1c47e31367
This allows to reduce the waiting time caused by shader compilation on some GPU-driver combo. A new settings in the User Preferences make it possible to override the default amount of worker threads and optionally use subprocesses. We still use only one worker thread in cases where there is no benefit with adding more workers (like AMD pro driver and Intel windows). It doesn't scale as much as subprocesses for material shader compilation but that is for other reasons explained in #139818. Add some heuristic to avoid too much memory usage and / or too many stalls. Also add some heuristic to the default number of subprocess for the platform that shows scalling. Historically, multithreaded compilation was prevented by the need of context per thread inside `DRWShader` module. Also there was no good scaling at that time. But nowadays numbers shows different results with good scaling with reasonable amount of threads on many platforms. Even if we are going for vulkan in the next release most of the legacy hardware will still use OpenGL for a few other releases. So it is relevant to make this easy improvement. See pull request for measurements. Pull Request: https://projects.blender.org/blender/blender/pulls/139821
77 lines
2.1 KiB
C++
77 lines
2.1 KiB
C++
/* SPDX-FileCopyrightText: 2005 Blender Authors
|
|
*
|
|
* SPDX-License-Identifier: GPL-2.0-or-later */
|
|
|
|
/** \file
|
|
* \ingroup gpu
|
|
*
|
|
* GPU Capabilities & workarounds
|
|
* This module expose the reported implementation limits & enabled
|
|
* workaround for drivers that needs specific code-paths.
|
|
*/
|
|
|
|
#pragma once
|
|
|
|
#include "BLI_sys_types.h"
|
|
|
|
int GPU_max_texture_size();
|
|
int GPU_max_texture_3d_size();
|
|
int GPU_max_texture_layers();
|
|
int GPU_max_textures();
|
|
int GPU_max_textures_vert();
|
|
int GPU_max_textures_geom();
|
|
int GPU_max_textures_frag();
|
|
int GPU_max_images();
|
|
int GPU_max_work_group_count(int index);
|
|
int GPU_max_work_group_size(int index);
|
|
int GPU_max_uniforms_vert();
|
|
int GPU_max_uniforms_frag();
|
|
int GPU_max_batch_indices();
|
|
int GPU_max_batch_vertices();
|
|
int GPU_max_vertex_attribs();
|
|
int GPU_max_varying_floats();
|
|
int GPU_max_shader_storage_buffer_bindings();
|
|
int GPU_max_compute_shader_storage_blocks();
|
|
int GPU_max_samplers();
|
|
size_t GPU_max_storage_buffer_size();
|
|
/* Used when binding subrange of SSBOs. In bytes.
|
|
* The start of the range must be aligned with this value. */
|
|
size_t GPU_storage_buffer_alignment();
|
|
|
|
int GPU_extensions_len();
|
|
const char *GPU_extension_get(int i);
|
|
|
|
int GPU_texture_size_with_limit(int res);
|
|
|
|
bool GPU_use_subprocess_compilation();
|
|
int GPU_max_parallel_compilations();
|
|
|
|
bool GPU_stencil_clasify_buffer_workaround();
|
|
bool GPU_node_link_instancing_workaround();
|
|
bool GPU_mip_render_workaround();
|
|
bool GPU_depth_blitting_workaround();
|
|
bool GPU_use_main_context_workaround();
|
|
bool GPU_use_hq_normals_workaround();
|
|
bool GPU_crappy_amd_driver();
|
|
|
|
bool GPU_vulkan_render_pass_workaround();
|
|
|
|
bool GPU_geometry_shader_support();
|
|
bool GPU_shader_draw_parameters_support();
|
|
bool GPU_hdr_support();
|
|
bool GPU_stencil_export_support();
|
|
bool GPU_clip_control_support();
|
|
|
|
bool GPU_mem_stats_supported();
|
|
void GPU_mem_stats_get(int *r_totalmem, int *r_freemem);
|
|
|
|
/**
|
|
* Return support for the active context + window.
|
|
*/
|
|
bool GPU_stereo_quadbuffer_support();
|
|
|
|
int GPU_minimum_per_vertex_stride();
|
|
|
|
/** WARNING: Should only be called at startup from creator_args. Never call it at runtime. */
|
|
void GPU_compilation_subprocess_override_set(int count);
|