|
Uni20
Asynchronous tensor and runtime library.
|
Functions | |
| template<std::size_t OperandCount, std::size_t MaximumRank> | |
| auto | make_contiguous_plan (std::size_t size) -> detail::cuda_reference::LoweredStridedElementwisePlan< OperandCount, MaximumRank > |
| template<class... Accesses> | |
| void | publish (cuda::Stream const &stream, Accesses &... accesses) |
| auto uni20::linalg::partitioned_buffer_detail::make_contiguous_plan | ( | std::size_t | size | ) | -> detail::cuda_reference::LoweredStridedElementwisePlan<OperandCount, MaximumRank> |
| void uni20::linalg::partitioned_buffer_detail::publish | ( | cuda::Stream const & | stream, |
| Accesses &... | accesses | ||
| ) |