# getri¶

Computes the inverse of an LU-factored general matrix determined by getrf.

Description

getri supports the following precisions.

T

float

double

std::complex<float>

std::complex<double>

The routine computes the inverse $$A^{-1}$$ of a general matrix $$A$$. Before calling this routine, call getrf to factorize $$A$$.

## getri (BUFFER Version)¶

Syntax

namespace oneapi::mkl::lapack {
void getri(sycl::queue &queue, std::int64_t n, sycl::buffer<T,1> &a, std::int64_t lda, sycl::buffer<std::int64_t,1> &ipiv, sycl::buffer<T,1> &scratchpad, std::int64_t scratchpad_size)
}


Input Parameters

queue

The queue where the routine should be executed.

n

The order of the matrix $$A$$ $$(0 \le n)$$.

a

The buffer a as returned by getrf. Must be of size at least $$\text{lda} \cdot \max(1,n)$$.

lda

The leading dimension of a $$(n \le \text{lda})$$.

ipiv

The buffer as returned by getrf. The dimension of ipiv must be at least $$\max(1, n)$$.

Size of scratchpad memory as a number of floating point elements of type T. Size should not be less than the value returned by getri_scratchpad_size function.

Output Parameters

a

Overwritten by the $$n \times n$$ matrix $$A$$.

Buffer holding scratchpad memory to be used by routine for storing intermediate results.

## getri (USM Version)¶

Syntax

namespace oneapi::mkl::lapack {
sycl::event getri(sycl::queue &queue, std::int64_t n, T *a, std::int64_t lda, std::int64_t *ipiv, T *scratchpad, std::int64_t scratchpad_size, const std::vector<sycl::event> &events = {})
}


Input Parameters

queue

The queue where the routine should be executed.

n

The order of the matrix $$A$$ $$(0 \le n)$$.

a

The array as returned by getrf. Must be of size at least $$\text{lda} \cdot \max(1,n)$$.

lda

The leading dimension of a $$(n \le \text{lda})$$.

ipiv

The array as returned by getrf. The dimension of ipiv must be at least $$\max(1, n)$$.

Size of scratchpad memory as a number of floating point elements of type T. Size should not be less than the value returned by getri_scratchpad_size function.

events

List of events to wait for before starting computation. Defaults to empty list.

Output Parameters

a

Overwritten by the $$n \times n$$ matrix $$A$$.