distributed memory (MPI) routines

Functions
int	TrMatVecProd_Naive (Mat *A, double *y, double *x, int pflag)

---

Detailed Description

These are distributed-memory routines.

Note that if the MPI flag is not set on the compilation stage, most of the routines listed here will run sequentially unless explicitly stated to the contrary in their description.

---

Function Documentation

int TrMatVecProd_Naive	(	Mat *	A,
		double *	y,
		double *	x,
		int	pflag
	)

Perform transposed matrix-vector multiplication, . This naive version does not require a precomputed communication structure. But communication volumes may be significant. Consequently in most of the cases is not optimized.

Warning:

[MPI ONLY!] this function does not exist in Midapack sequential version

See also:

TrMatVecProd MatLocalShape

Parameters:

mat	pointer
y	local input vector (distributed)
x	local output vector (overlapped)

Definition at line 380 of file mapmat.c.