是否可以等待来自暂存缓冲区的传输完成而不调用 vkQueueWaitIdle

以下一段代码向您展示了如何将顶点缓冲区数据从临时缓冲区传输到本地内存缓冲区：

bool Vulkan::UpdateVertexBuffer(std::vector<VERTEX>& data, VULKAN_BUFFER& vertex_buffer)
{
std::memcpy(this->staging_buffer.pointer, &data[0], vertex_buffer.size);
size_t flush_size = static_cast<size_t>(vertex_buffer.size);
unsigned int multiple = static_cast<unsigned int>(flush_size / this->physical_device.properties.limits.nonCoherentAtomSize);
flush_size = this->physical_device.properties.limits.nonCoherentAtomSize * ((uint64_t)multiple + 1);
VkMappedMemoryRange flush_range = {};
flush_range.sType = VK_STRUCTURE_TYPE_MAPPED_MEMORY_RANGE;
flush_range.pNext = nullptr;
flush_range.memory = this->staging_buffer.memory;
flush_range.offset = 0;
flush_range.size = flush_size;
vkFlushMappedMemoryRanges(this->device, 1, &flush_range);
VkResult result = vkWaitForFences(this->device, 1, &this->transfer.fence, VK_FALSE, 1000000000);
if(result != VK_SUCCESS) {
#if defined(_DEBUG)
std::cout << "UpdateVertexBuffer => vkWaitForFences : Timeout" << std::endl;
#endif
return false;
}
vkResetFences(this->device, 1, &this->transfer.fence);
VkCommandBufferBeginInfo command_buffer_begin_info = {};
command_buffer_begin_info.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_BEGIN_INFO;
command_buffer_begin_info.pNext = nullptr; 
command_buffer_begin_info.flags = VK_COMMAND_BUFFER_USAGE_ONE_TIME_SUBMIT_BIT;
command_buffer_begin_info.pInheritanceInfo = nullptr;
vkBeginCommandBuffer(this->transfer.command_buffer, &command_buffer_begin_info);
VkBufferCopy buffer_copy_info = {};
buffer_copy_info.srcOffset = 0;
buffer_copy_info.dstOffset = 0;
buffer_copy_info.size = vertex_buffer.size;
vkCmdCopyBuffer(this->transfer.command_buffer, this->staging_buffer.handle, vertex_buffer.handle, 1, &buffer_copy_info);
VkBufferMemoryBarrier buffer_memory_barrier = {};
buffer_memory_barrier.sType = VK_STRUCTURE_TYPE_BUFFER_MEMORY_BARRIER;
buffer_memory_barrier.pNext = nullptr;
buffer_memory_barrier.srcAccessMask = VK_ACCESS_MEMORY_WRITE_BIT;
buffer_memory_barrier.dstAccessMask = VK_ACCESS_VERTEX_ATTRIBUTE_READ_BIT;
buffer_memory_barrier.srcQueueFamilyIndex = this->queue_stack[this->transfer_stack_index].index;
buffer_memory_barrier.dstQueueFamilyIndex = this->queue_stack[this->graphics_stack_index].index;
buffer_memory_barrier.buffer = vertex_buffer.handle;
buffer_memory_barrier.offset = 0;
buffer_memory_barrier.size = VK_WHOLE_SIZE;
vkCmdPipelineBarrier(this->transfer.command_buffer, VK_PIPELINE_STAGE_TRANSFER_BIT, VK_PIPELINE_STAGE_VERTEX_INPUT_BIT, 0, 0, nullptr, 1, &buffer_memory_barrier, 0, nullptr);
vkEndCommandBuffer(this->transfer.command_buffer);
VkSubmitInfo submit_info = {};
submit_info.sType = VK_STRUCTURE_TYPE_SUBMIT_INFO;
submit_info.pNext = nullptr;
submit_info.waitSemaphoreCount = 0;
submit_info.pWaitSemaphores = nullptr;
submit_info.pWaitDstStageMask = nullptr;
submit_info.commandBufferCount = 1;
submit_info.pCommandBuffers = &this->transfer.command_buffer;
submit_info.signalSemaphoreCount = 0;
submit_info.pSignalSemaphores = nullptr;
VkResult result = vkQueueSubmit(this->queue_stack[this->transfer_stack_index].handle, 1, &submit_info, this->transfer.fence);
if(result != VK_SUCCESS) {
#if defined(_DEBUG)
std::cout << "UpdateVertexBuffer => vkQueueSubmit : Failed" << std::endl;
#endif
return false;
}
#if defined(_DEBUG)
std::cout << "UpdateVertexBuffer : Success" << std::endl;
#endif
return true;
}

它完美运行，没有任何验证层警告。但是当我调用 i 两次时，两个缓冲区都包含来自第二次调用的相同数据。例如：

UpdateVertexBuffer(cube_data, cube_buffer);
UpdateVertexBuffer(prism_data, prism_buffer);

这将导致cube_buffer和prism_buffer内部都有一个棱镜。要解决此问题，我可以简单地在两次调用之间等待几毫秒：

UpdateVertexBuffer(cube_data, cube_buffer);
std::this_thread::sleep_for(std::chrono::milliseconds(100));
UpdateVertexBuffer(prism_data, prism_buffer);

或者最好，我可以通过调用来替换围栏vkQueueWaitIdle(this->queue_stack[this->transfer_stack_index].handle);

在我看来，这将导致性能损失，并且围栏应该是等待传输操作正确完成的最佳方式，那么为什么当我使用围栏时，我的第一个缓冲区被秒填充。有没有办法在不使用vkQueueWaitIdle的情况下正确执行此操作.

感谢您的帮助。