MAGMA  1.6.1
Matrix Algebra for GPU and Multicore Architectures
 All Classes Files Functions Friends Groups Pages
single-complex precision

Functions

magma_int_t magma_ccuspaxpy (magmaFloatComplex *alpha, magma_c_sparse_matrix A, magmaFloatComplex *beta, magma_c_sparse_matrix B, magma_c_sparse_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: More...
 
magma_int_t magma_ccuspmm (magma_c_sparse_matrix A, magma_c_sparse_matrix B, magma_c_sparse_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. More...
 
magma_int_t magma_ccustomspmv (magmaFloatComplex alpha, magma_c_vector x, magmaFloatComplex beta, magma_c_vector y, magma_queue_t queue)
 This is an interface to any custom sparse matrix vector product. More...
 
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. More...
 
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. More...
 
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. More...
 
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. More...
 
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. More...
 
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. More...
 
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. More...
 
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. More...
 
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. More...
 
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. More...
 
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. More...
 
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. More...
 
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. More...
 

Detailed Description

Function Documentation

magma_int_t magma_ccuspaxpy ( magmaFloatComplex *  alpha,
magma_c_sparse_matrix  A,
magmaFloatComplex *  beta,
magma_c_sparse_matrix  B,
magma_c_sparse_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]alphamagmaFloatComplex* scalar
[in]Amagma_c_sparse_matrix input matrix
[in]betamagmaFloatComplex* scalar
[in]Bmagma_c_sparse_matrix input matrix
[out]ABmagma_c_sparse_matrix* output matrix AB = alpha * A + beta * B
[in]queuemagma_queue_t Queue to execute in.
magma_int_t magma_ccuspmm ( magma_c_sparse_matrix  A,
magma_c_sparse_matrix  B,
magma_c_sparse_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]Amagma_c_sparse_matrix input matrix
[in]Bmagma_c_sparse_matrix input matrix
[out]ABmagma_c_sparse_matrix* output matrix AB = A * B
[in]queuemagma_queue_t Queue to execute in.
magma_int_t magma_ccustomspmv ( magmaFloatComplex  alpha,
magma_c_vector  x,
magmaFloatComplex  beta,
magma_c_vector  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]alphamagmaFloatComplex scalar alpha
[in]xmagma_c_vector input vector x
[in]betamagmaFloatComplex scalar beta
[out]ymagma_c_vector output vector y
[in]queuemagma_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]transAmagma_trans_t transposition parameter for A
[in]mmagma_int_t number of rows in A
[in]nmagma_int_t number of columns in A
[in]alphamagmaFloatComplex scalar multiplier
[in]dvalmagmaFloatComplex_ptr array containing values of A in CSR
[in]drowptrmagmaIndex_ptr rowpointer of A in CSR
[in]dcolindmagmaIndex_ptr columnindices of A in CSR
[in]dxmagmaFloatComplex_ptr input vector x
[in]betamagmaFloatComplex scalar multiplier
[out]dymagmaFloatComplex_ptr input/output vector y
[in]queuemagma_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]transAmagma_trans_t transposition parameter for A
[in]mmagma_int_t number of rows in A
[in]nmagma_int_t number of columns in A
[in]alphamagmaFloatComplex scalar multiplier
[in]lambdamagmaFloatComplex scalar multiplier
[in]dvalmagmaFloatComplex_ptr array containing values of A in CSR
[in]drowptrmagmaIndex_ptr rowpointer of A in CSR
[in]dcolindmagmaIndex_ptr columnindices of A in CSR
[in]dxmagmaFloatComplex_ptr input vector x
[in]betamagmaFloatComplex scalar multiplier
[in]offsetmagma_int_t in case not the main diagonal is scaled
[in]blocksizemagma_int_t in case of processing multiple vectors
[in]addrowsmagmaIndex_ptr in case the matrixpowerskernel is used
[out]dymagmaFloatComplex_ptr output vector y
[in]queuemagma_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]transAmagma_trans_t transposition parameter for A
[in]mmagma_int_t number of rows in A
[in]nmagma_int_t number of columns in A
[in]nnz_per_rowmagma_int_t number of elements in the longest row
[in]alphamagmaFloatComplex scalar multiplier
[in]dvalmagmaFloatComplex_ptr array containing values of A in ELLPACK
[in]dcolindmagmaIndex_ptr columnindices of A in ELLPACK
[in]dxmagmaFloatComplex_ptr input vector x
[in]betamagmaFloatComplex scalar multiplier
[out]dymagmaFloatComplex_ptr input/output vector y
[in]queuemagma_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]transAmagma_trans_t transposition parameter for A
[in]mmagma_int_t number of rows in A
[in]nmagma_int_t number of columns in A
[in]nnz_per_rowmagma_int_t number of elements in the longest row
[in]alphamagmaFloatComplex scalar multiplier
[in]lambdamagmaFloatComplex scalar multiplier
[in]dvalmagmaFloatComplex_ptr array containing values of A in ELLPACK
[in]dcolindmagmaIndex_ptr columnindices of A in ELLPACK
[in]dxmagmaFloatComplex_ptr input vector x
[in]betamagmaFloatComplex scalar multiplier
[in]offsetmagma_int_t in case not the main diagonal is scaled
[in]blocksizemagma_int_t in case of processing multiple vectors
[in]addrowsmagmaIndex_ptr in case the matrixpowerskernel is used
[out]dymagmaFloatComplex_ptr input/output vector y
[in]queuemagma_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]transAmagma_trans_t transposition parameter for A
[in]mmagma_int_t number of rows
[in]nmagma_int_t number of columns
[in]nnz_per_rowmagma_int_t max number of nonzeros in a row
[in]alphamagmaFloatComplex scalar alpha
[in]dvalmagmaFloatComplex_ptr val array
[in]dcolindmagmaIndex_ptr col indices
[in]drowlengthmagmaIndex_ptr number of elements in each row
[in]dxmagmaFloatComplex_ptr input vector x
[in]betamagmaFloatComplex scalar beta
[out]dymagmaFloatComplex_ptr output vector y
[in]blocksizemagma_int_t threads per block
[in]alignmentmagma_int_t threads assigned to each row
[in]queuemagma_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]transAmagma_trans_t transposition parameter for A
[in]mmagma_int_t number of rows in A
[in]nmagma_int_t number of columns in A
[in]nnz_per_rowmagma_int_t number of elements in the longest row
[in]alphamagmaFloatComplex scalar multiplier
[in]lambdamagmaFloatComplex scalar multiplier
[in]dvalmagmaFloatComplex_ptr array containing values of A in ELL
[in]dcolindmagmaIndex_ptr columnindices of A in ELL
[in]dxmagmaFloatComplex_ptr input vector x
[in]betamagmaFloatComplex scalar multiplier
[in]offsetmagma_int_t in case not the main diagonal is scaled
[in]blocksizemagma_int_t in case of processing multiple vectors
[in]addrowsmagmaIndex_ptr in case the matrixpowerskernel is used
[out]dymagmaFloatComplex_ptr input/output vector y
[in]queuemagma_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]transAmagma_trans_t transposition parameter for A
[in]mmagma_int_t number of rows in A
[in]nmagma_int_t number of columns in A
[in]blocksizemagma_int_t number of rows in one ELL-slice
[in]slicesmagma_int_t number of slices in matrix
[in]alignmentmagma_int_t number of threads assigned to one row (=1)
[in]alphamagmaFloatComplex scalar multiplier
[in]dvalmagmaFloatComplex_ptr array containing values of A in SELLC/P
[in]dcolindmagmaIndex_ptr columnindices of A in SELLC/P
[in]drowptrmagmaIndex_ptr rowpointer of SELLP
[in]dxmagmaFloatComplex_ptr input vector x
[in]betamagmaFloatComplex scalar multiplier
[out]dymagmaFloatComplex_ptr input/output vector y
[in]queuemagma_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]transAmagma_trans_t transposition parameter for A
[in]mmagma_int_t number of rows in A
[in]nmagma_int_t number of columns in A
[in]blocksizemagma_int_t number of rows in one ELL-slice
[in]slicesmagma_int_t number of slices in matrix
[in]alignmentmagma_int_t number of threads assigned to one row
[in]alphamagmaFloatComplex scalar multiplier
[in]dvalmagmaFloatComplex_ptr array containing values of A in SELLP
[in]dcolindmagmaIndex_ptr columnindices of A in SELLP
[in]drowptrmagmaIndex_ptr rowpointer of SELLP
[in]dxmagmaFloatComplex_ptr input vector x
[in]betamagmaFloatComplex scalar multiplier
[out]dymagmaFloatComplex_ptr input/output vector y
[in]queuemagma_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]nint length of v_i and r
[in]kint

vectors v_i

Parameters
[in]vmagmaFloatComplex_ptr v = (v_0 .. v_i.. v_k)
[in]rmagmaFloatComplex_ptr r
[in]d1magmaFloatComplex_ptr workspace
[in]d2magmaFloatComplex_ptr workspace
[out]skpmagmaFloatComplex_ptr vector[k] of scalar products (<v_i,r>...)
[in]queuemagma_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]transAmagma_trans_t transposition parameter for A
[in]mmagma_int_t number of rows in A
[in]nmagma_int_t number of columns in A
[in]num_vecsmama_int_t number of vectors
[in]alphamagmaFloatComplex scalar multiplier
[in]dvalmagmaFloatComplex_ptr array containing values of A in CSR
[in]drowptrmagmaIndex_ptr rowpointer of A in CSR
[in]dcolindmagmaIndex_ptr columnindices of A in CSR
[in]dxmagmaFloatComplex_ptr input vector x
[in]betamagmaFloatComplex scalar multiplier
[out]dymagmaFloatComplex_ptr input/output vector y
[in]queuemagma_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]transAmagma_trans_t transposition parameter for A
[in]mmagma_int_t number of rows in A
[in]nmagma_int_t number of columns in A
[in]num_vecsmama_int_t number of vectors
[in]nnz_per_rowmagma_int_t number of elements in the longest row
[in]alphamagmaFloatComplex scalar multiplier
[in]dvalmagmaFloatComplex_ptr array containing values of A in ELLPACK
[in]dcolindmagmaIndex_ptr columnindices of A in ELLPACK
[in]dxmagmaFloatComplex_ptr input vector x
[in]betamagmaFloatComplex scalar multiplier
[out]dymagmaFloatComplex_ptr input/output vector y
[in]queuemagma_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]transAmagma_trans_t transposition parameter for A
[in]mmagma_int_t number of rows in A
[in]nmagma_int_t number of columns in A
[in]num_vecsmama_int_t number of vectors
[in]nnz_per_rowmagma_int_t number of elements in the longest row
[in]alphamagmaFloatComplex scalar multiplier
[in]dvalmagmaFloatComplex_ptr array containing values of A in ELL
[in]dcolindmagmaIndex_ptr columnindices of A in ELL
[in]dxmagmaFloatComplex_ptr input vector x
[in]betamagmaFloatComplex scalar multiplier
[out]dymagmaFloatComplex_ptr input/output vector y
[in]queuemagma_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]transAmagma_trans_t transpose A?
[in]mmagma_int_t number of rows in A
[in]nmagma_int_t number of columns in A
[in]num_vecsmagma_int_t number of columns in X and Y
[in]blocksizemagma_int_t number of rows in one ELL-slice
[in]slicesmagma_int_t number of slices in matrix
[in]alignmentmagma_int_t number of threads assigned to one row
[in]alphamagmaFloatComplex scalar multiplier
[in]dvalmagmaFloatComplex_ptr array containing values of A in SELLP
[in]dcolindmagmaIndex_ptr columnindices of A in SELLP
[in]drowptrmagmaIndex_ptr rowpointer of SELLP
[in]dxmagmaFloatComplex_ptr input vector x
[in]betamagmaFloatComplex scalar multiplier
[out]dymagmaFloatComplex_ptr input/output vector y
[in]queuemagma_queue_t Queue to execute in.