AccelBLAS_CUDA.hpp File Reference

Include dependency graph for AccelBLAS_CUDA.hpp:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Classes
class	BLASHandle< PlatformKind::CUDA >

Namespaces
	qmcplusplus
	helper functions for EinsplineSetBuilder
	qmcplusplus::compute
	qmcplusplus::compute::BLAS

Macros
#define	castNativeType   castCUDAType

Functions
void	gemm (BLASHandle< PlatformKind::CUDA > &handle, const char transa, const char transb, int m, int n, int k, const float &alpha, const float *A, int lda, const float *B, int ldb, const float &beta, float *C, int ldc)
void	gemm (BLASHandle< PlatformKind::CUDA > &handle, const char transa, const char transb, int m, int n, int k, const double &alpha, const double *A, int lda, const double *B, int ldb, const double &beta, double *C, int ldc)
void	gemm (BLASHandle< PlatformKind::CUDA > &handle, const char transa, const char transb, int m, int n, int k, const std::complex< float > &alpha, const std::complex< float > *A, int lda, const std::complex< float > *B, int ldb, const std::complex< float > &beta, std::complex< float > *C, int ldc)
void	gemm (BLASHandle< PlatformKind::CUDA > &handle, const char transa, const char transb, int m, int n, int k, const std::complex< double > &alpha, const std::complex< double > *A, int lda, const std::complex< double > *B, int ldb, const std::complex< double > &beta, std::complex< double > *C, int ldc)
void	gemv (BLASHandle< PlatformKind::CUDA > &handle, const char trans, const int m, const int n, const float &alpha, const float *const A, const int lda, const float *const x, const int incx, const float &beta, float *const y, const int incy)
void	gemv (BLASHandle< PlatformKind::CUDA > &handle, const char trans, const int m, const int n, const double &alpha, const double *const A, const int lda, const double *const x, const int incx, const double &beta, double *const y, const int incy)
void	gemv (BLASHandle< PlatformKind::CUDA > &handle, const char trans, const int m, const int n, const std::complex< float > &alpha, const std::complex< float > *A, const int lda, const std::complex< float > *x, const int incx, const std::complex< float > &beta, std::complex< float > *y, const int incy)
void	gemv (BLASHandle< PlatformKind::CUDA > &handle, const char trans, const int m, const int n, const std::complex< double > &alpha, const std::complex< double > *A, const int lda, const std::complex< double > *x, const int incx, const std::complex< double > &beta, std::complex< double > *y, const int incy)
template<typename T >
void	gemv_batched (BLASHandle< PlatformKind::CUDA > &handle, const char trans, const int m, const int n, const T *alpha, const T *const A[], const int lda, const T *const x[], const int incx, const T *beta, T *const y[], const int incy, const int batch_count)
void	ger (BLASHandle< PlatformKind::CUDA > &handle, const int m, const int n, const float &alpha, const float *const x, const int incx, const float *const y, const int incy, float *const A, const int lda)
void	ger (BLASHandle< PlatformKind::CUDA > &handle, const int m, const int n, const double &alpha, const double *const x, const int incx, const double *const y, const int incy, double *const A, const int lda)
void	ger (BLASHandle< PlatformKind::CUDA > &handle, const int m, const int n, const std::complex< float > &alpha, const std::complex< float > *x, const int incx, const std::complex< float > *y, const int incy, std::complex< float > *A, const int lda)
void	ger (BLASHandle< PlatformKind::CUDA > &handle, const int m, const int n, const std::complex< double > &alpha, const std::complex< double > *x, const int incx, const std::complex< double > *y, const int incy, std::complex< double > *A, const int lda)
template<typename T >
void	ger_batched (BLASHandle< PlatformKind::CUDA > &handle, const int m, const int n, const T *alpha, const T *const x[], const int incx, const T *const y[], const int incy, T *const A[], const int lda, const int batch_count)
template<typename T >
void	copy_batched (BLASHandle< PlatformKind::CUDA > &handle, const int n, const T *const in[], const int incx, T *const out[], const int incy, const int batch_count)
void	gemm_batched (BLASHandle< PlatformKind::CUDA > &handle, const char transa, const char transb, int m, int n, int k, const float &alpha, const float *const A[], int lda, const float *const B[], int ldb, const float &beta, float *const C[], int ldc, int batchCount)
void	gemm_batched (BLASHandle< PlatformKind::CUDA > &handle, const char transa, const char transb, int m, int n, int k, const std::complex< float > &alpha, const std::complex< float > *const A[], int lda, const std::complex< float > *const B[], int ldb, const std::complex< float > &beta, std::complex< float > *const C[], int ldc, int batchCount)
void	gemm_batched (BLASHandle< PlatformKind::CUDA > &handle, const char transa, const char transb, int m, int n, int k, const double &alpha, const double *const A[], int lda, const double *const B[], int ldb, const double &beta, double *const C[], int ldc, int batchCount)
void	gemm_batched (BLASHandle< PlatformKind::CUDA > &handle, const char transa, const char transb, int m, int n, int k, const std::complex< double > &alpha, const std::complex< double > *const A[], int lda, const std::complex< double > *const B[], int ldb, const std::complex< double > &beta, std::complex< double > *const C[], int ldc, int batchCount)

Macro Definition Documentation

castNativeType

#define castNativeType   castCUDAType

Definition at line 20 of file AccelBLAS_CUDA.hpp.

Referenced by qmcplusplus::compute::BLAS::gemm(), qmcplusplus::compute::BLAS::gemm_batched(), qmcplusplus::compute::BLAS::gemv(), and qmcplusplus::compute::BLAS::ger().