Vulkan临时缓冲区

一、简介
相比于显卡内部读取数据，单纯从CPU访问内存数据的方式性能不是最佳的。最佳的方式是采用VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT标志位，通常来说用在专用的图形卡，CPU是无法访问的。

二、临时缓冲区
创建临时缓冲区：
比较理想的实现方式是创建辅助函数来完成。如下创建函数createBuffer以及createVertexBuffer:
void createBuffer(VkDeviceSize size, VkBufferUsageFlags usage, VkMemoryPropertyFlags properties, VkBuffer& buffer, VkDeviceMemory& bufferMemory) {
VkBufferCreateInfo bufferInfo = {};
bufferInfo.sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO;
bufferInfo.size = size;
bufferInfo.usage = usage;
bufferInfo.sharingMode = VK_SHARING_MODE_EXCLUSIVE;

if (vkCreateBuffer(device, &bufferInfo, nullptr, &buffer) != VK_SUCCESS) {
throw std::runtime_error(“failed to create buffer!”);
}

VkMemoryRequirements memRequirements;
vkGetBufferMemoryRequirements(device, buffer, &memRequirements);

VkMemoryAllocateInfo allocInfo = {};
allocInfo.sType = VK_STRUCTURE_TYPE_MEMORY_ALLOCATE_INFO;
allocInfo.allocationSize = memRequirements.size;
allocInfo.memoryTypeIndex = findMemoryType(memRequirements.memoryTypeBits, properties);

if (vkAllocateMemory(device, &allocInfo, nullptr, &bufferMemory) != VK_SUCCESS) {
throw std::runtime_error(“failed to allocate buffer memory!”);
}

vkBindBufferMemory(device, buffer, bufferMemory, 0);
}

该函数需要传递缓冲区大小，内存属性和usage最终创建不同类型的缓冲区。最后两个参数保存输出的句柄。
void createVertexBuffer() {
VkDeviceSize bufferSize = sizeof(vertices[0]) * vertices.size();
createBuffer(bufferSize, VK_BUFFER_USAGE_VERTEX_BUFFER_BIT, VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT | VK_MEMORY_PROPERTY_HOST_COHERENT_BIT, vertexBuffer, vertexBufferMemory);

void* data;
vkMapMemory(device, vertexBufferMemory, 0, bufferSize, 0, &data);
memcpy(data, vertices.data(), (size_t) bufferSize);
vkUnmapMemory(device, vertexBufferMemory);
}

使用临时缓冲区:
现在改变createVertexBuffer函数，仅仅使用host缓冲区作为临时缓冲区，并且使用device缓冲区作为最终的顶点缓冲区:
void createVertexBuffer() {
VkDeviceSize bufferSize = sizeof(vertices[0]) * vertices.size();

VkBuffer stagingBuffer;
VkDeviceMemory stagingBufferMemory;
createBuffer(bufferSize, VK_BUFFER_USAGE_TRANSFER_SRC_BIT, VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT | VK_MEMORY_PROPERTY_HOST_COHERENT_BIT, stagingBuffer, stagingBufferMemory);

void* data;
vkMapMemory(device, stagingBufferMemory, 0, bufferSize, 0, &data);
memcpy(data, vertices.data(), (size_t) bufferSize);
vkUnmapMemory(device, stagingBufferMemory);

createBuffer(bufferSize, VK_BUFFER_USAGE_TRANSFER_DST_BIT | VK_BUFFER_USAGE_VERTEX_BUFFER_BIT, VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT, vertexBuffer, vertexBufferMemory);
}
使用stagingBuffer来划分stagingBufferMemory缓冲区用来映射、拷贝顶点数据。

使用命令缓冲区执行内存传输的操作命令，就像绘制命令一样。因此我们需要分配一个临时命令缓冲区。或许在这里希望为短期的缓冲区分别创建command pool，那么可以考虑内存分配的优化策略，在command pool生成期间使用VK_COMMAND_POOL_CREATE_TRANSIENT_BIT标志位。
void copyBuffer(VkBuffer srcBuffer, VkBuffer dstBuffer, VkDeviceSize size) {
VkCommandBufferAllocateInfo allocInfo = {};
allocInfo.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_ALLOCATE_INFO;
allocInfo.level = VK_COMMAND_BUFFER_LEVEL_PRIMARY;
allocInfo.commandPool = commandPool;
allocInfo.commandBufferCount = 1;

VkCommandBuffer commandBuffer;
vkAllocateCommandBuffers(device, &allocInfo, &commandBuffer);
}
立即使用命令缓冲过去进行记录：

VkCommandBufferBeginInfo beginInfo = {};
beginInfo.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_BEGIN_INFO;
beginInfo.flags = VK_COMMAND_BUFFER_USAGE_ONE_TIME_SUBMIT_BIT;

vkBeginCommandBuffer(commandBuffer, &beginInfo);

应用于绘制命令缓冲区的VK_COMMAND_BUFFER_USAGE_SIMULTANEOUS_USE_BIT标志位在此不必要，因为我们之需要使用一次命令缓冲区，等待该函数返回，直到复制操作完成。
VkBufferCopy copyRegion = {};
copyRegion.srcOffset = 0; // Optional
copyRegion.dstOffset = 0; // Optional
copyRegion.size = size;
vkCmdCopyBuffer(commandBuffer, srcBuffer, dstBuffer, 1, Region);
缓冲区内容使用vkCmdCopyBuffer命令传输。它使用source和destination缓冲区及一个缓冲区拷贝的区域作为参数。这个区域被定义在VkBufferCopy结构体中，描述源缓冲区的偏移量，目标缓冲区的偏移量和对应的大小。与vkMapMemory命令不同，这里不可以指定VK_WHOLE_SIZE。
vkEndCommandBuffer(commandBuffer);
此命令缓冲区仅包含拷贝命令，因此我们可以在此之后停止记录。现在执行命令缓冲区完成传输：
VkSubmitInfo submitInfo = {};
submitInfo.sType = VK_STRUCTURE_TYPE_SUBMIT_INFO;
submitInfo.commandBufferCount = 1;
submitInfo.pCommandBuffers = &commandBuffer;
vkQueueSubmit(graphicsQueue, 1, &submitInfo, VK_NULL_HANDLE);
vkQueueWaitIdle(graphicsQueue);
与绘制命令不同的是，这个时候我们不需要等待任何事件。我们只是想立即在缓冲区执行传输命令。这里有同样有两个方式等待传输命令完成。我们可以使用vkWaitForFences等待栅栏fence，或者只是使用vkQueueWaitIdle等待传输队列状态变为idle。一个栅栏允许安排多个连续的传输操作，而不是一次执行一个。这给了驱动程序更多的优化空间。
vkFreeCommandBuffers(device, commandPool, 1, &commandBuffer);
不要忘记清理用于传输命令的命令缓冲区。
我们可以从createVertexBuffer函数中调用copyBuffer，拷贝顶点数据到设备缓冲区中：
createBuffer(bufferSize, VK_BUFFER_USAGE_TRANSFER_DST_BIT | VK_BUFFER_USAGE_VERTEX_BUFFER_BIT, VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT, vertexBuffer, vertexBufferMemory);

copyBuffer(stagingBuffer, vertexBuffer, bufferSize)
当从暂存缓冲区拷贝数据到图形卡设备缓冲区完毕后，我们应该清理它：
…
copyBuffer(stagingBuffer, vertexBuffer, bufferSize);
vkDestroyBuffer(device, stagingBuffer, nullptr);
vkFreeMemory(device, stagingBufferMemory, nullptr);
}