为几何体info创建结构的代码:
// Query the 64-bit vertex/index buffer device address value through which buffer memory
// can be accessed in a shader
std::optional<VkDeviceAddress> vertexBufferAddress = geometry.getVertexBuffer().getBufferDeviceAddress();
if (vertexBufferAddress.has_value() == false)
{
OV_LOG_ERROR("Fail to retrive the device address of the vertex buffer. Probably geometry not uploaded.");
return false;
}
std::optional<VkDeviceAddress> faceBufferAddress = geometry.getFaceBuffer().getBufferDeviceAddress();
if (faceBufferAddress.has_value() == false)
{
OV_LOG_ERROR("Fail to retrive the device address of the face buffer. Probably geometry not uploaded.");
return false;
}
VkDeviceOrHostAddressConstKHR vertexDeviceOrHostAddressConst = {};
vertexDeviceOrHostAddressConst.deviceAddress = vertexBufferAddress.value();
VkDeviceOrHostAddressConstKHR faceDeviceOrHostAddressConst = {};
faceDeviceOrHostAddressConst.deviceAddress = faceBufferAddress.value();
// Structure specifying a triangle geometry in a bottom-level acceleration structure
VkAccelerationStructureGeometryTrianglesDataKHR accelerationStructureGeometryTrianglesData = {};
accelerationStructureGeometryTrianglesData.sType =
VK_STRUCTURE_TYPE_ACCELERATION_STRUCTURE_GEOMETRY_TRIANGLES_DATA_KHR;
accelerationStructureGeometryTrianglesData.pNext = NULL;
// Vertex glm::vec3
accelerationStructureGeometryTrianglesData.vertexFormat = VK_FORMAT_R32G32B32_SFLOAT;
accelerationStructureGeometryTrianglesData.vertexData = vertexDeviceOrHostAddressConst;
// sizeof(float) * 3 => vertex
// sizeof(uint32_t) * 3 => normal / uv / tangent
accelerationStructureGeometryTrianglesData.vertexStride = sizeof(Ov::Geometry::VertexData);
// # vertices = vertex buffer size bytes / vertex stride
accelerationStructureGeometryTrianglesData.maxVertex = geometry.getNrOfVertices();
accelerationStructureGeometryTrianglesData.indexType = VK_INDEX_TYPE_UINT32;
accelerationStructureGeometryTrianglesData.indexData = faceDeviceOrHostAddressConst;
// transformData is a device or host address to memory containing an optional reference to
// a VkTransformMatrixKHR structure
accelerationStructureGeometryTrianglesData.transformData = transformData;
// Union specifying acceleration structure geometry data
VkAccelerationStructureGeometryDataKHR accelerationStructureGeometryData = {};
accelerationStructureGeometryData.triangles = accelerationStructureGeometryTrianglesData;
// Structure specifying geometries to be built into an acceleration structure
VkAccelerationStructureGeometryKHR& accelerationStructureGeometry = reserved->geometriesAS.emplace_back();
accelerationStructureGeometry.sType = VK_STRUCTURE_TYPE_ACCELERATION_STRUCTURE_GEOMETRY_KHR;
accelerationStructureGeometry.pNext = NULL;
accelerationStructureGeometry.geometryType = VK_GEOMETRY_TYPE_TRIANGLES_KHR;
accelerationStructureGeometry.geometry = accelerationStructureGeometryData;
accelerationStructureGeometry.flags = geometryFlags;
// Structure specifying build offsets and counts for acceleration structure builds
VkAccelerationStructureBuildRangeInfoKHR& accelerationStructureBuildRangeInfoKHR = reserved->geometriesBuildRangeAS.emplace_back();
// primitiveCount defines the number of primitives for a corresponding acceleration structure geometry.
accelerationStructureBuildRangeInfoKHR.primitiveCount = geometry.getNrOfFaces();
accelerationStructureBuildRangeInfoKHR.primitiveOffset = 0;
accelerationStructureBuildRangeInfoKHR.firstVertex = 0;
accelerationStructureBuildRangeInfoKHR.transformOffset = 0;
// Structure specifying the geometry data used to build an acceleration structure.
reserved->accelerationStructureBuildGeometryInfo.sType =
VK_STRUCTURE_TYPE_ACCELERATION_STRUCTURE_BUILD_GEOMETRY_INFO_KHR;
reserved->accelerationStructureBuildGeometryInfo.pNext = NULL;
reserved->accelerationStructureBuildGeometryInfo.type = type;
reserved->accelerationStructureBuildGeometryInfo.flags = flags;
// VK_BUILD_ACCELERATION_STRUCTURE_MODE_BUILD_KHR => specifies that the destination acceleration
// structure will be built using the specified geometries.
reserved->accelerationStructureBuildGeometryInfo.mode = VK_BUILD_ACCELERATION_STRUCTURE_MODE_BUILD_KHR;
reserved->accelerationStructureBuildGeometryInfo.srcAccelerationStructure = VK_NULL_HANDLE;
reserved->accelerationStructureBuildGeometryInfo.dstAccelerationStructure = VK_NULL_HANDLE;
reserved->accelerationStructureBuildGeometryInfo.geometryCount = nrOfgeometriesStructuresAS;
// The index of each element of the pGeometries or ppGeometries members of VkAccelerationStructureBuildGeometryInfoKHR
// is used as the geometry index during ray traversal.The geometry index is available in ray shaders via the
// RayGeometryIndexKHR built - in, and is used to determine hitand intersection shaders executed
// during traversal.The geometry index is available to ray queries via the OpRayQueryGetIntersectionGeometryIndexKHR instruction.
reserved->accelerationStructureBuildGeometryInfo.pGeometries = geometriesStructuresAS.data();
reserved->accelerationStructureBuildGeometryInfo.ppGeometries = NULL;
reserved->accelerationStructureBuildGeometryInfo.scratchData = {};
// Structure specifying build sizes for an acceleration structure
VkAccelerationStructureBuildSizesInfoKHR accelerationStructureBuildSizesInfo = {};
accelerationStructureBuildSizesInfo.sType = VK_STRUCTURE_TYPE_ACCELERATION_STRUCTURE_BUILD_SIZES_INFO_KHR;
accelerationStructureBuildSizesInfo.pNext = NULL;
accelerationStructureBuildSizesInfo.accelerationStructureSize = 0;
accelerationStructureBuildSizesInfo.updateScratchSize = 0;
accelerationStructureBuildSizesInfo.buildScratchSize = 0;
// Retrieve the required size for an acceleration structure
// VK_ACCELERATION_STRUCTURE_BUILD_TYPE_DEVICE_KHR => requests the memory requirement for operations
// performed by the device.
PFN_vkGetAccelerationStructureBuildSizesKHR pvkGetAccelerationStructureBuildSizesKHR =
(PFN_vkGetAccelerationStructureBuildSizesKHR)vkGetDeviceProcAddr(logicalDevice.get().getVkDevice(), "vkGetAccelerationStructureBuildSizesKHR");
pvkGetAccelerationStructureBuildSizesKHR(logicalDevice.get().getVkDevice(),
VK_ACCELERATION_STRUCTURE_BUILD_TYPE_HOST_KHR,
&reserved->accelerationStructureBuildGeometryInfo,
&reserved->accelerationStructureBuildGeometryInfo.geometryCount,
&accelerationStructureBuildSizesInfo);
////////////////////
// Scratch buffer //
////////////////////
#pragma region ScratchBuffer
///////////////////////////
// Create scratch buffer //
///////////////////////////
// Create info buffer
VkBufferCreateInfo vkScratchBufferCreateInfo{};
vkScratchBufferCreateInfo.sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO;
// The second field of the struct is size, which specifies the size of the buffer in bytes
vkScratchBufferCreateInfo.size = accelerationStructureBuildSizesInfo.buildScratchSize;
// The third field is usage, which indicates for which purposes the data in the buffer
// is going to be used. It is possible to specify multiple purposes using a bitwise or.
// VK_BUFFER_USAGE_ACCELERATION_STRUCTURE_BUILD_INPUT_READ_ONLY_BIT_KHR => specifies that the buffer is suitable for
// use as a read-only input to an acceleration structure build.
// VK_BUFFER_USAGE_SHADER_DEVICE_ADDRESS_BIT => specifies that the buffer can be used to retrieve a buffer device address
// via vkGetBufferDeviceAddress and use that address to access the buffer’s memory from a shader.
vkScratchBufferCreateInfo.usage = VK_BUFFER_USAGE_ACCELERATION_STRUCTURE_BUILD_INPUT_READ_ONLY_BIT_KHR
| VK_BUFFER_USAGE_SHADER_DEVICE_ADDRESS_BIT | VK_BUFFER_USAGE_STORAGE_BUFFER_BIT;
// buffers can also be owned by a specific queue family or be shared between multiple
// at the same time.
// VK_SHARING_MODE_CONCURRENT specifies that concurrent access to any range or image subresource of the object
// from multiple queue families is supported.
vkScratchBufferCreateInfo.sharingMode = VK_SHARING_MODE_EXCLUSIVE;
// From which queue family the buffer will be accessed.
vkScratchBufferCreateInfo.pQueueFamilyIndices = NULL;
vkScratchBufferCreateInfo.queueFamilyIndexCount = 0;
// Create allocation info
VmaAllocationCreateInfo vmaScratchBufferAllocationCreateInfo = {};
// VMA_ALLOCATION_CREATE_MAPPED_BIT => Set this flag to use a memory that will be persistently
// mappedand retrieve pointer to it. It is valid to use this flag for allocation made from memory
// type that is not HOST_VISIBLE. This flag is then ignored and memory is not mapped. This is useful
// if you need an allocation that is efficient to use on GPU (DEVICE_LOCAL) and still want to map it
// directly if possible on platforms that support it (e.g. Intel GPU).
vmaScratchBufferAllocationCreateInfo.flags = VMA_ALLOCATION_CREATE_STRATEGY_MIN_MEMORY_BIT;
// Flags that must be set in a Memory Type chosen for an allocation.
vmaScratchBufferAllocationCreateInfo.requiredFlags = VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT;
if (!reserved->scratchBuffer.create(vkScratchBufferCreateInfo, vmaScratchBufferAllocationCreateInfo))
{
OV_LOG_ERROR("Fail creation scrath buffer for BLAS.");
this->free();
return false;
}
////////////////////////
// Set scratch buffer //
////////////////////////
std::optional<VkDeviceAddress> deviceAddress = reserved->scratchBuffer.getBufferDeviceAddress();
if (deviceAddress.has_value() == false)
{
OV_LOG_ERROR("Fail to retrieve the scratch buffer device address.");
this->free();
return false;
}
VkDeviceOrHostAddressKHR scratchDeviceOrHostAddress = {};
scratchDeviceOrHostAddress.deviceAddress = deviceAddress.value();
// ScratchData is the device or host address to memory that will be used as scratch memory for the build.
reserved->accelerationStructureBuildGeometryInfo.scratchData = scratchDeviceOrHostAddress;
#pragma endregion
/////////////////
// BLAS buffer //
/////////////////
#pragma region BLASBuffer
// Create BLASBuffer
// Create info buffer
VkBufferCreateInfo vkBLASBufferCreateInfo{};
vkBLASBufferCreateInfo.sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO;
// The second field of the struct is size, which specifies the size of the buffer in bytes
vkBLASBufferCreateInfo.size = accelerationStructureBuildSizesInfo.accelerationStructureSize;
// The third field is usage, which indicates for which purposes the data in the buffer
// is going to be used. It is possible to specify multiple purposes using a bitwise or.
// VK_BUFFER_USAGE_TRANSFER_SRC_BIT specifies that the buffer can be used as the source of a transfer command.
vkBLASBufferCreateInfo.usage = VK_BUFFER_USAGE_ACCELERATION_STRUCTURE_STORAGE_BIT_KHR |
VK_BUFFER_USAGE_SHADER_DEVICE_ADDRESS_BIT;
// buffers can also be owned by a specific queue family or be shared between multiple
// at the same time.
// VK_SHARING_MODE_CONCURRENT specifies that concurrent access to any range or image subresource of the object
// from multiple queue families is supported.
vkBLASBufferCreateInfo.sharingMode = VK_SHARING_MODE_EXCLUSIVE;
// From which queue family the buffer will be accessed.
vkBLASBufferCreateInfo.pQueueFamilyIndices = NULL;
vkBLASBufferCreateInfo.queueFamilyIndexCount = 0;
// Create allocation info
VmaAllocationCreateInfo vmaBLASBufferAllocationCreateInfo = {};
// VMA_ALLOCATION_CREATE_STRATEGY_MIN_MEMORY_BIT => Allocation strategy that chooses smallest possible free range for the allocation
// to minimize memory usage and fragmentation, possibly at the expense of allocation time.
vmaBLASBufferAllocationCreateInfo.flags = VMA_ALLOCATION_CREATE_STRATEGY_MIN_MEMORY_BIT;
// Flags that must be set in a Memory Type chosen for an allocation.
vmaBLASBufferAllocationCreateInfo.requiredFlags = VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT;
if (!reserved->accelerationStructureBuffer.create(vkBLASBufferCreateInfo, vmaBLASBufferAllocationCreateInfo))
{
OV_LOG_ERROR("Fail creation scrath buffer for BLAS.");
this->free();
return false;
}
#pragma endregion
//////////////
// Build AS //
//////////////
#pragma region BuildAS
// Structure specifying the parameters of a newly created acceleration structure object
VkAccelerationStructureCreateInfoKHR accelerationStructureCreateInfo = {};
accelerationStructureCreateInfo.sType = VK_STRUCTURE_TYPE_ACCELERATION_STRUCTURE_CREATE_INFO_KHR;
accelerationStructureCreateInfo.pNext = NULL;
accelerationStructureCreateInfo.createFlags = 0;
accelerationStructureCreateInfo.buffer = reserved->accelerationStructureBuffer.getVkBuffer();
accelerationStructureCreateInfo.offset = 0;
accelerationStructureCreateInfo.size = accelerationStructureBuildSizesInfo.accelerationStructureSize;
accelerationStructureCreateInfo.type = type;
accelerationStructureCreateInfo.deviceAddress = 0;
// Create a new acceleration structure object
PFN_vkCreateAccelerationStructureKHR pvkCreateAccelerationStructureKHR =
(PFN_vkCreateAccelerationStructureKHR)vkGetDeviceProcAddr(logicalDevice.get().getVkDevice(), "vkCreateAccelerationStructureKHR");
if (pvkCreateAccelerationStructureKHR(logicalDevice.get().getVkDevice(), &accelerationStructureCreateInfo, NULL,
&reserved->accelerationStructure) != VK_SUCCESS)
{
OV_LOG_ERROR("Fail to create AS, id: %d.", this->Ov::Object::getId());
this->free();
return false;
}
// dstAccelerationStructure is a pointer to the target acceleration structure for the build.
reserved->accelerationStructureBuildGeometryInfo.dstAccelerationStructure = reserved->accelerationStructure;
一夜好眠后，我找到了问题的答案。基本上，错误是由于传递给函数pvkGetAccelerationStructureBuildSizesKHR()的参数不正确。作为参数pMaxPrimitiveCounts，我传递了几何图形的数量，但有必要传递每个几何图形的原语数量。
Vulkan spec:
如果pBuildInfo->geometryCount不为0，则pMaxPrimitiveCounts必须是指向pBuildInfo->geometryCountuint32_t值数组的有效指针