Function cusparse_spmv 

pub fn cusparse_spmv(
    handle: &CusparseCompatHandle,
    alpha: f64,
    a: &HostCsr,
    x: &[f64],
    beta: f64,
    y: &mut [f64],
) -> SparseResult<()>

Computes the sparse matrix-vector product y = alpha * A * x + beta * y, mirroring cusparseSpMV for a CSR operand.

x must have length A.ncols and y length A.nrows. When beta == 0 the prior contents of y are ignored (overwritten), matching cuSPARSE.

Errors

Returns SparseError::DimensionMismatch if x.len() != A.ncols or y.len() != A.nrows.