Classes

• namespace tf taskflow namespace
  • class AsyncTask class to create a dependent asynchronous task (async task)
  • class BoundedTaskQueue class to create a lock-free bounded work-stealing queue
  • struct CachelineAligned struct to ensure cacheline-aligned storage for an object.
  • class ChromeObserver class to create an observer based on Chrome tracing format
  • class cudaDeviceAllocator class to create a CUDA device allocator
    • struct rebind its member type U is the equivalent allocator type to allocate elements of type U
  • class cudaEventBase class to create a smart pointer wrapper for managing cudaEvent_t
  • struct cudaEventCreator functor to create a cudaEvent_t object
  • struct cudaEventDeleter functor to delete a cudaEvent_t object
  • class cudaExecutionPolicy class to define execution policy for CUDA standard algorithms
  • class cudaFlow class to create a cudaFlow task dependency graph
  • class cudaFlowCapturer class to create a cudaFlow graph using stream capture
  • class cudaFlowLinearOptimizer class to capture a linear CUDA graph using a sequential stream
  • class cudaFlowOptimizerBase class to provide helper common methods for optimization algorithms
  • class cudaFlowRoundRobinOptimizer class to capture a CUDA graph using a round-robin algorithm
  • class cudaFlowSequentialOptimizer class to capture a CUDA graph using a sequential stream
  • class cudaGraphBase class to create a CUDA graph managed by C++ smart pointer
  • struct cudaGraphCreator a functor for creating a CUDA graph
  • struct cudaGraphDeleter a functor for deleting a CUDA graph
  • class cudaGraphExecBase class to create an executable CUDA graph managed by C++ smart pointer
  • struct cudaGraphExecCreator a functor for creating an executable CUDA graph
  • struct cudaGraphExecDeleter a functor for deleting an executable CUDA graph
  • class cudaScopedDevice class to create an RAII-styled context switch
  • class cudaStreamBase class to create a smart pointer wrapper for managing cudaStream_t
  • struct cudaStreamCreator functor to create a cudaStream_t object
  • struct cudaStreamDeleter functor to delete a cudaStream_t object
  • class cudaTask class to create a task handle of a CUDA Graph node
  • class cudaUSMAllocator class to create a unified shared memory (USM) allocator
    • struct rebind its member type U is the equivalent allocator type to allocate elements of type U
  • class DataPipe class to create a stage in a data-parallel pipeline
  • class DataPipeline class to create a data-parallel pipeline scheduling framework
  • struct DefaultClosureWrapper default closure wrapper that simply runs the given closure as is
  • struct DefaultTaskParams empty task parameter type for compile-time optimization
  • class DynamicPartitioner class to construct a dynamic partitioner for scheduling parallel algorithms
  • class Executor class to create an executor
  • class FlowBuilder class to build a task dependency graph
  • class Future class to access the result of an execution
  • class Graph class to create a graph object
  • class GuidedPartitioner class to construct a guided partitioner for scheduling parallel algorithms
  • class IndexRange class to create an index range of integral indices with a step size
  • class ObserverInterface class to derive an executor observer
  • class PartitionerBase class to derive a partitioner for scheduling parallel algorithms
  • class Pipe class to create a pipe object for a pipeline stage
  • class Pipeflow class to create a pipeflow object used by the pipe callable
  • class Pipeline class to create a pipeline scheduling framework
  • class RandomPartitioner class to construct a random partitioner for scheduling parallel algorithms
  • class Runtime class to include a runtime object in a task
  • class ScalablePipeline class to create a scalable pipeline object
  • class Semaphore class to create a semophore object for building a concurrency constraint
  • class SmallVector class to define a vector optimized for small array
  • class StaticPartitioner class to construct a static partitioner for scheduling parallel algorithms
  • class Subflow class to construct a subflow graph from the execution of a dynamic task
  • class Task class to create a task handle over a node in a taskflow graph
  • class Taskflow class to create a taskflow object
  • struct TaskParams task parameters to use when creating an asynchronous task
  • class TaskView class to access task information from the observer interface
  • class TFProfObserver class to create an observer based on the built-in taskflow profiler format
    • struct TaskSummary
    • struct WorkerSummary
  • class UnboundedTaskQueue class to create a lock-free unbounded work-stealing queue
  • class Worker class to create a worker in an executor
  • class WorkerInterface class to configure worker behavior in an executor
  • class WorkerView class to create an immutable view of a worker