warp.tile_cholesky_solve#
- warp.tile_cholesky_solve( ) Tile[Float, tuple[int]]#
Kernel
Solve for
xinAx = y.Note that computing the adjoint is not yet supported.
- Supported datatypes are:
float32
float64
- Parameters:
L – A square, lower triangular, matrix, such that
LL^T = A.y – A 1D or 2D tile of length
M.
- Returns:
A tile of the same shape as
ysuch thatLL^T x = y.