single precision
[Sparse BLAS]

Functions

magma_int_t magma_sgecsrmv (magma_trans_t transA, magma_int_t m, magma_int_t n, float alpha, float *d_val, magma_index_t *d_rowptr, magma_index_t *d_colind, float *d_x, float beta, float *d_y)
 This routine computes y = alpha * A * x + beta * y on the GPU.
magma_int_t magma_sgecsrmv_shift (magma_trans_t transA, magma_int_t m, magma_int_t n, float alpha, float lambda, float *d_val, magma_index_t *d_rowptr, magma_index_t *d_colind, float *d_x, float beta, int offset, int blocksize, magma_index_t *add_rows, float *d_y)
 This routine computes y = alpha * ( A -lambda I ) * x + beta * y on the GPU.
magma_int_t magma_sgeellmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t nnz_per_row, float alpha, float *d_val, magma_index_t *d_colind, float *d_x, float beta, float *d_y)
 This routine computes y = alpha * A * x + beta * y on the GPU.
magma_int_t magma_sgeellmv_shift (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t nnz_per_row, float alpha, float lambda, float *d_val, magma_index_t *d_colind, float *d_x, float beta, int offset, int blocksize, magma_index_t *add_rows, float *d_y)
 This routine computes y = alpha *( A - lambda I ) * x + beta * y on the GPU.
magma_int_t magma_sgeellrtmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t nnz_per_row, float alpha, float *d_val, magma_index_t *d_colind, magma_index_t *d_rowlength, float *d_x, float beta, float *d_y, magma_int_t alignment, magma_int_t blocksize)
 This routine computes y = alpha * A * x + beta * y on the GPU.
magma_int_t magma_sgeelltmv_shift (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t nnz_per_row, float alpha, float lambda, float *d_val, magma_index_t *d_colind, float *d_x, float beta, int offset, int blocksize, magma_index_t *add_rows, float *d_y)
 This routine computes y = alpha *( A - lambda I ) * x + beta * y on the GPU.
magma_int_t magma_sgesellpmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t blocksize, magma_int_t slices, magma_int_t alignment, float alpha, float *d_val, magma_index_t *d_colind, magma_index_t *d_rowptr, float *d_x, float beta, float *d_y)
 This routine computes y = alpha * A^t * x + beta * y on the GPU.
magma_int_t magma_sgesellcmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t blocksize, magma_int_t slices, magma_int_t alignment, float alpha, float *d_val, magma_index_t *d_colind, magma_index_t *d_rowptr, float *d_x, float beta, float *d_y)
 This routine computes y = alpha * A^t * x + beta * y on the GPU.
magma_int_t magma_smdotc (int n, int k, float *v, float *r, float *d1, float *d2, float *skp)
 Computes the scalar product of a set of vectors v_i such that.
magma_int_t magma_smgecsrmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t num_vecs, float alpha, float *d_val, magma_index_t *d_rowptr, magma_index_t *d_colind, float *d_x, float beta, float *d_y)
 This routine computes Y = alpha * A * X + beta * Y for X and Y sets of num_vec vectors on the GPU.
magma_int_t magma_smgeellmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t num_vecs, magma_int_t nnz_per_row, float alpha, float *d_val, magma_index_t *d_colind, float *d_x, float beta, float *d_y)
 This routine computes Y = alpha * A * X + beta * Y for X and Y sets of num_vec vectors on the GPU.
magma_int_t magma_smgeelltmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t num_vecs, magma_int_t nnz_per_row, float alpha, float *d_val, magma_index_t *d_colind, float *d_x, float beta, float *d_y)
 This routine computes Y = alpha * A * X + beta * Y for X and Y sets of num_vec vectors on the GPU.
magma_int_t magma_smgesellpmv (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, float alpha, float *d_val, magma_index_t *d_colind, magma_index_t *d_rowptr, float *d_x, float beta, float *d_y)
 This routine computes Y = alpha * A^t * X + beta * Y on the GPU.

Function Documentation

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

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

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

Parameters:
transA magma_trans_t transposition parameter for A
m magma_int_t number of rows in A
n magma_int_t number of columns in A
alpha float scalar multiplier
d_val float* array containing values of A in CSR
d_rowptr magma_int_t* rowpointer of A in CSR
d_colind magma_int_t* columnindices of A in CSR
d_x float* input vector x
beta float scalar multiplier
d_y float* input/output vector y
magma_int_t magma_sgecsrmv_shift ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
float  alpha,
float  lambda,
float *  d_val,
magma_index_t *  d_rowptr,
magma_index_t *  d_colind,
float *  d_x,
float  beta,
int  offset,
int  blocksize,
magma_index_t *  add_rows,
float *  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:
transA magma_trans_t transposition parameter for A
m magma_int_t number of rows in A
n magma_int_t number of columns in A
alpha float scalar multiplier
lambda float scalar multiplier
d_val float* array containing values of A in CSR
d_rowptr magma_int_t* rowpointer of A in CSR
d_colind magma_int_t* columnindices of A in CSR
d_x float* input vector x
beta float scalar multiplier
offset magma_int_t in case not the main diagonal is scaled
blocksize magma_int_t in case of processing multiple vectors
add_rows magma_int_t* in case the matrixpowerskernel is used
d_y float* output vector y
magma_int_t magma_sgeellmv ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  nnz_per_row,
float  alpha,
float *  d_val,
magma_index_t *  d_colind,
float *  d_x,
float  beta,
float *  d_y 
)

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

Input format is ELLPACK.

Parameters:
transA magma_trans_t transposition parameter for A
m magma_int_t number of rows in A
n magma_int_t number of columns in A
nnz_per_row magma_int_t number of elements in the longest row
alpha float scalar multiplier
d_val float* array containing values of A in ELLPACK
d_colind magma_int_t* columnindices of A in ELLPACK
d_x float* input vector x
beta float scalar multiplier
d_y float* input/output vector y
magma_int_t magma_sgeellmv_shift ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  nnz_per_row,
float  alpha,
float  lambda,
float *  d_val,
magma_index_t *  d_colind,
float *  d_x,
float  beta,
int  offset,
int  blocksize,
magma_index_t *  add_rows,
float *  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:
transA magma_trans_t transposition parameter for A
m magma_int_t number of rows in A
n magma_int_t number of columns in A
nnz_per_row magma_int_t number of elements in the longest row
alpha float scalar multiplier
lambda float scalar multiplier
d_val float* array containing values of A in ELLPACK
d_colind magma_int_t* columnindices of A in ELLPACK
d_x float* input vector x
beta float scalar multiplier
offset magma_int_t in case not the main diagonal is scaled
blocksize magma_int_t in case of processing multiple vectors
add_rows magma_int_t* in case the matrixpowerskernel is used
d_y float* input/output vector y
magma_int_t magma_sgeellrtmv ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  nnz_per_row,
float  alpha,
float *  d_val,
magma_index_t *  d_colind,
magma_index_t *  d_rowlength,
float *  d_x,
float  beta,
float *  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:
transA magma_trans_t transposition parameter for A
m magma_int_t number of rows
n magma_int_t number of columns
nnz_per_row magma_int_t max number of nonzeros in a row
alpha float scalar alpha
d_val float* val array
d_colind magma_int_t* col indices
d_rowlength magma_int_t* number of elements in each row
d_x float* input vector x
beta float scalar beta
d_y float* output vector y
blocksize magma_int_t threads per block
alignment magma_int_t threads assigned to each row
magma_int_t magma_sgeelltmv_shift ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  nnz_per_row,
float  alpha,
float  lambda,
float *  d_val,
magma_index_t *  d_colind,
float *  d_x,
float  beta,
int  offset,
int  blocksize,
magma_index_t *  add_rows,
float *  d_y 
)

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

Input format is ELL.

Parameters:
transA magma_trans_t transposition parameter for A
m magma_int_t number of rows in A
n magma_int_t number of columns in A
nnz_per_row magma_int_t number of elements in the longest row
alpha float scalar multiplier
lambda float scalar multiplier
d_val float* array containing values of A in ELL
d_colind magma_int_t* columnindices of A in ELL
d_x float* input vector x
beta float scalar multiplier
offset magma_int_t in case not the main diagonal is scaled
blocksize magma_int_t in case of processing multiple vectors
add_rows magma_int_t* in case the matrixpowerskernel is used
d_y float* input/output vector y
magma_int_t magma_sgesellcmv ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  blocksize,
magma_int_t  slices,
magma_int_t  alignment,
float  alpha,
float *  d_val,
magma_index_t *  d_colind,
magma_index_t *  d_rowptr,
float *  d_x,
float  beta,
float *  d_y 
)

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

Input format is SELLC/SELLP.

Parameters:
transA magma_trans_t transposition parameter for A
m magma_int_t number of rows in A
n magma_int_t number of columns in A
blocksize magma_int_t number of rows in one ELL-slice
slices magma_int_t number of slices in matrix
alignment magma_int_t number of threads assigned to one row (=1)
alpha float scalar multiplier
d_val float* array containing values of A in SELLC/P
d_colind magma_int_t* columnindices of A in SELLC/P
d_rowptr magma_int_t* rowpointer of SELLP
d_x float* input vector x
beta float scalar multiplier
d_y float* input/output vector y
magma_int_t magma_sgesellpmv ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  blocksize,
magma_int_t  slices,
magma_int_t  alignment,
float  alpha,
float *  d_val,
magma_index_t *  d_colind,
magma_index_t *  d_rowptr,
float *  d_x,
float  beta,
float *  d_y 
)

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

Input format is SELLP.

Parameters:
transA magma_trans_t transposition parameter for A
m magma_int_t number of rows in A
n magma_int_t number of columns in A
blocksize magma_int_t number of rows in one ELL-slice
slices magma_int_t number of slices in matrix
alignment magma_int_t number of threads assigned to one row
alpha float scalar multiplier
d_val float* array containing values of A in SELLP
d_colind magma_int_t* columnindices of A in SELLP
d_rowptr magma_int_t* rowpointer of SELLP
d_x float* input vector x
beta float scalar multiplier
d_y float* input/output vector y
magma_int_t magma_smdotc ( int  n,
int  k,
float *  v,
float *  r,
float *  d1,
float *  d2,
float *  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:
n int length of v_i and r
k int # vectors v_i
v float* v = (v_0 .. v_i.. v_k)
r float* r
d1 float* workspace
d2 float* workspace
skp float* vector[k] of scalar products (<v_i,r>...)
magma_int_t magma_smgecsrmv ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  num_vecs,
float  alpha,
float *  d_val,
magma_index_t *  d_rowptr,
magma_index_t *  d_colind,
float *  d_x,
float  beta,
float *  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:
transA magma_trans_t transposition parameter for A
m magma_int_t number of rows in A
n magma_int_t number of columns in A
num_vecs mama_int_t number of vectors
alpha float scalar multiplier
d_val float* array containing values of A in CSR
d_rowptr magma_int_t* rowpointer of A in CSR
d_colind magma_int_t* columnindices of A in CSR
d_x float* input vector x
beta float scalar multiplier
d_y float* input/output vector y
magma_int_t magma_smgeellmv ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  num_vecs,
magma_int_t  nnz_per_row,
float  alpha,
float *  d_val,
magma_index_t *  d_colind,
float *  d_x,
float  beta,
float *  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:
transA magma_trans_t transposition parameter for A
m magma_int_t number of rows in A
n magma_int_t number of columns in A
num_vecs mama_int_t number of vectors
nnz_per_row magma_int_t number of elements in the longest row
alpha float scalar multiplier
d_val float* array containing values of A in ELLPACK
d_colind magma_int_t* columnindices of A in ELLPACK
d_x float* input vector x
beta float scalar multiplier
d_y float* input/output vector y
magma_int_t magma_smgeelltmv ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  num_vecs,
magma_int_t  nnz_per_row,
float  alpha,
float *  d_val,
magma_index_t *  d_colind,
float *  d_x,
float  beta,
float *  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:
transA magma_trans_t transposition parameter for A
m magma_int_t number of rows in A
n magma_int_t number of columns in A
num_vecs mama_int_t number of vectors
nnz_per_row magma_int_t number of elements in the longest row
alpha float scalar multiplier
d_val float* array containing values of A in ELL
d_colind magma_int_t* columnindices of A in ELL
d_x float* input vector x
beta float scalar multiplier
d_y float* input/output vector y
magma_int_t magma_smgesellpmv ( 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,
float  alpha,
float *  d_val,
magma_index_t *  d_colind,
magma_index_t *  d_rowptr,
float *  d_x,
float  beta,
float *  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:
transA magma_trans_t transpose A?
m magma_int_t number of rows in A
n magma_int_t number of columns in A
num_vecs magma_int_t number of columns in X and Y
blocksize magma_int_t number of rows in one ELL-slice
slices magma_int_t number of slices in matrix
alignment magma_int_t number of threads assigned to one row
alpha float scalar multiplier
d_val float* array containing values of A in SELLP
d_colind magma_int_t* columnindices of A in SELLP
d_rowptr magma_int_t* rowpointer of SELLP
d_x float* input vector x
beta float scalar multiplier
d_y float* input/output vector y

Generated on 17 Sep 2014 for MAGMA by  doxygen 1.6.1