Functions | |
magma_int_t | magma_zcuspaxpy (magmaDoubleComplex *alpha, magma_z_matrix A, magmaDoubleComplex *beta, magma_z_matrix B, magma_z_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_zcuspmm (magma_z_matrix A, magma_z_matrix B, magma_z_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_zcustomspmv (magmaDoubleComplex alpha, magma_z_matrix x, magmaDoubleComplex beta, magma_z_matrix y, magma_queue_t queue) |
This is an interface to any custom sparse matrix vector product. | |
magma_int_t | magma_zgecsrmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magmaDoubleComplex alpha, magmaDoubleComplex_ptr dval, magmaIndex_ptr drowptr, magmaIndex_ptr dcolind, magmaDoubleComplex_ptr dx, magmaDoubleComplex beta, magmaDoubleComplex_ptr dy, magma_queue_t queue) |
This routine computes y = alpha * A * x + beta * y on the GPU. | |
magma_int_t | magma_zgecsrmv_shift (magma_trans_t transA, magma_int_t m, magma_int_t n, magmaDoubleComplex alpha, magmaDoubleComplex lambda, magmaDoubleComplex_ptr dval, magmaIndex_ptr drowptr, magmaIndex_ptr dcolind, magmaDoubleComplex_ptr dx, magmaDoubleComplex beta, int offset, int blocksize, magma_index_t *addrows, magmaDoubleComplex_ptr dy, magma_queue_t queue) |
This routine computes y = alpha * ( A -lambda I ) * x + beta * y on the GPU. | |
magma_int_t | magma_zgeellmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t nnz_per_row, magmaDoubleComplex alpha, magmaDoubleComplex_ptr dval, magmaIndex_ptr dcolind, magmaDoubleComplex_ptr dx, magmaDoubleComplex beta, magmaDoubleComplex_ptr dy, magma_queue_t queue) |
This routine computes y = alpha * A * x + beta * y on the GPU. | |
magma_int_t | magma_zgeellmv_shift (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t nnz_per_row, magmaDoubleComplex alpha, magmaDoubleComplex lambda, magmaDoubleComplex_ptr dval, magmaIndex_ptr dcolind, magmaDoubleComplex_ptr dx, magmaDoubleComplex beta, int offset, int blocksize, magmaIndex_ptr addrows, magmaDoubleComplex_ptr dy, magma_queue_t queue) |
This routine computes y = alpha *( A - lambda I ) * x + beta * y on the GPU. | |
magma_int_t | magma_zgeellrtmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t nnz_per_row, magmaDoubleComplex alpha, magmaDoubleComplex_ptr dval, magmaIndex_ptr dcolind, magmaIndex_ptr drowlength, magmaDoubleComplex_ptr dx, magmaDoubleComplex beta, magmaDoubleComplex_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_zgeelltmv_shift (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t nnz_per_row, magmaDoubleComplex alpha, magmaDoubleComplex lambda, magmaDoubleComplex_ptr dval, magmaIndex_ptr dcolind, magmaDoubleComplex_ptr dx, magmaDoubleComplex beta, int offset, int blocksize, magmaIndex_ptr addrows, magmaDoubleComplex_ptr dy, magma_queue_t queue) |
This routine computes y = alpha *( A - lambda I ) * x + beta * y on the GPU. | |
magma_int_t | magma_zgesellpmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t blocksize, magma_int_t slices, magma_int_t alignment, magmaDoubleComplex alpha, magmaDoubleComplex_ptr dval, magmaIndex_ptr dcolind, magmaIndex_ptr drowptr, magmaDoubleComplex_ptr dx, magmaDoubleComplex beta, magmaDoubleComplex_ptr dy, magma_queue_t queue) |
This routine computes y = alpha * A^t * x + beta * y on the GPU. | |
magma_int_t | magma_zgesellcmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t blocksize, magma_int_t slices, magma_int_t alignment, magmaDoubleComplex alpha, magmaDoubleComplex_ptr dval, magmaIndex_ptr dcolind, magmaIndex_ptr drowptr, magmaDoubleComplex_ptr dx, magmaDoubleComplex beta, magmaDoubleComplex_ptr dy, magma_queue_t queue) |
This routine computes y = alpha * A^t * x + beta * y on the GPU. | |
magma_int_t | magma_zmdotc (int n, int k, magmaDoubleComplex_ptr v, magmaDoubleComplex_ptr r, magmaDoubleComplex_ptr d1, magmaDoubleComplex_ptr d2, magmaDoubleComplex_ptr skp, magma_queue_t queue) |
Computes the scalar product of a set of vectors v_i such that. | |
magma_int_t | magma_zmgecsrmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t num_vecs, magmaDoubleComplex alpha, magmaDoubleComplex_ptr dval, magmaIndex_ptr drowptr, magmaIndex_ptr dcolind, magmaDoubleComplex_ptr dx, magmaDoubleComplex beta, magmaDoubleComplex_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_zmgeellmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t num_vecs, magma_int_t nnz_per_row, magmaDoubleComplex alpha, magmaDoubleComplex_ptr dval, magmaIndex_ptr dcolind, magmaDoubleComplex_ptr dx, magmaDoubleComplex beta, magmaDoubleComplex_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_zmgeelltmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t num_vecs, magma_int_t nnz_per_row, magmaDoubleComplex alpha, magmaDoubleComplex_ptr dval, magmaIndex_ptr dcolind, magmaDoubleComplex_ptr dx, magmaDoubleComplex beta, magmaDoubleComplex_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_zmgesellpmv (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, magmaDoubleComplex alpha, magmaDoubleComplex_ptr dval, magmaIndex_ptr dcolind, magmaIndex_ptr drowptr, magmaDoubleComplex_ptr dx, magmaDoubleComplex beta, magmaDoubleComplex_ptr dy, magma_queue_t queue) |
This routine computes Y = alpha * A^t * X + beta * Y on the GPU. |
magma_int_t magma_zcuspaxpy | ( | magmaDoubleComplex * | alpha, | |
magma_z_matrix | A, | |||
magmaDoubleComplex * | beta, | |||
magma_z_matrix | B, | |||
magma_z_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
[in] | alpha | magmaDoubleComplex* scalar |
[in] | A | magma_z_matrix input matrix |
[in] | beta | magmaDoubleComplex* scalar |
[in] | B | magma_z_matrix input matrix |
[out] | AB | magma_z_matrix* output matrix AB = alpha * A + beta * B |
[in] | queue | magma_queue_t Queue to execute in. |
magma_int_t magma_zcuspmm | ( | magma_z_matrix | A, | |
magma_z_matrix | B, | |||
magma_z_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.
[in] | A | magma_z_matrix input matrix |
[in] | B | magma_z_matrix input matrix |
[out] | AB | magma_z_matrix* output matrix AB = A * B |
[in] | queue | magma_queue_t Queue to execute in. |
magma_int_t magma_zcustomspmv | ( | magmaDoubleComplex | alpha, | |
magma_z_matrix | x, | |||
magmaDoubleComplex | beta, | |||
magma_z_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.
[in] | alpha | magmaDoubleComplex scalar alpha |
[in] | x | magma_z_matrix input vector x |
[in] | beta | magmaDoubleComplex scalar beta |
[out] | y | magma_z_matrix output vector y |
[in] | queue | magma_queue_t Queue to execute in. |
magma_int_t magma_zgecsrmv | ( | magma_trans_t | transA, | |
magma_int_t | m, | |||
magma_int_t | n, | |||
magmaDoubleComplex | alpha, | |||
magmaDoubleComplex_ptr | dval, | |||
magmaIndex_ptr | drowptr, | |||
magmaIndex_ptr | dcolind, | |||
magmaDoubleComplex_ptr | dx, | |||
magmaDoubleComplex | beta, | |||
magmaDoubleComplex_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).
[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 | magmaDoubleComplex scalar multiplier |
[in] | dval | magmaDoubleComplex_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 | magmaDoubleComplex_ptr input vector x |
[in] | beta | magmaDoubleComplex scalar multiplier |
[out] | dy | magmaDoubleComplex_ptr input/output vector y |
[in] | queue | magma_queue_t Queue to execute in. |
magma_int_t magma_zgecsrmv_shift | ( | magma_trans_t | transA, | |
magma_int_t | m, | |||
magma_int_t | n, | |||
magmaDoubleComplex | alpha, | |||
magmaDoubleComplex | lambda, | |||
magmaDoubleComplex_ptr | dval, | |||
magmaIndex_ptr | drowptr, | |||
magmaIndex_ptr | dcolind, | |||
magmaDoubleComplex_ptr | dx, | |||
magmaDoubleComplex | beta, | |||
int | offset, | |||
int | blocksize, | |||
magma_index_t * | addrows, | |||
magmaDoubleComplex_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.
[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 | magmaDoubleComplex scalar multiplier |
[in] | lambda | magmaDoubleComplex scalar multiplier |
[in] | dval | magmaDoubleComplex_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 | magmaDoubleComplex_ptr input vector x |
[in] | beta | magmaDoubleComplex 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 | magmaDoubleComplex_ptr output vector y |
[in] | queue | magma_queue_t Queue to execute in. |
magma_int_t magma_zgeellmv | ( | magma_trans_t | transA, | |
magma_int_t | m, | |||
magma_int_t | n, | |||
magma_int_t | nnz_per_row, | |||
magmaDoubleComplex | alpha, | |||
magmaDoubleComplex_ptr | dval, | |||
magmaIndex_ptr | dcolind, | |||
magmaDoubleComplex_ptr | dx, | |||
magmaDoubleComplex | beta, | |||
magmaDoubleComplex_ptr | dy, | |||
magma_queue_t | queue | |||
) |
This routine computes y = alpha * A * x + beta * y on the GPU.
Input format is ELLPACK.
[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 | magmaDoubleComplex scalar multiplier |
[in] | dval | magmaDoubleComplex_ptr array containing values of A in ELLPACK |
[in] | dcolind | magmaIndex_ptr columnindices of A in ELLPACK |
[in] | dx | magmaDoubleComplex_ptr input vector x |
[in] | beta | magmaDoubleComplex scalar multiplier |
[out] | dy | magmaDoubleComplex_ptr input/output vector y |
[in] | queue | magma_queue_t Queue to execute in. |
magma_int_t magma_zgeellmv_shift | ( | magma_trans_t | transA, | |
magma_int_t | m, | |||
magma_int_t | n, | |||
magma_int_t | nnz_per_row, | |||
magmaDoubleComplex | alpha, | |||
magmaDoubleComplex | lambda, | |||
magmaDoubleComplex_ptr | dval, | |||
magmaIndex_ptr | dcolind, | |||
magmaDoubleComplex_ptr | dx, | |||
magmaDoubleComplex | beta, | |||
int | offset, | |||
int | blocksize, | |||
magmaIndex_ptr | addrows, | |||
magmaDoubleComplex_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.
[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 | magmaDoubleComplex scalar multiplier |
[in] | lambda | magmaDoubleComplex scalar multiplier |
[in] | dval | magmaDoubleComplex_ptr array containing values of A in ELLPACK |
[in] | dcolind | magmaIndex_ptr columnindices of A in ELLPACK |
[in] | dx | magmaDoubleComplex_ptr input vector x |
[in] | beta | magmaDoubleComplex 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 | magmaDoubleComplex_ptr input/output vector y |
[in] | queue | magma_queue_t Queue to execute in. |
magma_int_t magma_zgeellrtmv | ( | magma_trans_t | transA, | |
magma_int_t | m, | |||
magma_int_t | n, | |||
magma_int_t | nnz_per_row, | |||
magmaDoubleComplex | alpha, | |||
magmaDoubleComplex_ptr | dval, | |||
magmaIndex_ptr | dcolind, | |||
magmaIndex_ptr | drowlength, | |||
magmaDoubleComplex_ptr | dx, | |||
magmaDoubleComplex | beta, | |||
magmaDoubleComplex_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.
[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 | magmaDoubleComplex scalar alpha |
[in] | dval | magmaDoubleComplex_ptr val array |
[in] | dcolind | magmaIndex_ptr col indices |
[in] | drowlength | magmaIndex_ptr number of elements in each row |
[in] | dx | magmaDoubleComplex_ptr input vector x |
[in] | beta | magmaDoubleComplex scalar beta |
[out] | dy | magmaDoubleComplex_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_zgeelltmv_shift | ( | magma_trans_t | transA, | |
magma_int_t | m, | |||
magma_int_t | n, | |||
magma_int_t | nnz_per_row, | |||
magmaDoubleComplex | alpha, | |||
magmaDoubleComplex | lambda, | |||
magmaDoubleComplex_ptr | dval, | |||
magmaIndex_ptr | dcolind, | |||
magmaDoubleComplex_ptr | dx, | |||
magmaDoubleComplex | beta, | |||
int | offset, | |||
int | blocksize, | |||
magmaIndex_ptr | addrows, | |||
magmaDoubleComplex_ptr | dy, | |||
magma_queue_t | queue | |||
) |
This routine computes y = alpha *( A - lambda I ) * x + beta * y on the GPU.
Input format is ELL.
[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 | magmaDoubleComplex scalar multiplier |
[in] | lambda | magmaDoubleComplex scalar multiplier |
[in] | dval | magmaDoubleComplex_ptr array containing values of A in ELL |
[in] | dcolind | magmaIndex_ptr columnindices of A in ELL |
[in] | dx | magmaDoubleComplex_ptr input vector x |
[in] | beta | magmaDoubleComplex 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 | magmaDoubleComplex_ptr input/output vector y |
[in] | queue | magma_queue_t Queue to execute in. |
magma_int_t magma_zgesellcmv | ( | magma_trans_t | transA, | |
magma_int_t | m, | |||
magma_int_t | n, | |||
magma_int_t | blocksize, | |||
magma_int_t | slices, | |||
magma_int_t | alignment, | |||
magmaDoubleComplex | alpha, | |||
magmaDoubleComplex_ptr | dval, | |||
magmaIndex_ptr | dcolind, | |||
magmaIndex_ptr | drowptr, | |||
magmaDoubleComplex_ptr | dx, | |||
magmaDoubleComplex | beta, | |||
magmaDoubleComplex_ptr | dy, | |||
magma_queue_t | queue | |||
) |
This routine computes y = alpha * A^t * x + beta * y on the GPU.
Input format is SELLC/SELLP.
[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 | magmaDoubleComplex scalar multiplier |
[in] | dval | magmaDoubleComplex_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 | magmaDoubleComplex_ptr input vector x |
[in] | beta | magmaDoubleComplex scalar multiplier |
[out] | dy | magmaDoubleComplex_ptr input/output vector y |
[in] | queue | magma_queue_t Queue to execute in. |
magma_int_t magma_zgesellpmv | ( | magma_trans_t | transA, | |
magma_int_t | m, | |||
magma_int_t | n, | |||
magma_int_t | blocksize, | |||
magma_int_t | slices, | |||
magma_int_t | alignment, | |||
magmaDoubleComplex | alpha, | |||
magmaDoubleComplex_ptr | dval, | |||
magmaIndex_ptr | dcolind, | |||
magmaIndex_ptr | drowptr, | |||
magmaDoubleComplex_ptr | dx, | |||
magmaDoubleComplex | beta, | |||
magmaDoubleComplex_ptr | dy, | |||
magma_queue_t | queue | |||
) |
This routine computes y = alpha * A^t * x + beta * y on the GPU.
Input format is SELLP.
[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 | magmaDoubleComplex scalar multiplier |
[in] | dval | magmaDoubleComplex_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 | magmaDoubleComplex_ptr input vector x |
[in] | beta | magmaDoubleComplex scalar multiplier |
[out] | dy | magmaDoubleComplex_ptr input/output vector y |
[in] | queue | magma_queue_t Queue to execute in. |
magma_int_t magma_zmdotc | ( | int | n, | |
int | k, | |||
magmaDoubleComplex_ptr | v, | |||
magmaDoubleComplex_ptr | r, | |||
magmaDoubleComplex_ptr | d1, | |||
magmaDoubleComplex_ptr | d2, | |||
magmaDoubleComplex_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.
[in] | n | int length of v_i and r |
[in] | k | int # vectors v_i |
[in] | v | magmaDoubleComplex_ptr v = (v_0 .. v_i.. v_k) |
[in] | r | magmaDoubleComplex_ptr r |
[in] | d1 | magmaDoubleComplex_ptr workspace |
[in] | d2 | magmaDoubleComplex_ptr workspace |
[out] | skp | magmaDoubleComplex_ptr vector[k] of scalar products (<v_i,r>...) |
[in] | queue | magma_queue_t Queue to execute in. |
magma_int_t magma_zmgecsrmv | ( | magma_trans_t | transA, | |
magma_int_t | m, | |||
magma_int_t | n, | |||
magma_int_t | num_vecs, | |||
magmaDoubleComplex | alpha, | |||
magmaDoubleComplex_ptr | dval, | |||
magmaIndex_ptr | drowptr, | |||
magmaIndex_ptr | dcolind, | |||
magmaDoubleComplex_ptr | dx, | |||
magmaDoubleComplex | beta, | |||
magmaDoubleComplex_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.
[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 | magmaDoubleComplex scalar multiplier |
[in] | dval | magmaDoubleComplex_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 | magmaDoubleComplex_ptr input vector x |
[in] | beta | magmaDoubleComplex scalar multiplier |
[out] | dy | magmaDoubleComplex_ptr input/output vector y |
[in] | queue | magma_queue_t Queue to execute in. |
magma_int_t magma_zmgeellmv | ( | magma_trans_t | transA, | |
magma_int_t | m, | |||
magma_int_t | n, | |||
magma_int_t | num_vecs, | |||
magma_int_t | nnz_per_row, | |||
magmaDoubleComplex | alpha, | |||
magmaDoubleComplex_ptr | dval, | |||
magmaIndex_ptr | dcolind, | |||
magmaDoubleComplex_ptr | dx, | |||
magmaDoubleComplex | beta, | |||
magmaDoubleComplex_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.
[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 | magmaDoubleComplex scalar multiplier |
[in] | dval | magmaDoubleComplex_ptr array containing values of A in ELLPACK |
[in] | dcolind | magmaIndex_ptr columnindices of A in ELLPACK |
[in] | dx | magmaDoubleComplex_ptr input vector x |
[in] | beta | magmaDoubleComplex scalar multiplier |
[out] | dy | magmaDoubleComplex_ptr input/output vector y |
[in] | queue | magma_queue_t Queue to execute in. |
magma_int_t magma_zmgeelltmv | ( | magma_trans_t | transA, | |
magma_int_t | m, | |||
magma_int_t | n, | |||
magma_int_t | num_vecs, | |||
magma_int_t | nnz_per_row, | |||
magmaDoubleComplex | alpha, | |||
magmaDoubleComplex_ptr | dval, | |||
magmaIndex_ptr | dcolind, | |||
magmaDoubleComplex_ptr | dx, | |||
magmaDoubleComplex | beta, | |||
magmaDoubleComplex_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.
[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 | magmaDoubleComplex scalar multiplier |
[in] | dval | magmaDoubleComplex_ptr array containing values of A in ELL |
[in] | dcolind | magmaIndex_ptr columnindices of A in ELL |
[in] | dx | magmaDoubleComplex_ptr input vector x |
[in] | beta | magmaDoubleComplex scalar multiplier |
[out] | dy | magmaDoubleComplex_ptr input/output vector y |
[in] | queue | magma_queue_t Queue to execute in. |
magma_int_t magma_zmgesellpmv | ( | 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, | |||
magmaDoubleComplex | alpha, | |||
magmaDoubleComplex_ptr | dval, | |||
magmaIndex_ptr | dcolind, | |||
magmaIndex_ptr | drowptr, | |||
magmaDoubleComplex_ptr | dx, | |||
magmaDoubleComplex | beta, | |||
magmaDoubleComplex_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!
[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 | magmaDoubleComplex scalar multiplier |
[in] | dval | magmaDoubleComplex_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 | magmaDoubleComplex_ptr input vector x |
[in] | beta | magmaDoubleComplex scalar multiplier |
[out] | dy | magmaDoubleComplex_ptr input/output vector y |
[in] | queue | magma_queue_t Queue to execute in. |