Crate wgpu

Macros

• kernel_source
  Generates kernel source code by replacing some information using templating.

Structs

• AutoGraphicsApi
  Automatic graphics API based on OS.
• CubeDim
• Dx12
  DirectX 12 graphics API.
• JitBackend
  Generic tensor backend that can be compiled just-in-time to any shader runtime
• JitTensor
  The basic tensor primitive struct.
• Metal
  Metal graphics API.
• OpenGl
  OpenGL graphics API.
• RuntimeOptions
  The values that control how a WGPU Runtime will perform its calculations.
• SourceKernel
  Wraps a kernel source into a cube task.
• SourceTemplate
  Kernel source code abstraction allowing for templating.
• Vulkan
  Vulkan graphics API.
• WebGpu
  WebGpu graphics API.
• WgpuResource
  The memory resource that can be allocated for wgpu.
• WgpuRuntime
  Runtime that uses the [wgpu] crate with the wgsl compiler. This is used in the Wgpu backend. For advanced configuration, use [init_sync] to pass in runtime options or to select a specific graphics API.
• WgpuServer
  Wgpu compute server.
• WgpuSetup
  A complete setup used to run wgpu.
• WgpuStorage
  Buffer storage for wgpu.
• WgslCompiler
  Wgsl Compiler.
• flex32
  A floating point type with relaxed precision, minimum f16, max [f32].

Enums

• MemoryConfiguration
  High level configuration of memory management.
• WgpuDevice
  The device struct when using the wgpu backend.

Traits

• BoolElement
  The element type for booleans for the jit backend.
• FloatElement
  The float element type for the jit backend.
• GraphicsApi
  The basic trait to specify which graphics API to use as Backend.
• IntElement
  The int element type for the jit backend.
• Kernel
  Implement this trait to create a kernel definition.
• KernelSource
  Kernel source to create a source
• WgpuElement
  The base element trait for the wgpu backend.

Functions

• build_info
  Create a vector containing the dimension, strides and shape of tensors.
• 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_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.
• into_contiguous
  Make a jit tensor contiguous.

Type Aliases

• Wgpu
  Tensor backend that uses the wgpu crate for executing GPU compute shaders.
• Wgsl