gemm_internal.h File Reference

#include "cblas.h"
#include "tensor/tensor.h"

Include dependency graph for gemm_internal.h:

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

Go to the source code of this file.

Functions
template<typename T >
bool	magmadnn::internal::gemm_check (Tensor< T > *A, Tensor< T > *B, Tensor< T > *C, unsigned int &M, unsigned int &N, unsigned int &K)
template<typename T >
void	magmadnn::internal::gemm_full (T alpha, Tensor< T > *A, Tensor< T > *B, T beta, Tensor< T > *C)

Detailed Description

Author

Daniel Nichols

Version

1.0

Date

2019-02-22

Copyright

Copyright (c) 2019

Function Documentation

gemm_check()

template<typename T >

bool magmadnn::internal::gemm_check	(	Tensor< T > *	A,
		Tensor< T > *	B,
		Tensor< T > *	C,
		unsigned int &	M,
		unsigned int &	N,
		unsigned int &	K
	)

Returns true if A, B, C are valid parameters for gemm_full. It also sets M, N, K to A.get_shape(0), B.get_shape(1), and A.get_shape(1), respectively.

Template Parameters

T

Parameters

A
B
C
M
N
K

Returns

true

false

Here is the call graph for this function:

Here is the caller graph for this function:

gemm_full()

template<typename T >

void magmadnn::internal::gemm_full	(	T	alpha,
		Tensor< T > *	A,
		Tensor< T > *	B,
		T	beta,
		Tensor< T > *	C
	)

Computes the matrix product C = alpha*(AB) + beta*C

Template Parameters

T

Parameters

alpha
A
B
beta
C