Module cudarc::driver::result

A thin wrapper around sys.

While all the functions here will return Result, they are mostly all still unsafe because order of operations really matters.

This also only exposes the *_async version of functions because mixing the two is confusing and even more unsafe.

This module also groups functions into sub-modules to make naming easier. For example [sys::cuStreamCreate()] turns into stream::create(), where stream is a module.

Modules

• ctx
  Context management functions (cuCtx*).
• device
  Device management functions (cuDevice*).
• event
• external_memory
• function
• module
  Module management functions (cuModule*).
• occupancy
• primary_ctx
  Primary context management functions (cuDevicePrimaryCtx*).
• stream
  Stream management functions (cuStream*).

Structs

• DriverError
  Wrapper around sys::CUresult. See nvidia’s CUresult docs

Functions

• free_async^⚠
  Frees memory with stream ordered semantics.
• free_sync^⚠
  Allocates memory
• init
  Initializes the CUDA driver API. MUST BE CALLED BEFORE ANYTHING ELSE
• launch_kernel^⚠
  Launches a cuda functions
• malloc_async^⚠
  Allocates memory with stream ordered semantics.
• malloc_sync^⚠
  Allocates memory
• mem_get_info
  Returns (free, total) memory in bytes.
• memcpy_dtod_async^⚠
  Copies memory from Device to Device with stream ordered semantics.
• memcpy_dtod_sync^⚠
  Copies memory from Device to Device
• memcpy_dtoh_async^⚠
  Copies memory from Device to Host with stream ordered semantics.
• memcpy_dtoh_sync^⚠
  Copies memory from Device to Host with stream ordered semantics.
• memcpy_htod_async^⚠
  Copies memory from Host to Device with stream ordered semantics.
• memcpy_htod_sync^⚠
  Copies memory from Host to Device
• memory_free^⚠
  Frees device memory.
• memset_d8_async^⚠
  Sets device memory with stream ordered semantics.
• memset_d8_sync^⚠
  Sets device memory with stream ordered semantics.