getri_batch¶

Computes the inverses of a batch of LU-factored matrices determined by getrf_batch.

getri_batch supports the following precisions.

T

float

double

std::complex<float>

std::complex<double>

Description

The routine computes the inverses A_i^-1 of a batch of general matrices A_i, A₂, …, A_{batch_size} . Before calling this routine, call getrf_batch to compute the LU factorization of A_i, A₂, …, A_{batch_size}.

getri_batch (BUFFER Version)¶

Syntax

void onemkl::lapack::getri_batch(cl::sycl::queue &queue, std::vector<std::int64_t> const &n, std::vector<cl::sycl::buffer<T, 1>> &a, std::vector<std::int64_t> const &lda, std::vector<cl::sycl::buffer<std::int64_t, 1>> &ipiv, std::vector<cl::sycl::buffer<std::int64_t, 1>> &info)¶

Input Parameters

queue: The queue where the routine should be executed.
n: A vector, n[i] is order of the matrix A_i(0≤n[i]).
a: A vector of buffers returned by getrf_batch. a[i] must be of size at least lda[i]*max(1, n[i]).
lda: A vector, lda[i] is the leading dimension of a[i] (n[i]≤lda[i]).
ipiv: A vector of buffers returned by getrf_batch. . The dimension of ipiv[i] must be at least max(1, n[i]).

Output Parameters

a

a[i] is overwritten by the n[i]-by-n[i] inverse matrix A_i^-1.

info

Vector of buffers containing error information.

If info[i]=0, the execution is successful.

If info[i]=-k, the k-th parameter had an illegal value.

Parent topic: LAPACK-like Extensions Routines