tbb_cuda_scheduler.hpp File Reference

Unified oneTBB scheduler for host and multi-device CUDA tasks. More...

#include "cuda_task.hpp"
#include "task_registry.hpp"
#include "tbb_scheduler.hpp"
#include "tbb_task_submission.hpp"
#include <cuda_runtime_api.h>
#include <oneapi/tbb/task_arena.h>
#include <oneapi/tbb/task_group.h>
#include <oneapi/tbb/task_scheduler_observer.h>
#include <uni20/backend/cuda/cuda_error.hpp>
#include <uni20/backend/cuda/device.hpp>
#include <uni20/backend/cuda/runtime.hpp>
#include <uni20/config.hpp>
#include <algorithm>
#include <memory>
#include <optional>
#include <utility>
#include <vector>

Include dependency graph for tbb_cuda_scheduler.hpp:

Go to the source code of this file.

Classes
class	uni20::async::TbbCudaScheduler
	Unified oneTBB scheduler with one host arena and one arena per CUDA device. More...
struct	uni20::async::TbbCudaSchedulerOptions
	Arena configuration for the unified host/CUDA TBB scheduler. More...

Namespaces
namespace	uni20
namespace	uni20::async
	This represents the reverse-mode adjoint for functions of complex variables, assuming a real-valued scalar loss function ( L \colon \mathbb{C} \to \mathbb{R} ).

Detailed Description

Unified oneTBB scheduler for host and multi-device CUDA tasks.