Functions
magma_int_t	magma_dbajac_csr (magma_int_t localiters, magma_d_matrix D, magma_d_matrix R, magma_d_matrix b, magma_d_matrix *x, magma_queue_t queue)
	This routine is a block-asynchronous Jacobi iteration performing s local Jacobi-updates within the block. More...

magma_int_t	magma_dbajac_csr_overlap (magma_int_t localiters, magma_int_t matrices, magma_int_t overlap, magma_d_matrix D, magma_d_matrix R, magma_d_matrix b, magma_d_matrix *x, magma_queue_t queue)
	This routine is a block-asynchronous Jacobi iteration with directed restricted additive Schwarz overlap (top-down) performing s local Jacobi-updates within the block. More...

magma_int_t	magma_dcompact (magma_int_t m, magma_int_t n, magmaDouble_ptr dA, magma_int_t ldda, magmaDouble_ptr dnorms, double tol, magmaInt_ptr active, magmaInt_ptr cBlock, magma_queue_t queue)
	ZCOMPACT takes a set of n vectors of size m (in dA) and their norms and compacts them into the cBlock size<=n vectors that have norms > tol. More...

magma_int_t	magma_djacobisetup_vector_gpu (magma_int_t num_rows, magma_d_matrix b, magma_d_matrix d, magma_d_matrix c, magma_d_matrix *x, magma_queue_t queue)
	Prepares the Jacobi Iteration according to x^(k+1) = D^(-1) * b - D^(-1) * (L+U) * x^k x^(k+1) = c - M * x^k. More...

magma_int_t	magma_dlobpcg_maxpy (magma_int_t num_rows, magma_int_t num_vecs, magmaDouble_ptr X, magmaDouble_ptr Y, magma_queue_t queue)
	This routine computes a axpy for a mxn matrix: More...

magma_int_t	magma_dbicgstab_1 (magma_int_t num_rows, magma_int_t num_cols, double beta, double omega, magmaDouble_ptr r, magmaDouble_ptr v, magmaDouble_ptr p, magma_queue_t queue)
	Mergels multiple operations into one kernel: More...

magma_int_t	magma_dbicgstab_2 (magma_int_t num_rows, magma_int_t num_cols, double alpha, magmaDouble_ptr r, magmaDouble_ptr v, magmaDouble_ptr s, magma_queue_t queue)
	Mergels multiple operations into one kernel: More...

magma_int_t	magma_dbicgstab_3 (magma_int_t num_rows, magma_int_t num_cols, double alpha, double omega, magmaDouble_ptr p, magmaDouble_ptr s, magmaDouble_ptr t, magmaDouble_ptr x, magmaDouble_ptr r, magma_queue_t queue)
	Mergels multiple operations into one kernel: More...

magma_int_t	magma_dbicgstab_4 (magma_int_t num_rows, magma_int_t num_cols, double alpha, double omega, magmaDouble_ptr y, magmaDouble_ptr z, magmaDouble_ptr s, magmaDouble_ptr t, magmaDouble_ptr x, magmaDouble_ptr r, magma_queue_t queue)
	Mergels multiple operations into one kernel: More...

magma_int_t	magma_dbicgmerge_spmv1 (magma_d_matrix A, magmaDouble_ptr d1, magmaDouble_ptr d2, magmaDouble_ptr dp, magmaDouble_ptr dr, magmaDouble_ptr dv, magmaDouble_ptr skp, magma_queue_t queue)
	Merges the first SpmV using CSR with the dot product and the computation of alpha. More...

magma_int_t	magma_dbicgmerge_spmv2 (magma_d_matrix A, magmaDouble_ptr d1, magmaDouble_ptr d2, magmaDouble_ptr ds, magmaDouble_ptr dt, magmaDouble_ptr skp, magma_queue_t queue)
	Merges the second SpmV using CSR with the dot product and the computation of omega. More...

magma_int_t	magma_dbicgmerge_xrbeta (magma_int_t n, magmaDouble_ptr d1, magmaDouble_ptr d2, magmaDouble_ptr rr, magmaDouble_ptr r, magmaDouble_ptr p, magmaDouble_ptr s, magmaDouble_ptr t, magmaDouble_ptr x, magmaDouble_ptr skp, magma_queue_t queue)
	Merges the second SpmV using CSR with the dot product and the computation of omega. More...

magma_int_t	magma_dbicgmerge1 (magma_int_t n, magmaDouble_ptr skp, magmaDouble_ptr v, magmaDouble_ptr r, magmaDouble_ptr p, magma_queue_t queue)
	Mergels multiple operations into one kernel: More...

magma_int_t	magma_dbicgmerge2 (magma_int_t n, magmaDouble_ptr skp, magmaDouble_ptr r, magmaDouble_ptr v, magmaDouble_ptr s, magma_queue_t queue)
	Mergels multiple operations into one kernel: More...

magma_int_t	magma_dbicgmerge3 (magma_int_t n, magmaDouble_ptr skp, magmaDouble_ptr p, magmaDouble_ptr s, magmaDouble_ptr t, magmaDouble_ptr x, magmaDouble_ptr r, magma_queue_t queue)
	Mergels multiple operations into one kernel: More...

magma_int_t	magma_dbicgmerge4 (magma_int_t type, magmaDouble_ptr skp, magma_queue_t queue)
	Performs some parameter operations for the BiCGSTAB with scalars on GPU. More...

magma_int_t	magma_dmergeblockkrylov (magma_int_t num_rows, magma_int_t num_cols, magmaDouble_ptr alpha, magmaDouble_ptr p, magmaDouble_ptr x, magma_queue_t queue)
	Mergels multiple operations into one kernel: More...

magma_int_t	magma_dcgmerge_spmv1 (magma_d_matrix A, magmaDouble_ptr d1, magmaDouble_ptr d2, magmaDouble_ptr dd, magmaDouble_ptr dz, magmaDouble_ptr skp, magma_queue_t queue)
	Merges the first SpmV using different formats with the dot product and the computation of rho. More...

magma_int_t	magma_dcgs_1 (magma_int_t num_rows, magma_int_t num_cols, double beta, magmaDouble_ptr r, magmaDouble_ptr q, magmaDouble_ptr u, magmaDouble_ptr p, magma_queue_t queue)
	Mergels multiple operations into one kernel: More...

magma_int_t	magma_dcgs_2 (magma_int_t num_rows, magma_int_t num_cols, magmaDouble_ptr r, magmaDouble_ptr u, magmaDouble_ptr p, magma_queue_t queue)
	Mergels multiple operations into one kernel: More...

magma_int_t	magma_dcgs_3 (magma_int_t num_rows, magma_int_t num_cols, double alpha, magmaDouble_ptr v_hat, magmaDouble_ptr u, magmaDouble_ptr q, magmaDouble_ptr t, magma_queue_t queue)
	Mergels multiple operations into one kernel: More...

magma_int_t	magma_dcgs_4 (magma_int_t num_rows, magma_int_t num_cols, double alpha, magmaDouble_ptr u_hat, magmaDouble_ptr t, magmaDouble_ptr x, magmaDouble_ptr r, magma_queue_t queue)
	Mergels multiple operations into one kernel: More...

magma_int_t	magma_didr_smoothing_1 (magma_int_t num_rows, magma_int_t num_cols, magmaDouble_ptr drs, magmaDouble_ptr dr, magmaDouble_ptr dt, magma_queue_t queue)
	Mergels multiple operations into one kernel: More...

magma_int_t	magma_didr_smoothing_2 (magma_int_t num_rows, magma_int_t num_cols, double omega, magmaDouble_ptr dx, magmaDouble_ptr dxs, magma_queue_t queue)
	Mergels multiple operations into one kernel: More...

magma_int_t	magma_dqmr_1 (magma_int_t num_rows, magma_int_t num_cols, double rho, double psi, magmaDouble_ptr y, magmaDouble_ptr z, magmaDouble_ptr v, magmaDouble_ptr w, magma_queue_t queue)
	Mergels multiple operations into one kernel: More...

magma_int_t	magma_dqmr_2 (magma_int_t num_rows, magma_int_t num_cols, double pde, double rde, magmaDouble_ptr y, magmaDouble_ptr z, magmaDouble_ptr p, magmaDouble_ptr q, magma_queue_t queue)
	Mergels multiple operations into one kernel: More...

magma_int_t	magma_dqmr_3 (magma_int_t num_rows, magma_int_t num_cols, double beta, magmaDouble_ptr pt, magmaDouble_ptr v, magmaDouble_ptr y, magma_queue_t queue)
	Mergels multiple operations into one kernel: More...

magma_int_t	magma_dqmr_4 (magma_int_t num_rows, magma_int_t num_cols, double eta, magmaDouble_ptr p, magmaDouble_ptr pt, magmaDouble_ptr d, magmaDouble_ptr s, magmaDouble_ptr x, magmaDouble_ptr r, magma_queue_t queue)
	Mergels multiple operations into one kernel: More...

magma_int_t	magma_dqmr_5 (magma_int_t num_rows, magma_int_t num_cols, double eta, double pds, magmaDouble_ptr p, magmaDouble_ptr pt, magmaDouble_ptr d, magmaDouble_ptr s, magmaDouble_ptr x, magmaDouble_ptr r, magma_queue_t queue)
	Mergels multiple operations into one kernel: More...

magma_int_t	magma_dqmr_6 (magma_int_t num_rows, magma_int_t num_cols, double beta, double rho, double psi, magmaDouble_ptr y, magmaDouble_ptr z, magmaDouble_ptr v, magmaDouble_ptr w, magmaDouble_ptr wt, magma_queue_t queue)
	Mergels multiple operations into one kernel: More...

magma_int_t	magma_dqmr_7 (magma_int_t num_rows, magma_int_t num_cols, double beta, magmaDouble_ptr pt, magmaDouble_ptr v, magmaDouble_ptr vt, magma_queue_t queue)
	Mergels multiple operations into one kernel: More...

magma_int_t	magma_dqmr_8 (magma_int_t num_rows, magma_int_t num_cols, double rho, double psi, magmaDouble_ptr vt, magmaDouble_ptr wt, magmaDouble_ptr y, magmaDouble_ptr z, magmaDouble_ptr v, magmaDouble_ptr w, magma_queue_t queue)
	Mergels multiple operations into one kernel: More...

magma_int_t	magma_dtfqmr_1 (magma_int_t num_rows, magma_int_t num_cols, double alpha, double sigma, magmaDouble_ptr v, magmaDouble_ptr Au, magmaDouble_ptr u_m, magmaDouble_ptr pu_m, magmaDouble_ptr u_mp1, magmaDouble_ptr w, magmaDouble_ptr d, magmaDouble_ptr Ad, magma_queue_t queue)
	Mergels multiple operations into one kernel: More...

magma_int_t	magma_dtfqmr_2 (magma_int_t num_rows, magma_int_t num_cols, double eta, magmaDouble_ptr d, magmaDouble_ptr Ad, magmaDouble_ptr x, magmaDouble_ptr r, magma_queue_t queue)
	Mergels multiple operations into one kernel: More...

magma_int_t	magma_dtfqmr_3 (magma_int_t num_rows, magma_int_t num_cols, double beta, magmaDouble_ptr w, magmaDouble_ptr u_m, magmaDouble_ptr u_mp1, magma_queue_t queue)
	Mergels multiple operations into one kernel: More...

magma_int_t	magma_dtfqmr_4 (magma_int_t num_rows, magma_int_t num_cols, double beta, magmaDouble_ptr Au_new, magmaDouble_ptr v, magmaDouble_ptr Au, magma_queue_t queue)
	Merges multiple operations into one kernel: More...

magma_int_t	magma_dtfqmr_5 (magma_int_t num_rows, magma_int_t num_cols, double alpha, double sigma, magmaDouble_ptr v, magmaDouble_ptr Au, magmaDouble_ptr u_mp1, magmaDouble_ptr w, magmaDouble_ptr d, magmaDouble_ptr Ad, magma_queue_t queue)
	Mergels multiple operations into one kernel: More...

magma_int_t	magma_dparic_csr (magma_d_matrix A, magma_d_matrix A_CSR, magma_queue_t queue)
	This routine iteratively computes an incomplete LU factorization. More...

magma_int_t	magma_dparilu_csr (magma_d_matrix A, magma_d_matrix L, magma_d_matrix U, magma_queue_t queue)
	This routine iteratively computes an incomplete LU factorization. More...

magma_int_t	magma_dparilut_sweep_gpu (magma_d_matrix A, magma_d_matrix L, magma_d_matrix *U, magma_queue_t queue)
	This function does an ParILUT sweep. More...

magma_int_t	magma_dparilut_residuals_gpu (magma_d_matrix A, magma_d_matrix L, magma_d_matrix U, magma_d_matrix *R, magma_queue_t queue)
	This function computes the ILU residual in the locations included in the sparsity pattern of R. More...

magma_int_t	magma_dvalinit_gpu (magma_int_t num_el, magmaDouble_ptr dval, magma_queue_t queue)
	Initializes a device array with zero. More...

magma_int_t	magma_dindexinit_gpu (magma_int_t num_el, magmaIndex_ptr dind, magma_queue_t queue)
	Initializes a device array with zero. More...

Detailed Description

Function Documentation

magma_int_t magma_dbajac_csr	(	magma_int_t	localiters,
		magma_d_matrix	D,
		magma_d_matrix	R,
		magma_d_matrix	b,
		magma_d_matrix *	x,
		magma_queue_t	queue
	)

This routine is a block-asynchronous Jacobi iteration performing s local Jacobi-updates within the block.

Input format is two CSR matrices, one containing the diagonal blocks, one containing the rest.

Parameters

[in]	localiters	magma_int_t number of local Jacobi-like updates
[in]	D	magma_d_matrix input matrix with diagonal blocks
[in]	R	magma_d_matrix input matrix with non-diagonal parts
[in]	b	magma_d_matrix RHS
[in]	x	magma_d_matrix* iterate/solution
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dbajac_csr_overlap	(	magma_int_t	localiters,
		magma_int_t	matrices,
		magma_int_t	overlap,
		magma_d_matrix *	D,
		magma_d_matrix *	R,
		magma_d_matrix	b,
		magma_d_matrix *	x,
		magma_queue_t	queue
	)

This routine is a block-asynchronous Jacobi iteration with directed restricted additive Schwarz overlap (top-down) performing s local Jacobi-updates within the block.

Input format is two CSR matrices, one containing the diagonal blocks, one containing the rest.

Parameters

[in]	localiters	magma_int_t number of local Jacobi-like updates
[in]	matrices	magma_int_t number of sub-matrices
[in]	overlap	magma_int_t size of the overlap
[in]	D	magma_d_matrix* set of matrices with diagonal blocks
[in]	R	magma_d_matrix* set of matrices with non-diagonal parts
[in]	b	magma_d_matrix RHS
[in]	x	magma_d_matrix* iterate/solution
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dcompact	(	magma_int_t	m,
		magma_int_t	n,
		magmaDouble_ptr	dA,
		magma_int_t	ldda,
		magmaDouble_ptr	dnorms,
		double	tol,
		magmaInt_ptr	active,
		magmaInt_ptr	cBlock,
		magma_queue_t	queue
	)

ZCOMPACT takes a set of n vectors of size m (in dA) and their norms and compacts them into the cBlock size<=n vectors that have norms > tol.

The active mask array has 1 or 0, showing if a vector remained or not in the compacted resulting set of vectors.

Parameters

[in]	m	INTEGER The number of rows of the matrix dA. M >= 0.
[in]	n	INTEGER The number of columns of the matrix dA. N >= 0.
[in,out]	dA	COMPLEX DOUBLE PRECISION array, dimension (LDDA,N) The m by n matrix dA.
[in]	ldda	INTEGER The leading dimension of the array dA. LDDA >= max(1,M).
[in]	dnorms	DOUBLE PRECISION array, dimension N The norms of the N vectors in dA
[in]	tol	DOUBLE PRECISON The tolerance value used in the criteria to compact or not.
[in,out]	active	INTEGER array, dimension N A mask of 1s and 0s showing if a vector remains or has been removed
[in,out]	cBlock	magmaInt_ptr The number of vectors that remain in dA (i.e., with norms > tol).
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_djacobisetup_vector_gpu	(	magma_int_t	num_rows,
		magma_d_matrix	b,
		magma_d_matrix	d,
		magma_d_matrix	c,
		magma_d_matrix *	x,
		magma_queue_t	queue
	)

Prepares the Jacobi Iteration according to x^(k+1) = D^(-1) * b - D^(-1) * (L+U) * x^k x^(k+1) = c - M * x^k.

Returns the vector c. It calls a GPU kernel

Parameters

[in]	num_rows	magma_int_t number of rows
[in]	b	magma_d_matrix RHS b
[in]	d	magma_d_matrix vector with diagonal entries
[out]	c	magma_d_matrix* c = D^(-1) * b
[out]	x	magma_d_matrix* iteration vector
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dlobpcg_maxpy	(	magma_int_t	num_rows,
		magma_int_t	num_vecs,
		magmaDouble_ptr	X,
		magmaDouble_ptr	Y,
		magma_queue_t	queue
	)

This routine computes a axpy for a mxn matrix:

Y = X + Y

It replaces: magma_daxpy(m*n, c_one, Y, 1, X, 1);

/ x1[0] x2[0] x3[0] \
| x1[1] x2[1] x3[1] |

X = | x1[2] x2[2] x3[2] | = x1[0] x1[1] x1[2] x1[3] x1[4] x2[0] x2[1] . | x1[3] x2[3] x3[3] | \ x1[4] x2[4] x3[4] /

Parameters

[in]	num_rows	magma_int_t number of rows
[in]	num_vecs	magma_int_t number of vectors
[in]	X	magmaDouble_ptr input vector X
[in,out]	Y	magmaDouble_ptr input/output vector Y
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dbicgstab_1	(	magma_int_t	num_rows,
		magma_int_t	num_cols,
		double	beta,
		double	omega,
		magmaDouble_ptr	r,
		magmaDouble_ptr	v,
		magmaDouble_ptr	p,
		magma_queue_t	queue
	)

Mergels multiple operations into one kernel:

p = r + beta * ( p - omega * v )

Parameters

[in]	num_rows	magma_int_t dimension m
[in]	num_cols	magma_int_t dimension n
[in]	beta	double scalar
[in]	omega	double scalar
[in]	r	magmaDouble_ptr vector
[in]	v	magmaDouble_ptr vector
[in,out]	p	magmaDouble_ptr vector
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dbicgstab_2	(	magma_int_t	num_rows,
		magma_int_t	num_cols,
		double	alpha,
		magmaDouble_ptr	r,
		magmaDouble_ptr	v,
		magmaDouble_ptr	s,
		magma_queue_t	queue
	)

Mergels multiple operations into one kernel:

s = r - alpha v

Parameters

[in]	num_rows	magma_int_t dimension m
[in]	num_cols	magma_int_t dimension n
[in]	alpha	double scalar
[in]	r	magmaDouble_ptr vector
[in]	v	magmaDouble_ptr vector
[in,out]	s	magmaDouble_ptr vector
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dbicgstab_3	(	magma_int_t	num_rows,
		magma_int_t	num_cols,
		double	alpha,
		double	omega,
		magmaDouble_ptr	p,
		magmaDouble_ptr	s,
		magmaDouble_ptr	t,
		magmaDouble_ptr	x,
		magmaDouble_ptr	r,
		magma_queue_t	queue
	)

Mergels multiple operations into one kernel:

x = x + alpha * p + omega * s r = s - omega * t

Parameters

[in]	num_rows	magma_int_t dimension m
[in]	num_cols	magma_int_t dimension n
[in]	alpha	double scalar
[in]	omega	double scalar
[in]	p	magmaDouble_ptr vector
[in]	s	magmaDouble_ptr vector
[in]	t	magmaDouble_ptr vector
[in,out]	x	magmaDouble_ptr vector
[in,out]	r	magmaDouble_ptr vector
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dbicgstab_4	(	magma_int_t	num_rows,
		magma_int_t	num_cols,
		double	alpha,
		double	omega,
		magmaDouble_ptr	y,
		magmaDouble_ptr	z,
		magmaDouble_ptr	s,
		magmaDouble_ptr	t,
		magmaDouble_ptr	x,
		magmaDouble_ptr	r,
		magma_queue_t	queue
	)

Mergels multiple operations into one kernel:

x = x + alpha * y + omega * z r = s - omega * t

Parameters

[in]	num_rows	magma_int_t dimension m
[in]	num_cols	magma_int_t dimension n
[in]	alpha	double scalar
[in]	omega	double scalar
[in]	y	magmaDouble_ptr vector
[in]	z	magmaDouble_ptr vector
[in]	s	magmaDouble_ptr vector
[in]	t	magmaDouble_ptr vector
[in,out]	x	magmaDouble_ptr vector
[in,out]	r	magmaDouble_ptr vector
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dbicgmerge_spmv1	(	magma_d_matrix	A,
		magmaDouble_ptr	d1,
		magmaDouble_ptr	d2,
		magmaDouble_ptr	dp,
		magmaDouble_ptr	dr,
		magmaDouble_ptr	dv,
		magmaDouble_ptr	skp,
		magma_queue_t	queue
	)

Merges the first SpmV using CSR with the dot product and the computation of alpha.

Parameters

[in]	A	magma_d_matrix system matrix
[in]	d1	magmaDouble_ptr temporary vector
[in]	d2	magmaDouble_ptr temporary vector
[in]	dp	magmaDouble_ptr input vector p
[in]	dr	magmaDouble_ptr input vector r
[in]	dv	magmaDouble_ptr output vector v
[in,out]	skp	magmaDouble_ptr array for parameters ( skp[0]=alpha )
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dbicgmerge_spmv2	(	magma_d_matrix	A,
		magmaDouble_ptr	d1,
		magmaDouble_ptr	d2,
		magmaDouble_ptr	ds,
		magmaDouble_ptr	dt,
		magmaDouble_ptr	skp,
		magma_queue_t	queue
	)

Merges the second SpmV using CSR with the dot product and the computation of omega.

Parameters

[in]	A	magma_d_matrix input matrix
[in]	d1	magmaDouble_ptr temporary vector
[in]	d2	magmaDouble_ptr temporary vector
[in]	ds	magmaDouble_ptr input vector s
[in]	dt	magmaDouble_ptr output vector t
[in,out]	skp	magmaDouble_ptr array for parameters
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dbicgmerge_xrbeta	(	magma_int_t	n,
		magmaDouble_ptr	d1,
		magmaDouble_ptr	d2,
		magmaDouble_ptr	rr,
		magmaDouble_ptr	r,
		magmaDouble_ptr	p,
		magmaDouble_ptr	s,
		magmaDouble_ptr	t,
		magmaDouble_ptr	x,
		magmaDouble_ptr	skp,
		magma_queue_t	queue
	)

Merges the second SpmV using CSR with the dot product and the computation of omega.

Parameters

[in]	n	int dimension n
[in]	d1	magmaDouble_ptr temporary vector
[in]	d2	magmaDouble_ptr temporary vector
[in]	rr	magmaDouble_ptr input vector rr
[in]	r	magmaDouble_ptr input/output vector r
[in]	p	magmaDouble_ptr input vector p
[in]	s	magmaDouble_ptr input vector s
[in]	t	magmaDouble_ptr input vector t
[out]	x	magmaDouble_ptr output vector x
[in]	skp	magmaDouble_ptr array for parameters
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dbicgmerge1	(	magma_int_t	n,
		magmaDouble_ptr	skp,
		magmaDouble_ptr	v,
		magmaDouble_ptr	r,
		magmaDouble_ptr	p,
		magma_queue_t	queue
	)

Mergels multiple operations into one kernel:

p = beta*p p = p-omega*beta*v p = p+r

-> p = r + beta * ( p - omega * v )

Parameters

[in]	n	int dimension n
[in]	skp	magmaDouble_ptr set of scalar parameters
[in]	v	magmaDouble_ptr input vector v
[in]	r	magmaDouble_ptr input vector r
[in,out]	p	magmaDouble_ptr input/output vector p
[in]	queue	magma_queue_t queue to execute in.

magma_int_t magma_dbicgmerge2	(	magma_int_t	n,
		magmaDouble_ptr	skp,
		magmaDouble_ptr	r,
		magmaDouble_ptr	v,
		magmaDouble_ptr	s,
		magma_queue_t	queue
	)

Mergels multiple operations into one kernel:

s=r s=s-alpha*v

-> s = r - alpha * v

Parameters

[in]	n	int dimension n
[in]	skp	magmaDouble_ptr set of scalar parameters
[in]	r	magmaDouble_ptr input vector r
[in]	v	magmaDouble_ptr input vector v
[out]	s	magmaDouble_ptr output vector s
[in]	queue	magma_queue_t queue to execute in.

magma_int_t magma_dbicgmerge3	(	magma_int_t	n,
		magmaDouble_ptr	skp,
		magmaDouble_ptr	p,
		magmaDouble_ptr	s,
		magmaDouble_ptr	t,
		magmaDouble_ptr	x,
		magmaDouble_ptr	r,
		magma_queue_t	queue
	)

Mergels multiple operations into one kernel:

x=x+alpha*p x=x+omega*s r=s r=r-omega*t

-> x = x + alpha * p + omega * s -> r = s - omega * t

Parameters

[in]	n	int dimension n
[in]	skp	magmaDouble_ptr set of scalar parameters
[in]	p	magmaDouble_ptr input p
[in]	s	magmaDouble_ptr input s
[in]	t	magmaDouble_ptr input t
[in,out]	x	magmaDouble_ptr input/output x
[in,out]	r	magmaDouble_ptr input/output r
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dbicgmerge4	(	magma_int_t	type,
		magmaDouble_ptr	skp,
		magma_queue_t	queue
	)

Performs some parameter operations for the BiCGSTAB with scalars on GPU.

Parameters

[in]	type	int kernel type
[in,out]	skp	magmaDouble_ptr vector with parameters
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dmergeblockkrylov	(	magma_int_t	num_rows,
		magma_int_t	num_cols,
		magmaDouble_ptr	alpha,
		magmaDouble_ptr	p,
		magmaDouble_ptr	x,
		magma_queue_t	queue
	)

Mergels multiple operations into one kernel:

v = y / rho y = y / rho w = wt / psi z = z / psi

Parameters

[in]	num_rows	magma_int_t dimension m
[in]	num_cols	magma_int_t dimension n
[in]	alpha	magmaDouble_ptr matrix containing all SKP
[in]	p	magmaDouble_ptr search directions
[in,out]	x	magmaDouble_ptr approximation vector
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dcgmerge_spmv1	(	magma_d_matrix	A,
		magmaDouble_ptr	d1,
		magmaDouble_ptr	d2,
		magmaDouble_ptr	dd,
		magmaDouble_ptr	dz,
		magmaDouble_ptr	skp,
		magma_queue_t	queue
	)

Merges the first SpmV using different formats with the dot product and the computation of rho.

Parameters

[in]	A	magma_d_matrix input matrix
[in]	d1	magmaDouble_ptr temporary vector
[in]	d2	magmaDouble_ptr temporary vector
[in]	dd	magmaDouble_ptr input vector d
[out]	dz	magmaDouble_ptr input vector z
[out]	skp	magmaDouble_ptr array for parameters ( skp[3]=rho )
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dcgs_1	(	magma_int_t	num_rows,
		magma_int_t	num_cols,
		double	beta,
		magmaDouble_ptr	r,
		magmaDouble_ptr	q,
		magmaDouble_ptr	u,
		magmaDouble_ptr	p,
		magma_queue_t	queue
	)

Mergels multiple operations into one kernel:

u = r + beta q p = u + beta*(q + beta*p)

Parameters

[in]	num_rows	magma_int_t dimension m
[in]	num_cols	magma_int_t dimension n
[in]	beta	double scalar
[in]	r	magmaDouble_ptr vector
[in]	q	magmaDouble_ptr vector
[in,out]	u	magmaDouble_ptr vector
[in,out]	p	magmaDouble_ptr vector
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dcgs_2	(	magma_int_t	num_rows,
		magma_int_t	num_cols,
		magmaDouble_ptr	r,
		magmaDouble_ptr	u,
		magmaDouble_ptr	p,
		magma_queue_t	queue
	)

Mergels multiple operations into one kernel:

u = r p = r

Parameters

[in]	num_rows	magma_int_t dimension m
[in]	num_cols	magma_int_t dimension n
[in]	r	magmaDouble_ptr vector
[in,out]	u	magmaDouble_ptr vector
[in,out]	p	magmaDouble_ptr vector
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dcgs_3	(	magma_int_t	num_rows,
		magma_int_t	num_cols,
		double	alpha,
		magmaDouble_ptr	v_hat,
		magmaDouble_ptr	u,
		magmaDouble_ptr	q,
		magmaDouble_ptr	t,
		magma_queue_t	queue
	)

Mergels multiple operations into one kernel:

q = u - alpha v_hat t = u + q

Parameters

[in]	num_rows	magma_int_t dimension m
[in]	num_cols	magma_int_t dimension n
[in]	alpha	double scalar
[in]	v_hat	magmaDouble_ptr vector
[in]	u	magmaDouble_ptr vector
[in,out]	q	magmaDouble_ptr vector
[in,out]	t	magmaDouble_ptr vector
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dcgs_4	(	magma_int_t	num_rows,
		magma_int_t	num_cols,
		double	alpha,
		magmaDouble_ptr	u_hat,
		magmaDouble_ptr	t,
		magmaDouble_ptr	x,
		magmaDouble_ptr	r,
		magma_queue_t	queue
	)

Mergels multiple operations into one kernel:

x = x + alpha u_hat r = r -alpha*A u_hat = r -alpha*t

Parameters

[in]	num_rows	magma_int_t dimension m
[in]	num_cols	magma_int_t dimension n
[in]	alpha	double scalar
[in]	u_hat	magmaDouble_ptr vector
[in]	t	magmaDouble_ptr vector
[in,out]	x	magmaDouble_ptr vector
[in,out]	r	magmaDouble_ptr vector
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_didr_smoothing_1	(	magma_int_t	num_rows,
		magma_int_t	num_cols,
		magmaDouble_ptr	drs,
		magmaDouble_ptr	dr,
		magmaDouble_ptr	dt,
		magma_queue_t	queue
	)

Mergels multiple operations into one kernel:

dt = drs - dr

Parameters

[in]	num_rows	magma_int_t dimension m
[in]	num_cols	magma_int_t dimension n
[in]	drs	magmaDouble_ptr vector
[in]	dr	magmaDouble_ptr vector
[in,out]	dt	magmaDouble_ptr vector
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_didr_smoothing_2	(	magma_int_t	num_rows,
		magma_int_t	num_cols,
		double	omega,
		magmaDouble_ptr	dx,
		magmaDouble_ptr	dxs,
		magma_queue_t	queue
	)

Mergels multiple operations into one kernel:

dxs = dxs - gamma*(dxs-dx)

Parameters

[in]	num_rows	magma_int_t dimension m
[in]	num_cols	magma_int_t dimension n
[in]	omega	double scalar
[in]	dx	magmaDouble_ptr vector
[in,out]	dxs	magmaDouble_ptr vector
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dqmr_1	(	magma_int_t	num_rows,
		magma_int_t	num_cols,
		double	rho,
		double	psi,
		magmaDouble_ptr	y,
		magmaDouble_ptr	z,
		magmaDouble_ptr	v,
		magmaDouble_ptr	w,
		magma_queue_t	queue
	)

Mergels multiple operations into one kernel:

v = y / rho y = y / rho w = wt / psi z = z / psi

Parameters

[in]	num_rows	magma_int_t dimension m
[in]	num_cols	magma_int_t dimension n
[in]	rho	double scalar
[in]	psi	double scalar
[in,out]	y	magmaDouble_ptr vector
[in,out]	z	magmaDouble_ptr vector
[in,out]	v	magmaDouble_ptr vector
[in,out]	w	magmaDouble_ptr vector
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dqmr_2	(	magma_int_t	num_rows,
		magma_int_t	num_cols,
		double	pde,
		double	rde,
		magmaDouble_ptr	y,
		magmaDouble_ptr	z,
		magmaDouble_ptr	p,
		magmaDouble_ptr	q,
		magma_queue_t	queue
	)

Mergels multiple operations into one kernel:

p = y - pde * p q = z - rde * q

Parameters

[in]	num_rows	magma_int_t dimension m
[in]	num_cols	magma_int_t dimension n
[in]	pde	double scalar
[in]	rde	double scalar
[in]	y	magmaDouble_ptr vector
[in]	z	magmaDouble_ptr vector
[in,out]	p	magmaDouble_ptr vector
[in,out]	q	magmaDouble_ptr vector
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dqmr_3	(	magma_int_t	num_rows,
		magma_int_t	num_cols,
		double	beta,
		magmaDouble_ptr	pt,
		magmaDouble_ptr	v,
		magmaDouble_ptr	y,
		magma_queue_t	queue
	)

Mergels multiple operations into one kernel:

v = pt - beta * v y = v

Parameters

[in]	num_rows	magma_int_t dimension m
[in]	num_cols	magma_int_t dimension n
[in]	beta	double scalar
[in]	pt	magmaDouble_ptr vector
[in,out]	v	magmaDouble_ptr vector
[in,out]	y	magmaDouble_ptr vector
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dqmr_4	(	magma_int_t	num_rows,
		magma_int_t	num_cols,
		double	eta,
		magmaDouble_ptr	p,
		magmaDouble_ptr	pt,
		magmaDouble_ptr	d,
		magmaDouble_ptr	s,
		magmaDouble_ptr	x,
		magmaDouble_ptr	r,
		magma_queue_t	queue
	)

Mergels multiple operations into one kernel:

d = eta * p; s = eta * pt; x = x + d; r = r - s;

Parameters

[in]	num_rows	magma_int_t dimension m
[in]	num_cols	magma_int_t dimension n
[in]	eta	double scalar
[in]	p	magmaDouble_ptr vector
[in]	pt	magmaDouble_ptr vector
[in,out]	d	magmaDouble_ptr vector
[in,out]	s	magmaDouble_ptr vector
[in,out]	x	magmaDouble_ptr vector
[in,out]	r	magmaDouble_ptr vector
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dqmr_5	(	magma_int_t	num_rows,
		magma_int_t	num_cols,
		double	eta,
		double	pds,
		magmaDouble_ptr	p,
		magmaDouble_ptr	pt,
		magmaDouble_ptr	d,
		magmaDouble_ptr	s,
		magmaDouble_ptr	x,
		magmaDouble_ptr	r,
		magma_queue_t	queue
	)

Mergels multiple operations into one kernel:

d = eta * p + pds * d; s = eta * pt + pds * s; x = x + d; r = r - s;

Parameters

[in]	num_rows	magma_int_t dimension m
[in]	num_cols	magma_int_t dimension n
[in]	eta	double scalar
[in]	pds	double scalar
[in]	p	magmaDouble_ptr vector
[in]	pt	magmaDouble_ptr vector
[in,out]	d	magmaDouble_ptr vector
[in,out]	s	magmaDouble_ptr vector
[in,out]	x	magmaDouble_ptr vector
[in,out]	r	magmaDouble_ptr vector
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dqmr_6	(	magma_int_t	num_rows,
		magma_int_t	num_cols,
		double	beta,
		double	rho,
		double	psi,
		magmaDouble_ptr	y,
		magmaDouble_ptr	z,
		magmaDouble_ptr	v,
		magmaDouble_ptr	w,
		magmaDouble_ptr	wt,
		magma_queue_t	queue
	)

Mergels multiple operations into one kernel:

wt = wt - conj(beta) * w v = y / rho y = y / rho w = wt / psi z = wt / psi

Parameters

[in]	num_rows	magma_int_t dimension m
[in]	num_cols	magma_int_t dimension n
[in]	beta	double scalar
[in]	rho	double scalar
[in]	psi	double scalar
[in,out]	y	magmaDouble_ptr vector
[in,out]	z	magmaDouble_ptr vector
[in,out]	v	magmaDouble_ptr vector
[in,out]	w	magmaDouble_ptr vector
[in,out]	wt	magmaDouble_ptr vector
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dqmr_7	(	magma_int_t	num_rows,
		magma_int_t	num_cols,
		double	beta,
		magmaDouble_ptr	pt,
		magmaDouble_ptr	v,
		magmaDouble_ptr	vt,
		magma_queue_t	queue
	)

Mergels multiple operations into one kernel:

vt = pt - beta * v

Parameters

[in]	num_rows	magma_int_t dimension m
[in]	num_cols	magma_int_t dimension n
[in]	beta	double scalar
[in]	pt	magmaDouble_ptr vector
[in,out]	v	magmaDouble_ptr vector
[in,out]	vt	magmaDouble_ptr vector
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dqmr_8	(	magma_int_t	num_rows,
		magma_int_t	num_cols,
		double	rho,
		double	psi,
		magmaDouble_ptr	vt,
		magmaDouble_ptr	wt,
		magmaDouble_ptr	y,
		magmaDouble_ptr	z,
		magmaDouble_ptr	v,
		magmaDouble_ptr	w,
		magma_queue_t	queue
	)

Mergels multiple operations into one kernel:

v = y / rho y = y / rho w = wt / psi z = z / psi

Parameters

[in]	num_rows	magma_int_t dimension m
[in]	num_cols	magma_int_t dimension n
[in]	rho	double scalar
[in]	psi	double scalar
[in]	vt	magmaDouble_ptr vector
[in]	wt	magmaDouble_ptr vector
[in,out]	y	magmaDouble_ptr vector
[in,out]	z	magmaDouble_ptr vector
[in,out]	v	magmaDouble_ptr vector
[in,out]	w	magmaDouble_ptr vector
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dtfqmr_1	(	magma_int_t	num_rows,
		magma_int_t	num_cols,
		double	alpha,
		double	sigma,
		magmaDouble_ptr	v,
		magmaDouble_ptr	Au,
		magmaDouble_ptr	u_m,
		magmaDouble_ptr	pu_m,
		magmaDouble_ptr	u_mp1,
		magmaDouble_ptr	w,
		magmaDouble_ptr	d,
		magmaDouble_ptr	Ad,
		magma_queue_t	queue
	)

Mergels multiple operations into one kernel:

u_mp1 = u_mp1 - alpha*v; w = w - alpha*Au; d = pu_m + sigma*d; Ad = Au + sigma*Ad;

Parameters

[in]	num_rows	magma_int_t dimension m
[in]	num_cols	magma_int_t dimension n
[in]	alpha	double scalar
[in]	sigma	double scalar
[in]	v	magmaDouble_ptr vector
[in]	Au	magmaDouble_ptr vector
[in,out]	u_m	magmaDouble_ptr vector
[in,out]	pu_m	magmaDouble_ptr vector
[in,out]	u_mp1	magmaDouble_ptr vector
[in,out]	w	magmaDouble_ptr vector
[in,out]	d	magmaDouble_ptr vector
[in,out]	Ad	magmaDouble_ptr vector
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dtfqmr_2	(	magma_int_t	num_rows,
		magma_int_t	num_cols,
		double	eta,
		magmaDouble_ptr	d,
		magmaDouble_ptr	Ad,
		magmaDouble_ptr	x,
		magmaDouble_ptr	r,
		magma_queue_t	queue
	)

Mergels multiple operations into one kernel:

x = x + eta * d r = r - eta * Ad

Parameters

[in]	num_rows	magma_int_t dimension m
[in]	num_cols	magma_int_t dimension n
[in]	eta	double scalar
[in]	d	magmaDouble_ptr vector
[in]	Ad	magmaDouble_ptr vector
[in,out]	x	magmaDouble_ptr vector
[in,out]	r	magmaDouble_ptr vector
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dtfqmr_3	(	magma_int_t	num_rows,
		magma_int_t	num_cols,
		double	beta,
		magmaDouble_ptr	w,
		magmaDouble_ptr	u_m,
		magmaDouble_ptr	u_mp1,
		magma_queue_t	queue
	)

Mergels multiple operations into one kernel:

u_mp1 = w + beta*u_mp1

Parameters

[in]	num_rows	magma_int_t dimension m
[in]	num_cols	magma_int_t dimension n
[in]	beta	double scalar
[in]	w	magmaDouble_ptr vector
[in]	u_m	magmaDouble_ptr vector
[in,out]	u_mp1	magmaDouble_ptr vector
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dtfqmr_4	(	magma_int_t	num_rows,
		magma_int_t	num_cols,
		double	beta,
		magmaDouble_ptr	Au_new,
		magmaDouble_ptr	v,
		magmaDouble_ptr	Au,
		magma_queue_t	queue
	)

Merges multiple operations into one kernel:

v = Au_new + beta*(Au+beta*v); Au = Au_new

Parameters

[in]	num_rows	magma_int_t dimension m
[in]	num_cols	magma_int_t dimension n
[in]	beta	double scalar
[in]	Au_new	magmaDouble_ptr vector
[in,out]	v	magmaDouble_ptr vector
[in,out]	Au	magmaDouble_ptr vector
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dtfqmr_5	(	magma_int_t	num_rows,
		magma_int_t	num_cols,
		double	alpha,
		double	sigma,
		magmaDouble_ptr	v,
		magmaDouble_ptr	Au,
		magmaDouble_ptr	u_mp1,
		magmaDouble_ptr	w,
		magmaDouble_ptr	d,
		magmaDouble_ptr	Ad,
		magma_queue_t	queue
	)

Mergels multiple operations into one kernel:

w = w - alpha*Au; d = pu_m + sigma*d; Ad = Au + sigma*Ad;

Parameters

[in]	num_rows	magma_int_t dimension m
[in]	num_cols	magma_int_t dimension n
[in]	alpha	double scalar
[in]	sigma	double scalar
[in]	v	magmaDouble_ptr vector
[in]	Au	magmaDouble_ptr vector
[in,out]	u_mp1	magmaDouble_ptr vector
[in,out]	w	magmaDouble_ptr vector
[in,out]	d	magmaDouble_ptr vector
[in,out]	Ad	magmaDouble_ptr vector
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dparic_csr	(	magma_d_matrix	A,
		magma_d_matrix	A_CSR,
		magma_queue_t	queue
	)

This routine iteratively computes an incomplete LU factorization.

For reference, see: E. Chow and A. Patel: "Fine-grained Parallel Incomplete LU Factorization", SIAM Journal on Scientific Computing, 37, C169-C193 (2015). This routine was used in the ISC 2015 paper: E. Chow et al.: "Asynchronous Iterative Algorithm for Computing Incomplete Factorizations on GPUs", ISC High Performance 2015, LNCS 9137, pp. 1-16, 2015.

The input format of the initial guess matrix A is Magma_CSRCOO, A_CSR is CSR or CSRCOO format.

Parameters

[in]	A	magma_d_matrix input matrix A - initial guess (lower triangular)
[in,out]	A_CSR	magma_d_matrix input/output matrix containing the IC approximation
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dparilu_csr	(	magma_d_matrix	A,
		magma_d_matrix	L,
		magma_d_matrix	U,
		magma_queue_t	queue
	)

This routine iteratively computes an incomplete LU factorization.

For reference, see: E. Chow and A. Patel: "Fine-grained Parallel Incomplete LU Factorization", SIAM Journal on Scientific Computing, 37, C169-C193 (2015). This routine was used in the ISC 2015 paper: E. Chow et al.: "Asynchronous Iterative Algorithm for Computing Incomplete Factorizations on GPUs", ISC High Performance 2015, LNCS 9137, pp. 1-16, 2015.

The input format of the system matrix is COO, the lower triangular factor L is stored in CSR, the upper triangular factor U is transposed, then also stored in CSR (equivalent to CSC format for the non-transposed U). Every component of L and U is handled by one thread.

Parameters

[in]	A	magma_d_matrix input matrix A determing initial guess & processing order
[in,out]	L	magma_d_matrix input/output matrix L containing the lower triangular factor
[in,out]	U	magma_d_matrix input/output matrix U containing the upper triangular factor
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dparilut_sweep_gpu	(	magma_d_matrix *	A,
		magma_d_matrix *	L,
		magma_d_matrix *	U,
		magma_queue_t	queue
	)

This function does an ParILUT sweep.

The difference to the ParILU sweep is that the nonzero pattern of A and the incomplete factors L and U can be different. The pattern determing which elements are iterated are hence the pattern of L and U, not A. L has a unit diagonal.

This is the GPU version of the asynchronous ParILUT sweep.

Parameters

[in]	A	magma_d_matrix* System matrix. The format is sorted CSR.
[in,out]	L	magma_d_matrix* Current approximation for the lower triangular factor The format is MAGMA_CSRCOO. This is sorted CSR plus the rowindexes being stored.
[in,out]	U	magma_d_matrix* Current approximation for the lower triangular factor The format is MAGMA_CSRCOO. This is sorted CSR plus the rowindexes being stored.
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dparilut_residuals_gpu	(	magma_d_matrix	A,
		magma_d_matrix	L,
		magma_d_matrix	U,
		magma_d_matrix *	R,
		magma_queue_t	queue
	)

This function computes the ILU residual in the locations included in the sparsity pattern of R.

Parameters

[in]	A	magma_d_matrix System matrix. The format is sorted CSR.
[in]	L	magma_d_matrix Current approximation for the lower triangular factor The format is MAGMA_CSRCOO. This is sorted CSR plus the rowindexes being stored.
[in]	U	magma_d_matrix Current approximation for the lower triangular factor The format is MAGMA_CSRCOO. This is sorted CSR plus the rowindexes being stored.
[in,out]	R	magma_d_matrix* Sparsity pattern on which the ILU residual is computed. R is in COO format. On output, R contains the ILU residual.
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dvalinit_gpu	(	magma_int_t	num_el,
		magmaDouble_ptr	dval,
		magma_queue_t	queue
	)

Initializes a device array with zero.

Parameters

[in]	num_el	magma_int_t size of array
[in,out]	dval	magmaDouble_ptr array to initialize
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dindexinit_gpu	(	magma_int_t	num_el,
		magmaIndex_ptr	dind,
		magma_queue_t	queue
	)

Initializes a device array with zero.

Parameters

[in]	num_el	magma_int_t size of array
[in,out]	dind	magmaIndex_ptr array to initialize
[in]	queue	magma_queue_t Queue to execute in.

Functions

Detailed Description

Function Documentation