single precision
[Sparse BLAS]

Functions

magma_int_t magma_scuspaxpy (float *alpha, magma_s_matrix A, float *beta, magma_s_matrix B, magma_s_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_scuspmm (magma_s_matrix A, magma_s_matrix B, magma_s_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_scustomspmv (float alpha, magma_s_matrix x, float beta, magma_s_matrix y, magma_queue_t queue)
 This is an interface to any custom sparse matrix vector product.
magma_int_t magma_sgecsrmv (magma_trans_t transA, magma_int_t m, magma_int_t n, float alpha, magmaFloat_ptr dval, magmaIndex_ptr drowptr, magmaIndex_ptr dcolind, magmaFloat_ptr dx, float beta, magmaFloat_ptr dy, magma_queue_t queue)
 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, magmaFloat_ptr dval, magmaIndex_ptr drowptr, magmaIndex_ptr dcolind, magmaFloat_ptr dx, float beta, int offset, int blocksize, magma_index_t *addrows, magmaFloat_ptr dy, magma_queue_t queue)
 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, magmaFloat_ptr dval, magmaIndex_ptr dcolind, magmaFloat_ptr dx, float beta, magmaFloat_ptr dy, magma_queue_t queue)
 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, magmaFloat_ptr dval, magmaIndex_ptr dcolind, magmaFloat_ptr dx, float beta, int offset, int blocksize, magmaIndex_ptr addrows, magmaFloat_ptr dy, magma_queue_t queue)
 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, magmaFloat_ptr dval, magmaIndex_ptr dcolind, magmaIndex_ptr drowlength, magmaFloat_ptr dx, float beta, magmaFloat_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_sgeelltmv_shift (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t nnz_per_row, float alpha, float lambda, magmaFloat_ptr dval, magmaIndex_ptr dcolind, magmaFloat_ptr dx, float beta, int offset, int blocksize, magmaIndex_ptr addrows, magmaFloat_ptr dy, magma_queue_t queue)
 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, magmaFloat_ptr dval, magmaIndex_ptr dcolind, magmaIndex_ptr drowptr, magmaFloat_ptr dx, float beta, magmaFloat_ptr dy, magma_queue_t queue)
 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, magmaFloat_ptr dval, magmaIndex_ptr dcolind, magmaIndex_ptr drowptr, magmaFloat_ptr dx, float beta, magmaFloat_ptr dy, magma_queue_t queue)
 This routine computes y = alpha * A^t * x + beta * y on the GPU.
magma_int_t magma_smdotc (int n, int k, magmaFloat_ptr v, magmaFloat_ptr r, magmaFloat_ptr d1, magmaFloat_ptr d2, magmaFloat_ptr skp, magma_queue_t queue)
 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, magmaFloat_ptr dval, magmaIndex_ptr drowptr, magmaIndex_ptr dcolind, magmaFloat_ptr dx, float beta, magmaFloat_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_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, magmaFloat_ptr dval, magmaIndex_ptr dcolind, magmaFloat_ptr dx, float beta, magmaFloat_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_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, magmaFloat_ptr dval, magmaIndex_ptr dcolind, magmaFloat_ptr dx, float beta, magmaFloat_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_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, magmaFloat_ptr dval, magmaIndex_ptr dcolind, magmaIndex_ptr drowptr, magmaFloat_ptr dx, float beta, magmaFloat_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_scuspaxpy ( float *  alpha,
magma_s_matrix  A,
float *  beta,
magma_s_matrix  B,
magma_s_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 float* scalar
[in] A magma_s_matrix input matrix
[in] beta float* scalar
[in] B magma_s_matrix input matrix
[out] AB magma_s_matrix* output matrix AB = alpha * A + beta * B
[in] queue magma_queue_t Queue to execute in.
magma_int_t magma_scuspmm ( magma_s_matrix  A,
magma_s_matrix  B,
magma_s_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_s_matrix input matrix
[in] B magma_s_matrix input matrix
[out] AB magma_s_matrix* output matrix AB = A * B
[in] queue magma_queue_t Queue to execute in.
magma_int_t magma_scustomspmv ( float  alpha,
magma_s_matrix  x,
float  beta,
magma_s_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 float scalar alpha
[in] x magma_s_matrix input vector x
[in] beta float scalar beta
[out] y magma_s_matrix output vector y
[in] queue magma_queue_t Queue to execute in.
magma_int_t magma_sgecsrmv ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
float  alpha,
magmaFloat_ptr  dval,
magmaIndex_ptr  drowptr,
magmaIndex_ptr  dcolind,
magmaFloat_ptr  dx,
float  beta,
magmaFloat_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 float scalar multiplier
[in] dval magmaFloat_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 magmaFloat_ptr input vector x
[in] beta float scalar multiplier
[out] dy magmaFloat_ptr input/output vector y
[in] queue magma_queue_t Queue to execute in.
magma_int_t magma_sgecsrmv_shift ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
float  alpha,
float  lambda,
magmaFloat_ptr  dval,
magmaIndex_ptr  drowptr,
magmaIndex_ptr  dcolind,
magmaFloat_ptr  dx,
float  beta,
int  offset,
int  blocksize,
magma_index_t *  addrows,
magmaFloat_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 float scalar multiplier
[in] lambda float scalar multiplier
[in] dval magmaFloat_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 magmaFloat_ptr input vector x
[in] beta float 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 magmaFloat_ptr output vector y
[in] queue magma_queue_t Queue to execute in.
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,
magmaFloat_ptr  dval,
magmaIndex_ptr  dcolind,
magmaFloat_ptr  dx,
float  beta,
magmaFloat_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 float scalar multiplier
[in] dval magmaFloat_ptr array containing values of A in ELLPACK
[in] dcolind magmaIndex_ptr columnindices of A in ELLPACK
[in] dx magmaFloat_ptr input vector x
[in] beta float scalar multiplier
[out] dy magmaFloat_ptr input/output vector y
[in] queue magma_queue_t Queue to execute in.
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,
magmaFloat_ptr  dval,
magmaIndex_ptr  dcolind,
magmaFloat_ptr  dx,
float  beta,
int  offset,
int  blocksize,
magmaIndex_ptr  addrows,
magmaFloat_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 float scalar multiplier
[in] lambda float scalar multiplier
[in] dval magmaFloat_ptr array containing values of A in ELLPACK
[in] dcolind magmaIndex_ptr columnindices of A in ELLPACK
[in] dx magmaFloat_ptr input vector x
[in] beta float 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 magmaFloat_ptr input/output vector y
[in] queue magma_queue_t Queue to execute in.
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,
magmaFloat_ptr  dval,
magmaIndex_ptr  dcolind,
magmaIndex_ptr  drowlength,
magmaFloat_ptr  dx,
float  beta,
magmaFloat_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 float scalar alpha
[in] dval magmaFloat_ptr val array
[in] dcolind magmaIndex_ptr col indices
[in] drowlength magmaIndex_ptr number of elements in each row
[in] dx magmaFloat_ptr input vector x
[in] beta float scalar beta
[out] dy magmaFloat_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_sgeelltmv_shift ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  nnz_per_row,
float  alpha,
float  lambda,
magmaFloat_ptr  dval,
magmaIndex_ptr  dcolind,
magmaFloat_ptr  dx,
float  beta,
int  offset,
int  blocksize,
magmaIndex_ptr  addrows,
magmaFloat_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 float scalar multiplier
[in] lambda float scalar multiplier
[in] dval magmaFloat_ptr array containing values of A in ELL
[in] dcolind magmaIndex_ptr columnindices of A in ELL
[in] dx magmaFloat_ptr input vector x
[in] beta float 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 magmaFloat_ptr input/output vector y
[in] queue magma_queue_t Queue to execute in.
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,
magmaFloat_ptr  dval,
magmaIndex_ptr  dcolind,
magmaIndex_ptr  drowptr,
magmaFloat_ptr  dx,
float  beta,
magmaFloat_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 float scalar multiplier
[in] dval magmaFloat_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 magmaFloat_ptr input vector x
[in] beta float scalar multiplier
[out] dy magmaFloat_ptr input/output vector y
[in] queue magma_queue_t Queue to execute in.
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,
magmaFloat_ptr  dval,
magmaIndex_ptr  dcolind,
magmaIndex_ptr  drowptr,
magmaFloat_ptr  dx,
float  beta,
magmaFloat_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 float scalar multiplier
[in] dval magmaFloat_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 magmaFloat_ptr input vector x
[in] beta float scalar multiplier
[out] dy magmaFloat_ptr input/output vector y
[in] queue magma_queue_t Queue to execute in.
magma_int_t magma_smdotc ( int  n,
int  k,
magmaFloat_ptr  v,
magmaFloat_ptr  r,
magmaFloat_ptr  d1,
magmaFloat_ptr  d2,
magmaFloat_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 magmaFloat_ptr v = (v_0 .. v_i.. v_k)
[in] r magmaFloat_ptr r
[in] d1 magmaFloat_ptr workspace
[in] d2 magmaFloat_ptr workspace
[out] skp magmaFloat_ptr vector[k] of scalar products (<v_i,r>...)
[in] queue magma_queue_t Queue to execute in.
magma_int_t magma_smgecsrmv ( magma_trans_t  transA,
magma_int_t  m,
magma_int_t  n,
magma_int_t  num_vecs,
float  alpha,
magmaFloat_ptr  dval,
magmaIndex_ptr  drowptr,
magmaIndex_ptr  dcolind,
magmaFloat_ptr  dx,
float  beta,
magmaFloat_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 float scalar multiplier
[in] dval magmaFloat_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 magmaFloat_ptr input vector x
[in] beta float scalar multiplier
[out] dy magmaFloat_ptr input/output vector y
[in] queue magma_queue_t Queue to execute in.
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,
magmaFloat_ptr  dval,
magmaIndex_ptr  dcolind,
magmaFloat_ptr  dx,
float  beta,
magmaFloat_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 float scalar multiplier
[in] dval magmaFloat_ptr array containing values of A in ELLPACK
[in] dcolind magmaIndex_ptr columnindices of A in ELLPACK
[in] dx magmaFloat_ptr input vector x
[in] beta float scalar multiplier
[out] dy magmaFloat_ptr input/output vector y
[in] queue magma_queue_t Queue to execute in.
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,
magmaFloat_ptr  dval,
magmaIndex_ptr  dcolind,
magmaFloat_ptr  dx,
float  beta,
magmaFloat_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 float scalar multiplier
[in] dval magmaFloat_ptr array containing values of A in ELL
[in] dcolind magmaIndex_ptr columnindices of A in ELL
[in] dx magmaFloat_ptr input vector x
[in] beta float scalar multiplier
[out] dy magmaFloat_ptr input/output vector y
[in] queue magma_queue_t Queue to execute in.
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,
magmaFloat_ptr  dval,
magmaIndex_ptr  dcolind,
magmaIndex_ptr  drowptr,
magmaFloat_ptr  dx,
float  beta,
magmaFloat_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 float scalar multiplier
[in] dval magmaFloat_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 magmaFloat_ptr input vector x
[in] beta float scalar multiplier
[out] dy magmaFloat_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