Thin C++-flavored wrappers for the CUDA Runtime API
api Directory Reference
Directory dependency graph for api:



file  apriori_compiled_kernel.hpp [code]
 An implementation of a subclass of kernel_t for kernels compiled together with the host-side program.
file  array.hpp [code]
 Contains a proxy class for CUDA arrays - GPU memory with 2-D or 3-D locality and hardware support for interpolated value retrieval); see also texture_view.hpp .
file  constants.hpp [code]
 Fundamental CUDA-related constants and enumerations, not dependent on any more complex abstractions, placed in relevant namespaces.
file  context.hpp [code]
 Contains a proxy class for CUDA execution contexts.
file  current_context.hpp [code]
file  current_device.hpp [code]
 Wrappers for getting and setting CUDA's choice of which device is 'current'.
file  device.hpp [code]
 A proxy class for CUDA devices, providing access to all Runtime API calls involving their use and management; and some device-related standalone functions.
file  device_properties.hpp [code]
 Classes for holding CUDA device properties and CUDA compute capability values.
file  devices.hpp [code]
 Code regarding the entirety of CUDA devices available on a system.
file  error.hpp [code]
 Facilities for exception-based handling of Runtime and Driver API errors, including a basic exception class wrapping ::std::runtime_error.
file  event.hpp [code]
 A CUDA event wrapper class and some associated free-standing functions.
file  ipc.hpp [code]
 wrappers for CUDA's facilities for sharing on-device memory addresses and CUDA events between host processes (Inter- Process Communication)
file  kernel.hpp [code]
 Contains a base wrapper class for CUDA kernels - both statically and dynamically compiled; and some related functionality.
file  kernel_launch.hpp [code]
 Variadic, chevron-less wrappers for the CUDA kernel launch mechanism.
file  launch_config_builder.hpp [code]
 Contains the launch.
file  launch_configuration.hpp [code]
 Contains the launch_configuration_t class and some auxiliary functions for it.
file  memory.hpp [code]
 freestanding wrapper functions for working with CUDA's various kinds of memory spaces, arranged into a relevant namespace hierarchy.
file  miscellany.hpp [code]
 Miscellaneous functionality which does not fit in another file, and does not depend on the main proxy classes.
file  module.hpp [code]
 Wrappers for working with modules of compiled CUDA code.
file  pci_id.hpp [code]
 Definition of a wrapper class for CUDA PCI device ID information.
file  pci_id_impl.hpp [code]
 iostream-related freestanding operator functions for cuda::device::pci_location_t instances and iostream-related methods of the cuda::device::pci_location_t class.
file  peer_to_peer.hpp [code]
 Settings and actions related to the interaction of multiple devices (adding on those already in device.hpp)
file  pointer.hpp [code]
 A wrapper class for host and/or device pointers, allowing easy access to CUDA's pointer attributes.
file  primary_context.hpp [code]
file  stream.hpp [code]
 A proxy class for CUDA streams, providing access to all Runtime API calls involving their use and management.
file  texture_view.hpp [code]
 Contains a "texture view" class, for hardware-accelerated access to CUDA arrays, and some related standalone functions and definitions.
file  types.hpp [code]
 Fundamental CUDA-related type definitions.
file  unique_ptr.hpp [code]
 A smart pointer for CUDA device- and host-side memory, similar to the standard library's ::std::unique_ptr.
file  versions.hpp [code]
 Wrappers for Runtime API functions involving versions - of the CUDA runtime and of the CUDA driver.
file  virtual_memory.hpp [code]