sb2st_kernels#

Functions

void ssb2st_kernels(
    const char* uplo,
    const INT   wantz,
    const INT   ttype,
    const INT   st,
    const INT   ed,
    const INT   sweep,
    const INT   n,
    const INT   nb,
    const INT   ib,
          f32*  A,
    const INT   lda,
          f32*  V,
          f32*  tau,
    const INT   ldvt,
          f32*  work
);
void ssb2st_kernels(const char *uplo, const INT wantz, const INT ttype, const INT st, const INT ed, const INT sweep, const INT n, const INT nb, const INT ib, f32 *A, const INT lda, f32 *V, f32 *tau, const INT ldvt, f32 *work)#

SSB2ST_KERNELS is an internal routine used by the SSYTRD_SB2ST subroutine.

Further Details:

Implemented by Azzam Haidar.

All details are available on technical report, SC11, SC13 papers.

Azzam Haidar, Hatem Ltaief, and Jack Dongarra. Parallel reduction to condensed forms for symmetric eigenvalue problems using aggregated fine-grained and memory-aware kernels. In Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis (SC ‘11), New York, NY, USA, Article 8 , 11 pages. https://doi.org/10.1145/2063384.2063394

A. Haidar, J. Kurzak, P. Luszczek, 2013. An improved parallel singular value algorithm and its implementation for multicore hardware, In Proceedings of 2013 International Conference for High Performance Computing, Networking, Storage and Analysis (SC ‘13). Denver, Colorado, USA, 2013. Article 90, 12 pages. https://doi.org/10.1145/2503210.2503292

A. Haidar, R. Solca, S. Tomov, T. Schulthess and J. Dongarra. A novel hybrid CPU-GPU generalized eigensolver for electronic structure calculations based on fine-grained memory aware tasks. International Journal of High Performance Computing Applications. Volume 28 Issue 2, Pages 196-209, May 2014. https://doi.org/10.1177/1094342013502097

Parameters

in
uplo

Specifies whether the upper or lower triangle is stored.

in
wantz

Indicates if eigenvalues only are requested, or both eigenvalues and eigenvectors.

in
ttype

Internal parameter.

in
st

Internal parameter for indices.

in
ed

Internal parameter for indices.

in
sweep

Internal parameter for indices.

in
n

The order of the matrix A.

in
nb

The size of the band.

in
ib

Internal parameter.

inout
A

A pointer to the matrix A.

in
lda

The leading dimension of the matrix A.

out
V

Array of dimension 2*n if eigenvalues only are requested or to be queried for vectors.

out
tau

Array of dimension (2*n). The scalar factors of the Householder reflectors are stored in this array.

in
ldvt

Internal parameter.

out
work

Workspace of size nb.

Functions

void dsb2st_kernels(
    const char* uplo,
    const INT   wantz,
    const INT   ttype,
    const INT   st,
    const INT   ed,
    const INT   sweep,
    const INT   n,
    const INT   nb,
    const INT   ib,
          f64*  A,
    const INT   lda,
          f64*  V,
          f64*  tau,
    const INT   ldvt,
          f64*  work
);
void dsb2st_kernels(const char *uplo, const INT wantz, const INT ttype, const INT st, const INT ed, const INT sweep, const INT n, const INT nb, const INT ib, f64 *A, const INT lda, f64 *V, f64 *tau, const INT ldvt, f64 *work)#

DSB2ST_KERNELS is an internal routine used by the DSYTRD_SB2ST subroutine.

Further Details:

Implemented by Azzam Haidar.

All details are available on technical report, SC11, SC13 papers.

Azzam Haidar, Hatem Ltaief, and Jack Dongarra. Parallel reduction to condensed forms for symmetric eigenvalue problems using aggregated fine-grained and memory-aware kernels. In Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis (SC ‘11), New York, NY, USA, Article 8 , 11 pages. https://doi.org/10.1145/2063384.2063394

A. Haidar, J. Kurzak, P. Luszczek, 2013. An improved parallel singular value algorithm and its implementation for multicore hardware, In Proceedings of 2013 International Conference for High Performance Computing, Networking, Storage and Analysis (SC ‘13). Denver, Colorado, USA, 2013. Article 90, 12 pages. https://doi.org/10.1145/2503210.2503292

A. Haidar, R. Solca, S. Tomov, T. Schulthess and J. Dongarra. A novel hybrid CPU-GPU generalized eigensolver for electronic structure calculations based on fine-grained memory aware tasks. International Journal of High Performance Computing Applications. Volume 28 Issue 2, Pages 196-209, May 2014. https://doi.org/10.1177/1094342013502097

Parameters

in
uplo

Specifies whether the upper or lower triangle is stored.

in
wantz

Indicates if eigenvalues only are requested, or both eigenvalues and eigenvectors.

in
ttype

Internal parameter.

in
st

Internal parameter for indices.

in
ed

Internal parameter for indices.

in
sweep

Internal parameter for indices.

in
n

The order of the matrix A.

in
nb

The size of the band.

in
ib

Internal parameter.

inout
A

A pointer to the matrix A.

in
lda

The leading dimension of the matrix A.

out
V

Array of dimension 2*n if eigenvalues only are requested or to be queried for vectors.

out
tau

Array of dimension (2*n). The scalar factors of the Householder reflectors are stored in this array.

in
ldvt

Internal parameter.

out
work

Workspace of size nb.