|
Uni20
Asynchronous tensor and runtime library.
|
Non-blocking CUDA-task acquisition of cuBLAS execution resources. More...
#include <uni20/async/cuda_task.hpp>#include <uni20/backend/cublas/execution.hpp>#include <uni20/backend/cuda/cuda_error.hpp>#include <atomic>#include <optional>Go to the source code of this file.
Classes | |
| class | uni20::cublas::ExecutionAcquireAwaiter |
| Awaiter that reserves a cuBLAS handle before waiting for an idle stream. More... | |
Namespaces | |
| namespace | uni20 |
| namespace | uni20::cublas |
Functions | |
| ExecutionAcquireAwaiter | uni20::cublas::acquire_execution (ExecutionPool &pool) noexcept |
| Acquire a cuBLAS handle and idle stream without blocking a CUDA task. | |
Non-blocking CUDA-task acquisition of cuBLAS execution resources.