56b0b709ea
This patch supports GPU OIDN denoising in the compositor. A new compositor performance option was added to allow choosing between CPU, GPU, and Auto device selection. Auto will use whatever the compositor is using for execution. The code is two folds, first, denoising code was adapted to use buffers as opposed to passing in pointers to filters directly, this is needed to support GPU devices. Second, device creation is now a bit more involved, it tries to choose the device is being used by the compositor for execution. Matching GPU devices is done by choosing the OIDN device that matches the UUID or LUID of the active GPU platform. We need both UUID and LUID because not all platforms support both. UUID is supported on all platforms except MacOS Metal, while LUID is only supported on Window and MacOS metal. If there is no active GPU device or matching is unsuccessful, we let OIDN choose the best device, which is typically the fastest. To support this case, UUID and LUID identifiers were added to the GPUPlatformGlobal and are initialized by the GPU backend if supported. OpenGL now requires GL_EXT_memory_object and GL_EXT_memory_object_win32 to support this use case, but it should function without it. Pull Request: https://projects.blender.org/blender/blender/pulls/136660
103 lines
2.9 KiB
C++
103 lines
2.9 KiB
C++
/* SPDX-FileCopyrightText: 2005 Blender Authors
|
|
*
|
|
* SPDX-License-Identifier: GPL-2.0-or-later */
|
|
|
|
/** \file
|
|
* \ingroup gpu
|
|
*/
|
|
|
|
#pragma once
|
|
|
|
#include <cstdint>
|
|
#include <optional>
|
|
#include <string>
|
|
|
|
#include "BLI_span.hh"
|
|
#include "BLI_utildefines.h"
|
|
|
|
#include "GPU_platform_backend_enum.h" // IWYU pragma: export
|
|
|
|
/* GPU platform support */
|
|
|
|
/* GPU Types */
|
|
enum eGPUDeviceType {
|
|
GPU_DEVICE_NVIDIA = (1 << 0),
|
|
GPU_DEVICE_ATI = (1 << 1),
|
|
GPU_DEVICE_INTEL = (1 << 2),
|
|
GPU_DEVICE_INTEL_UHD = (1 << 3),
|
|
GPU_DEVICE_APPLE = (1 << 4),
|
|
GPU_DEVICE_SOFTWARE = (1 << 5),
|
|
GPU_DEVICE_QUALCOMM = (1 << 6),
|
|
GPU_DEVICE_UNKNOWN = (1 << 7),
|
|
GPU_DEVICE_ANY = (0xff),
|
|
};
|
|
|
|
ENUM_OPERATORS(eGPUDeviceType, GPU_DEVICE_ANY)
|
|
|
|
enum eGPUOSType {
|
|
GPU_OS_WIN = (1 << 8),
|
|
GPU_OS_MAC = (1 << 9),
|
|
GPU_OS_UNIX = (1 << 10),
|
|
GPU_OS_ANY = (0xff00),
|
|
};
|
|
|
|
enum eGPUDriverType {
|
|
GPU_DRIVER_OFFICIAL = (1 << 16),
|
|
GPU_DRIVER_OPENSOURCE = (1 << 17),
|
|
GPU_DRIVER_SOFTWARE = (1 << 18),
|
|
GPU_DRIVER_ANY = (0xff0000),
|
|
};
|
|
|
|
enum eGPUSupportLevel {
|
|
GPU_SUPPORT_LEVEL_SUPPORTED,
|
|
GPU_SUPPORT_LEVEL_LIMITED,
|
|
GPU_SUPPORT_LEVEL_UNSUPPORTED,
|
|
};
|
|
|
|
enum GPUArchitectureType {
|
|
/* Immediate Mode Renderer (IMR).
|
|
* Typically, an IMR architecture will execute GPU work in sequence, rasterizing primitives in
|
|
* order. */
|
|
GPU_ARCHITECTURE_IMR = 0,
|
|
|
|
/* Tile-Based-Deferred-Renderer (TBDR).
|
|
* A TBDR architecture will typically execute the vertex stage up-front for all primitives,
|
|
* binning geometry into distinct tiled regions. Fragments will then be rasterized within
|
|
* the bounds of one tile at a time. */
|
|
GPU_ARCHITECTURE_TBDR = 1,
|
|
};
|
|
|
|
struct GPUDevice {
|
|
std::string identifier;
|
|
int index;
|
|
uint32_t vendor_id;
|
|
uint32_t device_id;
|
|
std::string name;
|
|
};
|
|
|
|
/* GPU Types */
|
|
/* TODO: Verify all use-cases of GPU_type_matches to determine which graphics API it should apply
|
|
* to, and replace with `GPU_type_matches_ex` where appropriate. */
|
|
bool GPU_type_matches(eGPUDeviceType device, eGPUOSType os, eGPUDriverType driver);
|
|
bool GPU_type_matches_ex(eGPUDeviceType device,
|
|
eGPUOSType os,
|
|
eGPUDriverType driver,
|
|
eGPUBackendType backend);
|
|
|
|
eGPUSupportLevel GPU_platform_support_level();
|
|
const char *GPU_platform_vendor();
|
|
const char *GPU_platform_renderer();
|
|
const char *GPU_platform_version();
|
|
const char *GPU_platform_support_level_key();
|
|
const char *GPU_platform_gpu_name();
|
|
GPUArchitectureType GPU_platform_architecture();
|
|
blender::Span<GPUDevice> GPU_platform_devices_list();
|
|
|
|
/* The UUID of the device. Can be an empty array, since it is not supported on all platforms. */
|
|
blender::Span<uint8_t> GPU_platform_uuid();
|
|
/* The LUID of the device. Can be an empty array, since it is not supported on all platforms. */
|
|
blender::Span<uint8_t> GPU_platform_luid();
|
|
/* A bit field with the nth bit active identifying the nth device with the same LUID. Only matters
|
|
* if LUID is defined. */
|
|
uint32_t GPU_platform_luid_node_mask();
|