ec80264d09
A draw list bundles multiple draw commands for the same geometry and sends the draw commands in a single command. This reduces the overhead of pipeline checking, resource validation and can keep the load higher on the gpu as more work needs to be done. Previously the draw list didn't bundle any commands and would still send each call separately to the GPU. This PR implements the bundling of the commands. Pull Request: https://projects.blender.org/blender/blender/pulls/117548
121 lines
3.5 KiB
C++
121 lines
3.5 KiB
C++
/* SPDX-FileCopyrightText: 2022 Blender Authors
|
|
*
|
|
* SPDX-License-Identifier: GPL-2.0-or-later */
|
|
|
|
/** \file
|
|
* \ingroup gpu
|
|
*/
|
|
#include "vk_shader.hh"
|
|
#include "vk_shader_interface.hh"
|
|
#include "vk_staging_buffer.hh"
|
|
#include "vk_state_manager.hh"
|
|
#include "vk_vertex_buffer.hh"
|
|
|
|
#include "vk_storage_buffer.hh"
|
|
|
|
namespace blender::gpu {
|
|
|
|
VKStorageBuffer::VKStorageBuffer(int size, GPUUsageType usage, const char *name)
|
|
: StorageBuf(size, name), usage_(usage)
|
|
{
|
|
}
|
|
|
|
void VKStorageBuffer::update(const void *data)
|
|
{
|
|
VKContext &context = *VKContext::get();
|
|
ensure_allocated();
|
|
VKStagingBuffer staging_buffer(buffer_, VKStagingBuffer::Direction::HostToDevice);
|
|
staging_buffer.host_buffer_get().update(data);
|
|
staging_buffer.copy_to_device(context);
|
|
}
|
|
|
|
void VKStorageBuffer::ensure_allocated()
|
|
{
|
|
if (!buffer_.is_allocated()) {
|
|
allocate();
|
|
}
|
|
}
|
|
|
|
void VKStorageBuffer::allocate()
|
|
{
|
|
const bool is_host_visible = ELEM(usage_, GPU_USAGE_STREAM);
|
|
VkBufferUsageFlags buffer_usage_flags = ELEM(usage_, GPU_USAGE_STREAM) ?
|
|
VK_BUFFER_USAGE_INDIRECT_BUFFER_BIT :
|
|
VK_BUFFER_USAGE_INDIRECT_BUFFER_BIT |
|
|
VK_BUFFER_USAGE_STORAGE_BUFFER_BIT |
|
|
VK_BUFFER_USAGE_TRANSFER_SRC_BIT |
|
|
VK_BUFFER_USAGE_TRANSFER_DST_BIT;
|
|
buffer_.create(size_in_bytes_, usage_, buffer_usage_flags, is_host_visible);
|
|
debug::object_label(buffer_.vk_handle(), name_);
|
|
}
|
|
|
|
void VKStorageBuffer::bind(int slot)
|
|
{
|
|
VKContext &context = *VKContext::get();
|
|
context.state_manager_get().storage_buffer_bind(*this, slot);
|
|
}
|
|
|
|
void VKStorageBuffer::bind(int slot,
|
|
shader::ShaderCreateInfo::Resource::BindType bind_type,
|
|
const GPUSamplerState /*sampler_state*/)
|
|
{
|
|
VKContext &context = *VKContext::get();
|
|
VKShader *shader = static_cast<VKShader *>(context.shader);
|
|
ensure_allocated();
|
|
const VKShaderInterface &shader_interface = shader->interface_get();
|
|
const std::optional<VKDescriptorSet::Location> location =
|
|
shader_interface.descriptor_set_location(bind_type, slot);
|
|
if (location) {
|
|
VKDescriptorSetTracker &descriptor_set = context.descriptor_set_get();
|
|
descriptor_set.bind(*this, *location);
|
|
}
|
|
}
|
|
|
|
void VKStorageBuffer::unbind()
|
|
{
|
|
unbind_from_active_context();
|
|
}
|
|
|
|
void VKStorageBuffer::clear(uint32_t clear_value)
|
|
{
|
|
ensure_allocated();
|
|
VKContext &context = *VKContext::get();
|
|
buffer_.clear(context, clear_value);
|
|
}
|
|
|
|
void VKStorageBuffer::copy_sub(VertBuf *src, uint dst_offset, uint src_offset, uint copy_size)
|
|
{
|
|
ensure_allocated();
|
|
|
|
VKVertexBuffer &src_vertex_buffer = *unwrap(src);
|
|
src_vertex_buffer.upload();
|
|
|
|
VkBufferCopy region = {};
|
|
region.srcOffset = src_offset;
|
|
region.dstOffset = dst_offset;
|
|
region.size = copy_size;
|
|
|
|
VKContext &context = *VKContext::get();
|
|
VKCommandBuffers &command_buffers = context.command_buffers_get();
|
|
command_buffers.copy(buffer_, src_vertex_buffer.vk_handle(), Span<VkBufferCopy>(®ion, 1));
|
|
context.flush();
|
|
}
|
|
|
|
void VKStorageBuffer::async_flush_to_host()
|
|
{
|
|
GPU_memory_barrier(GPU_BARRIER_BUFFER_UPDATE);
|
|
}
|
|
|
|
void VKStorageBuffer::read(void *data)
|
|
{
|
|
ensure_allocated();
|
|
VKContext &context = *VKContext::get();
|
|
context.flush();
|
|
|
|
VKStagingBuffer staging_buffer(buffer_, VKStagingBuffer::Direction::DeviceToHost);
|
|
staging_buffer.copy_from_device(context);
|
|
staging_buffer.host_buffer_get().read(data);
|
|
}
|
|
|
|
} // namespace blender::gpu
|