
Carta.tech

Packages

scalapackdoc

520
 cdttrf.3
 Compute an lu factorization of a complex tridiagonal matrix a using elimination without partial pivoting
 cdttrsv.3
 Solve one of the systems of equations l * x = b, l**t * x = b, or l**h * x = b,
 cpttrsv.3
 Solve one of the triangular systems l * x = b, or l**h * x = b,
 ddttrf.3
 Compute an lu factorization of a complex tridiagonal matrix a using elimination without partial pivoting
 ddttrsv.3
 Solve one of the systems of equations l * x = b, l**t * x = b, or l**h * x = b,
 dlamsh.3
 Send multiple shifts through a small (single node) matrix to see how consecutive small subdiagonal elements are modified by subsequent shifts in an effort to maximize the number of bulges that can be sent through
 dlaref.3
 Applie one or several householder reflectors of size 3 to one or two matrices (if column is specified) on either their rows or columns
 dlasorte.3
 Sort eigenpairs so that real eigenpairs are together and complex are together
 dlasrt2.3
 The numbers in d in increasing order (if id = 'i') or in decreasing order (if id = 'd' )
 dpttrsv.3
 Solve one of the triangular systems l**t* x = b, or l * x = b,
 dstein2.3
 Compute the eigenvectors of a real symmetric tridiagonal matrix t corresponding to specified eigenvalues, using inverse iteration
 dsteqr2.3
 I a modified version of lapack routine dsteqr
 pcdbsv.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pcdbtrf.3
 Compute a lu factorization of an nbyn complex banded diagonally dominantlike distributed matrix with bandwidth bwl, bwu
 pcdbtrs.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pcdbtrsv.3
 Solve a banded triangular system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pcdtsv.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pcdttrf.3
 Compute a lu factorization of an nbyn complex tridiagonal diagonally dominantlike distributed matrix a(1:n, ja:ja+n1)
 pcdttrs.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pcdttrsv.3
 Solve a tridiagonal triangular system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pcgbsv.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pcgbtrf.3
 Compute a lu factorization of an nbyn complex banded distributed matrix with bandwidth bwl, bwu
 pcgbtrs.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pcgebd2.3
 Reduce a complex general mbyn distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) to upper or lower bidiagonal form b by an unitary transformation
 pcgebrd.3
 Reduce a complex general mbyn distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) to upper or lower bidiagonal form b by an unitary transformation
 pcgecon.3
 Estimate the reciprocal of the condition number of a general distributed complex matrix a(ia:ia+n1,ja:ja+n1), in either the 1norm or the infinitynorm, using the lu factorization computed by pcgetrf
 pcgeequ.3
 Compute row and column scalings intended to equilibrate an mbyn distributed matrix sub( a ) = a(ia:ia+n1,ja:ja:ja+n1) and reduce its condition number
 pcgehd2.3
 Reduce a complex general distributed matrix sub( a ) to upper hessenberg form h by an unitary similarity transformation
 pcgehrd.3
 Reduce a complex general distributed matrix sub( a ) to upper hessenberg form h by an unitary similarity transformation
 pcgelq2.3
 Compute a lq factorization of a complex distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = l * q
 pcgelqf.3
 Compute a lq factorization of a complex distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = l * q
 pcgels.3
 Solve overdetermined or underdetermined complex linear systems involving an mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1),
 pcgeql2.3
 Compute a ql factorization of a complex distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = q * l
 pcgeqlf.3
 Compute a ql factorization of a complex distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = q * l
 pcgeqpf.3
 Compute a qr factorization with column pivoting of a mbyn distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1)
 pcgeqr2.3
 Compute a qr factorization of a complex distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = q * r
 pcgeqrf.3
 Compute a qr factorization of a complex distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = q * r
 pcgerfs.3
 Improve the computed solution to a system of linear equations and provides error bounds and backward error estimates for the solutions
 pcgerq2.3
 Compute a rq factorization of a complex distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = r * q
 pcgerqf.3
 Compute a rq factorization of a complex distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = r * q
 pcgesv.3
 Compute the solution to a complex system of linear equations sub( a ) * x = sub( b ),
 pcgetf2.3
 Compute an lu factorization of a general mbyn distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) using partial pivoting with row interchanges
 pcgetrf.3
 Compute an lu factorization of a general mbyn distributed matrix sub( a ) = (ia:ia+m1,ja:ja+n1) using partial pivoting with row interchanges
 pcgetri.3
 Compute the inverse of a distributed matrix using the lu factorization computed by pcgetrf
 pcgetrs.3
 Solve a system of distributed linear equations op( sub( a ) ) * x = sub( b ) with a general nbyn distributed matrix sub( a ) using the lu factorization computed by pcgetrf
 pcggqrf.3
 Compute a generalized qr factorization of an nbym matrix sub( a ) = a(ia:ia+n1,ja:ja+m1) and an nbyp matrix sub( b ) = b(ib:ib+n1,jb:jb+p1)
 pcggrqf.3
 Compute a generalized rq factorization of an mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1)
 pchegs2.3
 Reduce a complex hermitiandefinite generalized eigenproblem to standard form
 pchegst.3
 Reduce a complex hermitiandefinite generalized eigenproblem to standard form
 pchetd2.3
 Reduce a complex hermitian matrix sub( a ) to hermitian tridiagonal form t by an unitary similarity transformation
 pchetrd.3
 Reduce a complex hermitian matrix sub( a ) to hermitian tridiagonal form t by an unitary similarity transformation
 pclabrd.3
 Reduce the first nb rows and columns of a complex general mbyn distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) to upper or lower bidiagonal form by an unitary transformation q' * a * p, and returns the matrices x and y which are needed to apply the transfor mation to the unreduced part of sub( a )
 pclacgv.3
 Conjugate a complex vector of length n, sub( x ), where sub( x ) denotes x(ix,jx:jx+n1) if incx = descx( m_ ) and x(ix:ix+n1,jx) if incx = 1, and notes ===== each global data object is described by an associated description vector
 pclacon.3
 Estimate the 1norm of a square, complex distributed matrix a
 pclacp2.3
 Copie all or part of a distributed matrix a to another distributed matrix b
 pclacpy.3
 Copie all or part of a distributed matrix a to another distributed matrix b
 pclaevswp.3
 Move the eigenvectors (potentially unsorted) from where they are computed, to a scalapack standard block cyclic array, sorted so that the corresponding eigenvalues are sorted
 pclahrd.3
 Reduce the first nb columns of a complex general nby(nk+1) distributed matrix a(ia:ia+n1,ja:ja+nk) so that elements below the kth subdiagonal are zero
 pclange.3
 Return the value of the one norm, or the frobenius norm,
 pclanhe.3
 Return the value of the one norm, or the frobenius norm,
 pclanhs.3
 Return the value of the one norm, or the frobenius norm,
 pclansy.3
 Return the value of the one norm, or the frobenius norm,
 pclantr.3
 Return the value of the one norm, or the frobenius norm,
 pclapiv.3
 Applie either p (permutation matrix indicated by ipiv) or inv( p ) to a general mbyn distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1), resulting in row or column pivoting
 pclapv2.3
 Applie either p (permutation matrix indicated by ipiv) or inv( p ) to a mbyn distributed matrix sub( a ) denoting a(ia:ia+m1,ja:ja+n1), resulting in row or column pivoting
 pclaqge.3
 Equilibrate a general mbyn distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) using the row and scaling factors in the vectors r and c
 pclaqsy.3
 Equilibrate a symmetric distributed matrix sub( a ) = a(ia:ia+n1,ja:ja+n1) using the scaling factors in the vectors sr and sc
 pclarf.3
 Applie a complex elementary reflector q to a complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1), from either the left or the right
 pclarfb.3
 Applie a complex block reflector q or its conjugate transpose q**h to a complex mbyn distributed matrix sub( c ) denoting c(ic:ic+m1,jc:jc+n1), from the left or the right
 pclarfc.3
 Applie a complex elementary reflector q**h to a complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1),
 pclarfg.3
 Generate a complex elementary reflector h of order n, such that h * sub( x ) = h * ( x(iax,jax) ) = ( alpha ), h' * h = i
 pclarft.3
 Form the triangular factor t of a complex block reflector h of order n, which is defined as a product of k elementary reflectors
 pclarz.3
 Applie a complex elementary reflector q to a complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1), from either the left or the right
 pclarzb.3
 Applie a complex block reflector q or its conjugate transpose q**h to a complex mbyn distributed matrix sub( c ) denoting c(ic:ic+m1,jc:jc+n1), from the left or the right
 pclarzc.3
 Applie a complex elementary reflector q**h to a complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1),
 pclarzt.3
 Form the triangular factor t of a complex block reflector h of order n, which is defined as a product of k elementary reflectors as returned by pctzrzf
 pclascl.3
 Multiplie the mbyn complex distributed matrix sub( a ) denoting a(ia:ia+m1,ja:ja+n1) by the real scalar cto/cfrom
 pclase2.3
 Initialize an mbyn distributed matrix sub( a ) denoting a(ia:ia+m1,ja:ja+n1) to beta on the diagonal and alpha on the offdiagonals
 pclaset.3
 Initialize an mbyn distributed matrix sub( a ) denoting a(ia:ia+m1,ja:ja+n1) to beta on the diagonal and alpha on the offdiagonals
 pclassq.3
 Return the values scl and smsq such that ( scl**2 )*smsq = x( 1 )**2 +...+ x( n )**2 + ( scale**2 )*sumsq,
 pclaswp.3
 Perform a series of row or column interchanges on the distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1)
 pclatra.3
 Compute the trace of an nbyn distributed matrix sub( a ) denoting a( ia:ia+n1, ja:ja+n1 )
 pclatrd.3
 Reduce nb rows and columns of a complex hermitian distributed matrix sub( a ) = a(ia:ia+n1,ja:ja+n1) to complex tridiagonal form by an unitary similarity transformation q' * sub( a ) * q, and returns the matrices v and w which are needed to apply the transformation to the unreduced part of sub( a )
 pclatrs.3
 Solve a triangular system
 pclatrz.3
 Reduce the mbyn ( m=n ) complex upper trapezoidal matrix sub( a ) = [a(ia:ia+m1,ja:ja+m1) a(ia:ia+m1,ja+nl:ja+n1)]
 pclauu2.3
 Compute the product u * u' or l' * l, where the triangular factor u or l is stored in the upper or lower triangular part of the matrix sub( a ) = a(ia:ia+n1,ja:ja+n1)
 pclauum.3
 Compute the product u * u' or l' * l, where the triangular factor u or l is stored in the upper or lower triangular part of the distributed matrix sub( a ) = a(ia:ia+n1,ja:ja+n1)
 pcpbsv.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pcpbtrf.3
 Compute a cholesky factorization of an nbyn complex banded symmetric positive definite distributed matrix with bandwidth bw
 pcpbtrs.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pcpbtrsv.3
 Solve a banded triangular system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pcpocon.3
 Estimate the reciprocal of the condition number (in the 1norm) of a complex hermitian positive definite distributed matrix using the cholesky factorization a = u**h*u or a = l*l**h computed by pcpotrf
 pcpoequ.3
 Compute row and column scalings intended to equilibrate a distributed hermitian positive definite matrix sub( a ) = a(ia:ia+n1,ja:ja+n1) and reduce its condition number (with respect to the twonorm)
 pcporfs.3
 Improve the computed solution to a system of linear equations when the coefficient matrix is hermitian positive definite and provides error bounds and backward error estimates for the solutions
 pcposv.3
 Compute the solution to a complex system of linear equations sub( a ) * x = sub( b ),
 pcpotf2.3
 Compute the cholesky factorization of a complex hermitian positive definite distributed matrix sub( a )=a(ia:ia+n1,ja:ja+n1)
 pcpotrf.3
 Compute the cholesky factorization of an nbyn complex hermitian positive definite distributed matrix sub( a ) denoting a(ia:ia+n1, ja:ja+n1)
 pcpotri.3
 Compute the inverse of a complex hermitian positive definite distributed matrix sub( a ) = a(ia:ia+n1,ja:ja+n1) using the cholesky factorization sub( a ) = u**h*u or l*l**h computed by pcpotrf
 pcpotrs.3
 Solve a system of linear equations sub( a ) * x = sub( b ) a(ia:ia+n1,ja:ja+n1)*x = b(ib:ib+n1,jb:jb+nrhs1)
 pcptsv.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pcpttrf.3
 Compute a cholesky factorization of an nbyn complex tridiagonal symmetric positive definite distributed matrix a(1:n, ja:ja+n1)
 pcpttrs.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pcpttrsv.3
 Solve a tridiagonal triangular system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pcsrscl.3
 Multiplie an nelement complex distributed vector sub( x ) by the real scalar 1/a
 pcstein.3
 Compute the eigenvectors of a symmetric tridiagonal matrix in parallel, using inverse iteration
 pctrcon.3
 Estimate the reciprocal of the condition number of a triangular distributed matrix a(ia:ia+n1,ja:ja+n1), in either the 1norm or the infinitynorm
 pctrrfs.3
 Provide error bounds and backward error estimates for the solution to a system of linear equations with a triangular coefficient matrix
 pctrti2.3
 Compute the inverse of a complex upper or lower triangular block matrix sub( a ) = a(ia:ia+n1,ja:ja+n1)
 pctrtri.3
 Compute the inverse of a upper or lower triangular distributed matrix sub( a ) = a(ia:ia+n1,ja:ja+n1)
 pctrtrs.3
 Solve a triangular system of the form sub( a ) * x = sub( b ) or sub( a )**t * x = sub( b ) or sub( a )**h * x = sub( b ),
 pctzrzf.3
 Reduce the mbyn ( m=n ) complex upper trapezoidal matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) to upper triangular form by means of unitary transformations
 pcung2l.3
 Generate an mbyn complex distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal columns, which is defined as the last n columns of a product of k elementary reflectors of order m q = h(k)
 pcung2r.3
 Generate an mbyn complex distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal columns, which is defined as the first n columns of a product of k elementary reflectors of order m q = h(1) h(2)
 pcungl2.3
 Generate an mbyn complex distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal rows, which is defined as the first m rows of a product of k elementary reflectors of order n q = h(k)'
 pcunglq.3
 Generate an mbyn complex distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal rows, which is defined as the first m rows of a product of k elementary reflectors of order n q = h(k)'
 pcungql.3
 Generate an mbyn complex distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal columns, which is defined as the last n columns of a product of k elementary reflectors of order m q = h(k)
 pcungqr.3
 Generate an mbyn complex distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal columns, which is defined as the first n columns of a product of k elementary reflectors of order m q = h(1) h(2)
 pcungr2.3
 Generate an mbyn complex distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal rows, which is defined as the last m rows of a product of k elementary reflectors of order n q = h(1)' h(2)'
 pcungrq.3
 Generate an mbyn complex distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal rows, which is defined as the last m rows of a product of k elementary reflectors of order n q = h(1)' h(2)'
 pcunm2l.3
 Overwrite the general complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pcunm2r.3
 Overwrite the general complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pcunmbr.3
 Vect = 'q', pcunmbr overwrites the general complex distributed mbyn matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pcunmhr.3
 Overwrite the general complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pcunml2.3
 Overwrite the general complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pcunmlq.3
 Overwrite the general complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pcunmql.3
 Overwrite the general complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pcunmqr.3
 Overwrite the general complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pcunmr2.3
 Overwrite the general complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pcunmr3.3
 Overwrite the general complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pcunmrq.3
 Overwrite the general complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pcunmrz.3
 Overwrite the general complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pcunmtr.3
 Overwrite the general complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pddbsv.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pddbtrf.3
 Compute a lu factorization of an nbyn real banded diagonally dominantlike distributed matrix with bandwidth bwl, bwu
 pddbtrs.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pddbtrsv.3
 Solve a banded triangular system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pddtsv.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pddttrf.3
 Compute a lu factorization of an nbyn real tridiagonal diagonally dominantlike distributed matrix a(1:n, ja:ja+n1)
 pddttrs.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pddttrsv.3
 Solve a tridiagonal triangular system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pdgbsv.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pdgbtrf.3
 Compute a lu factorization of an nbyn real banded distributed matrix with bandwidth bwl, bwu
 pdgbtrs.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pdgebd2.3
 Reduce a real general mbyn distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) to upper or lower bidiagonal form b by an orthogonal transformation
 pdgebrd.3
 Reduce a real general mbyn distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) to upper or lower bidiagonal form b by an orthogonal transformation
 pdgecon.3
 Estimate the reciprocal of the condition number of a general distributed real matrix a(ia:ia+n1,ja:ja+n1), in either the 1norm or the infinitynorm, using the lu factorization computed by pdgetrf
 pdgeequ.3
 Compute row and column scalings intended to equilibrate an mbyn distributed matrix sub( a ) = a(ia:ia+n1,ja:ja:ja+n1) and reduce its condition number
 pdgehd2.3
 Reduce a real general distributed matrix sub( a ) to upper hessenberg form h by an orthogonal similarity transforma tion
 pdgehrd.3
 Reduce a real general distributed matrix sub( a ) to upper hessenberg form h by an orthogonal similarity transforma tion
 pdgelq2.3
 Compute a lq factorization of a real distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = l * q
 pdgelqf.3
 Compute a lq factorization of a real distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = l * q
 pdgels.3
 Solve overdetermined or underdetermined real linear systems involving an mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1),
 pdgeql2.3
 Compute a ql factorization of a real distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = q * l
 pdgeqlf.3
 Compute a ql factorization of a real distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = q * l
 pdgeqpf.3
 Compute a qr factorization with column pivoting of a mbyn distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1)
 pdgeqr2.3
 Compute a qr factorization of a real distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = q * r
 pdgeqrf.3
 Compute a qr factorization of a real distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = q * r
 pdgerfs.3
 Improve the computed solution to a system of linear equations and provides error bounds and backward error estimates for the solutions
 pdgerq2.3
 Compute a rq factorization of a real distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = r * q
 pdgerqf.3
 Compute a rq factorization of a real distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = r * q
 pdgesv.3
 Compute the solution to a real system of linear equations sub( a ) * x = sub( b ),
 pdgesvd.3
 Compute the singular value decomposition (svd) of an mbyn matrix a, optionally computing the left and/or right singular vectors
 pdgetf2.3
 Compute an lu factorization of a general mbyn distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) using partial pivoting with row interchanges
 pdgetrf.3
 Compute an lu factorization of a general mbyn distributed matrix sub( a ) = (ia:ia+m1,ja:ja+n1) using partial pivoting with row interchanges
 pdgetri.3
 Compute the inverse of a distributed matrix using the lu factorization computed by pdgetrf
 pdgetrs.3
 Solve a system of distributed linear equations op( sub( a ) ) * x = sub( b ) with a general nbyn distributed matrix sub( a ) using the lu factorization computed by pdgetrf
 pdggqrf.3
 Compute a generalized qr factorization of an nbym matrix sub( a ) = a(ia:ia+n1,ja:ja+m1) and an nbyp matrix sub( b ) = b(ib:ib+n1,jb:jb+p1)
 pdggrqf.3
 Compute a generalized rq factorization of an mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1)
 pdlabad.3
 Take as input the values computed by pdlamch for underflow and overflow, and returns the square root of each of these values if the log of large is sufficiently large
 pdlabrd.3
 Reduce the first nb rows and columns of a real general mbyn distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) to upper or lower bidiagonal form by an orthogonal transformation q' * a * p,
 pdlacon.3
 Estimate the 1norm of a square, real distributed matrix a
 pdlaconsb.3
 Look for two consecutive small subdiagonal elements by seeing the effect of starting a double shift qr iteration given by h44, h33, & h43h34 and see if this would make a subdiagonal negligible
 pdlacp2.3
 Copie all or part of a distributed matrix a to another distributed matrix b
 pdlacp3.3
 I an auxiliary routine that copies from a global parallel array into a local replicated array or vise versa
 pdlacpy.3
 Copie all or part of a distributed matrix a to another distributed matrix b
 pdlaevswp.3
 Move the eigenvectors (potentially unsorted) from where they are computed, to a scalapack standard block cyclic array, sorted so that the corresponding eigenvalues are sorted
 pdlahqr.3
 I an auxiliary routine used to find the schur decomposition and or eigenvalues of a matrix already in hessenberg form from cols ilo to ihi
 pdlahrd.3
 Reduce the first nb columns of a real general nby(nk+1) distributed matrix a(ia:ia+n1,ja:ja+nk) so that elements below the kth subdiagonal are zero
 pdlamch.3
 Determine double precision machine parameters
 pdlange.3
 Return the value of the one norm, or the frobenius norm,
 pdlanhs.3
 Return the value of the one norm, or the frobenius norm,
 pdlansy.3
 Return the value of the one norm, or the frobenius norm,
 pdlantr.3
 Return the value of the one norm, or the frobenius norm,
 pdlapiv.3
 Applie either p (permutation matrix indicated by ipiv) or inv( p ) to a general mbyn distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1), resulting in row or column pivoting
 pdlapv2.3
 Applie either p (permutation matrix indicated by ipiv) or inv( p ) to a mbyn distributed matrix sub( a ) denoting a(ia:ia+m1,ja:ja+n1), resulting in row or column pivoting
 pdlaqge.3
 Equilibrate a general mbyn distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) using the row and scaling factors in the vectors r and c
 pdlaqsy.3
 Equilibrate a symmetric distributed matrix sub( a ) = a(ia:ia+n1,ja:ja+n1) using the scaling factors in the vectors sr and sc
 pdlared1d.3
 Redistribute a 1d array it assumes that the input array, bycol, is distributed across rows and that all process column contain the same copy of bycol
 pdlared2d.3
 Redistribute a 1d array it assumes that the input array, byrow, is distributed across columns and that all process rows contain the same copy of byrow
 pdlarf.3
 Applie a real elementary reflector q (or q**t) to a real mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1), from either the left or the right
 pdlarfb.3
 Applie a real block reflector q or its transpose q**t to a real distributed mbyn matrix sub( c ) = c(ic:ic+m1,jc:jc+n1)
 pdlarfg.3
 Generate a real elementary reflector h of order n, such that h * sub( x ) = h * ( x(iax,jax) ) = ( alpha ), h' * h = i
 pdlarft.3
 Form the triangular factor t of a real block reflector h of order n, which is defined as a product of k elementary reflectors
 pdlarz.3
 Applie a real elementary reflector q (or q**t) to a real mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1), from either the left or the right
 pdlarzb.3
 Applie a real block reflector q or its transpose q**t to a real distributed mbyn matrix sub( c ) = c(ic:ic+m1,jc:jc+n1)
 pdlarzt.3
 Form the triangular factor t of a real block reflector h of order n, which is defined as a product of k elementary reflectors as returned by pdtzrzf
 pdlascl.3
 Multiplie the mbyn real distributed matrix sub( a ) denoting a(ia:ia+m1,ja:ja+n1) by the real scalar cto/cfrom
 pdlase2.3
 Initialize an mbyn distributed matrix sub( a ) denoting a(ia:ia+m1,ja:ja+n1) to beta on the diagonal and alpha on the offdiagonals
 pdlaset.3
 Initialize an mbyn distributed matrix sub( a ) denoting a(ia:ia+m1,ja:ja+n1) to beta on the diagonal and alpha on the offdiagonals
 pdlasmsub.3
 Look for a small subdiagonal element from the bottom of the matrix that it can safely set to zero
 pdlassq.3
 Return the values scl and smsq such that ( scl**2 )*smsq = x( 1 )**2 +...+ x( n )**2 + ( scale**2 )*sumsq,
 pdlaswp.3
 Perform a series of row or column interchanges on the distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1)
 pdlatra.3
 Compute the trace of an nbyn distributed matrix sub( a ) denoting a( ia:ia+n1, ja:ja+n1 )
 pdlatrd.3
 Reduce nb rows and columns of a real symmetric distributed matrix sub( a ) = a(ia:ia+n1,ja:ja+n1) to symmetric tridiagonal form by an orthogonal similarity transformation q' * sub( a ) * q,
 pdlatrs.3
 Solve a triangular system
 pdlatrz.3
 Reduce the mbyn ( m=n ) real upper trapezoidal matrix sub( a ) = [ a(ia:ia+m1,ja:ja+m1) a(ia:ia+m1,ja+nl:ja+n1) ] to upper triangular form by means of orthogonal transformations
 pdlauu2.3
 Compute the product u * u' or l' * l, where the triangular factor u or l is stored in the upper or lower triangular part of the matrix sub( a ) = a(ia:ia+n1,ja:ja+n1)
 pdlauum.3
 Compute the product u * u' or l' * l, where the triangular factor u or l is stored in the upper or lower triangular part of the distributed matrix sub( a ) = a(ia:ia+n1,ja:ja+n1)
 pdlawil.3
 Get the transform given by h44,h33, & h43h34 into v starting at row m
 pdorg2l.3
 Generate an mbyn real distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal columns, which is defined as the last n columns of a product of k elementary reflectors of order m q = h(k)
 pdorg2r.3
 Generate an mbyn real distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal columns, which is defined as the first n columns of a product of k elementary reflectors of order m q = h(1) h(2)
 pdorgl2.3
 Generate an mbyn real distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal rows, which is defined as the first m rows of a product of k elementary reflectors of order n q = h(k)
 pdorglq.3
 Generate an mbyn real distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal rows, which is defined as the first m rows of a product of k elementary reflectors of order n q = h(k)
 pdorgql.3
 Generate an mbyn real distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal columns, which is defined as the last n columns of a product of k elementary reflectors of order m q = h(k)
 pdorgqr.3
 Generate an mbyn real distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal columns, which is defined as the first n columns of a product of k elementary reflectors of order m q = h(1) h(2)
 pdorgr2.3
 Generate an mbyn real distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal rows, which is defined as the last m rows of a product of k elementary reflectors of order n q = h(1) h(2)
 pdorgrq.3
 Generate an mbyn real distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal rows, which is defined as the last m rows of a product of k elementary reflectors of order n q = h(1) h(2)
 pdorm2l.3
 Overwrite the general real mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pdorm2r.3
 Overwrite the general real mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pdormbr.3
 Vect = 'q', pdormbr overwrites the general real distributed mbyn matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pdormhr.3
 Overwrite the general real mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pdorml2.3
 Overwrite the general real mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pdormlq.3
 Overwrite the general real mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pdormql.3
 Overwrite the general real mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pdormqr.3
 Overwrite the general real mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pdormr2.3
 Overwrite the general real mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pdormr3.3
 Overwrite the general real mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pdormrq.3
 Overwrite the general real mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pdormrz.3
 Overwrite the general real mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pdormtr.3
 Overwrite the general real mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pdpbsv.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pdpbtrf.3
 Compute a cholesky factorization of an nbyn real banded symmetric positive definite distributed matrix with bandwidth bw
 pdpbtrs.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pdpbtrsv.3
 Solve a banded triangular system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pdpocon.3
 Estimate the reciprocal of the condition number (in the 1norm) of a real symmetric positive definite distributed matrix using the cholesky factorization a = u**t*u or a = l*l**t computed by pdpotrf
 pdpoequ.3
 Compute row and column scalings intended to equilibrate a distributed symmetric positive definite matrix sub( a ) = a(ia:ia+n1,ja:ja+n1) and reduce its condition number (with respect to the twonorm)
 pdporfs.3
 Improve the computed solution to a system of linear equations when the coefficient matrix is symmetric positive definite and provides error bounds and backward error estimates for the solutions
 pdposv.3
 Compute the solution to a real system of linear equations sub( a ) * x = sub( b ),
 pdpotf2.3
 Compute the cholesky factorization of a real symmetric positive definite distributed matrix sub( a )=a(ia:ia+n1,ja:ja+n1)
 pdpotrf.3
 Compute the cholesky factorization of an nbyn real symmetric positive definite distributed matrix sub( a ) denoting a(ia:ia+n1, ja:ja+n1)
 pdpotri.3
 Compute the inverse of a real symmetric positive definite distributed matrix sub( a ) = a(ia:ia+n1,ja:ja+n1) using the cholesky factorization sub( a ) = u**t*u or l*l**t computed by pdpotrf
 pdpotrs.3
 Solve a system of linear equations sub( a ) * x = sub( b ) a(ia:ia+n1,ja:ja+n1)*x = b(ib:ib+n1,jb:jb+nrhs1)
 pdptsv.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pdpttrf.3
 Compute a cholesky factorization of an nbyn real tridiagonal symmetric positive definite distributed matrix a(1:n, ja:ja+n1)
 pdpttrs.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pdpttrsv.3
 Solve a tridiagonal triangular system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pdrscl.3
 Multiplie an nelement real distributed vector sub( x ) by the real scalar 1/a
 pdstebz.3
 Compute the eigenvalues of a symmetric tridiagonal matrix in parallel
 pdstein.3
 Compute the eigenvectors of a symmetric tridiagonal matrix in parallel, using inverse iteration
 pdsygs2.3
 Reduce a real symmetricdefinite generalized eigenproblem to standard form
 pdsygst.3
 Reduce a real symmetricdefinite generalized eigenproblem to standard form
 pdsytd2.3
 Reduce a real symmetric matrix sub( a ) to symmetric tridiagonal form t by an orthogonal similarity transformation
 pdsytrd.3
 Reduce a real symmetric matrix sub( a ) to symmetric tridiagonal form t by an orthogonal similarity transformation
 pdtrcon.3
 Estimate the reciprocal of the condition number of a triangular distributed matrix a(ia:ia+n1,ja:ja+n1), in either the 1norm or the infinitynorm
 pdtrrfs.3
 Provide error bounds and backward error estimates for the solution to a system of linear equations with a triangular coefficient matrix
 pdtrti2.3
 Compute the inverse of a real upper or lower triangular block matrix sub( a ) = a(ia:ia+n1,ja:ja+n1)
 pdtrtri.3
 Compute the inverse of a upper or lower triangular distributed matrix sub( a ) = a(ia:ia+n1,ja:ja+n1)
 pdtrtrs.3
 Solve a triangular system of the form sub( a ) * x = sub( b ) or sub( a )**t * x = sub( b ),
 pdtzrzf.3
 Reduce the mbyn ( m=n ) real upper trapezoidal matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) to upper triangular form by means of orthogonal transformations
 pdzsum1.3
 Return the sum of absolute values of a complex distributed vector sub( x ) in asum,
 pscsum1.3
 Return the sum of absolute values of a complex distributed vector sub( x ) in asum,
 psdbsv.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 psdbtrf.3
 Compute a lu factorization of an nbyn real banded diagonally dominantlike distributed matrix with bandwidth bwl, bwu
 psdbtrs.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 psdbtrsv.3
 Solve a banded triangular system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 psdtsv.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 psdttrf.3
 Compute a lu factorization of an nbyn real tridiagonal diagonally dominantlike distributed matrix a(1:n, ja:ja+n1)
 psdttrs.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 psdttrsv.3
 Solve a tridiagonal triangular system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 psgbsv.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 psgbtrf.3
 Compute a lu factorization of an nbyn real banded distributed matrix with bandwidth bwl, bwu
 psgbtrs.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 psgebd2.3
 Reduce a real general mbyn distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) to upper or lower bidiagonal form b by an orthogonal transformation
 psgebrd.3
 Reduce a real general mbyn distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) to upper or lower bidiagonal form b by an orthogonal transformation
 psgecon.3
 Estimate the reciprocal of the condition number of a general distributed real matrix a(ia:ia+n1,ja:ja+n1), in either the 1norm or the infinitynorm, using the lu factorization computed by psgetrf
 psgeequ.3
 Compute row and column scalings intended to equilibrate an mbyn distributed matrix sub( a ) = a(ia:ia+n1,ja:ja:ja+n1) and reduce its condition number
 psgehd2.3
 Reduce a real general distributed matrix sub( a ) to upper hessenberg form h by an orthogonal similarity transforma tion
 psgehrd.3
 Reduce a real general distributed matrix sub( a ) to upper hessenberg form h by an orthogonal similarity transforma tion
 psgelq2.3
 Compute a lq factorization of a real distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = l * q
 psgelqf.3
 Compute a lq factorization of a real distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = l * q
 psgels.3
 Solve overdetermined or underdetermined real linear systems involving an mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1),
 psgeql2.3
 Compute a ql factorization of a real distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = q * l
 psgeqlf.3
 Compute a ql factorization of a real distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = q * l
 psgeqpf.3
 Compute a qr factorization with column pivoting of a mbyn distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1)
 psgeqr2.3
 Compute a qr factorization of a real distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = q * r
 psgeqrf.3
 Compute a qr factorization of a real distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = q * r
 psgerfs.3
 Improve the computed solution to a system of linear equations and provides error bounds and backward error estimates for the solutions
 psgerq2.3
 Compute a rq factorization of a real distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = r * q
 psgerqf.3
 Compute a rq factorization of a real distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = r * q
 psgesv.3
 Compute the solution to a real system of linear equations sub( a ) * x = sub( b ),
 psgesvd.3
 Compute the singular value decomposition (svd) of an mbyn matrix a, optionally computing the left and/or right singular vectors
 psgetf2.3
 Compute an lu factorization of a general mbyn distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) using partial pivoting with row interchanges
 psgetrf.3
 Compute an lu factorization of a general mbyn distributed matrix sub( a ) = (ia:ia+m1,ja:ja+n1) using partial pivoting with row interchanges
 psgetri.3
 Compute the inverse of a distributed matrix using the lu factorization computed by psgetrf
 psgetrs.3
 Solve a system of distributed linear equations op( sub( a ) ) * x = sub( b ) with a general nbyn distributed matrix sub( a ) using the lu factorization computed by psgetrf
 psggqrf.3
 Compute a generalized qr factorization of an nbym matrix sub( a ) = a(ia:ia+n1,ja:ja+m1) and an nbyp matrix sub( b ) = b(ib:ib+n1,jb:jb+p1)
 psggrqf.3
 Compute a generalized rq factorization of an mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1)
 pslabad.3
 Take as input the values computed by pslamch for underflow and overflow, and returns the square root of each of these values if the log of large is sufficiently large
 pslabrd.3
 Reduce the first nb rows and columns of a real general mbyn distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) to upper or lower bidiagonal form by an orthogonal transformation q' * a * p,
 pslacon.3
 Estimate the 1norm of a square, real distributed matrix a
 pslaconsb.3
 Look for two consecutive small subdiagonal elements by seeing the effect of starting a double shift qr iteration given by h44, h33, & h43h34 and see if this would make a subdiagonal negligible
 pslacp2.3
 Copie all or part of a distributed matrix a to another distributed matrix b
 pslacp3.3
 I an auxiliary routine that copies from a global parallel array into a local replicated array or vise versa
 pslacpy.3
 Copie all or part of a distributed matrix a to another distributed matrix b
 pslaevswp.3
 Move the eigenvectors (potentially unsorted) from where they are computed, to a scalapack standard block cyclic array, sorted so that the corresponding eigenvalues are sorted
 pslahqr.3
 I an auxiliary routine used to find the schur decomposition and or eigenvalues of a matrix already in hessenberg form from cols ilo to ihi
 pslahrd.3
 Reduce the first nb columns of a real general nby(nk+1) distributed matrix a(ia:ia+n1,ja:ja+nk) so that elements below the kth subdiagonal are zero
 pslamch.3
 Determine single precision machine parameters
 pslange.3
 Return the value of the one norm, or the frobenius norm,
 pslanhs.3
 Return the value of the one norm, or the frobenius norm,
 pslansy.3
 Return the value of the one norm, or the frobenius norm,
 pslantr.3
 Return the value of the one norm, or the frobenius norm,
 pslapiv.3
 Applie either p (permutation matrix indicated by ipiv) or inv( p ) to a general mbyn distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1), resulting in row or column pivoting
 pslapv2.3
 Applie either p (permutation matrix indicated by ipiv) or inv( p ) to a mbyn distributed matrix sub( a ) denoting a(ia:ia+m1,ja:ja+n1), resulting in row or column pivoting
 pslaqge.3
 Equilibrate a general mbyn distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) using the row and scaling factors in the vectors r and c
 pslaqsy.3
 Equilibrate a symmetric distributed matrix sub( a ) = a(ia:ia+n1,ja:ja+n1) using the scaling factors in the vectors sr and sc
 pslared1d.3
 Redistribute a 1d array it assumes that the input array, bycol, is distributed across rows and that all process column contain the same copy of bycol
 pslared2d.3
 Redistribute a 1d array it assumes that the input array, byrow, is distributed across columns and that all process rows contain the same copy of byrow
 pslarf.3
 Applie a real elementary reflector q (or q**t) to a real mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1), from either the left or the right
 pslarfb.3
 Applie a real block reflector q or its transpose q**t to a real distributed mbyn matrix sub( c ) = c(ic:ic+m1,jc:jc+n1)
 pslarfg.3
 Generate a real elementary reflector h of order n, such that h * sub( x ) = h * ( x(iax,jax) ) = ( alpha ), h' * h = i
 pslarft.3
 Form the triangular factor t of a real block reflector h of order n, which is defined as a product of k elementary reflectors
 pslarz.3
 Applie a real elementary reflector q (or q**t) to a real mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1), from either the left or the right
 pslarzb.3
 Applie a real block reflector q or its transpose q**t to a real distributed mbyn matrix sub( c ) = c(ic:ic+m1,jc:jc+n1)
 pslarzt.3
 Form the triangular factor t of a real block reflector h of order n, which is defined as a product of k elementary reflectors as returned by pstzrzf
 pslascl.3
 Multiplie the mbyn real distributed matrix sub( a ) denoting a(ia:ia+m1,ja:ja+n1) by the real scalar cto/cfrom
 pslase2.3
 Initialize an mbyn distributed matrix sub( a ) denoting a(ia:ia+m1,ja:ja+n1) to beta on the diagonal and alpha on the offdiagonals
 pslaset.3
 Initialize an mbyn distributed matrix sub( a ) denoting a(ia:ia+m1,ja:ja+n1) to beta on the diagonal and alpha on the offdiagonals
 pslasmsub.3
 Look for a small subdiagonal element from the bottom of the matrix that it can safely set to zero
 pslassq.3
 Return the values scl and smsq such that ( scl**2 )*smsq = x( 1 )**2 +...+ x( n )**2 + ( scale**2 )*sumsq,
 pslaswp.3
 Perform a series of row or column interchanges on the distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1)
 pslatra.3
 Compute the trace of an nbyn distributed matrix sub( a ) denoting a( ia:ia+n1, ja:ja+n1 )
 pslatrd.3
 Reduce nb rows and columns of a real symmetric distributed matrix sub( a ) = a(ia:ia+n1,ja:ja+n1) to symmetric tridiagonal form by an orthogonal similarity transformation q' * sub( a ) * q,
 pslatrs.3
 Solve a triangular system
 pslatrz.3
 Reduce the mbyn ( m=n ) real upper trapezoidal matrix sub( a ) = [ a(ia:ia+m1,ja:ja+m1) a(ia:ia+m1,ja+nl:ja+n1) ] to upper triangular form by means of orthogonal transformations
 pslauu2.3
 Compute the product u * u' or l' * l, where the triangular factor u or l is stored in the upper or lower triangular part of the matrix sub( a ) = a(ia:ia+n1,ja:ja+n1)
 pslauum.3
 Compute the product u * u' or l' * l, where the triangular factor u or l is stored in the upper or lower triangular part of the distributed matrix sub( a ) = a(ia:ia+n1,ja:ja+n1)
 pslawil.3
 Get the transform given by h44,h33, & h43h34 into v starting at row m
 psorg2l.3
 Generate an mbyn real distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal columns, which is defined as the last n columns of a product of k elementary reflectors of order m q = h(k)
 psorg2r.3
 Generate an mbyn real distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal columns, which is defined as the first n columns of a product of k elementary reflectors of order m q = h(1) h(2)
 psorgl2.3
 Generate an mbyn real distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal rows, which is defined as the first m rows of a product of k elementary reflectors of order n q = h(k)
 psorglq.3
 Generate an mbyn real distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal rows, which is defined as the first m rows of a product of k elementary reflectors of order n q = h(k)
 psorgql.3
 Generate an mbyn real distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal columns, which is defined as the last n columns of a product of k elementary reflectors of order m q = h(k)
 psorgqr.3
 Generate an mbyn real distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal columns, which is defined as the first n columns of a product of k elementary reflectors of order m q = h(1) h(2)
 psorgr2.3
 Generate an mbyn real distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal rows, which is defined as the last m rows of a product of k elementary reflectors of order n q = h(1) h(2)
 psorgrq.3
 Generate an mbyn real distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal rows, which is defined as the last m rows of a product of k elementary reflectors of order n q = h(1) h(2)
 psorm2l.3
 Overwrite the general real mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 psorm2r.3
 Overwrite the general real mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 psormbr.3
 Vect = 'q', psormbr overwrites the general real distributed mbyn matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 psormhr.3
 Overwrite the general real mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 psorml2.3
 Overwrite the general real mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 psormlq.3
 Overwrite the general real mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 psormql.3
 Overwrite the general real mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 psormqr.3
 Overwrite the general real mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 psormr2.3
 Overwrite the general real mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 psormr3.3
 Overwrite the general real mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 psormrq.3
 Overwrite the general real mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 psormrz.3
 Overwrite the general real mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 psormtr.3
 Overwrite the general real mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pspbsv.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pspbtrf.3
 Compute a cholesky factorization of an nbyn real banded symmetric positive definite distributed matrix with bandwidth bw
 pspbtrs.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pspbtrsv.3
 Solve a banded triangular system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pspocon.3
 Estimate the reciprocal of the condition number (in the 1norm) of a real symmetric positive definite distributed matrix using the cholesky factorization a = u**t*u or a = l*l**t computed by pspotrf
 pspoequ.3
 Compute row and column scalings intended to equilibrate a distributed symmetric positive definite matrix sub( a ) = a(ia:ia+n1,ja:ja+n1) and reduce its condition number (with respect to the twonorm)
 psporfs.3
 Improve the computed solution to a system of linear equations when the coefficient matrix is symmetric positive definite and provides error bounds and backward error estimates for the solutions
 psposv.3
 Compute the solution to a real system of linear equations sub( a ) * x = sub( b ),
 pspotf2.3
 Compute the cholesky factorization of a real symmetric positive definite distributed matrix sub( a )=a(ia:ia+n1,ja:ja+n1)
 pspotrf.3
 Compute the cholesky factorization of an nbyn real symmetric positive definite distributed matrix sub( a ) denoting a(ia:ia+n1, ja:ja+n1)
 pspotri.3
 Compute the inverse of a real symmetric positive definite distributed matrix sub( a ) = a(ia:ia+n1,ja:ja+n1) using the cholesky factorization sub( a ) = u**t*u or l*l**t computed by pspotrf
 pspotrs.3
 Solve a system of linear equations sub( a ) * x = sub( b ) a(ia:ia+n1,ja:ja+n1)*x = b(ib:ib+n1,jb:jb+nrhs1)
 psptsv.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pspttrf.3
 Compute a cholesky factorization of an nbyn real tridiagonal symmetric positive definite distributed matrix a(1:n, ja:ja+n1)
 pspttrs.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pspttrsv.3
 Solve a tridiagonal triangular system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 psrscl.3
 Multiplie an nelement real distributed vector sub( x ) by the real scalar 1/a
 psstebz.3
 Compute the eigenvalues of a symmetric tridiagonal matrix in parallel
 psstein.3
 Compute the eigenvectors of a symmetric tridiagonal matrix in parallel, using inverse iteration
 pssygs2.3
 Reduce a real symmetricdefinite generalized eigenproblem to standard form
 pssygst.3
 Reduce a real symmetricdefinite generalized eigenproblem to standard form
 pssytd2.3
 Reduce a real symmetric matrix sub( a ) to symmetric tridiagonal form t by an orthogonal similarity transformation
 pssytrd.3
 Reduce a real symmetric matrix sub( a ) to symmetric tridiagonal form t by an orthogonal similarity transformation
 pstrcon.3
 Estimate the reciprocal of the condition number of a triangular distributed matrix a(ia:ia+n1,ja:ja+n1), in either the 1norm or the infinitynorm
 pstrrfs.3
 Provide error bounds and backward error estimates for the solution to a system of linear equations with a triangular coefficient matrix
 pstrti2.3
 Compute the inverse of a real upper or lower triangular block matrix sub( a ) = a(ia:ia+n1,ja:ja+n1)
 pstrtri.3
 Compute the inverse of a upper or lower triangular distributed matrix sub( a ) = a(ia:ia+n1,ja:ja+n1)
 pstrtrs.3
 Solve a triangular system of the form sub( a ) * x = sub( b ) or sub( a )**t * x = sub( b ),
 pstzrzf.3
 Reduce the mbyn ( m=n ) real upper trapezoidal matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) to upper triangular form by means of orthogonal transformations
 pzdbsv.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pzdbtrf.3
 Compute a lu factorization of an nbyn complex banded diagonally dominantlike distributed matrix with bandwidth bwl, bwu
 pzdbtrs.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pzdbtrsv.3
 Solve a banded triangular system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pzdrscl.3
 Multiplie an nelement complex distributed vector sub( x ) by the real scalar 1/a
 pzdtsv.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pzdttrf.3
 Compute a lu factorization of an nbyn complex tridiagonal diagonally dominantlike distributed matrix a(1:n, ja:ja+n1)
 pzdttrs.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pzdttrsv.3
 Solve a tridiagonal triangular system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pzgbsv.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pzgbtrf.3
 Compute a lu factorization of an nbyn complex banded distributed matrix with bandwidth bwl, bwu
 pzgbtrs.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pzgebd2.3
 Reduce a complex general mbyn distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) to upper or lower bidiagonal form b by an unitary transformation
 pzgebrd.3
 Reduce a complex general mbyn distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) to upper or lower bidiagonal form b by an unitary transformation
 pzgecon.3
 Estimate the reciprocal of the condition number of a general distributed complex matrix a(ia:ia+n1,ja:ja+n1), in either the 1norm or the infinitynorm, using the lu factorization computed by pzgetrf
 pzgeequ.3
 Compute row and column scalings intended to equilibrate an mbyn distributed matrix sub( a ) = a(ia:ia+n1,ja:ja:ja+n1) and reduce its condition number
 pzgehd2.3
 Reduce a complex general distributed matrix sub( a ) to upper hessenberg form h by an unitary similarity transformation
 pzgehrd.3
 Reduce a complex general distributed matrix sub( a ) to upper hessenberg form h by an unitary similarity transformation
 pzgelq2.3
 Compute a lq factorization of a complex distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = l * q
 pzgelqf.3
 Compute a lq factorization of a complex distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = l * q
 pzgels.3
 Solve overdetermined or underdetermined complex linear systems involving an mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1),
 pzgeql2.3
 Compute a ql factorization of a complex distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = q * l
 pzgeqlf.3
 Compute a ql factorization of a complex distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = q * l
 pzgeqpf.3
 Compute a qr factorization with column pivoting of a mbyn distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1)
 pzgeqr2.3
 Compute a qr factorization of a complex distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = q * r
 pzgeqrf.3
 Compute a qr factorization of a complex distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = q * r
 pzgerfs.3
 Improve the computed solution to a system of linear equations and provides error bounds and backward error estimates for the solutions
 pzgerq2.3
 Compute a rq factorization of a complex distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = r * q
 pzgerqf.3
 Compute a rq factorization of a complex distributed mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) = r * q
 pzgesv.3
 Compute the solution to a complex system of linear equations sub( a ) * x = sub( b ),
 pzgetf2.3
 Compute an lu factorization of a general mbyn distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) using partial pivoting with row interchanges
 pzgetrf.3
 Compute an lu factorization of a general mbyn distributed matrix sub( a ) = (ia:ia+m1,ja:ja+n1) using partial pivoting with row interchanges
 pzgetri.3
 Compute the inverse of a distributed matrix using the lu factorization computed by pzgetrf
 pzgetrs.3
 Solve a system of distributed linear equations op( sub( a ) ) * x = sub( b ) with a general nbyn distributed matrix sub( a ) using the lu factorization computed by pzgetrf
 pzggqrf.3
 Compute a generalized qr factorization of an nbym matrix sub( a ) = a(ia:ia+n1,ja:ja+m1) and an nbyp matrix sub( b ) = b(ib:ib+n1,jb:jb+p1)
 pzggrqf.3
 Compute a generalized rq factorization of an mbyn matrix sub( a ) = a(ia:ia+m1,ja:ja+n1)
 pzhegs2.3
 Reduce a complex hermitiandefinite generalized eigenproblem to standard form
 pzhegst.3
 Reduce a complex hermitiandefinite generalized eigenproblem to standard form
 pzhetd2.3
 Reduce a complex hermitian matrix sub( a ) to hermitian tridiagonal form t by an unitary similarity transformation
 pzhetrd.3
 Reduce a complex hermitian matrix sub( a ) to hermitian tridiagonal form t by an unitary similarity transformation
 pzlabrd.3
 Reduce the first nb rows and columns of a complex general mbyn distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) to upper or lower bidiagonal form by an unitary transformation q' * a * p, and returns the matrices x and y which are needed to apply the transfor mation to the unreduced part of sub( a )
 pzlacgv.3
 Conjugate a complex vector of length n, sub( x ), where sub( x ) denotes x(ix,jx:jx+n1) if incx = descx( m_ ) and x(ix:ix+n1,jx) if incx = 1, and notes ===== each global data object is described by an associated description vector
 pzlacon.3
 Estimate the 1norm of a square, complex distributed matrix a
 pzlacp2.3
 Copie all or part of a distributed matrix a to another distributed matrix b
 pzlacpy.3
 Copie all or part of a distributed matrix a to another distributed matrix b
 pzlaevswp.3
 Move the eigenvectors (potentially unsorted) from where they are computed, to a scalapack standard block cyclic array, sorted so that the corresponding eigenvalues are sorted
 pzlahrd.3
 Reduce the first nb columns of a complex general nby(nk+1) distributed matrix a(ia:ia+n1,ja:ja+nk) so that elements below the kth subdiagonal are zero
 pzlange.3
 Return the value of the one norm, or the frobenius norm,
 pzlanhe.3
 Return the value of the one norm, or the frobenius norm,
 pzlanhs.3
 Return the value of the one norm, or the frobenius norm,
 pzlansy.3
 Return the value of the one norm, or the frobenius norm,
 pzlantr.3
 Return the value of the one norm, or the frobenius norm,
 pzlapiv.3
 Applie either p (permutation matrix indicated by ipiv) or inv( p ) to a general mbyn distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1), resulting in row or column pivoting
 pzlapv2.3
 Applie either p (permutation matrix indicated by ipiv) or inv( p ) to a mbyn distributed matrix sub( a ) denoting a(ia:ia+m1,ja:ja+n1), resulting in row or column pivoting
 pzlaqge.3
 Equilibrate a general mbyn distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) using the row and scaling factors in the vectors r and c
 pzlaqsy.3
 Equilibrate a symmetric distributed matrix sub( a ) = a(ia:ia+n1,ja:ja+n1) using the scaling factors in the vectors sr and sc
 pzlarf.3
 Applie a complex elementary reflector q to a complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1), from either the left or the right
 pzlarfb.3
 Applie a complex block reflector q or its conjugate transpose q**h to a complex mbyn distributed matrix sub( c ) denoting c(ic:ic+m1,jc:jc+n1), from the left or the right
 pzlarfc.3
 Applie a complex elementary reflector q**h to a complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1),
 pzlarfg.3
 Generate a complex elementary reflector h of order n, such that h * sub( x ) = h * ( x(iax,jax) ) = ( alpha ), h' * h = i
 pzlarft.3
 Form the triangular factor t of a complex block reflector h of order n, which is defined as a product of k elementary reflectors
 pzlarz.3
 Applie a complex elementary reflector q to a complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1), from either the left or the right
 pzlarzb.3
 Applie a complex block reflector q or its conjugate transpose q**h to a complex mbyn distributed matrix sub( c ) denoting c(ic:ic+m1,jc:jc+n1), from the left or the right
 pzlarzc.3
 Applie a complex elementary reflector q**h to a complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1),
 pzlarzt.3
 Form the triangular factor t of a complex block reflector h of order n, which is defined as a product of k elementary reflectors as returned by pztzrzf
 pzlascl.3
 Multiplie the mbyn complex distributed matrix sub( a ) denoting a(ia:ia+m1,ja:ja+n1) by the real scalar cto/cfrom
 pzlase2.3
 Initialize an mbyn distributed matrix sub( a ) denoting a(ia:ia+m1,ja:ja+n1) to beta on the diagonal and alpha on the offdiagonals
 pzlaset.3
 Initialize an mbyn distributed matrix sub( a ) denoting a(ia:ia+m1,ja:ja+n1) to beta on the diagonal and alpha on the offdiagonals
 pzlassq.3
 Return the values scl and smsq such that ( scl**2 )*smsq = x( 1 )**2 +...+ x( n )**2 + ( scale**2 )*sumsq,
 pzlaswp.3
 Perform a series of row or column interchanges on the distributed matrix sub( a ) = a(ia:ia+m1,ja:ja+n1)
 pzlatra.3
 Compute the trace of an nbyn distributed matrix sub( a ) denoting a( ia:ia+n1, ja:ja+n1 )
 pzlatrd.3
 Reduce nb rows and columns of a complex hermitian distributed matrix sub( a ) = a(ia:ia+n1,ja:ja+n1) to complex tridiagonal form by an unitary similarity transformation q' * sub( a ) * q, and returns the matrices v and w which are needed to apply the transformation to the unreduced part of sub( a )
 pzlatrs.3
 Solve a triangular system
 pzlatrz.3
 Reduce the mbyn ( m=n ) complex upper trapezoidal matrix sub( a ) = [a(ia:ia+m1,ja:ja+m1) a(ia:ia+m1,ja+nl:ja+n1)]
 pzlauu2.3
 Compute the product u * u' or l' * l, where the triangular factor u or l is stored in the upper or lower triangular part of the matrix sub( a ) = a(ia:ia+n1,ja:ja+n1)
 pzlauum.3
 Compute the product u * u' or l' * l, where the triangular factor u or l is stored in the upper or lower triangular part of the distributed matrix sub( a ) = a(ia:ia+n1,ja:ja+n1)
 pzpbsv.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pzpbtrf.3
 Compute a cholesky factorization of an nbyn complex banded symmetric positive definite distributed matrix with bandwidth bw
 pzpbtrs.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pzpbtrsv.3
 Solve a banded triangular system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pzpocon.3
 Estimate the reciprocal of the condition number (in the 1norm) of a complex hermitian positive definite distributed matrix using the cholesky factorization a = u**h*u or a = l*l**h computed by pzpotrf
 pzpoequ.3
 Compute row and column scalings intended to equilibrate a distributed hermitian positive definite matrix sub( a ) = a(ia:ia+n1,ja:ja+n1) and reduce its condition number (with respect to the twonorm)
 pzporfs.3
 Improve the computed solution to a system of linear equations when the coefficient matrix is hermitian positive definite and provides error bounds and backward error estimates for the solutions
 pzposv.3
 Compute the solution to a complex system of linear equations sub( a ) * x = sub( b ),
 pzpotf2.3
 Compute the cholesky factorization of a complex hermitian positive definite distributed matrix sub( a )=a(ia:ia+n1,ja:ja+n1)
 pzpotrf.3
 Compute the cholesky factorization of an nbyn complex hermitian positive definite distributed matrix sub( a ) denoting a(ia:ia+n1, ja:ja+n1)
 pzpotri.3
 Compute the inverse of a complex hermitian positive definite distributed matrix sub( a ) = a(ia:ia+n1,ja:ja+n1) using the cholesky factorization sub( a ) = u**h*u or l*l**h computed by pzpotrf
 pzpotrs.3
 Solve a system of linear equations sub( a ) * x = sub( b ) a(ia:ia+n1,ja:ja+n1)*x = b(ib:ib+n1,jb:jb+nrhs1)
 pzptsv.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pzpttrf.3
 Compute a cholesky factorization of an nbyn complex tridiagonal symmetric positive definite distributed matrix a(1:n, ja:ja+n1)
 pzpttrs.3
 Solve a system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pzpttrsv.3
 Solve a tridiagonal triangular system of linear equations a(1:n, ja:ja+n1) * x = b(ib:ib+n1, 1:nrhs)
 pzstein.3
 Compute the eigenvectors of a symmetric tridiagonal matrix in parallel, using inverse iteration
 pztrcon.3
 Estimate the reciprocal of the condition number of a triangular distributed matrix a(ia:ia+n1,ja:ja+n1), in either the 1norm or the infinitynorm
 pztrrfs.3
 Provide error bounds and backward error estimates for the solution to a system of linear equations with a triangular coefficient matrix
 pztrti2.3
 Compute the inverse of a complex upper or lower triangular block matrix sub( a ) = a(ia:ia+n1,ja:ja+n1)
 pztrtri.3
 Compute the inverse of a upper or lower triangular distributed matrix sub( a ) = a(ia:ia+n1,ja:ja+n1)
 pztrtrs.3
 Solve a triangular system of the form sub( a ) * x = sub( b ) or sub( a )**t * x = sub( b ) or sub( a )**h * x = sub( b ),
 pztzrzf.3
 Reduce the mbyn ( m=n ) complex upper trapezoidal matrix sub( a ) = a(ia:ia+m1,ja:ja+n1) to upper triangular form by means of unitary transformations
 pzung2l.3
 Generate an mbyn complex distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal columns, which is defined as the last n columns of a product of k elementary reflectors of order m q = h(k)
 pzung2r.3
 Generate an mbyn complex distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal columns, which is defined as the first n columns of a product of k elementary reflectors of order m q = h(1) h(2)
 pzungl2.3
 Generate an mbyn complex distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal rows, which is defined as the first m rows of a product of k elementary reflectors of order n q = h(k)'
 pzunglq.3
 Generate an mbyn complex distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal rows, which is defined as the first m rows of a product of k elementary reflectors of order n q = h(k)'
 pzungql.3
 Generate an mbyn complex distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal columns, which is defined as the last n columns of a product of k elementary reflectors of order m q = h(k)
 pzungqr.3
 Generate an mbyn complex distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal columns, which is defined as the first n columns of a product of k elementary reflectors of order m q = h(1) h(2)
 pzungr2.3
 Generate an mbyn complex distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal rows, which is defined as the last m rows of a product of k elementary reflectors of order n q = h(1)' h(2)'
 pzungrq.3
 Generate an mbyn complex distributed matrix q denoting a(ia:ia+m1,ja:ja+n1) with orthonormal rows, which is defined as the last m rows of a product of k elementary reflectors of order n q = h(1)' h(2)'
 pzunm2l.3
 Overwrite the general complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pzunm2r.3
 Overwrite the general complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pzunmbr.3
 Vect = 'q', pzunmbr overwrites the general complex distributed mbyn matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pzunmhr.3
 Overwrite the general complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pzunml2.3
 Overwrite the general complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pzunmlq.3
 Overwrite the general complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pzunmql.3
 Overwrite the general complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pzunmqr.3
 Overwrite the general complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pzunmr2.3
 Overwrite the general complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pzunmr3.3
 Overwrite the general complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pzunmrq.3
 Overwrite the general complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pzunmrz.3
 Overwrite the general complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 pzunmtr.3
 Overwrite the general complex mbyn distributed matrix sub( c ) = c(ic:ic+m1,jc:jc+n1) with side = 'l' side = 'r' trans = 'n'
 sdttrf.3
 Compute an lu factorization of a complex tridiagonal matrix a using elimination without partial pivoting
 sdttrsv.3
 Solve one of the systems of equations l * x = b, l**t * x = b, or l**h * x = b,
 slamsh.3
 Send multiple shifts through a small (single node) matrix to see how consecutive small subdiagonal elements are modified by subsequent shifts in an effort to maximize the number of bulges that can be sent through
 slaref.3
 Applie one or several householder reflectors of size 3 to one or two matrices (if column is specified) on either their rows or columns
 slasorte.3
 Sort eigenpairs so that real eigenpairs are together and complex are together
 slasrt2.3
 The numbers in d in increasing order (if id = 'i') or in decreasing order (if id = 'd' )
 spttrsv.3
 Solve one of the triangular systems l**t* x = b, or l * x = b,
 sstein2.3
 Compute the eigenvectors of a real symmetric tridiagonal matrix t corresponding to specified eigenvalues, using inverse iteration
 ssteqr2.3
 I a modified version of lapack routine ssteqr
 zdttrf.3
 Compute an lu factorization of a complex tridiagonal matrix a using elimination without partial pivoting
 zdttrsv.3
 Solve one of the systems of equations l * x = b, l**t * x = b, or l**h * x = b,
 zpttrsv.3
 Solve one of the triangular systems l * x = b, or l**h * x = b,