Files
test2/source/blender/gpu/intern/gpu_capabilities.cc
Miguel Pozo 74224b25a5 GPU: Add GPU_shader_batch_create_from_infos
This is the first commit of the several required to support
subprocess-based parallel compilation on OpenGL.
This provides the base API and implementation, and exposes the max
subprocesses setting on the UI, but it's not used by any code yet.

More information and the rest of the code can be found in #121925.

This one includes:
- A new `GPU_shader_batch` API that allows requesting the compilation
  of multiple shaders at once, allowing GPU backed to compile them in
  parallel and asynchronously without blocking the Blender UI.
- A virtual `ShaderCompiler` class that backends can use to add their
  own implementation.
- A `ShaderCompilerGeneric` class that implements synchronous/blocking
  compilation of batches for backends that don't have their own
  implementation yet.
- A `GLShaderCompiler` that supports parallel compilation using
  subprocesses.
- A new `BLI_subprocess` API, including IPC (required for the
  `GLShaderCompiler` implementation).
- The implementation of the subprocess program in
  `GPU_compilation_subprocess`.
- A new `Max Shader Compilation Subprocesses` option in
  `Preferences > System > Memory & Limits` to enable parallel shader
  compilation and the max number of subprocesses to allocate (each
  subprocess has a relatively high memory footprint).

Implementation Overview:
There's a single `GLShaderCompiler` shared by all OpenGL contexts.
This class stores a pool of up to `GCaps.max_parallel_compilations`
subprocesses that can be used for compilation.
Each subprocess has a shared memory pool used for sending the shader
source code from the main Blender process and for receiving the already
compiled shader binary from the subprocess. This is synchronized using
a series of shared semaphores.
The subprocesses maintain a shader cache on disk inside a
`BLENDER_SHADER_CACHE` folder at the OS temporary folder.
Shaders that fail to compile are tried to be compiled again locally for
proper error reports.
Hanged subprocesses are currently detected using a timeout of 30s.

Pull Request: https://projects.blender.org/blender/blender/pulls/122232
2024-06-05 18:45:57 +02:00

242 lines
3.9 KiB
C++

/* SPDX-FileCopyrightText: 2005 Blender Authors
*
* SPDX-License-Identifier: GPL-2.0-or-later */
/** \file
* \ingroup gpu
*
* Wrap OpenGL features such as textures, shaders and GLSL
* with checks for drivers and GPU support.
*/
#include "DNA_userdef_types.h" /* For `U.glreslimit`. */
#include "GPU_capabilities.hh"
#include "gpu_context_private.hh"
#include "gpu_capabilities_private.hh"
namespace blender::gpu {
GPUCapabilities GCaps;
}
using namespace blender::gpu;
/* -------------------------------------------------------------------- */
/** \name Capabilities
* \{ */
int GPU_max_texture_size()
{
return GCaps.max_texture_size;
}
int GPU_max_texture_3d_size()
{
return GCaps.max_texture_3d_size;
}
int GPU_texture_size_with_limit(int res)
{
int size = GPU_max_texture_size();
int reslimit = (U.glreslimit != 0) ? min_ii(U.glreslimit, size) : size;
return min_ii(reslimit, res);
}
int GPU_max_texture_layers()
{
return GCaps.max_texture_layers;
}
int GPU_max_textures_vert()
{
return GCaps.max_textures_vert;
}
int GPU_max_textures_geom()
{
return GCaps.max_textures_geom;
}
int GPU_max_textures_frag()
{
return GCaps.max_textures_frag;
}
int GPU_max_textures()
{
return GCaps.max_textures;
}
int GPU_max_images()
{
return GCaps.max_images;
}
int GPU_max_work_group_count(int index)
{
return GCaps.max_work_group_count[index];
}
int GPU_max_work_group_size(int index)
{
return GCaps.max_work_group_size[index];
}
int GPU_max_uniforms_vert()
{
return GCaps.max_uniforms_vert;
}
int GPU_max_uniforms_frag()
{
return GCaps.max_uniforms_frag;
}
int GPU_max_batch_indices()
{
return GCaps.max_batch_indices;
}
int GPU_max_batch_vertices()
{
return GCaps.max_batch_vertices;
}
int GPU_max_vertex_attribs()
{
return GCaps.max_vertex_attribs;
}
int GPU_max_varying_floats()
{
return GCaps.max_varying_floats;
}
int GPU_extensions_len()
{
return GCaps.extensions_len;
}
const char *GPU_extension_get(int i)
{
return GCaps.extension_get ? GCaps.extension_get(i) : "\0";
}
int GPU_max_samplers()
{
return GCaps.max_samplers;
}
bool GPU_use_parallel_compilation()
{
return GCaps.max_parallel_compilations > 0;
}
bool GPU_mip_render_workaround()
{
return GCaps.mip_render_workaround;
}
bool GPU_depth_blitting_workaround()
{
return GCaps.depth_blitting_workaround;
}
bool GPU_use_main_context_workaround()
{
return GCaps.use_main_context_workaround;
}
bool GPU_crappy_amd_driver()
{
/* Currently are the same drivers with the `unused_fb_slot` problem. */
return GCaps.broken_amd_driver;
}
bool GPU_use_hq_normals_workaround()
{
return GCaps.use_hq_normals_workaround;
}
bool GPU_clear_viewport_workaround()
{
return GCaps.clear_viewport_workaround;
}
bool GPU_geometry_shader_support()
{
return GCaps.geometry_shader_support;
}
bool GPU_shader_draw_parameters_support()
{
return GCaps.shader_draw_parameters_support;
}
bool GPU_hdr_support()
{
return GCaps.hdr_viewport_support;
}
bool GPU_texture_view_support()
{
return GCaps.texture_view_support;
}
bool GPU_stencil_export_support()
{
return GCaps.stencil_export_support;
}
int GPU_max_shader_storage_buffer_bindings()
{
return GCaps.max_shader_storage_buffer_bindings;
}
int GPU_max_compute_shader_storage_blocks()
{
return GCaps.max_compute_shader_storage_blocks;
}
int GPU_minimum_per_vertex_stride()
{
return GCaps.minimum_per_vertex_stride;
}
bool GPU_transform_feedback_support()
{
return GCaps.transform_feedback_support;
}
size_t GPU_max_storage_buffer_size()
{
return GCaps.max_storage_buffer_size;
}
/** \} */
/* -------------------------------------------------------------------- */
/** \name Memory statistics
* \{ */
bool GPU_mem_stats_supported()
{
return GCaps.mem_stats_support;
}
void GPU_mem_stats_get(int *r_totalmem, int *r_freemem)
{
Context::get()->memory_statistics_get(r_totalmem, r_freemem);
}
bool GPU_stereo_quadbuffer_support()
{
return Context::get()->front_right != nullptr;
}
/** \} */