Extended API

• Bit
• Execution model
  • Host threads
  • Device threads
  • CUDA APIs
• Exception Handling
  • cuda::cuda_error
• Memory model
  • Thread Scopes
  • Synchronization primitives
  • Atomicity
  • Data Races
  • Example: Message Passing
• Thread Groups
  • Data Members
  • Member Functions
  • Notes
  • Example
• Synchronization Primitives
• Asynchronous Operations
• Memory access properties
• Functional
• Fancy Iterators
  • cuda::constant_iterator
  • cuda::counting_iterator
  • cuda::discard_iterator
  • cuda::heterogeneous_iterator
  • cuda::permutation_iterator
  • cuda::shuffle_iterator
  • cuda::strided_iterator
  • cuda::tabulate_output_iterator
  • cuda::transform_input_output_iterator
  • cuda::transform_iterator
  • cuda::transform_output_iterator
  • cuda::zip_iterator
  • cuda::zip_transform_iterator
  • cuda::zip_function
  • Iterators
  • shuffle_iterator
• Type traits
• Vector Tuple Protocol
  • Structured Bindings
  • Supported Vector Types
  • Example
  • See Also
• Numeric
• Random
• Memory
• Memory Resources
• Math
• Mdspan
• Tensor Memory Accelerator (TMA)
• Warp
• Utility
• Work stealing
  • Example