|
template<typename T , typename ReduceOp > |
T | TiledArray::reduce_cuda_kernel_impl (ReduceOp &&op, const T *arg, std::size_t n, T init, cudaStream_t stream, int device_id) |
| T = reduce(T* arg) More...
|
|
template<typename T > |
T | TiledArray::product_reduce_cuda_kernel_impl (const T *arg, std::size_t n, cudaStream_t stream, int device_id) |
|
template<typename T > |
T | TiledArray::sum_reduce_cuda_kernel_impl (const T *arg, std::size_t n, cudaStream_t stream, int device_id) |
|
template<typename T > |
T | TiledArray::max_reduce_cuda_kernel_impl (const T *arg, std::size_t n, cudaStream_t stream, int device_id) |
|
template<typename T > |
T | TiledArray::min_reduce_cuda_kernel_impl (const T *arg, std::size_t n, cudaStream_t stream, int device_id) |
|
template<typename T > |
T | TiledArray::absmax_reduce_cuda_kernel_impl (const T *arg, std::size_t n, cudaStream_t stream, int device_id) |
|
template<typename T > |
T | TiledArray::absmin_reduce_cuda_kernel_impl (const T *arg, std::size_t n, cudaStream_t stream, int device_id) |
|