![]() |
imate
C++/CUDA Reference
|
#include "./cublas_impl_kernels.h"#include <cuda_runtime.h>#include "../_cu_definitions/cu_types.h"#include "./atomic_add.h"#include "../_cu_arithmetics/cu_arithmetics.h"Go to the source code of this file.
Namespaces | |
| namespace | cublas_impl_kernels |
| Templated kernel code for implenentations of several BLAS-type functions in CUDA. | |
Functions | |
| template<typename DataType , typename ComputeType , unsigned int block_size> | |
| __global__ void | cublas_impl_kernels::cublasTgemv_kernel (const bool trans, const int m, const int n, const DataType alpha, const DataType *RESTRICT A, const int lda, const DataType *RESTRICT x, const int incx, const DataType beta, DataType *RESTRICT y, const int incy) |
| Performs the operation \( \boldsymbol{y} = \alpha
\mathbf{A} \boldsymbol{x} + \beta \boldsymbol{y} \). | |
| template<typename DataType > | |
| __global__ void | cublas_impl_kernels::cublasTcopy_kernel (const int n, const DataType *RESTRICT x, const int incx, DataType *RESTRICT y, const int incy) |
| Performs \( \boldsymbol{y} = \boldsymbol{x} \). | |
| template<typename DataType > | |
| __global__ void | cublas_impl_kernels::cublasTaxpy_kernel (const int n, const DataType alpha, const DataType *RESTRICT x, const int incx, DataType *RESTRICT y, const int incy) |
| Performs \( \boldsymbol{y} = \alpha \boldsymbol{x} +
\boldsymbol{y} \). | |
| template<typename DataType , typename ComputeType , unsigned int block_size> | |
| __global__ void | cublas_impl_kernels::cublasTdot_kernel (const int n, const DataType *RESTRICT x, const int incx, const DataType *RESTRICT y, const int incy, ComputeType *RESTRICT result) |
| Computes \( a = \boldsymbol{x} \cdot \boldsymbol{y} \). | |
| template<typename DataType , typename ComputeType , unsigned int block_size> | |
| __global__ void | cublas_impl_kernels::cublasTnrm2_kernel (const int n, const DataType *RESTRICT x, const int incx, ComputeType *RESTRICT result) |
| Computes \( a = \boldsymbol{x} \cdot \boldsymbol{x} \). | |
| template<typename DataType > | |
| __global__ void | cublas_impl_kernels::cublasTscal_kernel (const int n, const DataType alpha, DataType *RESTRICT x, const int incx) |
| Performs \( \boldsymbol{x} = \alpha \boldsymbol{x}
\). | |