MAGMA  1.5.0
Matrix Algebra for GPU and Multicore Architectures
 All Functions Groups
double precision

Functions

magma_int_t magma_dgecsrmv (magma_trans_t transA, magma_int_t m, magma_int_t n, double alpha, double *d_val, magma_index_t *d_rowptr, magma_index_t *d_colind, double *d_x, double beta, double *d_y)
 This routine computes y = alpha * A * x + beta * y on the GPU. More...
 
magma_int_t magma_dgecsrmv_shift (magma_trans_t transA, magma_int_t m, magma_int_t n, double alpha, double lambda, double *d_val, magma_index_t *d_rowptr, magma_index_t *d_colind, double *d_x, double beta, int offset, int blocksize, magma_index_t *add_rows, double *d_y)
 This routine computes y = alpha * ( A -lambda I ) * x + beta * y on the GPU. More...
 
magma_int_t magma_dgeellmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t nnz_per_row, double alpha, double *d_val, magma_index_t *d_colind, double *d_x, double beta, double *d_y)
 This routine computes y = alpha * A * x + beta * y on the GPU. More...
 
magma_int_t magma_dgeellmv_shift (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t nnz_per_row, double alpha, double lambda, double *d_val, magma_index_t *d_colind, double *d_x, double beta, int offset, int blocksize, magma_index_t *add_rows, double *d_y)
 This routine computes y = alpha *( A - lambda I ) * x + beta * y on the GPU. More...
 
magma_int_t magma_dgeellrtmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t nnz_per_row, double alpha, double *d_val, magma_index_t *d_colind, magma_index_t *d_rowlength, double *d_x, double beta, double *d_y, magma_int_t alignment, magma_int_t blocksize)
 This routine computes y = alpha * A * x + beta * y on the GPU. More...
 
magma_int_t magma_dgeelltmv_shift (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t nnz_per_row, double alpha, double lambda, double *d_val, magma_index_t *d_colind, double *d_x, double beta, int offset, int blocksize, magma_index_t *add_rows, double *d_y)
 This routine computes y = alpha *( A - lambda I ) * x + beta * y on the GPU. More...
 
magma_int_t magma_dgesellpmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t blocksize, magma_int_t slices, magma_int_t alignment, double alpha, double *d_val, magma_index_t *d_colind, magma_index_t *d_rowptr, double *d_x, double beta, double *d_y)
 This routine computes y = alpha * A^t * x + beta * y on the GPU. More...
 
magma_int_t magma_dgesellcmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t blocksize, magma_int_t slices, magma_int_t alignment, double alpha, double *d_val, magma_index_t *d_colind, magma_index_t *d_rowptr, double *d_x, double beta, double *d_y)
 This routine computes y = alpha * A^t * x + beta * y on the GPU. More...
 
magma_int_t magma_dmdotc (int n, int k, double *v, double *r, double *d1, double *d2, double *skp)
 Computes the scalar product of a set of vectors v_i such that. More...
 
magma_int_t magma_dmgecsrmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t num_vecs, double alpha, double *d_val, magma_index_t *d_rowptr, magma_index_t *d_colind, double *d_x, double beta, double *d_y)
 This routine computes Y = alpha * A * X + beta * Y for X and Y sets of num_vec vectors on the GPU. More...
 
magma_int_t magma_dmgeellmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t num_vecs, magma_int_t nnz_per_row, double alpha, double *d_val, magma_index_t *d_colind, double *d_x, double beta, double *d_y)
 This routine computes Y = alpha * A * X + beta * Y for X and Y sets of num_vec vectors on the GPU. More...
 
magma_int_t magma_dmgeelltmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t num_vecs, magma_int_t nnz_per_row, double alpha, double *d_val, magma_index_t *d_colind, double *d_x, double beta, double *d_y)
 This routine computes Y = alpha * A * X + beta * Y for X and Y sets of num_vec vectors on the GPU. More...
 
magma_int_t magma_dmgesellpmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t num_vecs, magma_int_t blocksize, magma_int_t slices, magma_int_t alignment, double alpha, double *d_val, magma_index_t *d_colind, magma_index_t *d_rowptr, double *d_x, double beta, double *d_y)
 This routine computes Y = alpha * A^t * X + beta * Y on the GPU. More...
 

Detailed Description

Function Documentation

magma_int_t magma_dgecsrmv ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
double  alpha,
double *  d_val,
magma_index_t *  d_rowptr,
magma_index_t *  d_colind,
double *  d_x,
double  beta,
double *  d_y 
)

This routine computes y = alpha * A * x + beta * y on the GPU.

The input format is CSR (val, row, col).

Parameters
transAmagma_trans_t transposition parameter for A
mmagma_int_t number of rows in A
nmagma_int_t number of columns in A
alphadouble scalar multiplier
d_valdouble* array containing values of A in CSR
d_rowptrmagma_int_t* rowpointer of A in CSR
d_colindmagma_int_t* columnindices of A in CSR
d_xdouble* input vector x
betadouble scalar multiplier
d_ydouble* input/output vector y
magma_int_t magma_dgecsrmv_shift ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
double  alpha,
double  lambda,
double *  d_val,
magma_index_t *  d_rowptr,
magma_index_t *  d_colind,
double *  d_x,
double  beta,
int  offset,
int  blocksize,
magma_index_t *  add_rows,
double *  d_y 
)

This routine computes y = alpha * ( A -lambda I ) * x + beta * y on the GPU.

It is a shifted version of the CSR-SpMV.

Parameters
transAmagma_trans_t transposition parameter for A
mmagma_int_t number of rows in A
nmagma_int_t number of columns in A
alphadouble scalar multiplier
lambdadouble scalar multiplier
d_valdouble* array containing values of A in CSR
d_rowptrmagma_int_t* rowpointer of A in CSR
d_colindmagma_int_t* columnindices of A in CSR
d_xdouble* input vector x
betadouble scalar multiplier
offsetmagma_int_t in case not the main diagonal is scaled
blocksizemagma_int_t in case of processing multiple vectors
add_rowsmagma_int_t* in case the matrixpowerskernel is used
d_ydouble* output vector y
magma_int_t magma_dgeellmv ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  nnz_per_row,
double  alpha,
double *  d_val,
magma_index_t *  d_colind,
double *  d_x,
double  beta,
double *  d_y 
)

This routine computes y = alpha * A * x + beta * y on the GPU.

Input format is ELLPACK.

Parameters
transAmagma_trans_t transposition parameter for A
mmagma_int_t number of rows in A
nmagma_int_t number of columns in A
nnz_per_rowmagma_int_t number of elements in the longest row
alphadouble scalar multiplier
d_valdouble* array containing values of A in ELLPACK
d_colindmagma_int_t* columnindices of A in ELLPACK
d_xdouble* input vector x
betadouble scalar multiplier
d_ydouble* input/output vector y
magma_int_t magma_dgeellmv_shift ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  nnz_per_row,
double  alpha,
double  lambda,
double *  d_val,
magma_index_t *  d_colind,
double *  d_x,
double  beta,
int  offset,
int  blocksize,
magma_index_t *  add_rows,
double *  d_y 
)

This routine computes y = alpha *( A - lambda I ) * x + beta * y on the GPU.

Input format is ELLPACK. It is the shifted version of the ELLPACK SpMV.

Parameters
transAmagma_trans_t transposition parameter for A
mmagma_int_t number of rows in A
nmagma_int_t number of columns in A
nnz_per_rowmagma_int_t number of elements in the longest row
alphadouble scalar multiplier
lambdadouble scalar multiplier
d_valdouble* array containing values of A in ELLPACK
d_colindmagma_int_t* columnindices of A in ELLPACK
d_xdouble* input vector x
betadouble scalar multiplier
offsetmagma_int_t in case not the main diagonal is scaled
blocksizemagma_int_t in case of processing multiple vectors
add_rowsmagma_int_t* in case the matrixpowerskernel is used
d_ydouble* input/output vector y
magma_int_t magma_dgeellrtmv ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  nnz_per_row,
double  alpha,
double *  d_val,
magma_index_t *  d_colind,
magma_index_t *  d_rowlength,
double *  d_x,
double  beta,
double *  d_y,
magma_int_t  alignment,
magma_int_t  blocksize 
)

This routine computes y = alpha * A * x + beta * y on the GPU.

Input format is ELLRT. The ideas are taken from "Improving the performance of the sparse matrix vector product with GPUs", (CIT 2010), and modified to provide correct values.

Parameters
transAmagma_trans_t transposition parameter for A
mmagma_int_t number of rows
nmagma_int_t number of columns
nnz_per_rowmagma_int_t max number of nonzeros in a row
alphadouble scalar alpha
d_valdouble* val array
d_colindmagma_int_t* col indices
d_rowlengthmagma_int_t* number of elements in each row
d_xdouble* input vector x
betadouble scalar beta
d_ydouble* output vector y
blocksizemagma_int_t threads per block
alignmentmagma_int_t threads assigned to each row
magma_int_t magma_dgeelltmv_shift ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  nnz_per_row,
double  alpha,
double  lambda,
double *  d_val,
magma_index_t *  d_colind,
double *  d_x,
double  beta,
int  offset,
int  blocksize,
magma_index_t *  add_rows,
double *  d_y 
)

This routine computes y = alpha *( A - lambda I ) * x + beta * y on the GPU.

Input format is ELL.

Parameters
transAmagma_trans_t transposition parameter for A
mmagma_int_t number of rows in A
nmagma_int_t number of columns in A
nnz_per_rowmagma_int_t number of elements in the longest row
alphadouble scalar multiplier
lambdadouble scalar multiplier
d_valdouble* array containing values of A in ELL
d_colindmagma_int_t* columnindices of A in ELL
d_xdouble* input vector x
betadouble scalar multiplier
offsetmagma_int_t in case not the main diagonal is scaled
blocksizemagma_int_t in case of processing multiple vectors
add_rowsmagma_int_t* in case the matrixpowerskernel is used
d_ydouble* input/output vector y
magma_int_t magma_dgesellcmv ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  blocksize,
magma_int_t  slices,
magma_int_t  alignment,
double  alpha,
double *  d_val,
magma_index_t *  d_colind,
magma_index_t *  d_rowptr,
double *  d_x,
double  beta,
double *  d_y 
)

This routine computes y = alpha * A^t * x + beta * y on the GPU.

Input format is SELLC/SELLP.

Parameters
transAmagma_trans_t transposition parameter for A
mmagma_int_t number of rows in A
nmagma_int_t number of columns in A
blocksizemagma_int_t number of rows in one ELL-slice
slicesmagma_int_t number of slices in matrix
alignmentmagma_int_t number of threads assigned to one row (=1)
alphadouble scalar multiplier
d_valdouble* array containing values of A in SELLC/P
d_colindmagma_int_t* columnindices of A in SELLC/P
d_rowptrmagma_int_t* rowpointer of SELLP
d_xdouble* input vector x
betadouble scalar multiplier
d_ydouble* input/output vector y
magma_int_t magma_dgesellpmv ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  blocksize,
magma_int_t  slices,
magma_int_t  alignment,
double  alpha,
double *  d_val,
magma_index_t *  d_colind,
magma_index_t *  d_rowptr,
double *  d_x,
double  beta,
double *  d_y 
)

This routine computes y = alpha * A^t * x + beta * y on the GPU.

Input format is SELLP.

Parameters
transAmagma_trans_t transposition parameter for A
mmagma_int_t number of rows in A
nmagma_int_t number of columns in A
blocksizemagma_int_t number of rows in one ELL-slice
slicesmagma_int_t number of slices in matrix
alignmentmagma_int_t number of threads assigned to one row
alphadouble scalar multiplier
d_valdouble* array containing values of A in SELLP
d_colindmagma_int_t* columnindices of A in SELLP
d_rowptrmagma_int_t* rowpointer of SELLP
d_xdouble* input vector x
betadouble scalar multiplier
d_ydouble* input/output vector y
magma_int_t magma_dmdotc ( int  n,
int  k,
double *  v,
double *  r,
double *  d1,
double *  d2,
double *  skp 
)

Computes the scalar product of a set of vectors v_i such that.

skp = ( <v_0,r>, <v_1,r>, .. )

Returns the vector skp.

Parameters
nint length of v_i and r
kint

vectors v_i

Parameters
vdouble* v = (v_0 .. v_i.. v_k)
rdouble* r
d1double* workspace
d2double* workspace
skpdouble* vector[k] of scalar products (<v_i,r>...)
magma_int_t magma_dmgecsrmv ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  num_vecs,
double  alpha,
double *  d_val,
magma_index_t *  d_rowptr,
magma_index_t *  d_colind,
double *  d_x,
double  beta,
double *  d_y 
)

This routine computes Y = alpha * A * X + beta * Y for X and Y sets of num_vec vectors on the GPU.

Input format is CSR.

Parameters
transAmagma_trans_t transposition parameter for A
mmagma_int_t number of rows in A
nmagma_int_t number of columns in A
num_vecsmama_int_t number of vectors
alphadouble scalar multiplier
d_valdouble* array containing values of A in CSR
d_rowptrmagma_int_t* rowpointer of A in CSR
d_colindmagma_int_t* columnindices of A in CSR
d_xdouble* input vector x
betadouble scalar multiplier
d_ydouble* input/output vector y
magma_int_t magma_dmgeellmv ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  num_vecs,
magma_int_t  nnz_per_row,
double  alpha,
double *  d_val,
magma_index_t *  d_colind,
double *  d_x,
double  beta,
double *  d_y 
)

This routine computes Y = alpha * A * X + beta * Y for X and Y sets of num_vec vectors on the GPU.

Input format is ELLPACK.

Parameters
transAmagma_trans_t transposition parameter for A
mmagma_int_t number of rows in A
nmagma_int_t number of columns in A
num_vecsmama_int_t number of vectors
nnz_per_rowmagma_int_t number of elements in the longest row
alphadouble scalar multiplier
d_valdouble* array containing values of A in ELLPACK
d_colindmagma_int_t* columnindices of A in ELLPACK
d_xdouble* input vector x
betadouble scalar multiplier
d_ydouble* input/output vector y
magma_int_t magma_dmgeelltmv ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  num_vecs,
magma_int_t  nnz_per_row,
double  alpha,
double *  d_val,
magma_index_t *  d_colind,
double *  d_x,
double  beta,
double *  d_y 
)

This routine computes Y = alpha * A * X + beta * Y for X and Y sets of num_vec vectors on the GPU.

Input format is ELL.

Parameters
transAmagma_trans_t transposition parameter for A
mmagma_int_t number of rows in A
nmagma_int_t number of columns in A
num_vecsmama_int_t number of vectors
nnz_per_rowmagma_int_t number of elements in the longest row
alphadouble scalar multiplier
d_valdouble* array containing values of A in ELL
d_colindmagma_int_t* columnindices of A in ELL
d_xdouble* input vector x
betadouble scalar multiplier
d_ydouble* input/output vector y
magma_int_t magma_dmgesellpmv ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  num_vecs,
magma_int_t  blocksize,
magma_int_t  slices,
magma_int_t  alignment,
double  alpha,
double *  d_val,
magma_index_t *  d_colind,
magma_index_t *  d_rowptr,
double *  d_x,
double  beta,
double *  d_y 
)

This routine computes Y = alpha * A^t * X + beta * Y on the GPU.

Input format is SELLP. Note, that the input format for X is row-major while the output format for Y is column major!

Parameters
transAmagma_trans_t transpose A?
mmagma_int_t number of rows in A
nmagma_int_t number of columns in A
num_vecsmagma_int_t number of columns in X and Y
blocksizemagma_int_t number of rows in one ELL-slice
slicesmagma_int_t number of slices in matrix
alignmentmagma_int_t number of threads assigned to one row
alphadouble scalar multiplier
d_valdouble* array containing values of A in SELLP
d_colindmagma_int_t* columnindices of A in SELLP
d_rowptrmagma_int_t* rowpointer of SELLP
d_xdouble* input vector x
betadouble scalar multiplier
d_ydouble* input/output vector y