SuperLU Distributed 8.2.1
Distributed memory sparse direct solver
|
► EXAMPLE | |
dcreate_matrix.c | Read the matrix from data file |
dcreate_matrix3d.c | Read the matrix from data file |
dcreate_matrix_perturbed.c | Read the matrix from data file |
dnrformat_loc3d.c | |
dreadhb.c | Read a DOUBLE PRECISION matrix stored in Harwell-Boeing format |
dreadtriple.c | |
memory.c | Memory utilities |
pdddrive3d_coarse_batch.c | Driver program for PDGSSVX3D example |
pddistribute.c | Re-distribute A on the 2D process mesh |
pddrive.c | Driver program for PDGSSVX example |
pddrive1.c | Driver program for PDGSSVX example |
pddrive1_ABglobal.c | Driver program for pdgssvx_ABglobal example |
pddrive2.c | Driver program for PDGSSVX example |
pddrive2_ABglobal.c | Driver program for pdgssvx_ABglobal example |
pddrive3.c | Driver program for PDGSSVX example |
pddrive3_ABglobal.c | Driver program for pdgssvx_ABglobal example |
pddrive3d.c | Driver program for PDGSSVX3D example |
pddrive3d1.c | Driver program for PDGSSVX3D example |
pddrive3d2.c | Driver program for PDGSSVX3D example |
pddrive3d3.c | Driver program for PDGSSVX3D example |
pddrive4.c | This example illustrates how to divide up the processes into subgroups |
pddrive4_ABglobal.c | This example illustrates how to divide up the processes into subgroups |
pddrive_ABglobal.c | Driver program for pdgssvx_ABglobal example |
pddrive_spawn.c | Driver program for PDGSSVX example |
pddrive_Zajac.c | |
pdgsrfs_ABXglobal.c | Improves the computed solution and provies error bounds |
pdgssvx.c | Solves a system of linear equations A*X=B |
pdgstrf2.c | Performs panel LU factorization |
pdsymbfact_distdata.c | Redistribute the symbolic structure of L and U from the distribution |
psdrive.c | Driver program for PSGSSVX example |
psdrive1.c | Driver program for PSGSSVX example |
psdrive1_ABglobal.c | Driver program for psgssvx_ABglobal example |
psdrive2.c | Driver program for PSGSSVX example |
psdrive2_ABglobal.c | Driver program for psgssvx_ABglobal example |
psdrive3.c | Driver program for PSGSSVX example |
psdrive3_ABglobal.c | Driver program for psgssvx_ABglobal example |
psdrive3d.c | Driver program for PSGSSVX3D example |
psdrive3d1.c | Driver program for PSGSSVX3D example |
psdrive3d2.c | Driver program for PSGSSVX3D example |
psdrive3d3.c | Driver program for PSGSSVX3D example |
psdrive4.c | This example illustrates how to divide up the processes into subgroups |
psdrive4_ABglobal.c | This example illustrates how to divide up the processes into subgroups |
psdrive_ABglobal.c | Driver program for psgssvx_ABglobal example |
psgsrfs_tracking.c | Improves the computed solution to a system of linear equations and provides error bounds and backward error estimates |
psgssvx_tracking.c | Solves a system of linear equations A*X=B |
psutil.c | Several matrix utilities |
psymbfact.c | Implements parallel symbolic factorization |
pzdrive.c | Driver program for PZGSSVX example |
pzdrive1.c | Driver program for PZGSSVX example |
pzdrive1_ABglobal.c | Driver program for pzgssvx_ABglobal example |
pzdrive2.c | Driver program for PZGSSVX example |
pzdrive2_ABglobal.c | Driver program for pzgssvx_ABglobal example |
pzdrive3.c | Driver program for PZGSSVX example |
pzdrive3_ABglobal.c | Driver program for pzgssvx_ABglobal example |
pzdrive3d.c | Driver program for PZGSSVX3D example |
pzdrive3d1.c | Driver program for PZGSSVX3D example |
pzdrive3d2.c | Driver program for PZGSSVX3D example |
pzdrive3d3.c | Driver program for PZGSSVX3D example |
pzdrive4.c | This example illustrates how to divide up the processes into subgroups |
pzdrive4_ABglobal.c | This example illustrates how to divide up the processes into subgroups |
pzdrive_ABglobal.c | Driver program for pzgssvx_ABglobal example |
pzdrive_spawn.c | Driver program for PZGSSVX example |
pzgsmv.c | |
pzgstrs_Bglobal_Bsend.c | Solves a system of distributed linear equations |
pzgstrs_lsum_Bsend.c | Performs block modifications |
screate_A_x_b.c | Read the matrix from data file |
screate_matrix.c | Read the matrix from data file |
screate_matrix3d.c | Read the matrix from data file |
screate_matrix_perturbed.c | Read the matrix from data file |
sdistribute.c | Distribute the matrix onto the 2D process mesh |
util.c | Utilities functions |
zcreate_matrix.c | Read the matrix from data file |
zcreate_matrix3d.c | Read the matrix from data file |
zcreate_matrix3d_Jake.c | Read the matrix from data file |
zcreate_matrix_perturbed.c | Read the matrix from data file |
zlook_ahead_update.c | |
znrformat_loc3d.c | |
zreadhb.c | Read a DOUBLE COMPLEX PRECISION matrix stored in Harwell-Boeing format |
zreadtriple.c | |
► FORTRAN | |
c2f_dcreate_matrix_x_b.c | Read the matrix from data file, then distribute it in a distributed CSR format |
c2f_zcreate_matrix_x_b.c | Read the matrix from data file, then distribute it in a distributed CSR format |
c_fortran_pdgssvx_ABglobal.c | |
c_fortran_slugrid.c | |
dcreate_dist_matrix.c | Distribute the input matrix in a distributed compressed row format |
dhbcode1.f90 | Fortran code for reading a sparse matrix in Harwell-Boeing format |
f_5x5.F90 | |
f_pddrive.F90 | The driver program to solve a linear system with default options |
f_pddrive3d.F90 | The driver program to solve a linear system with default options |
f_pddrive_ABglobal.f | |
f_pddrive_old.f90 | |
f_psdrive.F90 | The driver program to solve a linear system with default options |
f_pzdrive.F90 | The driver program to solve a linear system with default options |
f_pzdrive3d.F90 | The driver program to solve a linear system with default options |
sp_ienv.c | Chooses machine-dependent parameters for the local environment |
superlu_c2f_dwrap.c | |
superlu_c2f_swrap.c | |
superlu_c2f_wrap.c | |
superlu_c2f_zwrap.c | |
superlu_mod.f90 | This module contains Fortran-side wrappers for the SuperLU get/set functions |
superlupara.f90 | This module contains some parameter used in SuperLU for Fortran90 user |
zcreate_dist_matrix.c | Distribute the input matrix in a distributed compressed row format |
zhbcode1.f90 | Fortran code for reading a sparse matrix in Harwell-Boeing format |
► SRC | |
► BAK | |
acc_aux.c | |
acc_aux.h | |
colamd.c | A sparse matrix column ordering algorithm |
colamd.h | Colamd prototypes and definitions |
comm.c | Broadcast an array of dtype numbers |
comm_tree.c | |
communication_aux.c | Auxiliary routines to support communication in 3D algorithms |
dbinary_io.c | |
dcommunication_aux.c | |
dcomplex.h | Header for dcomplex.c |
dcomplex_dist.c | Defines common arithmetic operations for complex type |
ddistribute.c | Distribute the matrix onto the 2D process mesh |
dgather.c | |
dgsequ_dist.c | Computes row and column scalings |
dlangs_dist.c | Returns the value of the one norm, the infinity norm, or the element of largest value |
dlaqgs_dist.c | Equilibrates a general sparse M by N matrix A |
dldperm_dist.c | Finds a row permutation so that the matrix has large entries on the diagonal |
dlook_ahead_update.c | |
dlustruct_gpu.h | Descriptions and declarations for structures used in GPU |
dmach_dist.c | |
dmemory_dist.c | Memory utilities |
dmyblas2_dist.c | Level 2 BLAS operations: solves and matvec, written in C |
dnrformat_loc3d.c | |
dreadhb.c | Read a DOUBLE PRECISION matrix stored in Harwell-Boeing format |
dreadMM.c | Contributed by Francois-Henry Rouet |
dreadrb.c | Read a matrix stored in Rutherford-Boeing format |
dreadtriple.c | |
dreadtriple_noheader.c | |
dscatter.c | |
dscatter3d.c | |
dSchCompUdt-2Ddynamic.c | |
dSchCompUdt-gpu.c | |
dsp_blas2_dist.c | Sparse BLAS 2, using some dense BLAS 2 operations |
dsp_blas3_dist.c | Sparse BLAS3, using some dense BLAS3 operations |
dstatic_schedule.c | Performs static scheduling for the look-ahead factorization algorithm |
dsuperlu_blas.c | |
dsuperlu_gpu.cu | |
dtreeFactorization.c | |
dtreeFactorizationGPU.c | Factorization routines for the subtree using 2D process grid, with GPUs |
dtrfAux.c | |
dtrfCommWrapper.c | |
dutil_dist.c | Several matrix utilities |
etree.c | Elimination tree computation and layout routines |
get_perm_c.c | Gets matrix permutation |
get_perm_c_parmetis.c | Gets matrix permutation |
gpu_api_utils.c | |
gpu_api_utils.h | |
gpu_wrapper.h | |
machines.h | These macros define which machine will be used |
mc64ad_dist.c | Permute large entries to the main diagonal |
memory.c | Memory utilities |
mmd.c | Implements the minimum degree algorithm |
old_colamd.c | An approximate minimum degree column ordering algorithm |
old_colamd.h | Colamd include file |
pd3dcomm.c | |
pddistribute.c | Re-distribute A on the 2D process mesh |
pdGetDiagU.c | |
pdgsequ.c | Computes row and column scalings |
pdgsmv.c | Parallel sparse matrix-vector multiplication |
pdgsmv_AXglobal.c | Performs sparse matrix-vector multiplication |
pdgsrfs.c | Improves the computed solution to a system of linear equations and provides error bounds and backward error estimates |
pdgsrfs_ABXglobal.c | Improves the computed solution and provies error bounds |
pdgssvx.c | Solves a system of linear equations A*X=B |
pdgssvx3d.c | Solves a system of linear equations A*X=B using 3D process grid |
pdgssvx_ABglobal.c | Solves a system of linear equations A*X=B, |
pdgstrf.c | Performs LU factorization in parallel |
pdgstrf2.c | Performs panel LU factorization |
pdgstrf3d.c | Performs LU factorization in 3D process grid |
pdgstrf_irecv.c | Performs LU factorization in parallel |
pdgstrf_sherry.c | |
pdgstrf_X1.c | Performs the LU factorization in parallel |
pdgstrs.c | Solves a system of distributed linear equations A*X = B with a general N-by-N matrix A using the LU factors computed previously |
pdgstrs1.c | Solves a system of distributed linear equations |
pdgstrs_Bglobal.c | Solves a system of distributed linear equations A*X = B with a general N-by-N matrix A using the LU factorization |
pdgstrs_Bglobal_Bsend.c | Solves a system of distributed linear equations |
pdgstrs_lsum.c | Perform local block modifications: lsum[i] -= L_i,k * X[k] |
pdgstrs_lsum_cuda.cu | |
pdgstrsL.c | Solves a lower triangular system L*X = B, with L being the lower triangular factor computed previously by PDGSTRF |
pdlangs.c | Returns the value of the one norm, or the Frobenius norm, or the infinity norm, or the element of largest value |
pdlaqgs.c | Equilibrates a general sparse M by N matrix |
pdsymbfact_distdata.c | Redistribute the symbolic structure of L and U from the distribution |
pdutil.c | Several matrix utilities |
ps3dcomm.c | |
psdistribute.c | Re-distribute A on the 2D process mesh |
psGetDiagU.c | |
psgsequ.c | Computes row and column scalings |
psgsmv.c | Parallel sparse matrix-vector multiplication |
psgsmv_AXglobal.c | Performs sparse matrix-vector multiplication |
psgsrfs.c | Improves the computed solution to a system of linear equations and provides error bounds and backward error estimates |
psgsrfs_ABXglobal.c | Improves the computed solution and provies error bounds |
psgssvx.c | Solves a system of linear equations A*X=B |
psgssvx3d.c | Solves a system of linear equations A*X=B using 3D process grid |
psgssvx_ABglobal.c | Solves a system of linear equations A*X=B, |
psgstrf.c | Performs LU factorization in parallel |
psgstrf2.c | Performs panel LU factorization |
psgstrf3d.c | Performs LU factorization in 3D process grid |
psgstrs.c | Solves a system of distributed linear equations A*X = B with a general N-by-N matrix A using the LU factors computed previously |
psgstrs1.c | Solves a system of distributed linear equations |
psgstrs_Bglobal.c | Solves a system of distributed linear equations A*X = B with a general N-by-N matrix A using the LU factorization |
psgstrs_lsum.c | Perform local block modifications: lsum[i] -= L_i,k * X[k] |
pslangs.c | Returns the value of the one norm, or the Frobenius norm, or the infinity norm, or the element of largest value |
pslaqgs.c | Equilibrates a general sparse M by N matrix |
pssymbfact_distdata.c | Redistribute the symbolic structure of L and U from the distribution |
psutil.c | Several matrix utilities |
psymbfact.c | Implements parallel symbolic factorization |
psymbfact.h | Definitions for parallel symbolic factorization routine |
psymbfact_util.c | Utilities for parallel symbolic factorization routine |
pxerr_dist.c | |
pz3dcomm.c | |
pzdistribute.c | Re-distribute A on the 2D process mesh |
pzGetDiagU.c | |
pzgsequ.c | Computes row and column scalings |
pzgsmv.c | Parallel sparse matrix-vector multiplication |
pzgsmv_AXglobal.c | Performs sparse matrix-vector multiplication |
pzgsrfs.c | Improves the computed solution to a system of linear equations and provides error bounds and backward error estimates |
pzgsrfs_ABXglobal.c | Improves the computed solution and provies error bounds |
pzgssvx.c | Solves a system of linear equations A*X=B |
pzgssvx3d.c | Solves a system of linear equations A*X=B using 3D process grid |
pzgssvx_ABglobal.c | Solves a system of linear equations A*X=B, |
pzgstrf.c | Performs LU factorization in parallel |
pzgstrf2.c | Performs panel LU factorization |
pzgstrf3d.c | Performs LU factorization in 3D process grid |
pzgstrf_irecv.c | Performs LU factorization in parallel |
pzgstrs.c | Solves a system of distributed linear equations A*X = B with a general N-by-N matrix A using the LU factors computed previously |
pzgstrs1.c | Solves a system of distributed linear equations |
pzgstrs_Bglobal.c | Solves a system of distributed linear equations A*X = B with a general N-by-N matrix A using the LU factorization |
pzgstrs_lsum.c | Perform local block modifications: lsum[i] -= L_i,k * X[k] |
pzlangs.c | Returns the value of the one norm, or the Frobenius norm, or the infinity norm, or the element of largest value |
pzlaqgs.c | Equilibrates a general sparse M by N matrix |
pzsymbfact_distdata.c | Redistribute the symbolic structure of L and U from the distribution |
pzutil.c | Several matrix utilities |
sbinary_io.c | |
scan.cu | |
scatter.c | |
scatter.h | |
scommunication_aux.c | |
sdistribute.c | Distribute the matrix onto the 2D process mesh |
sec_structs.c | Auxiliary routines in 3D algorithms |
sgather.c | |
sgsequ_dist.c | Computes row and column scalings |
slangs_dist.c | Returns the value of the one norm, the infinity norm, or the element of largest value Modified from SuperLU routine SLANGS |
slaqgs_dist.c | Equlibrates a general sprase matrix |
sldperm_dist.c | Finds a row permutation so that the matrix has large entries on the diagonal |
slook_ahead_update.c | |
slustruct_gpu.h | Descriptions and declarations for structures used in GPU |
smach_dist.c | |
smemory_dist.c | Memory utilities |
smyblas2_dist.c | Level 2 BLAS operations: solves and matvec, written in C |
snrformat_loc3d.c | |
sp_colorder.c | Permutes the columns of the original matrix |
sp_ienv.c | Chooses machine-dependent parameters for the local environment |
sreadhb.c | Read a FLOAT PRECISION matrix stored in Harwell-Boeing format |
sreadMM.c | Contributed by Francois-Henry Rouet |
sreadrb.c | Read a matrix stored in Rutherford-Boeing format |
sreadtriple.c | |
sreadtriple_noheader.c | |
sscatter.c | |
sscatter3d.c | |
sSchCompUdt-2Ddynamic.c | |
sSchCompUdt-cuda.c | |
sSchCompUdt-gpu.c | |
ssp_blas2_dist.c | Sparse BLAS 2, using some dense BLAS 2 operations |
ssp_blas3_dist.c | Sparse BLAS3, using some dense BLAS3 operations |
sstatic_schedule.c | Performs static scheduling for the look-ahead factorization algorithm |
ssuperlu_blas.c | |
ssuperlu_gpu.cu | |
streeFactorization.c | |
streeFactorizationGPU.c | Factorization routines for the subtree using 2D process grid, with GPUs |
strfAux.c | |
strfCommWrapper.c | |
superlu_ddefs.h | Distributed SuperLU data types and function prototypes |
superlu_defs.h | Definitions which are precision-neutral |
superlu_dist_config.h | |
superlu_dist_version.c | |
superlu_enum_consts.h | Enum constants header file |
superlu_FCnames.h | Macro definitions |
superlu_FortranCInterface.h | |
superlu_gpu_utils.cu | |
superlu_grid.c | SuperLU grid utilities |
superlu_grid3d.c | SuperLU grid utilities |
superlu_sdefs.h | Distributed SuperLU data types and function prototypes |
superlu_timer.c | Returns the time in seconds used by the process |
superlu_zdefs.h | Distributed SuperLU data types and function prototypes |
supermatrix.h | Matrix type definitions |
supernodal_etree.c | Function to generate supernodal etree |
supernodalForest.c | SuperLU utilities |
sutil_dist.c | Several matrix utilities |
symbfact.c | Performs a symbolic factorization |
treeFactorization.c | Factorization routines in 3D algorithms |
treeFactorizationGPU.c | |
trfAux.c | Auxiliary routines to support 3D algorithms |
util.c | Utilities functions |
util_dist.h | Header for utilities |
wingetopt.c | |
wingetopt.h | |
xerr_dist.c | |
zbinary_io.c | |
zcommunication_aux.c | |
zdistribute.c | Distribute the matrix onto the 2D process mesh |
zgather.c | |
zgsequ_dist.c | Computes row and column scalings |
zlangs_dist.c | Returns the one norm, or the Frobenius norm, or the infinity norm, or the element of largest value |
zlaqgs_dist.c | Equilibrates a general sparse M by N matrix A |
zldperm_dist.c | Finds a row permutation so that the matrix has large entries on the diagonal |
zlook_ahead_update.c | |
zlustruct_gpu.h | Descriptions and declarations for structures used in GPU |
zmemory_dist.c | Memory utilities |
zmyblas2_dist.c | Level 2 BLAS operations: solves and matvec, written in C |
znrformat_loc3d.c | |
zreadhb.c | Read a DOUBLE COMPLEX PRECISION matrix stored in Harwell-Boeing format |
zreadMM.c | Contributed by Francois-Henry Rouet |
zreadrb.c | Read a matrix stored in Rutherford-Boeing format |
zreadtriple.c | |
zreadtriple_noheader.c | |
zscatter.c | |
zscatter3d.c | |
zSchCompUdt-2Ddynamic.c | |
zSchCompUdt-gpu.c | |
zsp_blas2_dist.c | Sparse BLAS 2, using some dense BLAS 2 operations |
zsp_blas3_dist.c | Sparse BLAS3, using some dense BLAS3 operations |
zstatic_schedule.c | Performs static scheduling for the look-ahead factorization algorithm |
zsuperlu_blas.c | |
zsuperlu_gpu.cu | |
ztreeFactorization.c | |
ztreeFactorizationGPU.c | Factorization routines for the subtree using 2D process grid, with GPUs |
ztrfAux.c | |
ztrfCommWrapper.c | |
zutil_dist.c | Several matrix utilities |
acc_aux.c | |
acc_aux.h | |
colamd.c | A sparse matrix column ordering algorithm |
colamd.h | Colamd prototypes and definitions |
comm.c | Broadcast an array of dtype numbers |
comm_tree.c | |
communication_aux.c | Auxiliary routines to support communication in 3D algorithms |
d_c2cpp_GetHWPM.cpp | Get heavy-weight perfect matching (HWPM) |
dbinary_io.c | |
dcommunication_aux.c | |
dcomplex.h | Header for dcomplex.c |
dcomplex_dist.c | Defines common arithmetic operations for complex type |
ddistribute.c | Distribute the matrix onto the 2D process mesh |
dgather.c | |
dgsequ_dist.c | Computes row and column scalings |
dHWPM_CombBLAS.hpp | Get HWPM, heavy-weight perfect matching |
dlangs_dist.c | Returns the value of the one norm, the infinity norm, or the element of largest value Modified from SuperLU routine DLANGS |
dlaqgs_dist.c | Equlibrates a general sprase matrix |
dldperm_dist.c | Finds a row permutation so that the matrix has large entries on the diagonal |
dlook_ahead_update.c | |
dlustruct_gpu.h | Descriptions and declarations for structures used in GPU |
dmach_dist.c | |
dmemory_dist.c | Memory utilities |
dmyblas2_dist.c | Level 2 BLAS operations: solves and matvec, written in C |
dnrformat_loc3d.c | |
dreadhb.c | Read a DOUBLE PRECISION matrix stored in Harwell-Boeing format |
dreadMM.c | Contributed by Francois-Henry Rouet |
dreadrb.c | Read a matrix stored in Rutherford-Boeing format |
dreadtriple.c | |
dreadtriple_noheader.c | |
dscatter.c | |
dscatter3d.c | |
dSchCompUdt-2Ddynamic.c | |
dSchCompUdt-gpu.c | |
dSchCompUdt-gpuOffload-alt.c | |
dsp_blas2_dist.c | Sparse BLAS 2, using some dense BLAS 2 operations |
dsp_blas3_dist.c | Sparse BLAS3, using some dense BLAS3 operations |
dstatic_schedule.c | Performs static scheduling for the look-ahead factorization algorithm |
dsuperlu_blas.c | |
dsuperlu_gpu.cu | |
dsuperlu_gpu.hip.cpp | |
dtreeFactorization.c | |
dtreeFactorizationGPU.c | Factorization routines for the subtree using 2D process grid, with GPUs |
dtrfAux.c | |
dtrfCommWrapper.c | |
dutil_dist.c | Several matrix utilities |
etree.c | Elimination tree computation and layout routines |
get_perm_c.c | Gets matrix permutation |
get_perm_c_parmetis.c | Gets matrix permutation |
gpu_api_utils.c | |
gpu_api_utils.h | |
gpu_wrapper.h | Wrappers for multiple types of GPUs |
html_mainpage.h | |
machines.h | These macros define which machine will be used |
mc64ad_dist.c | Permute large entries to the main diagonal |
memory.c | Memory utilities |
mmd.c | Implements the minimum degree algorithm |
old_colamd.c | An approximate minimum degree column ordering algorithm |
old_colamd.h | Colamd include file |
pd3dcomm.c | |
pddistribute.c | Re-distribute A on the 2D process mesh |
pdGetDiagU.c | |
pdgsequ.c | Computes row and column scalings |
pdgsmv.c | Parallel sparse matrix-vector multiplication |
pdgsmv_AXglobal.c | Performs sparse matrix-vector multiplication |
pdgsrfs.c | Improves the computed solution to a system of linear equations and provides error bounds and backward error estimates |
pdgsrfs_ABXglobal.c | Improves the computed solution and provies error bounds |
pdgsrfs_trs32.c | Improves the computed solution to a system of linear equations and provides error bounds and backward error estimates |
pdgssvx.c | Solves a system of linear equations A*X=B |
pdgssvx3d.c | Solves a system of linear equations A*X=B using 3D process grid |
pdgssvx_ABglobal.c | Solves a system of linear equations A*X=B, |
pdgssvx_trf32.c | Solves a system of linear equations A*X=B with mixed-precision |
pdgstrf.c | Performs LU factorization in parallel |
pdgstrf2.c | Performs panel LU factorization |
pdgstrf3d.c | Performs LU factorization in 3D process grid |
pdgstrf_irecv.c | Performs LU factorization in parallel |
pdgstrf_sherry.c | |
pdgstrf_X1.c | Performs the LU factorization in parallel |
pdgstrs.c | Solves a system of distributed linear equations A*X = B with a general N-by-N matrix A using the LU factors computed previously |
pdgstrs1.c | Solves a system of distributed linear equations |
pdgstrs_Bglobal.c | Solves a system of distributed linear equations A*X = B with a general N-by-N matrix A using the LU factorization |
pdgstrs_Bglobal_Bsend.c | Solves a system of distributed linear equations |
pdgstrs_lsum.c | Perform local block modifications: lsum[i] -= L_i,k * X[k] |
pdgstrs_lsum_cuda.cu | |
pdgstrs_lsum_cuda.hip.cpp | |
pdgstrsL.c | Solves a lower triangular system L*X = B, with L being the lower triangular factor computed previously by PDGSTRF |
pdlangs.c | Returns the value of the one norm, or the Frobenius norm, or the infinity norm, or the element of largest value |
pdlaqgs.c | Equilibrates a general sparse M by N matrix |
pdsymbfact_distdata.c | Redistribute the symbolic structure of L and U from the distribution |
pdutil.c | Several matrix utilities |
ps3dcomm.c | |
psdistribute.c | Re-distribute A on the 2D process mesh |
psGetDiagU.c | |
psgsequ.c | Computes row and column scalings |
psgsequb.c | Computes row and column scalings, restricting the scale factors to be power-of-radix |
psgsmv.c | Parallel sparse matrix-vector multiplication |
psgsmv_AXglobal.c | Performs sparse matrix-vector multiplication |
psgsmv_d2.c | Parallel sparse matrix-vector multiplication |
psgsrfs.c | Improves the computed solution to a system of linear equations and provides error bounds and backward error estimates |
psgsrfs_ABXglobal.c | Improves the computed solution and provies error bounds |
psgsrfs_d2.c | Improves the computed solution to a system of linear equations and provides error bounds and backward error estimates |
psgssvx.c | Solves a system of linear equations A*X=B |
psgssvx3d.c | Solves a system of linear equations A*X=B using 3D process grid |
psgssvx_ABglobal.c | Solves a system of linear equations A*X=B, |
psgssvx_d2.c | Solves a system of linear equations A*X=B |
psgstrf.c | Performs LU factorization in parallel |
psgstrf2.c | Performs panel LU factorization |
psgstrf3d.c | Performs LU factorization in 3D process grid |
psgstrs.c | Solves a system of distributed linear equations A*X = B with a general N-by-N matrix A using the LU factors computed previously |
psgstrs1.c | Solves a system of distributed linear equations |
psgstrs_Bglobal.c | Solves a system of distributed linear equations A*X = B with a general N-by-N matrix A using the LU factorization |
psgstrs_lsum.c | Perform local block modifications: lsum[i] -= L_i,k * X[k] |
pslangs.c | Returns the value of the one norm, or the Frobenius norm, or the infinity norm, or the element of largest value |
pslaqgs.c | Equilibrates a general sparse M by N matrix |
pssymbfact_distdata.c | Redistribute the symbolic structure of L and U from the distribution |
psutil.c | Several matrix utilities |
psymbfact.c | Implements parallel symbolic factorization |
psymbfact.h | Definitions for parallel symbolic factorization routine |
psymbfact_util.c | Utilities for parallel symbolic factorization routine |
pxerr_dist.c | |
pz3dcomm.c | |
pzdistribute.c | Re-distribute A on the 2D process mesh |
pzGetDiagU.c | |
pzgsequ.c | Computes row and column scalings |
pzgsmv.c | Parallel sparse matrix-vector multiplication |
pzgsmv_AXglobal.c | Performs sparse matrix-vector multiplication |
pzgsrfs.c | Improves the computed solution to a system of linear equations and provides error bounds and backward error estimates |
pzgsrfs_ABXglobal.c | Improves the computed solution and provies error bounds |
pzgssvx.c | Solves a system of linear equations A*X=B |
pzgssvx3d.c | Solves a system of linear equations A*X=B using 3D process grid |
pzgssvx_ABglobal.c | Solves a system of linear equations A*X=B, |
pzgstrf.c | Performs LU factorization in parallel |
pzgstrf2.c | Performs panel LU factorization |
pzgstrf3d.c | Performs LU factorization in 3D process grid |
pzgstrf_irecv.c | Performs LU factorization in parallel |
pzgstrs.c | Solves a system of distributed linear equations A*X = B with a general N-by-N matrix A using the LU factors computed previously |
pzgstrs1.c | Solves a system of distributed linear equations |
pzgstrs_Bglobal.c | Solves a system of distributed linear equations A*X = B with a general N-by-N matrix A using the LU factorization |
pzgstrs_lsum.c | Perform local block modifications: lsum[i] -= L_i,k * X[k] |
pzlangs.c | Returns the value of the one norm, or the Frobenius norm, or the infinity norm, or the element of largest value |
pzlaqgs.c | Equilibrates a general sparse M by N matrix |
pzsymbfact_distdata.c | Redistribute the symbolic structure of L and U from the distribution |
pzutil.c | Several matrix utilities |
s_c2cpp_GetHWPM.cpp | Get heavy-weight perfect matching (HWPM) |
sbinary_io.c | |
scan.cu | |
scatter.c | |
scatter.h | |
scommunication_aux.c | |
sdistribute.c | Distribute the matrix onto the 2D process mesh |
sec_structs.c | Auxiliary routines in 3D algorithms |
sgather.c | |
sgsequ_dist.c | Computes row and column scalings |
slangs_dist.c | Returns the value of the one norm, the infinity norm, or the element of largest value Modified from SuperLU routine SLANGS |
slaqgs_dist.c | Equlibrates a general sprase matrix |
sldperm_dist.c | Finds a row permutation so that the matrix has large entries on the diagonal |
slook_ahead_update.c | |
slustruct_gpu.h | Descriptions and declarations for structures used in GPU |
smach_dist.c | |
smemory_dist.c | Memory utilities |
smyblas2_dist.c | Level 2 BLAS operations: solves and matvec, written in C |
snrformat_loc3d.c | |
sp_colorder.c | Permutes the columns of the original matrix |
sp_ienv.c | Chooses machine-dependent parameters for the local environment |
sreadhb.c | Read a FLOAT PRECISION matrix stored in Harwell-Boeing format |
sreadMM.c | Contributed by Francois-Henry Rouet |
sreadrb.c | Read a matrix stored in Rutherford-Boeing format |
sreadtriple.c | |
sreadtriple_noheader.c | |
sscatter.c | |
sscatter3d.c | |
sSchCompUdt-2Ddynamic.c | |
sSchCompUdt-cuda.c | |
sSchCompUdt-gpu.c | |
ssp_blas2_dist.c | Sparse BLAS 2, using some dense BLAS 2 operations |
ssp_blas3_dist.c | Sparse BLAS3, using some dense BLAS3 operations |
sstatic_schedule.c | Performs static scheduling for the look-ahead factorization algorithm |
ssuperlu_blas.c | |
ssuperlu_gpu.cu | |
ssuperlu_gpu.hip.cpp | |
streeFactorization.c | |
streeFactorizationGPU.c | Factorization routines for the subtree using 2D process grid, with GPUs |
strfAux.c | |
strfCommWrapper.c | |
superlu_ddefs.h | Distributed SuperLU data types and function prototypes |
superlu_defs.h | Definitions which are precision-neutral |
superlu_dist_config.h | |
superlu_dist_version.c | |
superlu_enum_consts.h | Enum constants header file |
superlu_FCnames.h | Macro definitions |
superlu_FortranCInterface.h | |
superlu_gpu_utils.cu | |
superlu_gpu_utils.hip.cpp | |
superlu_grid.c | SuperLU grid utilities |
superlu_grid3d.c | SuperLU grid utilities |
superlu_sdefs.h | Distributed SuperLU data types and function prototypes |
superlu_timer.c | Returns the time in seconds used by the process |
superlu_zdefs.h | Distributed SuperLU data types and function prototypes |
supermatrix.h | Matrix type definitions |
supernodal_etree.c | Function to generate supernodal etree |
supernodalForest.c | SuperLU utilities |
sutil_dist.c | Several matrix utilities |
symbfact.c | Performs a symbolic factorization |
treeFactorization.c | Factorization routines in 3D algorithms |
treeFactorizationGPU.c | |
TreeInterface.cpp | |
trfAux.c | Auxiliary routines to support 3D algorithms |
util.c | Utilities functions |
util_dist.h | Header for utilities |
wingetopt.c | |
wingetopt.h | |
xerr_dist.c | |
z_c2cpp_GetHWPM.cpp | Get heavy-weight perfect matching (HWPM) |
zbinary_io.c | |
zcommunication_aux.c | |
zdistribute.c | Distribute the matrix onto the 2D process mesh |
zgather.c | |
zgsequ_dist.c | Computes row and column scalings |
zHWPM_CombBLAS.hpp | Get HWPM, heavy-weight perfect matching |
zlangs_dist.c | Returns the value of the one norm, the infinity norm, or the element of largest value Modified from SuperLU routine ZLANGS |
zlaqgs_dist.c | Equlibrates a general sprase matrix |
zldperm_dist.c | Finds a row permutation so that the matrix has large entries on the diagonal |
zlook_ahead_update.c | |
zlustruct_gpu.h | Descriptions and declarations for structures used in GPU |
zmemory_dist.c | Memory utilities |
zmyblas2_dist.c | Level 2 BLAS operations: solves and matvec, written in C |
znrformat_loc3d.c | |
zreadhb.c | Read a DOUBLE COMPLEX PRECISION matrix stored in Harwell-Boeing format |
zreadMM.c | Contributed by Francois-Henry Rouet |
zreadrb.c | Read a matrix stored in Rutherford-Boeing format |
zreadtriple.c | |
zreadtriple_noheader.c | |
zscatter.c | |
zscatter3d.c | |
zSchCompUdt-2Ddynamic.c | |
zSchCompUdt-gpu.c | |
zsp_blas2_dist.c | Sparse BLAS 2, using some dense BLAS 2 operations |
zsp_blas3_dist.c | Sparse BLAS3, using some dense BLAS3 operations |
zstatic_schedule.c | Performs static scheduling for the look-ahead factorization algorithm |
zsuperlu_blas.c | |
zsuperlu_gpu.cu | |
zsuperlu_gpu.hip.cpp | |
ztreeFactorization.c | |
ztreeFactorizationGPU.c | Factorization routines for the subtree using 2D process grid, with GPUs |
ztrfAux.c | |
ztrfCommWrapper.c | |
zutil_dist.c | Several matrix utilities |
► TEST | |
dcreate_matrix.c | Read the matrix from data file |
pdcompute_resid.c | Test for small residual |
pdtest.c | Driver program for testing PDGSSVX |
pstest.c | Driver program for testing PSGSSVX |
pzcompute_resid.c | Test for small residual |
pztest.c | Driver program for testing PZGSSVX |
zcreate_matrix.c | Read the matrix from data file |