getrs_batch (Group Version)#
Solves a batch of systems of linear equations with a batch of
LU-factored square coefficient matrices, with multiple right-hand sides.
This routine belongs to the oneapi::mkl::lapack namespace.
Description#
The routine solves for Xi (iϵ{1...batch_size}) the
following systems of linear equations:
Ai *Xi =Bi Iftrans = mkl::transpose::notransAiT *Xi =Bi Iftrans = mkl::transpose::transAiH *Xi =Bi Iftrans = mkl::transpose::conjtrans
Before calling this routine you must call getrf_batch (Group Version) to
compute the LU factorization of A i.
The total number of problems to solve, batch_size, is a sum of sizes
of all of the groups of parameters as provided by``group_sizes`` array.
API#
Syntax#
namespace oneapi::mkl::lapack {
sycl::event getrs_batch(sycl::queue &queue,
mkl::transpose *trans,
int64_t *n,
int64_t *nrhs,
const T * const *a,
int64_t *lda,
const int64_t * const *ipiv,
T **b,
int64_t *ldb,
int64_t group_count,
int64_t *group_sizes,
T *scratchpad,
int64_t scratchpad_size,
const std::vector<sycl::event> &events = {})
}
This function supports the following precisions and devices:
T |
Devices supported |
|---|---|
|
CPU and GPU |
|
CPU and GPU |
|
CPU and GPU |
|
CPU and GPU |
Input Parameters#
- queue
Device queue where calculations will be performed.
- trans
Array of
group_countparameters transg indicating the form of the equations for the groupg:If trans = mkl::transpose::nontrans, then
Ai*Xi =Bi is solved forXi.If trans = mkl::transpose::trans, then
AiT*Xi =Bi is solved forXi.If trans = mkl::transpose::conjtrans, then
AiH*Xi =Bi is solved forXi.- n
Array of
group_countparametersng specifying the order of the matricesAi and the number of rows in matricesBi belonging to groupg(ng ≥ 0).- nrhs
Array of
group_countparameters nrhsg specifying the number of right hand sides for groupg(nrhsg ≥ 0).- a
Array of
batch_sizepointers to factorization of the matricesAi, as returned by getrf_batch (Group Version). The pointers must be device-accessible.- lda
Array of
group_countparameters ldag specifying the leading dimension ofAi from groupg(ldag ≥max(1, ng)).- ipiv
The ipiv array, as returned by getrf_batch (Group Version). The pointers must be device-accessible.
- b
The array containing
batch_sizepointers to the matricesBi whose columns are the right-hand sides for the systems of equations. The pointers must be device-accessible.- ldb
Array of
group_countparameters ldbg specifying the leading dimensions ofBi in the groupg(ldbg ≥max(1, ng)).- group_count
Specifies the number of groups of parameters. Must be at least 0.
- group_sizes
Array of group_count integers. Array element with index
gspecifies the number of problems to solve for each of the groups of parametersg. So the total number of problems to solve,batch_size, is a sum of all parameter group sizes.- scratchpad
Scratchpad memory to be used by routine for storing intermediate results.
- scratchpad_size
Size of scratchpad memory as a number of floating point elements of type T. Size should not be less then the value returned by getrs_batch_scratchpad_size (Group Version).
- events
List of events to wait for before starting computation. Defaults to empty list.
Output Parameters#
- b
Overwritten by the solution matrices
Xi.
Exceptions#
Exception |
Description |
|---|---|
|
This exception is thrown when problems occur during calculations. You can obtain the info code of the problem using the info() method of the exception object: If If If |
Return Values#
Output event to wait on to ensure computation is complete.