Computes a rank-1 update of a general matrix.
event ger(queue &exec_queue, std::int64_t m, std::int64_t n, T alpha, const T *x, std::int64_t incx, const T *y, std::int64_t incy, T *a, std::int64_t lda, const vector_class<event> &dependencies = {});
The USM version of ger supports the following precisions and devices.
T | Devices Supported |
---|---|
float | Host, CPU, and GPU |
double | Host, CPU, and GPU |
The ger routines compute a scalar-vector-vector product and add the result to a general matrix. The operation is defined as
A <- alpha*x*yT + A
where:
alpha is scalar,
A is an m-by-n matrix,
x is a vector length m,
y is a vector length n.
The queue where the routine should be executed.
Number of rows of A. Must be at least zero.
Number of columns of A. Must be at least zero.
Scaling factor for the matrix-vector product.
Pointer to input vector x. The array holding input vector x must be of size at least (1 + (m - 1)*abs(incx)). See Matrix and Vector Storage for more details.
Stride of vector x.
Pointer to input/output vector y. The array holding input/output vector y must be of size at least (1 + (n - 1)*abs(incy)). See Matrix and Vector Storage for more details.
Stride of vector y.
The array holding input matrix A must have size at least lda*n if column major layout is used, or at least lda*m if row major layout is used.
Leading dimension of matrix A. It must be positive and at least m if column major layout is used or at least n if row major layout is used.
List of events to wait for before starting computation, if any. If omitted, defaults to no dependencies.
Pointer to the updated matrix A.
Output event to wait on to ensure computation is complete.