Vulkan: Report and enable subgroup size control device extension.

Certain Vulkan ICDs (Intel ones notably) will compile SPIR-V
shaders with an liberal, compiler-selected, subgroup size (i.e.
either 8, 16 or 32). For more context, see [1].

This can be a problem for compute, when one shader stores data
in device memory using a subgroup-size dependent layout, to be
consumed by a another shader. Problems arise when the compiler
decides to compile both shaders with different subgroup sizes.

To work-around this, the VK_EXT_subgroup_size_control device
extension was introduced recently: it allows the device to
report the min/max subgroup sizes it provides, and allows
the Vulkan program to control the subgroup size precisely
if it wants to.

This patch adds support to the Vulkan backend to report and
enable the extension if it is available. Note that:

- The corresponding VkStructureType enum values and
  struct types are not rolled to the third-party Vulkan
  headers used by Dawn yet, so vulkan_platform.h has been
  modified to define them if necessary. This can be
  removed in the future when the Vulkan-Headers are
  updated in a different patch.

- This modifies VulkanDeviceInfo::GatherDeviceInfo() to
  use VkGetPhysicalDevice{Properties2,Features2} if the
  VK_KHR_get_device_properties2 instance extension is
  available. Otherwise, the Vulkan 1.0 APIs
  VkGetPhysicalDevice{Properties,Features} are used instead
  (and it is assumed that no subgroup size control is
  possible).

- This changes the definition of VulkanDeviceKnobs to
  make room for the required pNext-linked chains of
  extensions.

- A helper class, PNextChainBuilder is also provided in
  UtilsVulkan.h to make it easy to build pNext-linked
  extension struct chains at runtime, as required when
  probing device propertires/features, or when
  creating a new VkDevice handle.

Apart from that, there is no change in behaviour in this CL.
I.e. a later CL might force a specific subgroup size for
consistency, or introduce a new API to let Dawn clients
select a fixed subgroup size.

[1] https://bugs.freedesktop.org/show_bug.cgi?id=108875

Change-Id: I524af6ff3479f25b0a8bb139a062fe632c826893
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/16020
Reviewed-by: Austin Eng <enga@chromium.org>
Reviewed-by: Corentin Wallez <cwallez@chromium.org>
Commit-Queue: Corentin Wallez <cwallez@chromium.org>
4 files changed
tree: f288a4414fece0f0fa7c8416dbf9ec3bfbba6164
  1. build_overrides/
  2. docs/
  3. examples/
  4. generator/
  5. infra/
  6. scripts/
  7. src/
  8. third_party/
  9. .clang-format
  10. .gitattributes
  11. .gitignore
  12. .gn
  13. AUTHORS
  14. BUILD.gn
  15. CMakeLists.txt
  16. codereview.settings
  17. CONTRIBUTING.md
  18. dawn.json
  19. dawn_wire.json
  20. DEPS
  21. LICENSE
  22. OWNERS
  23. PRESUBMIT.py
  24. README.chromium
  25. README.md
README.md

Dawn, a WebGPU implementation

Dawn is an open-source and cross-platform implementation of the work-in-progress WebGPU standard. More precisely it implements webgpu.h that is a one-to-one mapping with the WebGPU IDL. Dawn is meant to be integrated as part of a larger system and is the underlying implementation of WebGPU in Chromium.

Dawn provides several WebGPU building blocks:

  • WebGPU C/C++ headers that applications and other building blocks use.
    • The webgpu.h version that Dawn implements.
    • A C++ wrapper for the webgpu.h.
  • A “native” implementation of WebGPU using platforms' GPU APIs:
    • D3D12 on Windows 10
    • Metal on macOS and iOS
    • Vulkan on Windows, Linux, ChromeOS, Android and Fuchsia
    • OpenGL as best effort where available
  • A client-server implementation of WebGPU for applications that are in a sandbox without access to native drivers

Helpful links:

Documentation table of content

Developer documentation:

User documentation: (TODO, figure out what overlaps with webgpu.h docs)

Status

(TODO)

License

Apache 2.0 Public License, please see LICENSE.

Disclaimer

This is not an officially supported Google product.