Solves a system of distributed linear equations A*X = B with a general N-by-N matrix A using the LU factors computed previously. More...

#include <math.h>
#include "superlu_sdefs.h"

Include dependency graph for psgstrs3d.c:

Macros
#define	ISEND_IRECV

Functions
int_t	strs_B_init3d (int_t nsupers, float x, int nrhs, sLUstruct_t LUstruct, gridinfo3d_t *grid3d)

int_t	strs_B_init3d_newsolve (int_t nsupers, float x, int nrhs, sLUstruct_t LUstruct, gridinfo3d_t grid3d, strf3Dpartition_t trf3Dpartition)

int	strs_compute_communication_structure (superlu_dist_options_t options, int_t n, sLUstruct_t LUstruct, sScalePermstruct_t ScalePermstruct, int supernodeMask, gridinfo_t grid, SuperLUStat_t stat)

int_t	strs_x_reduction_newsolve (int_t nsupers, float x, int nrhs, sLUstruct_t LUstruct, gridinfo3d_t grid3d, strf3Dpartition_t trf3Dpartition, float recvbuf, xtrsTimer_t xtrsTimer)

int_t	strs_x_broadcast_newsolve (int_t nsupers, float x, int nrhs, sLUstruct_t LUstruct, gridinfo3d_t grid3d, strf3Dpartition_t trf3Dpartition, float recvbuf, xtrsTimer_t xtrsTimer)

int_t	sreduceSolvedX_newsolve (int_t treeId, int_t sender, int_t receiver, float x, int nrhs, strf3Dpartition_t trf3Dpartition, sLUstruct_t LUstruct, gridinfo3d_t grid3d, float recvbuf, xtrsTimer_t xtrsTimer)

int_t	strs_X_gather3d (float x, int nrhs, strf3Dpartition_t trf3Dpartition, sLUstruct_t LUstruct, gridinfo3d_t grid3d, xtrsTimer_t *xtrsTimer)

int_t	sp2pSolvedX3d (int_t treeId, int_t sender, int_t receiver, float x, int nrhs, strf3Dpartition_t trf3Dpartition, sLUstruct_t LUstruct, gridinfo3d_t grid3d, xtrsTimer_t *xtrsTimer)

int_t	sfsolveReduceLsum3d (int_t treeId, int_t sender, int_t receiver, float lsum, float recvbuf, int nrhs, strf3Dpartition_t trf3Dpartition, sLUstruct_t LUstruct, gridinfo3d_t grid3d, xtrsTimer_t xtrsTimer)

int_t	sbsolve_Xt_bcast (int_t ilvl, sxT_struct xT_s, int nrhs, strf3Dpartition_t trf3Dpartition, sLUstruct_t LUstruct, gridinfo3d_t grid3d, xtrsTimer_t *xtrsTimer)

int_t	slsumForestFsolve (int_t k, float lsum, float x, float rtemp, sxT_struct xT_s, int nrhs, sLUstruct_t LUstruct, strf3Dpartition_t trf3Dpartition, gridinfo3d_t grid3d, SuperLUStat_t stat)

int_t	snonLeafForestForwardSolve3d (int_t treeId, sLUstruct_t LUstruct, sScalePermstruct_t ScalePermstruct, strf3Dpartition_t trf3Dpartition, gridinfo3d_t grid3d, float x, float lsum, sxT_struct xT_s, float recvbuf, float rtemp, MPI_Request send_req, int nrhs, sSOLVEstruct_t SOLVEstruct, SuperLUStat_t stat, xtrsTimer_t *xtrsTimer)

int_t	sleafForestForwardSolve3d (superlu_dist_options_t options, int_t treeId, int_t n, sLUstruct_t LUstruct, sScalePermstruct_t ScalePermstruct, strf3Dpartition_t trf3Dpartition, gridinfo3d_t grid3d, float x, float lsum, float recvbuf, float rtemp, MPI_Request send_req, int nrhs, sSOLVEstruct_t SOLVEstruct, SuperLUStat_t stat, xtrsTimer_t *xtrsTimer)

void	slsum_fmod_leaf (int_t treeId, strf3Dpartition_t trf3Dpartition, float lsum, float x, float xk, float rtemp, int nrhs, int knsupc, int_t k, int fmod, int_t nlb, int_t lptr, int_t luptr, int_t xsup, gridinfo_t grid, sLocalLU_t Llu, MPI_Request send_req[], SuperLUStat_t stat, xtrsTimer_t *xtrsTimer)

int_t	sleafForestForwardSolve3d_newsolve (superlu_dist_options_t options, int_t n, sLUstruct_t LUstruct, sScalePermstruct_t ScalePermstruct, strf3Dpartition_t trf3Dpartition, gridinfo3d_t grid3d, float x, float lsum, float recvbuf, float rtemp, MPI_Request send_req, int nrhs, sSOLVEstruct_t SOLVEstruct, SuperLUStat_t stat, xtrsTimer_t *xtrsTimer)

void	sForwardSolve3d_newsolve_reusepdgstrs (superlu_dist_options_t options, int_t n, sLUstruct_t LUstruct, sScalePermstruct_t ScalePermstruct, int supernodeMask, gridinfo3d_t grid3d, float x, float lsum, int nrhs, sSOLVEstruct_t SOLVEstruct, SuperLUStat_t stat, xtrsTimer_t xtrsTimer)

void	slsum_fmod_leaf_newsolve (strf3Dpartition_t trf3Dpartition, float lsum, float x, float xk, float rtemp, int nrhs, int knsupc, int_t k, int fmod, int_t nlb, int_t lptr, int_t luptr, int_t xsup, gridinfo_t grid, sLocalLU_t Llu, MPI_Request send_req[], SuperLUStat_t stat, xtrsTimer_t *xtrsTimer)

int_t	slasum_bmod_Tree (int_t pTree, int_t cTree, float lsum, float x, sxT_struct xT_s, int nrhs, slsumBmod_buff_t lbmod_buf, sLUstruct_t LUstruct, strf3Dpartition_t trf3Dpartition, gridinfo3d_t grid3d, SuperLUStat_t stat)

int_t	sinitLsumBmod_buff (int_t ns, int nrhs, slsumBmod_buff_t *lbmod_buf)

int_t	sfreeLsumBmod_buff (slsumBmod_buff_t *lbmod_buf)

int	spackUblock (int ldu, int_t indCols, int_t knsupc, int_t iklrow, int_t usub, float tempu, float uval)

int_t	spackXbmod (int_t knsupc, int_t ncols, int_t nrhs, int_t indCols, float xk, float *tempx)

int_t	slsumBmod (int_t gik, int_t gjk, int nrhs, slsumBmod_buff_t lbmod_buf, int_t usub, float uval, float xk, float lsum, int_t xsup, SuperLUStat_t *stat)

int_t	slsumForestBsolve (int_t k, int_t treeId, float lsum, float x, sxT_struct xT_s, int nrhs, slsumBmod_buff_t lbmod_buf, sLUstruct_t LUstruct, strf3Dpartition_t trf3Dpartition, gridinfo3d_t grid3d, SuperLUStat_t stat)

int_t	sbCastXk2Pck (int_t k, sxT_struct xT_s, int nrhs, sLUstruct_t LUstruct, gridinfo_t grid, xtrsTimer_t xtrsTimer)

int_t	slsumReducePrK (int_t k, float x, float lsum, float recvbuf, int nrhs, sLUstruct_t LUstruct, gridinfo_t grid, xtrsTimer_t xtrsTimer)

int_t	snonLeafForestBackSolve3d (int_t treeId, sLUstruct_t LUstruct, sScalePermstruct_t ScalePermstruct, strf3Dpartition_t trf3Dpartition, gridinfo3d_t grid3d, float x, float lsum, sxT_struct xT_s, float recvbuf, MPI_Request send_req, int nrhs, slsumBmod_buff_t lbmod_buf, sSOLVEstruct_t SOLVEstruct, SuperLUStat_t stat, xtrsTimer_t *xtrsTimer)

int_t	sleafForestBackSolve3d (superlu_dist_options_t options, int_t treeId, int_t n, sLUstruct_t LUstruct, sScalePermstruct_t ScalePermstruct, strf3Dpartition_t trf3Dpartition, gridinfo3d_t grid3d, float x, float lsum, float recvbuf, MPI_Request send_req, int nrhs, slsumBmod_buff_t lbmod_buf, sSOLVEstruct_t SOLVEstruct, SuperLUStat_t stat, xtrsTimer_t *xtrsTimer)

int_t	sleafForestBackSolve3d_newsolve (superlu_dist_options_t options, int_t n, sLUstruct_t LUstruct, strf3Dpartition_t trf3Dpartition, gridinfo3d_t grid3d, float x, float lsum, float recvbuf, MPI_Request send_req, int nrhs, slsumBmod_buff_t lbmod_buf, sSOLVEstruct_t SOLVEstruct, SuperLUStat_t stat, xtrsTimer_t xtrsTimer)

void	sBackSolve3d_newsolve_reusepdgstrs (superlu_dist_options_t options, int_t n, sLUstruct_t LUstruct, int supernodeMask, gridinfo3d_t grid3d, float x, float lsum, int nrhs, sSOLVEstruct_t SOLVEstruct, SuperLUStat_t stat, xtrsTimer_t *xtrsTimer)

void	slsum_bmod_GG (float lsum, float x, float xk, int nrhs, slsumBmod_buff_t lbmod_buf, int_t k, int bmod, int_t Urbs, Ucb_indptr_t Ucb_indptr, int_t Ucb_valptr, int_t xsup, gridinfo_t grid, sLocalLU_t Llu, MPI_Request send_req[], SuperLUStat_t stat, xtrsTimer_t *xtrsTimer)

void	slsum_bmod_GG_newsolve (strf3Dpartition_t trf3Dpartition, float lsum, float x, float xk, int nrhs, slsumBmod_buff_t lbmod_buf, int_t k, int bmod, int_t Urbs, Ucb_indptr_t Ucb_indptr, int_t Ucb_valptr, int_t xsup, gridinfo_t grid, sLocalLU_t Llu, MPI_Request send_req[], SuperLUStat_t stat, xtrsTimer_t xtrsTimer)

int_t	slocalSolveXkYk (trtype_t trtype, int_t k, float x, int nrhs, sLUstruct_t LUstruct, gridinfo_t grid, SuperLUStat_t stat)

int_t	siBcastXk2Pck (int_t k, float x, int nrhs, int sendList, MPI_Request send_req, sLUstruct_t LUstruct, gridinfo_t grid, xtrsTimer_t *xtrsTimer)

int_t	psReDistribute3d_B_to_X (float B, int_t m_loc, int nrhs, int_t ldb, int_t fst_row, int_t ilsum, float x, sScalePermstruct_t ScalePermstruct, Glu_persist_t Glu_persist, gridinfo3d_t grid3d, sSOLVEstruct_t *SOLVEstruct)

int_t	psReDistribute3d_X_to_B (int_t n, float B, int_t m_loc, int_t ldb, int_t fst_row, int nrhs, float x, int_t ilsum, sScalePermstruct_t ScalePermstruct, Glu_persist_t Glu_persist, gridinfo3d_t grid3d, sSOLVEstruct_t *SOLVEstruct)

void	psgstrs3d (superlu_dist_options_t options, int_t n, sLUstruct_t LUstruct, sScalePermstruct_t ScalePermstruct, strf3Dpartition_t trf3Dpartition, gridinfo3d_t grid3d, float B, int_t m_loc, int_t fst_row, int_t ldb, int nrhs, sSOLVEstruct_t SOLVEstruct, SuperLUStat_t stat, int *info)

void	psgstrs3d_newsolve (superlu_dist_options_t options, int_t n, sLUstruct_t LUstruct, sScalePermstruct_t ScalePermstruct, strf3Dpartition_t trf3Dpartition, gridinfo3d_t grid3d, float B, int_t m_loc, int_t fst_row, int_t ldb, int nrhs, sSOLVEstruct_t SOLVEstruct, SuperLUStat_t stat, int *info)

int_t	psgsTrForwardSolve3d (superlu_dist_options_t options, int_t n, sLUstruct_t LUstruct, sScalePermstruct_t ScalePermstruct, strf3Dpartition_t trf3Dpartition, gridinfo3d_t grid3d, float x3d, float lsum3d, sxT_struct xT_s, float recvbuf, MPI_Request send_req, int nrhs, sSOLVEstruct_t SOLVEstruct, SuperLUStat_t stat, xtrsTimer_t *xtrsTimer)

int_t	psgsTrForwardSolve3d_newsolve (superlu_dist_options_t options, int_t n, sLUstruct_t LUstruct, sScalePermstruct_t ScalePermstruct, strf3Dpartition_t trf3Dpartition, gridinfo3d_t grid3d, float x3d, float lsum3d, float recvbuf, MPI_Request send_req, int nrhs, sSOLVEstruct_t SOLVEstruct, SuperLUStat_t stat, xtrsTimer_t xtrsTimer)

int_t	psgsTrBackSolve3d (superlu_dist_options_t options, int_t n, sLUstruct_t LUstruct, sScalePermstruct_t ScalePermstruct, strf3Dpartition_t trf3Dpartition, gridinfo3d_t grid3d, float x3d, float lsum3d, sxT_struct xT_s, float recvbuf, MPI_Request send_req, int nrhs, sSOLVEstruct_t SOLVEstruct, SuperLUStat_t stat, xtrsTimer_t *xtrsTimer)

int_t	psgsTrBackSolve3d_newsolve (superlu_dist_options_t options, int_t n, sLUstruct_t LUstruct, strf3Dpartition_t trf3Dpartition, gridinfo3d_t grid3d, float x3d, float lsum3d, float recvbuf, MPI_Request send_req, int nrhs, sSOLVEstruct_t SOLVEstruct, SuperLUStat_t stat, xtrsTimer_t *xtrsTimer)

Variables
float *	sready_x

float *	sready_lsum

Detailed Description

Solves a system of distributed linear equations A*X = B with a general N-by-N matrix A using the LU factors computed previously.

The source code is distributed under BSD license, see the file License.txt at the top-level directory.

-- Distributed SuperLU routine (version 9.0) --
Lawrence Berkeley National Lab, Univ. of California Berkeley.
October 15, 2008
September 18, 2018  version 6.0
February 8, 2019  version 6.1.1

Macro Definition Documentation

◆ ISEND_IRECV

#define ISEND_IRECV

Function Documentation

◆ psgsTrBackSolve3d()

int_t psgsTrBackSolve3d	(	superlu_dist_options_t *	options,
		int_t	n,
		sLUstruct_t *	LUstruct,
		sScalePermstruct_t *	ScalePermstruct,
		strf3Dpartition_t *	trf3Dpartition,
		gridinfo3d_t *	grid3d,
		float *	x3d,
		float *	lsum3d,
		sxT_struct *	xT_s,
		float *	recvbuf,
		MPI_Request *	send_req,
		int	nrhs,
		sSOLVEstruct_t *	SOLVEstruct,
		SuperLUStat_t *	stat,
		xtrsTimer_t *	xtrsTimer
	)

Loop over all the levels from root to leaf

Adding dlsumBmod_buff_t* lbmod_buf

Here is the call graph for this function:

Here is the caller graph for this function:

◆ psgsTrBackSolve3d_newsolve()

int_t psgsTrBackSolve3d_newsolve	(	superlu_dist_options_t *	options,
		int_t	n,
		sLUstruct_t *	LUstruct,
		strf3Dpartition_t *	trf3Dpartition,
		gridinfo3d_t *	grid3d,
		float *	x3d,
		float *	lsum3d,
		float *	recvbuf,
		MPI_Request *	send_req,
		int	nrhs,
		sSOLVEstruct_t *	SOLVEstruct,
		SuperLUStat_t *	stat,
		xtrsTimer_t *	xtrsTimer
	)

Adding dlsumBmod_buff_t* lbmod_buf

Here is the call graph for this function:

Here is the caller graph for this function:

◆ psgsTrForwardSolve3d()

int_t psgsTrForwardSolve3d	(	superlu_dist_options_t *	options,
		int_t	n,
		sLUstruct_t *	LUstruct,
		sScalePermstruct_t *	ScalePermstruct,
		strf3Dpartition_t *	trf3Dpartition,
		gridinfo3d_t *	grid3d,
		float *	x3d,
		float *	lsum3d,
		sxT_struct *	xT_s,
		float *	recvbuf,
		MPI_Request *	send_req,
		int	nrhs,
		sSOLVEstruct_t *	SOLVEstruct,
		SuperLUStat_t *	stat,
		xtrsTimer_t *	xtrsTimer
	)

Loop over all the levels from root to leaf

Here is the call graph for this function:

Here is the caller graph for this function:

◆ psgsTrForwardSolve3d_newsolve()

int_t psgsTrForwardSolve3d_newsolve	(	superlu_dist_options_t *	options,
		int_t	n,
		sLUstruct_t *	LUstruct,
		sScalePermstruct_t *	ScalePermstruct,
		strf3Dpartition_t *	trf3Dpartition,
		gridinfo3d_t *	grid3d,
		float *	x3d,
		float *	lsum3d,
		float *	recvbuf,
		MPI_Request *	send_req,
		int	nrhs,
		sSOLVEstruct_t *	SOLVEstruct,
		SuperLUStat_t *	stat,
		xtrsTimer_t *	xtrsTimer
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ psgstrs3d()

void psgstrs3d	(	superlu_dist_options_t *	options,
		int_t	n,
		sLUstruct_t *	LUstruct,
		sScalePermstruct_t *	ScalePermstruct,
		strf3Dpartition_t *	trf3Dpartition,
		gridinfo3d_t *	grid3d,
		float *	B,
		int_t	m_loc,
		int_t	fst_row,
		int_t	ldb,
		int	nrhs,
		sSOLVEstruct_t *	SOLVEstruct,
		SuperLUStat_t *	stat,
		int *	info
	)

Purpose


PSGSTRS solves a system of distributed linear equations
A*X = B with a general N-by-N matrix A using the LU factorization
computed by PSGSTRF.
If the equilibration, and row and column permutations were performed,
the LU factorization was performed for A1 where
    A1 = Pc*Pr*diag(R)*A*diag(C)*Pc^T = L*U
and the linear system solved is
    A1 * Y = Pc*Pr*B1, where B was overwritten by B1 = diag(R)*B, and
the permutation to B1 by Pc*Pr is applied internally in this routine.

Arguments


n      (input) int (global)
       The order of the system of linear equations.

LUstruct (input) sLUstruct_t*
       The distributed data structures storing L and U factors.
       The L and U factors are obtained from PSGSTRF for
       the possibly scaled and permuted matrix A.
       See superlu_ddefs.h for the definition of 'sLUstruct_t'.
       A may be scaled and permuted into A1, so that
       A1 = Pc*Pr*diag(R)*A*diag(C)*Pc^T = L*U

grid   (input) gridinfo_t*
       The 2D process mesh. It contains the MPI communicator, the number
       of process rows (NPROW), the number of process columns (NPCOL),
       and my process rank. It is an input argument to all the
       parallel routines.
       Grid can be initialized by subroutine SUPERLU_GRIDINIT.
       See superlu_defs.h for the definition of 'gridinfo_t'.

B      (input/output) float*
       On entry, the distributed right-hand side matrix of the possibly
       equilibrated system. That is, B may be overwritten by diag(R)*B.
       On exit, the distributed solution matrix Y of the possibly
       equilibrated system if info = 0, where Y = Pc*diag(C)^(-1)*X,
       and X is the solution of the original system.

m_loc  (input) int (local)
       The local row dimension of matrix B.

fst_row (input) int (global)
       The row number of B's first row in the global matrix.

ldb    (input) int (local)
       The leading dimension of matrix B.

nrhs   (input) int (global)
       Number of right-hand sides.

SOLVEstruct (input) sSOLVEstruct_t* (global)
       Contains the information for the communication during the
       solution phase.

stat   (output) SuperLUStat_t*
       Record the statistics about the triangular solves.
       See util.h for the definition of 'SuperLUStat_t'.

info   (output) int*
    = 0: successful exit
    < 0: if info = -i, the i-th argument had an illegal value

Initializing xT

Setup the headers for xT

Reduce the Solve flops from all the grids to grid zero

Here is the call graph for this function:

Here is the caller graph for this function:

◆ psgstrs3d_newsolve()

void psgstrs3d_newsolve	(	superlu_dist_options_t *	options,
		int_t	n,
		sLUstruct_t *	LUstruct,
		sScalePermstruct_t *	ScalePermstruct,
		strf3Dpartition_t *	trf3Dpartition,
		gridinfo3d_t *	grid3d,
		float *	B,
		int_t	m_loc,
		int_t	fst_row,
		int_t	ldb,
		int	nrhs,
		sSOLVEstruct_t *	SOLVEstruct,
		SuperLUStat_t *	stat,
		int *	info
	)

Reduce the Solve flops from all the grids to grid zero

Here is the call graph for this function:

Here is the caller graph for this function:

◆ psReDistribute3d_B_to_X()

int_t psReDistribute3d_B_to_X	(	float *	B,
		int_t	m_loc,
		int	nrhs,
		int_t	ldb,
		int_t	fst_row,
		int_t *	ilsum,
		float *	x,
		sScalePermstruct_t *	ScalePermstruct,
		Glu_persist_t *	Glu_persist,
		gridinfo3d_t *	grid3d,
		sSOLVEstruct_t *	SOLVEstruct
	)

Purpose

  Re-distribute B on the diagonal processes of the 2D process mesh (only on grid 0).

Note

  This routine can only be called after the routine pxgstrs_init(),
  in which the structures of the send and receive buffers are set up.

Arguments


B      (input) float*
       The distributed right-hand side matrix of the possibly
       equilibrated system.

m_loc  (input) int (local)
       The local row dimension of matrix B.

nrhs   (input) int (global)
       Number of right-hand sides.

ldb    (input) int (local)
       Leading dimension of matrix B.

fst_row (input) int (global)
       The row number of B's first row in the global matrix.

ilsum  (input) int* (global)
       Starting position of each supernode in a full array.

x      (output) float*
       The solution vector. It is valid only on the diagonal processes.

ScalePermstruct (input) dScalePermstruct_t*
       The data structure to store the scaling and permutation vectors
       describing the transformations performed to the original matrix A.

grid   (input) gridinfo_t*
       The 2D process mesh.

SOLVEstruct (input) dSOLVEstruct_t*
       Contains the information for the communication during the
       solution phase.

Return value

Here is the call graph for this function:

Here is the caller graph for this function:

◆ psReDistribute3d_X_to_B()

int_t psReDistribute3d_X_to_B	(	int_t	n,
		float *	B,
		int_t	m_loc,
		int_t	ldb,
		int_t	fst_row,
		int	nrhs,
		float *	x,
		int_t *	ilsum,
		sScalePermstruct_t *	ScalePermstruct,
		Glu_persist_t *	Glu_persist,
		gridinfo3d_t *	grid3d,
		sSOLVEstruct_t *	SOLVEstruct
	)

Purpose

  Re-distribute X on the diagonal processes to B distributed on all
  the processes (only on grid 0)

Note

  This routine can only be called after the routine pxgstrs_init(),
  in which the structures of the send and receive buffers are set up.

Here is the call graph for this function:

Here is the caller graph for this function:

◆ sBackSolve3d_newsolve_reusepdgstrs()

void sBackSolve3d_newsolve_reusepdgstrs	(	superlu_dist_options_t *	options,
		int_t	n,
		sLUstruct_t *	LUstruct,
		int *	supernodeMask,
		gridinfo3d_t *	grid3d,
		float *	x,
		float *	lsum,
		int	nrhs,
		sSOLVEstruct_t *	SOLVEstruct,
		SuperLUStat_t *	stat,
		xtrsTimer_t *	xtrsTimer
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ sbCastXk2Pck()

int_t sbCastXk2Pck	(	int_t	k,
		sxT_struct *	xT_s,
		int	nrhs,
		sLUstruct_t *	LUstruct,
		gridinfo_t *	grid,
		xtrsTimer_t *	xtrsTimer
	)

Here is the caller graph for this function:

◆ sbsolve_Xt_bcast()

int_t sbsolve_Xt_bcast	(	int_t	ilvl,
		sxT_struct *	xT_s,
		int	nrhs,
		strf3Dpartition_t *	trf3Dpartition,
		sLUstruct_t *	LUstruct,
		gridinfo3d_t *	grid3d,
		xtrsTimer_t *	xtrsTimer
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ sForwardSolve3d_newsolve_reusepdgstrs()

void sForwardSolve3d_newsolve_reusepdgstrs	(	superlu_dist_options_t *	options,
		int_t	n,
		sLUstruct_t *	LUstruct,
		sScalePermstruct_t *	ScalePermstruct,
		int *	supernodeMask,
		gridinfo3d_t *	grid3d,
		float *	x,
		float *	lsum,
		int	nrhs,
		sSOLVEstruct_t *	SOLVEstruct,
		SuperLUStat_t *	stat,
		xtrsTimer_t *	xtrsTimer
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ sfreeLsumBmod_buff()

int_t sfreeLsumBmod_buff ( slsumBmod_buff_t * lbmod_buf )

Here is the caller graph for this function:

◆ sfsolveReduceLsum3d()

int_t sfsolveReduceLsum3d	(	int_t	treeId,
		int_t	sender,
		int_t	receiver,
		float *	lsum,
		float *	recvbuf,
		int	nrhs,
		strf3Dpartition_t *	trf3Dpartition,
		sLUstruct_t *	LUstruct,
		gridinfo3d_t *	grid3d,
		xtrsTimer_t *	xtrsTimer
	)

Here is the caller graph for this function:

◆ siBcastXk2Pck()

int_t siBcastXk2Pck	(	int_t	k,
		float *	x,
		int	nrhs,
		int **	sendList,
		MPI_Request *	send_req,
		sLUstruct_t *	LUstruct,
		gridinfo_t *	grid,
		xtrsTimer_t *	xtrsTimer
	)

Here is the caller graph for this function:

◆ sinitLsumBmod_buff()

int_t sinitLsumBmod_buff	(	int_t	ns,
		int	nrhs,
		slsumBmod_buff_t *	lbmod_buf
	)

Here is the caller graph for this function:

◆ slasum_bmod_Tree()

int_t slasum_bmod_Tree	(	int_t	pTree,
		int_t	cTree,
		float *	lsum,
		float *	x,
		sxT_struct *	xT_s,
		int	nrhs,
		slsumBmod_buff_t *	lbmod_buf,
		sLUstruct_t *	LUstruct,
		strf3Dpartition_t *	trf3Dpartition,
		gridinfo3d_t *	grid3d,
		SuperLUStat_t *	stat
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ sleafForestBackSolve3d()

int_t sleafForestBackSolve3d	(	superlu_dist_options_t *	options,
		int_t	treeId,
		int_t	n,
		sLUstruct_t *	LUstruct,
		sScalePermstruct_t *	ScalePermstruct,
		strf3Dpartition_t *	trf3Dpartition,
		gridinfo3d_t *	grid3d,
		float *	x,
		float *	lsum,
		float *	recvbuf,
		MPI_Request *	send_req,
		int	nrhs,
		slsumBmod_buff_t *	lbmod_buf,
		sSOLVEstruct_t *	SOLVEstruct,
		SuperLUStat_t *	stat,
		xtrsTimer_t *	xtrsTimer
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ sleafForestBackSolve3d_newsolve()

int_t sleafForestBackSolve3d_newsolve	(	superlu_dist_options_t *	options,
		int_t	n,
		sLUstruct_t *	LUstruct,
		strf3Dpartition_t *	trf3Dpartition,
		gridinfo3d_t *	grid3d,
		float *	x,
		float *	lsum,
		float *	recvbuf,
		MPI_Request *	send_req,
		int	nrhs,
		slsumBmod_buff_t *	lbmod_buf,
		sSOLVEstruct_t *	SOLVEstruct,
		SuperLUStat_t *	stat,
		xtrsTimer_t *	xtrsTimer
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ sleafForestForwardSolve3d()

int_t sleafForestForwardSolve3d	(	superlu_dist_options_t *	options,
		int_t	treeId,
		int_t	n,
		sLUstruct_t *	LUstruct,
		sScalePermstruct_t *	ScalePermstruct,
		strf3Dpartition_t *	trf3Dpartition,
		gridinfo3d_t *	grid3d,
		float *	x,
		float *	lsum,
		float *	recvbuf,
		float *	rtemp,
		MPI_Request *	send_req,
		int	nrhs,
		sSOLVEstruct_t *	SOLVEstruct,
		SuperLUStat_t *	stat,
		xtrsTimer_t *	xtrsTimer
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ sleafForestForwardSolve3d_newsolve()

int_t sleafForestForwardSolve3d_newsolve	(	superlu_dist_options_t *	options,
		int_t	n,
		sLUstruct_t *	LUstruct,
		sScalePermstruct_t *	ScalePermstruct,
		strf3Dpartition_t *	trf3Dpartition,
		gridinfo3d_t *	grid3d,
		float *	x,
		float *	lsum,
		float *	recvbuf,
		float *	rtemp,
		MPI_Request *	send_req,
		int	nrhs,
		sSOLVEstruct_t *	SOLVEstruct,
		SuperLUStat_t *	stat,
		xtrsTimer_t *	xtrsTimer
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ slocalSolveXkYk()

int_t slocalSolveXkYk	(	trtype_t	trtype,
		int_t	k,
		float *	x,
		int	nrhs,
		sLUstruct_t *	LUstruct,
		gridinfo_t *	grid,
		SuperLUStat_t *	stat
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ slsum_bmod_GG()

void slsum_bmod_GG	(	float *	lsum,
		float *	x,
		float *	xk,
		int	nrhs,
		slsumBmod_buff_t *	lbmod_buf,
		int_t	k,
		int *	bmod,
		int_t *	Urbs,
		Ucb_indptr_t **	Ucb_indptr,
		int_t **	Ucb_valptr,
		int_t *	xsup,
		gridinfo_t *	grid,
		sLocalLU_t *	Llu,
		MPI_Request	send_req[],
		SuperLUStat_t *	stat,
		xtrsTimer_t *	xtrsTimer
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ slsum_bmod_GG_newsolve()

void slsum_bmod_GG_newsolve	(	strf3Dpartition_t *	trf3Dpartition,
		float *	lsum,
		float *	x,
		float *	xk,
		int	nrhs,
		slsumBmod_buff_t *	lbmod_buf,
		int_t	k,
		int *	bmod,
		int_t *	Urbs,
		Ucb_indptr_t **	Ucb_indptr,
		int_t **	Ucb_valptr,
		int_t *	xsup,
		gridinfo_t *	grid,
		sLocalLU_t *	Llu,
		MPI_Request	send_req[],
		SuperLUStat_t *	stat,
		xtrsTimer_t *	xtrsTimer
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ slsum_fmod_leaf()

void slsum_fmod_leaf	(	int_t	treeId,
		strf3Dpartition_t *	trf3Dpartition,
		float *	lsum,
		float *	x,
		float *	xk,
		float *	rtemp,
		int	nrhs,
		int	knsupc,
		int_t	k,
		int *	fmod,
		int_t	nlb,
		int_t	lptr,
		int_t	luptr,
		int_t *	xsup,
		gridinfo_t *	grid,
		sLocalLU_t *	Llu,
		MPI_Request	send_req[],
		SuperLUStat_t *	stat,
		xtrsTimer_t *	xtrsTimer
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ slsum_fmod_leaf_newsolve()

void slsum_fmod_leaf_newsolve	(	strf3Dpartition_t *	trf3Dpartition,
		float *	lsum,
		float *	x,
		float *	xk,
		float *	rtemp,
		int	nrhs,
		int	knsupc,
		int_t	k,
		int *	fmod,
		int_t	nlb,
		int_t	lptr,
		int_t	luptr,
		int_t *	xsup,
		gridinfo_t *	grid,
		sLocalLU_t *	Llu,
		MPI_Request	send_req[],
		SuperLUStat_t *	stat,
		xtrsTimer_t *	xtrsTimer
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ slsumBmod()

int_t slsumBmod	(	int_t	gik,
		int_t	gjk,
		int	nrhs,
		slsumBmod_buff_t *	lbmod_buf,
		int_t *	usub,
		float *	uval,
		float *	xk,
		float *	lsum,
		int_t *	xsup,
		SuperLUStat_t *	stat
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ slsumForestBsolve()

int_t slsumForestBsolve	(	int_t	k,
		int_t	treeId,
		float *	lsum,
		float *	x,
		sxT_struct *	xT_s,
		int	nrhs,
		slsumBmod_buff_t *	lbmod_buf,
		sLUstruct_t *	LUstruct,
		strf3Dpartition_t *	trf3Dpartition,
		gridinfo3d_t *	grid3d,
		SuperLUStat_t *	stat
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ slsumForestFsolve()

int_t slsumForestFsolve	(	int_t	k,
		float *	lsum,
		float *	x,
		float *	rtemp,
		sxT_struct *	xT_s,
		int	nrhs,
		sLUstruct_t *	LUstruct,
		strf3Dpartition_t *	trf3Dpartition,
		gridinfo3d_t *	grid3d,
		SuperLUStat_t *	stat
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ slsumReducePrK()

int_t slsumReducePrK	(	int_t	k,
		float *	x,
		float *	lsum,
		float *	recvbuf,
		int	nrhs,
		sLUstruct_t *	LUstruct,
		gridinfo_t *	grid,
		xtrsTimer_t *	xtrsTimer
	)

Here is the caller graph for this function:

◆ snonLeafForestBackSolve3d()

int_t snonLeafForestBackSolve3d	(	int_t	treeId,
		sLUstruct_t *	LUstruct,
		sScalePermstruct_t *	ScalePermstruct,
		strf3Dpartition_t *	trf3Dpartition,
		gridinfo3d_t *	grid3d,
		float *	x,
		float *	lsum,
		sxT_struct *	xT_s,
		float *	recvbuf,
		MPI_Request *	send_req,
		int	nrhs,
		slsumBmod_buff_t *	lbmod_buf,
		sSOLVEstruct_t *	SOLVEstruct,
		SuperLUStat_t *	stat,
		xtrsTimer_t *	xtrsTimer
	)

Pkk(Yk) = sumOver_PrK (Yk)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ snonLeafForestForwardSolve3d()

int_t snonLeafForestForwardSolve3d	(	int_t	treeId,
		sLUstruct_t *	LUstruct,
		sScalePermstruct_t *	ScalePermstruct,
		strf3Dpartition_t *	trf3Dpartition,
		gridinfo3d_t *	grid3d,
		float *	x,
		float *	lsum,
		sxT_struct *	xT_s,
		float *	recvbuf,
		float *	rtemp,
		MPI_Request *	send_req,
		int	nrhs,
		sSOLVEstruct_t *	SOLVEstruct,
		SuperLUStat_t *	stat,
		xtrsTimer_t *	xtrsTimer
	)

Pkk(Yk) = sumOver_PrK (Yk)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ sp2pSolvedX3d()

int_t sp2pSolvedX3d	(	int_t	treeId,
		int_t	sender,
		int_t	receiver,
		float *	x,
		int	nrhs,
		strf3Dpartition_t *	trf3Dpartition,
		sLUstruct_t *	LUstruct,
		gridinfo3d_t *	grid3d,
		xtrsTimer_t *	xtrsTimer
	)

Here is the caller graph for this function:

◆ spackUblock()

int spackUblock	(	int	ldu,
		int_t *	indCols,
		int_t	knsupc,
		int_t	iklrow,
		int_t *	usub,
		float *	tempu,
		float *	uval
	)

Here is the caller graph for this function:

◆ spackXbmod()

int_t spackXbmod	(	int_t	knsupc,
		int_t	ncols,
		int_t	nrhs,
		int_t *	indCols,
		float *	xk,
		float *	tempx
	)

Here is the caller graph for this function:

◆ sreduceSolvedX_newsolve()

int_t sreduceSolvedX_newsolve	(	int_t	treeId,
		int_t	sender,
		int_t	receiver,
		float *	x,
		int	nrhs,
		strf3Dpartition_t *	trf3Dpartition,
		sLUstruct_t *	LUstruct,
		gridinfo3d_t *	grid3d,
		float *	recvbuf,
		xtrsTimer_t *	xtrsTimer
	)

Here is the caller graph for this function:

◆ strs_B_init3d()

int_t strs_B_init3d	(	int_t	nsupers,
		float *	x,
		int	nrhs,
		sLUstruct_t *	LUstruct,
		gridinfo3d_t *	grid3d
	)

Here is the caller graph for this function:

◆ strs_B_init3d_newsolve()

int_t strs_B_init3d_newsolve	(	int_t	nsupers,
		float *	x,
		int	nrhs,
		sLUstruct_t *	LUstruct,
		gridinfo3d_t *	grid3d,
		strf3Dpartition_t *	trf3Dpartition
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ strs_compute_communication_structure()

int strs_compute_communication_structure	(	superlu_dist_options_t *	options,
		int_t	n,
		sLUstruct_t *	LUstruct,
		sScalePermstruct_t *	ScalePermstruct,
		int *	supernodeMask,
		gridinfo_t *	grid,
		SuperLUStat_t *	stat
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ strs_x_broadcast_newsolve()

int_t strs_x_broadcast_newsolve	(	int_t	nsupers,
		float *	x,
		int	nrhs,
		sLUstruct_t *	LUstruct,
		gridinfo3d_t *	grid3d,
		strf3Dpartition_t *	trf3Dpartition,
		float *	recvbuf,
		xtrsTimer_t *	xtrsTimer
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ strs_X_gather3d()

int_t strs_X_gather3d	(	float *	x,
		int	nrhs,
		strf3Dpartition_t *	trf3Dpartition,
		sLUstruct_t *	LUstruct,
		gridinfo3d_t *	grid3d,
		xtrsTimer_t *	xtrsTimer
	)

Here is the call graph for this function:

Here is the caller graph for this function:

◆ strs_x_reduction_newsolve()

int_t strs_x_reduction_newsolve	(	int_t	nsupers,
		float *	x,
		int	nrhs,
		sLUstruct_t *	LUstruct,
		gridinfo3d_t *	grid3d,
		strf3Dpartition_t *	trf3Dpartition,
		float *	recvbuf,
		xtrsTimer_t *	xtrsTimer
	)

Here is the call graph for this function:

Here is the caller graph for this function:

Macros

Functions

Variables

Detailed Description

Macro Definition Documentation

◆ ISEND_IRECV

Function Documentation

◆ psgsTrBackSolve3d()

◆ psgsTrBackSolve3d_newsolve()

◆ psgsTrForwardSolve3d()

◆ psgsTrForwardSolve3d_newsolve()

◆ psgstrs3d()

◆ psgstrs3d_newsolve()

◆ psReDistribute3d_B_to_X()

◆ psReDistribute3d_X_to_B()

◆ sBackSolve3d_newsolve_reusepdgstrs()

◆ sbCastXk2Pck()

◆ sbsolve_Xt_bcast()

◆ sForwardSolve3d_newsolve_reusepdgstrs()

◆ sfreeLsumBmod_buff()

◆ sfsolveReduceLsum3d()

◆ siBcastXk2Pck()

◆ sinitLsumBmod_buff()

◆ slasum_bmod_Tree()

◆ sleafForestBackSolve3d()

◆ sleafForestBackSolve3d_newsolve()

◆ sleafForestForwardSolve3d()

◆ sleafForestForwardSolve3d_newsolve()

◆ slocalSolveXkYk()

◆ slsum_bmod_GG()

◆ slsum_bmod_GG_newsolve()

◆ slsum_fmod_leaf()

◆ slsum_fmod_leaf_newsolve()

◆ slsumBmod()

◆ slsumForestBsolve()

◆ slsumForestFsolve()

◆ slsumReducePrK()

◆ snonLeafForestBackSolve3d()

◆ snonLeafForestForwardSolve3d()

◆ sp2pSolvedX3d()

◆ spackUblock()

◆ spackXbmod()

◆ sreduceSolvedX_newsolve()

◆ strs_B_init3d()

◆ strs_B_init3d_newsolve()

◆ strs_compute_communication_structure()

◆ strs_x_broadcast_newsolve()

◆ strs_X_gather3d()

◆ strs_x_reduction_newsolve()

Variable Documentation

◆ sready_lsum

◆ sready_x