Crate cubecl_wgpu

Re-exports§

AutoGraphicsApi: Automatic graphics API based on OS.
Dx12: DirectX 12 graphics API.
Metal: Metal graphics API.
OpenGl: OpenGL graphics API.
RuntimeOptions: The values that control how a WGPU Runtime will perform its calculations.
Vulkan: Vulkan graphics API.
WebGpu: WebGpu graphics API.
WgpuDevice: The device struct when using the wgpu backend.
WgpuMemory: The memory that can be allocated for wgpu.
WgpuResource: The memory resource that can be allocated for wgpu.
WgpuRuntime: Runtime that uses the wgpu crate.
WgpuServer: Wgpu compute server.
WgpuSetup: A complete setup used to run wgpu.
WgpuStorage: Buffer storage for wgpu.
WgslCompiler: Wgsl Compiler.

AutoCompiler: Compiler that dispatches to the most appropriate shader language backend for the active wgpu backend.
AutoRepresentation: Owned compiled kernel representation matching the variants of AutoCompiler.
AutoRepresentationRef: Borrowed counterpart of AutoRepresentation, useful when only read access is needed.
Backend: Backends supported by wgpu.
CompilerInfo
MemoryConfiguration: High level configuration of memory management.
ParamsTransfer
WgpuBackend: The graphics API a WgpuDevice comes up on, which also settles the shader compiler it is fed: SPIR-V on Vulkan, MSL on Metal, WGSL elsewhere.
WgpuCompilerInitError: An explicitly selected wgpu compiler cannot serve the selected graphics backend or device.
WgpuDeviceKind: Which of a machine’s wgpu devices, leaving the graphics API aside.
WgpuInitError: A recoverable failure while acquiring or registering a wgpu runtime.

GraphicsApi: The basic trait to specify which graphics API to use as Backend.
WgpuCompiler: Extension trait implemented by every compiler usable with the wgpu runtime.

init_device: Create a WgpuDevice on an existing WgpuSetup. Useful when you want to share a device between CubeCL and other wgpu-dependent libraries.
init_device_with_api: Import a setup with an explicitly selected graphics API.
init_setup: Like init_setup_async, but synchronous. On wasm, it is necessary to use init_setup_async instead.
init_setup_async: Initialize a client on the given device with the given options. This function is useful to configure the runtime options or to pick a different graphics API.
try_init_device: Register an existing setup without changing its enabled GPU capabilities.
try_init_device_with_api: Register an existing setup with an explicitly selected graphics API.
try_init_setup: Fallible synchronous initialization. Use try_init_setup_async on wasm.
try_init_setup_async: Initialize the selected runtime, returning acquisition or registration failures.

PipelineEntry: Compiler kind and info used when compiling a specific kernel. Used to determine parameter passing strategies. What a launch needs from a compiled kernel: the pipeline, the parameter strategy, and the per-buffer IO the taint bookkeeping stages from. The IO rides in the cache because on a hit nothing else of the compilation survives.