Kokkos Core Kernels Package Version of the Day
Type declarations that all Kokkos devices must provide.
|The tag (what type of kokkos_object is this). |
|The device type (same as this class). |
|This device's preferred memory space. |
|The size_type typedef best suited for this device. |
|This device's preferred array layout. |
|This device's host mirror type. |
Functions that all Kokkos devices must implement.
|static KOKKOS_INLINE_FUNCTION int||in_parallel ()|
|True if and only if this method is being called in a thread-parallel function. |
|static bool||sleep ()|
|Set the device in a "sleep" state. |
|static bool||wake ()|
|Wake the device from the 'sleep' state so it is ready for work. |
|static void||fence ()|
|Wait until all dispatched functors complete. |
|static void||finalize ()|
|Free any resources being consumed by the device. |
|static void||print_configuration (std::ostream &, const bool detail=false)|
|Print configuration information to the given output stream. |
|static void||initialize (const SelectDevice=SelectDevice())|
|Initialize, telling the CUDA run-time library which device to use. |
|static void||initialize (int device)|
|static void||initialize (int device, int)|
|static int||is_initialized ()|
|static size_type||device_arch ()|
|Cuda device architecture of the selected device. |
|static size_type||detect_device_count ()|
|Query device count. |
|static std::vector< unsigned >||detect_device_arch ()|
|Detect the available devices and their architecture as defined by the __CUDA_ARCH__ specification. |
|static unsigned||team_max ()|
|static unsigned||team_recommended ()|
Kokkos device that uses CUDA to run on GPUs.
A "device" represents a parallel execution model. It tells Kokkos how to parallelize the execution of kernels in a parallel_for or parallel_reduce. For example, the Threads device uses Pthreads or C++11 threads on a CPU, the OpenMP device uses the OpenMP language extensions, and the Serial device executes "parallel" kernels sequentially. The Cuda device uses NVIDIA's CUDA programming model to execute kernels in parallel on GPUs.
|typedef Impl::DeviceTag Kokkos::Cuda::kokkos_tag|
|typedef CudaSpace::size_type Kokkos::Cuda::size_type|
|static KOKKOS_INLINE_FUNCTION int Kokkos::Cuda::in_parallel||(||)||
|static bool Kokkos::Cuda::sleep||(||)||
Set the device in a "sleep" state.
This function sets the device in a "sleep" state in which it is not ready for work. This may consume less resources than if the device were in an "awake" state, but it may also take time to bring the device from a sleep state to be ready for work.
|static bool Kokkos::Cuda::wake||(||)||
Wake the device from the 'sleep' state so it is ready for work.
|static void Kokkos::Cuda::fence||(||)||
Wait until all dispatched functors complete.
The parallel_for or parallel_reduce dispatch of a functor may return asynchronously, before the functor completes. This method does not return until all dispatched functors on this device have completed.
|static void Kokkos::Cuda::finalize||(||)||
Free any resources being consumed by the device.
|static void Kokkos::Cuda::print_configuration||(||std::ostream &||,|
|const bool||detail =
Print configuration information to the given output stream.
|static void Kokkos::Cuda::initialize||(||const SelectDevice|| = ||)||
Initialize, telling the CUDA run-time library which device to use.
|static size_type Kokkos::Cuda::device_arch||(||)||
Cuda device architecture of the selected device.
This matches the __CUDA_ARCH__ specification.
|static size_type Kokkos::Cuda::detect_device_count||(||)||
Query device count.
|static std::vector<unsigned> Kokkos::Cuda::detect_device_arch||(||)||
Detect the available devices and their architecture as defined by the __CUDA_ARCH__ specification.