single-complex precision
[Sparse BLAS]

Functions

magma_int_t magma_ccuspaxpy (magmaFloatComplex *alpha, magma_c_matrix A, magmaFloatComplex *beta, magma_c_matrix B, magma_c_matrix *AB, magma_queue_t queue)
 This is an interface to the cuSPARSE routine csrgeam computing the sum of two sparse matrices stored in csr format:.
magma_int_t magma_ccuspmm (magma_c_matrix A, magma_c_matrix B, magma_c_matrix *AB, magma_queue_t queue)
 This is an interface to the cuSPARSE routine csrmm computing the product of two sparse matrices stored in csr format.
magma_int_t magma_ccustomspmv (magmaFloatComplex alpha, magma_c_matrix x, magmaFloatComplex beta, magma_c_matrix y, magma_queue_t queue)
 This is an interface to any custom sparse matrix vector product.
magma_int_t magma_cgecsrmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magmaFloatComplex alpha, magmaFloatComplex_ptr dval, magmaIndex_ptr drowptr, magmaIndex_ptr dcolind, magmaFloatComplex_ptr dx, magmaFloatComplex beta, magmaFloatComplex_ptr dy, magma_queue_t queue)
 This routine computes y = alpha * A * x + beta * y on the GPU.
magma_int_t magma_cgecsrmv_shift (magma_trans_t transA, magma_int_t m, magma_int_t n, magmaFloatComplex alpha, magmaFloatComplex lambda, magmaFloatComplex_ptr dval, magmaIndex_ptr drowptr, magmaIndex_ptr dcolind, magmaFloatComplex_ptr dx, magmaFloatComplex beta, int offset, int blocksize, magma_index_t *addrows, magmaFloatComplex_ptr dy, magma_queue_t queue)
 This routine computes y = alpha * ( A -lambda I ) * x + beta * y on the GPU.
magma_int_t magma_cgeellmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t nnz_per_row, magmaFloatComplex alpha, magmaFloatComplex_ptr dval, magmaIndex_ptr dcolind, magmaFloatComplex_ptr dx, magmaFloatComplex beta, magmaFloatComplex_ptr dy, magma_queue_t queue)
 This routine computes y = alpha * A * x + beta * y on the GPU.
magma_int_t magma_cgeellmv_shift (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t nnz_per_row, magmaFloatComplex alpha, magmaFloatComplex lambda, magmaFloatComplex_ptr dval, magmaIndex_ptr dcolind, magmaFloatComplex_ptr dx, magmaFloatComplex beta, int offset, int blocksize, magmaIndex_ptr addrows, magmaFloatComplex_ptr dy, magma_queue_t queue)
 This routine computes y = alpha *( A - lambda I ) * x + beta * y on the GPU.
magma_int_t magma_cgeellrtmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t nnz_per_row, magmaFloatComplex alpha, magmaFloatComplex_ptr dval, magmaIndex_ptr dcolind, magmaIndex_ptr drowlength, magmaFloatComplex_ptr dx, magmaFloatComplex beta, magmaFloatComplex_ptr dy, magma_int_t alignment, magma_int_t blocksize, magma_queue_t queue)
 This routine computes y = alpha * A * x + beta * y on the GPU.
magma_int_t magma_cgeelltmv_shift (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t nnz_per_row, magmaFloatComplex alpha, magmaFloatComplex lambda, magmaFloatComplex_ptr dval, magmaIndex_ptr dcolind, magmaFloatComplex_ptr dx, magmaFloatComplex beta, int offset, int blocksize, magmaIndex_ptr addrows, magmaFloatComplex_ptr dy, magma_queue_t queue)
 This routine computes y = alpha *( A - lambda I ) * x + beta * y on the GPU.
magma_int_t magma_cgesellpmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t blocksize, magma_int_t slices, magma_int_t alignment, magmaFloatComplex alpha, magmaFloatComplex_ptr dval, magmaIndex_ptr dcolind, magmaIndex_ptr drowptr, magmaFloatComplex_ptr dx, magmaFloatComplex beta, magmaFloatComplex_ptr dy, magma_queue_t queue)
 This routine computes y = alpha * A^t * x + beta * y on the GPU.
magma_int_t magma_cgesellcmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t blocksize, magma_int_t slices, magma_int_t alignment, magmaFloatComplex alpha, magmaFloatComplex_ptr dval, magmaIndex_ptr dcolind, magmaIndex_ptr drowptr, magmaFloatComplex_ptr dx, magmaFloatComplex beta, magmaFloatComplex_ptr dy, magma_queue_t queue)
 This routine computes y = alpha * A^t * x + beta * y on the GPU.
magma_int_t magma_cmdotc (int n, int k, magmaFloatComplex_ptr v, magmaFloatComplex_ptr r, magmaFloatComplex_ptr d1, magmaFloatComplex_ptr d2, magmaFloatComplex_ptr skp, magma_queue_t queue)
 Computes the scalar product of a set of vectors v_i such that.
magma_int_t magma_cmgecsrmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t num_vecs, magmaFloatComplex alpha, magmaFloatComplex_ptr dval, magmaIndex_ptr drowptr, magmaIndex_ptr dcolind, magmaFloatComplex_ptr dx, magmaFloatComplex beta, magmaFloatComplex_ptr dy, magma_queue_t queue)
 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_cmgeellmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t num_vecs, magma_int_t nnz_per_row, magmaFloatComplex alpha, magmaFloatComplex_ptr dval, magmaIndex_ptr dcolind, magmaFloatComplex_ptr dx, magmaFloatComplex beta, magmaFloatComplex_ptr dy, magma_queue_t queue)
 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_cmgeelltmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t num_vecs, magma_int_t nnz_per_row, magmaFloatComplex alpha, magmaFloatComplex_ptr dval, magmaIndex_ptr dcolind, magmaFloatComplex_ptr dx, magmaFloatComplex beta, magmaFloatComplex_ptr dy, magma_queue_t queue)
 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_cmgesellpmv (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, magmaFloatComplex alpha, magmaFloatComplex_ptr dval, magmaIndex_ptr dcolind, magmaIndex_ptr drowptr, magmaFloatComplex_ptr dx, magmaFloatComplex beta, magmaFloatComplex_ptr dy, magma_queue_t queue)
 This routine computes Y = alpha * A^t * X + beta * Y on the GPU.

Function Documentation

magma_int_t magma_ccuspaxpy ( magmaFloatComplex *  alpha,
magma_c_matrix  A,
magmaFloatComplex *  beta,
magma_c_matrix  B,
magma_c_matrix *  AB,
magma_queue_t  queue 
)

This is an interface to the cuSPARSE routine csrgeam computing the sum of two sparse matrices stored in csr format:.

C = alpha * A + beta * B

Parameters:
[in] alpha magmaFloatComplex* scalar
[in] A magma_c_matrix input matrix
[in] beta magmaFloatComplex* scalar
[in] B magma_c_matrix input matrix
[out] AB magma_c_matrix* output matrix AB = alpha * A + beta * B
[in] queue magma_queue_t Queue to execute in.
magma_int_t magma_ccuspmm ( magma_c_matrix  A,
magma_c_matrix  B,
magma_c_matrix *  AB,
magma_queue_t  queue 
)

This is an interface to the cuSPARSE routine csrmm computing the product of two sparse matrices stored in csr format.

Parameters:
[in] A magma_c_matrix input matrix
[in] B magma_c_matrix input matrix
[out] AB magma_c_matrix* output matrix AB = A * B
[in] queue magma_queue_t Queue to execute in.
magma_int_t magma_ccustomspmv ( magmaFloatComplex  alpha,
magma_c_matrix  x,
magmaFloatComplex  beta,
magma_c_matrix  y,
magma_queue_t  queue 
)

This is an interface to any custom sparse matrix vector product.

It should compute y = alpha*FUNCTION(x) + beta*y The vectors are located on the device, the scalars on the CPU.

Parameters:
[in] alpha magmaFloatComplex scalar alpha
[in] x magma_c_matrix input vector x
[in] beta magmaFloatComplex scalar beta
[out] y magma_c_matrix output vector y
[in] queue magma_queue_t Queue to execute in.
magma_int_t magma_cgecsrmv ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magmaFloatComplex  alpha,
magmaFloatComplex_ptr  dval,
magmaIndex_ptr  drowptr,
magmaIndex_ptr  dcolind,
magmaFloatComplex_ptr  dx,
magmaFloatComplex  beta,
magmaFloatComplex_ptr  dy,
magma_queue_t  queue 
)

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

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

Parameters:
[in] transA magma_trans_t transposition parameter for A
[in] m magma_int_t number of rows in A
[in] n magma_int_t number of columns in A
[in] alpha magmaFloatComplex scalar multiplier
[in] dval magmaFloatComplex_ptr array containing values of A in CSR
[in] drowptr magmaIndex_ptr rowpointer of A in CSR
[in] dcolind magmaIndex_ptr columnindices of A in CSR
[in] dx magmaFloatComplex_ptr input vector x
[in] beta magmaFloatComplex scalar multiplier
[out] dy magmaFloatComplex_ptr input/output vector y
[in] queue magma_queue_t Queue to execute in.
magma_int_t magma_cgecsrmv_shift ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magmaFloatComplex  alpha,
magmaFloatComplex  lambda,
magmaFloatComplex_ptr  dval,
magmaIndex_ptr  drowptr,
magmaIndex_ptr  dcolind,
magmaFloatComplex_ptr  dx,
magmaFloatComplex  beta,
int  offset,
int  blocksize,
magma_index_t *  addrows,
magmaFloatComplex_ptr  dy,
magma_queue_t  queue 
)

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

It is a shifted version of the CSR-SpMV.

Parameters:
[in] transA magma_trans_t transposition parameter for A
[in] m magma_int_t number of rows in A
[in] n magma_int_t number of columns in A
[in] alpha magmaFloatComplex scalar multiplier
[in] lambda magmaFloatComplex scalar multiplier
[in] dval magmaFloatComplex_ptr array containing values of A in CSR
[in] drowptr magmaIndex_ptr rowpointer of A in CSR
[in] dcolind magmaIndex_ptr columnindices of A in CSR
[in] dx magmaFloatComplex_ptr input vector x
[in] beta magmaFloatComplex scalar multiplier
[in] offset magma_int_t in case not the main diagonal is scaled
[in] blocksize magma_int_t in case of processing multiple vectors
[in] addrows magmaIndex_ptr in case the matrixpowerskernel is used
[out] dy magmaFloatComplex_ptr output vector y
[in] queue magma_queue_t Queue to execute in.
magma_int_t magma_cgeellmv ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  nnz_per_row,
magmaFloatComplex  alpha,
magmaFloatComplex_ptr  dval,
magmaIndex_ptr  dcolind,
magmaFloatComplex_ptr  dx,
magmaFloatComplex  beta,
magmaFloatComplex_ptr  dy,
magma_queue_t  queue 
)

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

Input format is ELLPACK.

Parameters:
[in] transA magma_trans_t transposition parameter for A
[in] m magma_int_t number of rows in A
[in] n magma_int_t number of columns in A
[in] nnz_per_row magma_int_t number of elements in the longest row
[in] alpha magmaFloatComplex scalar multiplier
[in] dval magmaFloatComplex_ptr array containing values of A in ELLPACK
[in] dcolind magmaIndex_ptr columnindices of A in ELLPACK
[in] dx magmaFloatComplex_ptr input vector x
[in] beta magmaFloatComplex scalar multiplier
[out] dy magmaFloatComplex_ptr input/output vector y
[in] queue magma_queue_t Queue to execute in.
magma_int_t magma_cgeellmv_shift ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  nnz_per_row,
magmaFloatComplex  alpha,
magmaFloatComplex  lambda,
magmaFloatComplex_ptr  dval,
magmaIndex_ptr  dcolind,
magmaFloatComplex_ptr  dx,
magmaFloatComplex  beta,
int  offset,
int  blocksize,
magmaIndex_ptr  addrows,
magmaFloatComplex_ptr  dy,
magma_queue_t  queue 
)

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:
[in] transA magma_trans_t transposition parameter for A
[in] m magma_int_t number of rows in A
[in] n magma_int_t number of columns in A
[in] nnz_per_row magma_int_t number of elements in the longest row
[in] alpha magmaFloatComplex scalar multiplier
[in] lambda magmaFloatComplex scalar multiplier
[in] dval magmaFloatComplex_ptr array containing values of A in ELLPACK
[in] dcolind magmaIndex_ptr columnindices of A in ELLPACK
[in] dx magmaFloatComplex_ptr input vector x
[in] beta magmaFloatComplex scalar multiplier
[in] offset magma_int_t in case not the main diagonal is scaled
[in] blocksize magma_int_t in case of processing multiple vectors
[in] addrows magmaIndex_ptr in case the matrixpowerskernel is used
[out] dy magmaFloatComplex_ptr input/output vector y
[in] queue magma_queue_t Queue to execute in.
magma_int_t magma_cgeellrtmv ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  nnz_per_row,
magmaFloatComplex  alpha,
magmaFloatComplex_ptr  dval,
magmaIndex_ptr  dcolind,
magmaIndex_ptr  drowlength,
magmaFloatComplex_ptr  dx,
magmaFloatComplex  beta,
magmaFloatComplex_ptr  dy,
magma_int_t  alignment,
magma_int_t  blocksize,
magma_queue_t  queue 
)

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:
[in] transA magma_trans_t transposition parameter for A
[in] m magma_int_t number of rows
[in] n magma_int_t number of columns
[in] nnz_per_row magma_int_t max number of nonzeros in a row
[in] alpha magmaFloatComplex scalar alpha
[in] dval magmaFloatComplex_ptr val array
[in] dcolind magmaIndex_ptr col indices
[in] drowlength magmaIndex_ptr number of elements in each row
[in] dx magmaFloatComplex_ptr input vector x
[in] beta magmaFloatComplex scalar beta
[out] dy magmaFloatComplex_ptr output vector y
[in] blocksize magma_int_t threads per block
[in] alignment magma_int_t threads assigned to each row
[in] queue magma_queue_t Queue to execute in.
magma_int_t magma_cgeelltmv_shift ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  nnz_per_row,
magmaFloatComplex  alpha,
magmaFloatComplex  lambda,
magmaFloatComplex_ptr  dval,
magmaIndex_ptr  dcolind,
magmaFloatComplex_ptr  dx,
magmaFloatComplex  beta,
int  offset,
int  blocksize,
magmaIndex_ptr  addrows,
magmaFloatComplex_ptr  dy,
magma_queue_t  queue 
)

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

Input format is ELL.

Parameters:
[in] transA magma_trans_t transposition parameter for A
[in] m magma_int_t number of rows in A
[in] n magma_int_t number of columns in A
[in] nnz_per_row magma_int_t number of elements in the longest row
[in] alpha magmaFloatComplex scalar multiplier
[in] lambda magmaFloatComplex scalar multiplier
[in] dval magmaFloatComplex_ptr array containing values of A in ELL
[in] dcolind magmaIndex_ptr columnindices of A in ELL
[in] dx magmaFloatComplex_ptr input vector x
[in] beta magmaFloatComplex scalar multiplier
[in] offset magma_int_t in case not the main diagonal is scaled
[in] blocksize magma_int_t in case of processing multiple vectors
[in] addrows magmaIndex_ptr in case the matrixpowerskernel is used
[out] dy magmaFloatComplex_ptr input/output vector y
[in] queue magma_queue_t Queue to execute in.
magma_int_t magma_cgesellcmv ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  blocksize,
magma_int_t  slices,
magma_int_t  alignment,
magmaFloatComplex  alpha,
magmaFloatComplex_ptr  dval,
magmaIndex_ptr  dcolind,
magmaIndex_ptr  drowptr,
magmaFloatComplex_ptr  dx,
magmaFloatComplex  beta,
magmaFloatComplex_ptr  dy,
magma_queue_t  queue 
)

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

Input format is SELLC/SELLP.

Parameters:
[in] transA magma_trans_t transposition parameter for A
[in] m magma_int_t number of rows in A
[in] n magma_int_t number of columns in A
[in] blocksize magma_int_t number of rows in one ELL-slice
[in] slices magma_int_t number of slices in matrix
[in] alignment magma_int_t number of threads assigned to one row (=1)
[in] alpha magmaFloatComplex scalar multiplier
[in] dval magmaFloatComplex_ptr array containing values of A in SELLC/P
[in] dcolind magmaIndex_ptr columnindices of A in SELLC/P
[in] drowptr magmaIndex_ptr rowpointer of SELLP
[in] dx magmaFloatComplex_ptr input vector x
[in] beta magmaFloatComplex scalar multiplier
[out] dy magmaFloatComplex_ptr input/output vector y
[in] queue magma_queue_t Queue to execute in.
magma_int_t magma_cgesellpmv ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  blocksize,
magma_int_t  slices,
magma_int_t  alignment,
magmaFloatComplex  alpha,
magmaFloatComplex_ptr  dval,
magmaIndex_ptr  dcolind,
magmaIndex_ptr  drowptr,
magmaFloatComplex_ptr  dx,
magmaFloatComplex  beta,
magmaFloatComplex_ptr  dy,
magma_queue_t  queue 
)

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

Input format is SELLP.

Parameters:
[in] transA magma_trans_t transposition parameter for A
[in] m magma_int_t number of rows in A
[in] n magma_int_t number of columns in A
[in] blocksize magma_int_t number of rows in one ELL-slice
[in] slices magma_int_t number of slices in matrix
[in] alignment magma_int_t number of threads assigned to one row
[in] alpha magmaFloatComplex scalar multiplier
[in] dval magmaFloatComplex_ptr array containing values of A in SELLP
[in] dcolind magmaIndex_ptr columnindices of A in SELLP
[in] drowptr magmaIndex_ptr rowpointer of SELLP
[in] dx magmaFloatComplex_ptr input vector x
[in] beta magmaFloatComplex scalar multiplier
[out] dy magmaFloatComplex_ptr input/output vector y
[in] queue magma_queue_t Queue to execute in.
magma_int_t magma_cmdotc ( int  n,
int  k,
magmaFloatComplex_ptr  v,
magmaFloatComplex_ptr  r,
magmaFloatComplex_ptr  d1,
magmaFloatComplex_ptr  d2,
magmaFloatComplex_ptr  skp,
magma_queue_t  queue 
)

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:
[in] n int length of v_i and r
[in] k int # vectors v_i
[in] v magmaFloatComplex_ptr v = (v_0 .. v_i.. v_k)
[in] r magmaFloatComplex_ptr r
[in] d1 magmaFloatComplex_ptr workspace
[in] d2 magmaFloatComplex_ptr workspace
[out] skp magmaFloatComplex_ptr vector[k] of scalar products (<v_i,r>...)
[in] queue magma_queue_t Queue to execute in.
magma_int_t magma_cmgecsrmv ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  num_vecs,
magmaFloatComplex  alpha,
magmaFloatComplex_ptr  dval,
magmaIndex_ptr  drowptr,
magmaIndex_ptr  dcolind,
magmaFloatComplex_ptr  dx,
magmaFloatComplex  beta,
magmaFloatComplex_ptr  dy,
magma_queue_t  queue 
)

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:
[in] transA magma_trans_t transposition parameter for A
[in] m magma_int_t number of rows in A
[in] n magma_int_t number of columns in A
[in] num_vecs mama_int_t number of vectors
[in] alpha magmaFloatComplex scalar multiplier
[in] dval magmaFloatComplex_ptr array containing values of A in CSR
[in] drowptr magmaIndex_ptr rowpointer of A in CSR
[in] dcolind magmaIndex_ptr columnindices of A in CSR
[in] dx magmaFloatComplex_ptr input vector x
[in] beta magmaFloatComplex scalar multiplier
[out] dy magmaFloatComplex_ptr input/output vector y
[in] queue magma_queue_t Queue to execute in.
magma_int_t magma_cmgeellmv ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  num_vecs,
magma_int_t  nnz_per_row,
magmaFloatComplex  alpha,
magmaFloatComplex_ptr  dval,
magmaIndex_ptr  dcolind,
magmaFloatComplex_ptr  dx,
magmaFloatComplex  beta,
magmaFloatComplex_ptr  dy,
magma_queue_t  queue 
)

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:
[in] transA magma_trans_t transposition parameter for A
[in] m magma_int_t number of rows in A
[in] n magma_int_t number of columns in A
[in] num_vecs mama_int_t number of vectors
[in] nnz_per_row magma_int_t number of elements in the longest row
[in] alpha magmaFloatComplex scalar multiplier
[in] dval magmaFloatComplex_ptr array containing values of A in ELLPACK
[in] dcolind magmaIndex_ptr columnindices of A in ELLPACK
[in] dx magmaFloatComplex_ptr input vector x
[in] beta magmaFloatComplex scalar multiplier
[out] dy magmaFloatComplex_ptr input/output vector y
[in] queue magma_queue_t Queue to execute in.
magma_int_t magma_cmgeelltmv ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  num_vecs,
magma_int_t  nnz_per_row,
magmaFloatComplex  alpha,
magmaFloatComplex_ptr  dval,
magmaIndex_ptr  dcolind,
magmaFloatComplex_ptr  dx,
magmaFloatComplex  beta,
magmaFloatComplex_ptr  dy,
magma_queue_t  queue 
)

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:
[in] transA magma_trans_t transposition parameter for A
[in] m magma_int_t number of rows in A
[in] n magma_int_t number of columns in A
[in] num_vecs mama_int_t number of vectors
[in] nnz_per_row magma_int_t number of elements in the longest row
[in] alpha magmaFloatComplex scalar multiplier
[in] dval magmaFloatComplex_ptr array containing values of A in ELL
[in] dcolind magmaIndex_ptr columnindices of A in ELL
[in] dx magmaFloatComplex_ptr input vector x
[in] beta magmaFloatComplex scalar multiplier
[out] dy magmaFloatComplex_ptr input/output vector y
[in] queue magma_queue_t Queue to execute in.
magma_int_t magma_cmgesellpmv ( 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,
magmaFloatComplex  alpha,
magmaFloatComplex_ptr  dval,
magmaIndex_ptr  dcolind,
magmaIndex_ptr  drowptr,
magmaFloatComplex_ptr  dx,
magmaFloatComplex  beta,
magmaFloatComplex_ptr  dy,
magma_queue_t  queue 
)

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:
[in] transA magma_trans_t transpose A?
[in] m magma_int_t number of rows in A
[in] n magma_int_t number of columns in A
[in] num_vecs magma_int_t number of columns in X and Y
[in] blocksize magma_int_t number of rows in one ELL-slice
[in] slices magma_int_t number of slices in matrix
[in] alignment magma_int_t number of threads assigned to one row
[in] alpha magmaFloatComplex scalar multiplier
[in] dval magmaFloatComplex_ptr array containing values of A in SELLP
[in] dcolind magmaIndex_ptr columnindices of A in SELLP
[in] drowptr magmaIndex_ptr rowpointer of SELLP
[in] dx magmaFloatComplex_ptr input vector x
[in] beta magmaFloatComplex scalar multiplier
[out] dy magmaFloatComplex_ptr input/output vector y
[in] queue magma_queue_t Queue to execute in.

Generated on 3 May 2015 for MAGMA by  doxygen 1.6.1