---
_id: '16277'
abstract:
- lang: eng
text: CP2K is an open source electronic structure and molecular dynamics software
package to perform atomistic simulations of solid-state, liquid, molecular, and
biological systems. It is especially aimed at massively parallel and linear-scaling
electronic structure methods and state-of-theart ab initio molecular dynamics
simulations. Excellent performance for electronic structure calculations is achieved
using novel algorithms implemented for modern high-performance computing systems.
This review revisits the main capabilities of CP2K to perform efficient and accurate
electronic structure simulations. The emphasis is put on density functional theory
and multiple post–Hartree–Fock methods using the Gaussian and plane wave approach
and its augmented all-electron extension.
article_number: '194103'
author:
- first_name: Thomas
full_name: Kühne, Thomas
id: '49079'
last_name: Kühne
- first_name: Marcella
full_name: Iannuzzi, Marcella
last_name: Iannuzzi
- first_name: Mauro Del
full_name: Ben, Mauro Del
last_name: Ben
- first_name: Vladimir V.
full_name: Rybkin, Vladimir V.
last_name: Rybkin
- first_name: Patrick
full_name: Seewald, Patrick
last_name: Seewald
- first_name: Frederick
full_name: Stein, Frederick
last_name: Stein
- first_name: Teodoro
full_name: Laino, Teodoro
last_name: Laino
- first_name: Rustam Z.
full_name: Khaliullin, Rustam Z.
last_name: Khaliullin
- first_name: Ole
full_name: Schütt, Ole
last_name: Schütt
- first_name: Florian
full_name: Schiffmann, Florian
last_name: Schiffmann
- first_name: Dorothea
full_name: Golze, Dorothea
last_name: Golze
- first_name: Jan
full_name: Wilhelm, Jan
last_name: Wilhelm
- first_name: Sergey
full_name: Chulkov, Sergey
last_name: Chulkov
- first_name: Mohammad Hossein Bani-Hashemian
full_name: Mohammad Hossein Bani-Hashemian, Mohammad Hossein Bani-Hashemian
last_name: Mohammad Hossein Bani-Hashemian
- first_name: Valéry
full_name: Weber, Valéry
last_name: Weber
- first_name: Urban
full_name: Borstnik, Urban
last_name: Borstnik
- first_name: Mathieu
full_name: Taillefumier, Mathieu
last_name: Taillefumier
- first_name: Alice Shoshana
full_name: Jakobovits, Alice Shoshana
last_name: Jakobovits
- first_name: Alfio
full_name: Lazzaro, Alfio
last_name: Lazzaro
- first_name: Hans
full_name: Pabst, Hans
last_name: Pabst
- first_name: Tiziano
full_name: Müller, Tiziano
last_name: Müller
- first_name: Robert
full_name: Schade, Robert
id: '75963'
last_name: Schade
orcid: 0000-0002-6268-539
- first_name: Manuel
full_name: Guidon, Manuel
last_name: Guidon
- first_name: Samuel
full_name: Andermatt, Samuel
last_name: Andermatt
- first_name: Nico
full_name: Holmberg, Nico
last_name: Holmberg
- first_name: Gregory K.
full_name: Schenter, Gregory K.
last_name: Schenter
- first_name: Anna
full_name: Hehn, Anna
last_name: Hehn
- first_name: Augustin
full_name: Bussy, Augustin
last_name: Bussy
- first_name: Fabian
full_name: Belleflamme, Fabian
last_name: Belleflamme
- first_name: Gloria
full_name: Tabacchi, Gloria
last_name: Tabacchi
- first_name: Andreas
full_name: Glöß, Andreas
last_name: Glöß
- first_name: Michael
full_name: Lass, Michael
id: '24135'
last_name: Lass
orcid: 0000-0002-5708-7632
- first_name: Iain
full_name: Bethune, Iain
last_name: Bethune
- first_name: Christopher J.
full_name: Mundy, Christopher J.
last_name: Mundy
- first_name: Christian
full_name: Plessl, Christian
id: '16153'
last_name: Plessl
orcid: 0000-0001-5728-9982
- first_name: Matt
full_name: Watkins, Matt
last_name: Watkins
- first_name: Joost
full_name: VandeVondele, Joost
last_name: VandeVondele
- first_name: Matthias
full_name: Krack, Matthias
last_name: Krack
- first_name: Jürg
full_name: Hutter, Jürg
last_name: Hutter
citation:
ama: 'Kühne T, Iannuzzi M, Ben MD, et al. CP2K: An electronic structure and molecular
dynamics software package - Quickstep: Efficient and accurate electronic structure
calculations. The Journal of Chemical Physics. 2020;152(19). doi:10.1063/5.0007045'
apa: 'Kühne, T., Iannuzzi, M., Ben, M. D., Rybkin, V. V., Seewald, P., Stein, F.,
Laino, T., Khaliullin, R. Z., Schütt, O., Schiffmann, F., Golze, D., Wilhelm,
J., Chulkov, S., Mohammad Hossein Bani-Hashemian, M. H. B.-H., Weber, V., Borstnik,
U., Taillefumier, M., Jakobovits, A. S., Lazzaro, A., … Hutter, J. (2020). CP2K:
An electronic structure and molecular dynamics software package - Quickstep: Efficient
and accurate electronic structure calculations. The Journal of Chemical Physics,
152(19), Article 194103. https://doi.org/10.1063/5.0007045'
bibtex: '@article{Kühne_Iannuzzi_Ben_Rybkin_Seewald_Stein_Laino_Khaliullin_Schütt_Schiffmann_et
al._2020, title={CP2K: An electronic structure and molecular dynamics software
package - Quickstep: Efficient and accurate electronic structure calculations},
volume={152}, DOI={10.1063/5.0007045},
number={19194103}, journal={The Journal of Chemical Physics}, author={Kühne, Thomas
and Iannuzzi, Marcella and Ben, Mauro Del and Rybkin, Vladimir V. and Seewald,
Patrick and Stein, Frederick and Laino, Teodoro and Khaliullin, Rustam Z. and
Schütt, Ole and Schiffmann, Florian and et al.}, year={2020} }'
chicago: 'Kühne, Thomas, Marcella Iannuzzi, Mauro Del Ben, Vladimir V. Rybkin, Patrick
Seewald, Frederick Stein, Teodoro Laino, et al. “CP2K: An Electronic Structure
and Molecular Dynamics Software Package - Quickstep: Efficient and Accurate Electronic
Structure Calculations.” The Journal of Chemical Physics 152, no. 19 (2020).
https://doi.org/10.1063/5.0007045.'
ieee: 'T. Kühne et al., “CP2K: An electronic structure and molecular dynamics
software package - Quickstep: Efficient and accurate electronic structure calculations,”
The Journal of Chemical Physics, vol. 152, no. 19, Art. no. 194103, 2020,
doi: 10.1063/5.0007045.'
mla: 'Kühne, Thomas, et al. “CP2K: An Electronic Structure and Molecular Dynamics
Software Package - Quickstep: Efficient and Accurate Electronic Structure Calculations.”
The Journal of Chemical Physics, vol. 152, no. 19, 194103, 2020, doi:10.1063/5.0007045.'
short: T. Kühne, M. Iannuzzi, M.D. Ben, V.V. Rybkin, P. Seewald, F. Stein, T. Laino,
R.Z. Khaliullin, O. Schütt, F. Schiffmann, D. Golze, J. Wilhelm, S. Chulkov, M.H.B.-H.
Mohammad Hossein Bani-Hashemian, V. Weber, U. Borstnik, M. Taillefumier, A.S.
Jakobovits, A. Lazzaro, H. Pabst, T. Müller, R. Schade, M. Guidon, S. Andermatt,
N. Holmberg, G.K. Schenter, A. Hehn, A. Bussy, F. Belleflamme, G. Tabacchi, A.
Glöß, M. Lass, I. Bethune, C.J. Mundy, C. Plessl, M. Watkins, J. VandeVondele,
M. Krack, J. Hutter, The Journal of Chemical Physics 152 (2020).
date_created: 2020-03-10T15:12:31Z
date_updated: 2023-08-02T14:56:21Z
ddc:
- '540'
department:
- _id: '27'
- _id: '518'
- _id: '304'
doi: 10.1063/5.0007045
external_id:
arxiv:
- '2003.03868'
file:
- access_level: closed
content_type: application/pdf
creator: lass
date_created: 2020-05-25T15:21:56Z
date_updated: 2020-05-25T15:21:56Z
file_id: '17061'
file_name: 5.0007045.pdf
file_size: 4887650
relation: main_file
success: 1
file_date_updated: 2020-05-25T15:21:56Z
has_accepted_license: '1'
intvolume: ' 152'
issue: '19'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://aip.scitation.org/doi/pdf/10.1063/5.0007045?download=true
oa: '1'
project:
- _id: '52'
name: Computing Resources Provided by the Paderborn Center for Parallel Computing
- _id: '32'
grant_number: PL 595/2-1 / 320898746
name: Performance and Efficiency in HPC with Custom Computing
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
publication: The Journal of Chemical Physics
publication_status: published
quality_controlled: '1'
status: public
title: 'CP2K: An electronic structure and molecular dynamics software package - Quickstep:
Efficient and accurate electronic structure calculations'
type: journal_article
user_id: '75963'
volume: 152
year: '2020'
...
---
_id: '16898'
abstract:
- lang: eng
text: "Electronic structure calculations based on density-functional theory (DFT)\r\nrepresent
a significant part of today's HPC workloads and pose high demands on\r\nhigh-performance
computing resources. To perform these quantum-mechanical DFT\r\ncalculations on
complex large-scale systems, so-called linear scaling methods\r\ninstead of conventional
cubic scaling methods are required. In this work, we\r\ntake up the idea of the
submatrix method and apply it to the DFT computations\r\nin the software package
CP2K. For that purpose, we transform the underlying\r\nnumeric operations on distributed,
large, sparse matrices into computations on\r\nlocal, much smaller and nearly
dense matrices. This allows us to exploit the\r\nfull floating-point performance
of modern CPUs and to make use of dedicated\r\naccelerator hardware, where performance
has been limited by memory bandwidth\r\nbefore. We demonstrate both functionality
and performance of our implementation\r\nand show how it can be accelerated with
GPUs and FPGAs."
author:
- first_name: Michael
full_name: Lass, Michael
id: '24135'
last_name: Lass
orcid: 0000-0002-5708-7632
- first_name: Robert
full_name: Schade, Robert
id: '75963'
last_name: Schade
orcid: 0000-0002-6268-539
- first_name: Thomas
full_name: Kühne, Thomas
id: '49079'
last_name: Kühne
- first_name: Christian
full_name: Plessl, Christian
id: '16153'
last_name: Plessl
orcid: 0000-0001-5728-9982
citation:
ama: 'Lass M, Schade R, Kühne T, Plessl C. A Submatrix-Based Method for Approximate
Matrix Function Evaluation in the Quantum Chemistry Code CP2K. In: Proc. International
Conference for High Performance Computing, Networking, Storage and Analysis (SC).
IEEE Computer Society; 2020:1127-1140. doi:10.1109/SC41405.2020.00084'
apa: Lass, M., Schade, R., Kühne, T., & Plessl, C. (2020). A Submatrix-Based
Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code
CP2K. Proc. International Conference for High Performance Computing, Networking,
Storage and Analysis (SC), 1127–1140. https://doi.org/10.1109/SC41405.2020.00084
bibtex: '@inproceedings{Lass_Schade_Kühne_Plessl_2020, place={Los Alamitos, CA,
USA}, title={A Submatrix-Based Method for Approximate Matrix Function Evaluation
in the Quantum Chemistry Code CP2K}, DOI={10.1109/SC41405.2020.00084},
booktitle={Proc. International Conference for High Performance Computing, Networking,
Storage and Analysis (SC)}, publisher={IEEE Computer Society}, author={Lass, Michael
and Schade, Robert and Kühne, Thomas and Plessl, Christian}, year={2020}, pages={1127–1140}
}'
chicago: 'Lass, Michael, Robert Schade, Thomas Kühne, and Christian Plessl. “A Submatrix-Based
Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code
CP2K.” In Proc. International Conference for High Performance Computing, Networking,
Storage and Analysis (SC), 1127–40. Los Alamitos, CA, USA: IEEE Computer Society,
2020. https://doi.org/10.1109/SC41405.2020.00084.'
ieee: 'M. Lass, R. Schade, T. Kühne, and C. Plessl, “A Submatrix-Based Method for
Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K,” in
Proc. International Conference for High Performance Computing, Networking,
Storage and Analysis (SC), Atlanta, GA, US, 2020, pp. 1127–1140, doi: 10.1109/SC41405.2020.00084.'
mla: Lass, Michael, et al. “A Submatrix-Based Method for Approximate Matrix Function
Evaluation in the Quantum Chemistry Code CP2K.” Proc. International Conference
for High Performance Computing, Networking, Storage and Analysis (SC), IEEE
Computer Society, 2020, pp. 1127–40, doi:10.1109/SC41405.2020.00084.
short: 'M. Lass, R. Schade, T. Kühne, C. Plessl, in: Proc. International Conference
for High Performance Computing, Networking, Storage and Analysis (SC), IEEE Computer
Society, Los Alamitos, CA, USA, 2020, pp. 1127–1140.'
conference:
location: Atlanta, GA, US
name: 'SC20: International Conference for High Performance Computing, Networking,
Storage and Analysis (SC)'
date_created: 2020-04-28T14:44:21Z
date_updated: 2023-08-02T14:55:59Z
department:
- _id: '27'
- _id: '518'
- _id: '304'
doi: 10.1109/SC41405.2020.00084
external_id:
arxiv:
- '2004.10811'
language:
- iso: eng
main_file_link:
- url: https://ieeexplore.ieee.org/document/9355245
page: 1127-1140
place: Los Alamitos, CA, USA
project:
- _id: '52'
name: Computing Resources Provided by the Paderborn Center for Parallel Computing
- _id: '32'
grant_number: PL 595/2-1 / 320898746
name: Performance and Efficiency in HPC with Custom Computing
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
publication: Proc. International Conference for High Performance Computing, Networking,
Storage and Analysis (SC)
publisher: IEEE Computer Society
quality_controlled: '1'
status: public
title: A Submatrix-Based Method for Approximate Matrix Function Evaluation in the
Quantum Chemistry Code CP2K
type: conference
user_id: '75963'
year: '2020'
...
---
_id: '12878'
abstract:
- lang: eng
text: In scientific computing, the acceleration of atomistic computer simulations
by means of custom hardware is finding ever-growing application. A major limitation,
however, is that the high efficiency in terms of performance and low power consumption
entails the massive usage of low precision computing units. Here, based on the
approximate computing paradigm, we present an algorithmic method to compensate
for numerical inaccuracies due to low accuracy arithmetic operations rigorously,
yet still obtaining exact expectation values using a properly modified Langevin-type
equation.
article_number: '39'
author:
- first_name: Varadarajan
full_name: Rengaraj, Varadarajan
last_name: Rengaraj
- first_name: Michael
full_name: Lass, Michael
id: '24135'
last_name: Lass
orcid: 0000-0002-5708-7632
- first_name: Christian
full_name: Plessl, Christian
id: '16153'
last_name: Plessl
orcid: 0000-0001-5728-9982
- first_name: Thomas
full_name: Kühne, Thomas
id: '49079'
last_name: Kühne
citation:
ama: Rengaraj V, Lass M, Plessl C, Kühne T. Accurate Sampling with Noisy Forces
from Approximate Computing. Computation. 2020;8(2). doi:10.3390/computation8020039
apa: Rengaraj, V., Lass, M., Plessl, C., & Kühne, T. (2020). Accurate Sampling
with Noisy Forces from Approximate Computing. Computation, 8(2),
Article 39. https://doi.org/10.3390/computation8020039
bibtex: '@article{Rengaraj_Lass_Plessl_Kühne_2020, title={Accurate Sampling with
Noisy Forces from Approximate Computing}, volume={8}, DOI={10.3390/computation8020039},
number={239}, journal={Computation}, publisher={MDPI}, author={Rengaraj, Varadarajan
and Lass, Michael and Plessl, Christian and Kühne, Thomas}, year={2020} }'
chicago: Rengaraj, Varadarajan, Michael Lass, Christian Plessl, and Thomas Kühne.
“Accurate Sampling with Noisy Forces from Approximate Computing.” Computation
8, no. 2 (2020). https://doi.org/10.3390/computation8020039.
ieee: 'V. Rengaraj, M. Lass, C. Plessl, and T. Kühne, “Accurate Sampling with Noisy
Forces from Approximate Computing,” Computation, vol. 8, no. 2, Art. no.
39, 2020, doi: 10.3390/computation8020039.'
mla: Rengaraj, Varadarajan, et al. “Accurate Sampling with Noisy Forces from Approximate
Computing.” Computation, vol. 8, no. 2, 39, MDPI, 2020, doi:10.3390/computation8020039.
short: V. Rengaraj, M. Lass, C. Plessl, T. Kühne, Computation 8 (2020).
date_created: 2019-07-23T12:03:07Z
date_updated: 2023-09-26T11:43:52Z
department:
- _id: '27'
- _id: '518'
- _id: '304'
doi: 10.3390/computation8020039
external_id:
arxiv:
- '1907.08497'
intvolume: ' 8'
issue: '2'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://www.mdpi.com/2079-3197/8/2/39/pdf
oa: '1'
project:
- _id: '52'
name: Computing Resources Provided by the Paderborn Center for Parallel Computing
- _id: '32'
grant_number: PL 595/2-1 / 320898746
name: Performance and Efficiency in HPC with Custom Computing
publication: Computation
publisher: MDPI
quality_controlled: '1'
status: public
title: Accurate Sampling with Noisy Forces from Approximate Computing
type: journal_article
user_id: '15278'
volume: 8
year: '2020'
...
---
_id: '15478'
abstract:
- lang: eng
text: Stratix 10 FPGA cards have a good potential for the acceleration of HPC workloads
since the Stratix 10 product line introduces devices with a large number of DSP
and memory blocks. The high level synthesis of OpenCL codes can play a fundamental
role for FPGAs in HPC, because it allows to implement different designs with lower
development effort compared to hand optimized HDL. However, Stratix 10 cards are
still hard to fully exploit using the Intel FPGA SDK for OpenCL. The implementation
of designs with thousands of concurrent arithmetic operations often suffers from
place and route problems that limit the maximum frequency or entirely prevent
a successful synthesis. In order to overcome these issues for the implementation
of the matrix multiplication, we formulate Cannon's matrix multiplication algorithm
with regard to its efficient synthesis within the FPGA logic. We obtain a two-level
block algorithm, where the lower level sub-matrices are multiplied using our Cannon's
algorithm implementation. Following this design approach with multiple compute
units, we are able to get maximum frequencies close to and above 300 MHz with
high utilization of DSP and memory blocks. This allows for performance results
above 1 TeraFLOPS.
author:
- first_name: Paolo
full_name: Gorlani, Paolo
id: '72045'
last_name: Gorlani
- first_name: Tobias
full_name: Kenter, Tobias
id: '3145'
last_name: Kenter
- first_name: Christian
full_name: Plessl, Christian
id: '16153'
last_name: Plessl
orcid: 0000-0001-5728-9982
citation:
ama: 'Gorlani P, Kenter T, Plessl C. OpenCL Implementation of Cannon’s Matrix Multiplication
Algorithm on Intel Stratix 10 FPGAs. In: Proceedings of the International Conference
on Field-Programmable Technology (FPT). IEEE; 2019. doi:10.1109/ICFPT47387.2019.00020'
apa: Gorlani, P., Kenter, T., & Plessl, C. (2019). OpenCL Implementation of
Cannon’s Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs. In Proceedings
of the International Conference on Field-Programmable Technology (FPT). IEEE.
https://doi.org/10.1109/ICFPT47387.2019.00020
bibtex: '@inproceedings{Gorlani_Kenter_Plessl_2019, title={OpenCL Implementation
of Cannon’s Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs}, DOI={10.1109/ICFPT47387.2019.00020},
booktitle={Proceedings of the International Conference on Field-Programmable Technology
(FPT)}, publisher={IEEE}, author={Gorlani, Paolo and Kenter, Tobias and Plessl,
Christian}, year={2019} }'
chicago: Gorlani, Paolo, Tobias Kenter, and Christian Plessl. “OpenCL Implementation
of Cannon’s Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs.” In Proceedings
of the International Conference on Field-Programmable Technology (FPT). IEEE,
2019. https://doi.org/10.1109/ICFPT47387.2019.00020.
ieee: P. Gorlani, T. Kenter, and C. Plessl, “OpenCL Implementation of Cannon’s Matrix
Multiplication Algorithm on Intel Stratix 10 FPGAs,” in Proceedings of the
International Conference on Field-Programmable Technology (FPT), 2019.
mla: Gorlani, Paolo, et al. “OpenCL Implementation of Cannon’s Matrix Multiplication
Algorithm on Intel Stratix 10 FPGAs.” Proceedings of the International Conference
on Field-Programmable Technology (FPT), IEEE, 2019, doi:10.1109/ICFPT47387.2019.00020.
short: 'P. Gorlani, T. Kenter, C. Plessl, in: Proceedings of the International Conference
on Field-Programmable Technology (FPT), IEEE, 2019.'
conference:
name: International Conference on Field-Programmable Technology (FPT)
date_created: 2020-01-09T12:54:48Z
date_updated: 2022-01-06T06:52:26Z
ddc:
- '004'
department:
- _id: '27'
- _id: '518'
doi: 10.1109/ICFPT47387.2019.00020
file:
- access_level: closed
content_type: application/pdf
creator: plessl
date_created: 2020-01-09T12:53:57Z
date_updated: 2020-01-09T12:53:57Z
file_id: '15479'
file_name: gorlani19_fpt.pdf
file_size: 250559
relation: main_file
success: 1
file_date_updated: 2020-01-09T12:53:57Z
has_accepted_license: '1'
language:
- iso: eng
project:
- _id: '33'
grant_number: 01|H16005
name: HighPerMeshes
- _id: '32'
grant_number: PL 595/2-1
name: Performance and Efficiency in HPC with Custom Computing
publication: Proceedings of the International Conference on Field-Programmable Technology
(FPT)
publisher: IEEE
quality_controlled: '1'
status: public
title: OpenCL Implementation of Cannon's Matrix Multiplication Algorithm on Intel
Stratix 10 FPGAs
type: conference
user_id: '3145'
year: '2019'
...
---
_id: '21'
abstract:
- lang: eng
text: "We address the general mathematical problem of computing the inverse p-th\r\nroot
of a given matrix in an efficient way. A new method to construct iteration\r\nfunctions
that allow calculating arbitrary p-th roots and their inverses of\r\nsymmetric
positive definite matrices is presented. We show that the order of\r\nconvergence
is at least quadratic and that adaptively adjusting a parameter q\r\nalways leads
to an even faster convergence. In this way, a better performance\r\nthan with
previously known iteration schemes is achieved. The efficiency of the\r\niterative
functions is demonstrated for various matrices with different\r\ndensities, condition
numbers and spectral radii."
author:
- first_name: Dorothee
full_name: Richters, Dorothee
last_name: Richters
- first_name: Michael
full_name: Lass, Michael
id: '24135'
last_name: Lass
orcid: 0000-0002-5708-7632
- first_name: Andrea
full_name: Walther, Andrea
last_name: Walther
- first_name: Christian
full_name: Plessl, Christian
id: '16153'
last_name: Plessl
orcid: 0000-0001-5728-9982
- first_name: Thomas
full_name: Kühne, Thomas
id: '49079'
last_name: Kühne
citation:
ama: Richters D, Lass M, Walther A, Plessl C, Kühne T. A General Algorithm to Calculate
the Inverse Principal p-th Root of Symmetric Positive Definite Matrices. Communications
in Computational Physics. 2019;25(2):564-585. doi:10.4208/cicp.OA-2018-0053
apa: Richters, D., Lass, M., Walther, A., Plessl, C., & Kühne, T. (2019). A
General Algorithm to Calculate the Inverse Principal p-th Root of Symmetric Positive
Definite Matrices. Communications in Computational Physics, 25(2),
564–585. https://doi.org/10.4208/cicp.OA-2018-0053
bibtex: '@article{Richters_Lass_Walther_Plessl_Kühne_2019, title={A General Algorithm
to Calculate the Inverse Principal p-th Root of Symmetric Positive Definite Matrices},
volume={25}, DOI={10.4208/cicp.OA-2018-0053},
number={2}, journal={Communications in Computational Physics}, publisher={Global
Science Press}, author={Richters, Dorothee and Lass, Michael and Walther, Andrea
and Plessl, Christian and Kühne, Thomas}, year={2019}, pages={564–585} }'
chicago: 'Richters, Dorothee, Michael Lass, Andrea Walther, Christian Plessl, and
Thomas Kühne. “A General Algorithm to Calculate the Inverse Principal P-Th Root
of Symmetric Positive Definite Matrices.” Communications in Computational Physics
25, no. 2 (2019): 564–85. https://doi.org/10.4208/cicp.OA-2018-0053.'
ieee: 'D. Richters, M. Lass, A. Walther, C. Plessl, and T. Kühne, “A General Algorithm
to Calculate the Inverse Principal p-th Root of Symmetric Positive Definite Matrices,”
Communications in Computational Physics, vol. 25, no. 2, pp. 564–585, 2019,
doi: 10.4208/cicp.OA-2018-0053.'
mla: Richters, Dorothee, et al. “A General Algorithm to Calculate the Inverse Principal
P-Th Root of Symmetric Positive Definite Matrices.” Communications in Computational
Physics, vol. 25, no. 2, Global Science Press, 2019, pp. 564–85, doi:10.4208/cicp.OA-2018-0053.
short: D. Richters, M. Lass, A. Walther, C. Plessl, T. Kühne, Communications in
Computational Physics 25 (2019) 564–585.
date_created: 2017-07-25T14:48:26Z
date_updated: 2023-09-26T11:45:02Z
department:
- _id: '27'
- _id: '518'
- _id: '304'
- _id: '104'
doi: 10.4208/cicp.OA-2018-0053
external_id:
arxiv:
- '1703.02456'
intvolume: ' 25'
issue: '2'
language:
- iso: eng
page: 564-585
project:
- _id: '32'
grant_number: PL 595/2-1 / 320898746
name: Performance and Efficiency in HPC with Custom Computing
- _id: '52'
name: Computing Resources Provided by the Paderborn Center for Parallel Computing
publication: Communications in Computational Physics
publisher: Global Science Press
quality_controlled: '1'
status: public
title: A General Algorithm to Calculate the Inverse Principal p-th Root of Symmetric
Positive Definite Matrices
type: journal_article
user_id: '15278'
volume: 25
year: '2019'
...
---
_id: '20'
abstract:
- lang: eng
text: "Approximate computing has shown to provide new ways to improve performance\r\nand
power consumption of error-resilient applications. While many of these\r\napplications
can be found in image processing, data classification or machine\r\nlearning,
we demonstrate its suitability to a problem from scientific\r\ncomputing. Utilizing
the self-correcting behavior of iterative algorithms, we\r\nshow that approximate
computing can be applied to the calculation of inverse\r\nmatrix p-th roots which
are required in many applications in scientific\r\ncomputing. Results show great
opportunities to reduce the computational effort\r\nand bandwidth required for
the execution of the discussed algorithm, especially\r\nwhen targeting special
accelerator hardware."
author:
- first_name: Michael
full_name: Lass, Michael
id: '24135'
last_name: Lass
orcid: 0000-0002-5708-7632
- first_name: Thomas
full_name: Kühne, Thomas
id: '49079'
last_name: Kühne
- first_name: Christian
full_name: Plessl, Christian
id: '16153'
last_name: Plessl
orcid: 0000-0001-5728-9982
citation:
ama: Lass M, Kühne T, Plessl C. Using Approximate Computing for the Calculation
of Inverse Matrix p-th Roots. Embedded Systems Letters. 2018;10(2):33-36.
doi:10.1109/LES.2017.2760923
apa: Lass, M., Kühne, T., & Plessl, C. (2018). Using Approximate Computing for
the Calculation of Inverse Matrix p-th Roots. Embedded Systems Letters,
10(2), 33–36. https://doi.org/10.1109/LES.2017.2760923
bibtex: '@article{Lass_Kühne_Plessl_2018, title={Using Approximate Computing for
the Calculation of Inverse Matrix p-th Roots}, volume={10}, DOI={10.1109/LES.2017.2760923},
number={2}, journal={Embedded Systems Letters}, publisher={IEEE}, author={Lass,
Michael and Kühne, Thomas and Plessl, Christian}, year={2018}, pages={33–36} }'
chicago: 'Lass, Michael, Thomas Kühne, and Christian Plessl. “Using Approximate
Computing for the Calculation of Inverse Matrix P-Th Roots.” Embedded Systems
Letters 10, no. 2 (2018): 33–36. https://doi.org/10.1109/LES.2017.2760923.'
ieee: M. Lass, T. Kühne, and C. Plessl, “Using Approximate Computing for the Calculation
of Inverse Matrix p-th Roots,” Embedded Systems Letters, vol. 10, no. 2,
pp. 33–36, 2018.
mla: Lass, Michael, et al. “Using Approximate Computing for the Calculation of Inverse
Matrix P-Th Roots.” Embedded Systems Letters, vol. 10, no. 2, IEEE, 2018,
pp. 33–36, doi:10.1109/LES.2017.2760923.
short: M. Lass, T. Kühne, C. Plessl, Embedded Systems Letters 10 (2018) 33–36.
date_created: 2017-07-25T14:41:08Z
date_updated: 2022-01-06T06:54:18Z
department:
- _id: '27'
- _id: '518'
- _id: '304'
doi: 10.1109/LES.2017.2760923
external_id:
arxiv:
- '1703.02283'
intvolume: ' 10'
issue: '2'
language:
- iso: eng
page: ' 33-36'
project:
- _id: '32'
grant_number: PL 595/2-1
name: Performance and Efficiency in HPC with Custom Computing
- _id: '52'
name: Computing Resources Provided by the Paderborn Center for Parallel Computing
publication: Embedded Systems Letters
publication_identifier:
eissn:
- 1943-0671
issn:
- 1943-0663
publication_status: published
publisher: IEEE
status: public
title: Using Approximate Computing for the Calculation of Inverse Matrix p-th Roots
type: journal_article
user_id: '16153'
volume: 10
year: '2018'
...
---
_id: '1590'
abstract:
- lang: eng
text: "We present the submatrix method, a highly parallelizable method for the approximate
calculation of inverse p-th roots of large sparse symmetric matrices which are
required in different scientific applications. Following the idea of Approximate
Computing, we allow imprecision in the final result in order to utilize the sparsity
of the input matrix and to allow massively parallel execution. For an n x n matrix,
the proposed algorithm allows to distribute the calculations over n nodes with
only little communication overhead. The result matrix exhibits the same sparsity
pattern as the input matrix, allowing for efficient reuse of allocated data structures.\r\n\r\nWe
evaluate the algorithm with respect to the error that it introduces into calculated
results, as well as its performance and scalability. We demonstrate that the error
is relatively limited for well-conditioned matrices and that results are still
valuable for error-resilient applications like preconditioning even for ill-conditioned
matrices. We discuss the execution time and scaling of the algorithm on a theoretical
level and present a distributed implementation of the algorithm using MPI and
OpenMP. We demonstrate the scalability of this implementation by running it on
a high-performance compute cluster comprised of 1024 CPU cores, showing a speedup
of 665x compared to single-threaded execution."
author:
- first_name: Michael
full_name: Lass, Michael
id: '24135'
last_name: Lass
orcid: 0000-0002-5708-7632
- first_name: Stephan
full_name: Mohr, Stephan
last_name: Mohr
- first_name: Hendrik
full_name: Wiebeler, Hendrik
last_name: Wiebeler
- first_name: Thomas
full_name: Kühne, Thomas
id: '49079'
last_name: Kühne
- first_name: Christian
full_name: Plessl, Christian
id: '16153'
last_name: Plessl
orcid: 0000-0001-5728-9982
citation:
ama: 'Lass M, Mohr S, Wiebeler H, Kühne T, Plessl C. A Massively Parallel Algorithm
for the Approximate Calculation of Inverse p-th Roots of Large Sparse Matrices.
In: Proc. Platform for Advanced Scientific Computing (PASC) Conference.
ACM; 2018. doi:10.1145/3218176.3218231'
apa: Lass, M., Mohr, S., Wiebeler, H., Kühne, T., & Plessl, C. (2018). A Massively
Parallel Algorithm for the Approximate Calculation of Inverse p-th Roots of Large
Sparse Matrices. Proc. Platform for Advanced Scientific Computing (PASC) Conference.
Platform for Advanced Scientific Computing Conference (PASC), Basel, Switzerland.
https://doi.org/10.1145/3218176.3218231
bibtex: '@inproceedings{Lass_Mohr_Wiebeler_Kühne_Plessl_2018, place={New York, NY,
USA}, title={A Massively Parallel Algorithm for the Approximate Calculation of
Inverse p-th Roots of Large Sparse Matrices}, DOI={10.1145/3218176.3218231},
booktitle={Proc. Platform for Advanced Scientific Computing (PASC) Conference},
publisher={ACM}, author={Lass, Michael and Mohr, Stephan and Wiebeler, Hendrik
and Kühne, Thomas and Plessl, Christian}, year={2018} }'
chicago: 'Lass, Michael, Stephan Mohr, Hendrik Wiebeler, Thomas Kühne, and Christian
Plessl. “A Massively Parallel Algorithm for the Approximate Calculation of Inverse
P-Th Roots of Large Sparse Matrices.” In Proc. Platform for Advanced Scientific
Computing (PASC) Conference. New York, NY, USA: ACM, 2018. https://doi.org/10.1145/3218176.3218231.'
ieee: 'M. Lass, S. Mohr, H. Wiebeler, T. Kühne, and C. Plessl, “A Massively Parallel
Algorithm for the Approximate Calculation of Inverse p-th Roots of Large Sparse
Matrices,” presented at the Platform for Advanced Scientific Computing Conference
(PASC), Basel, Switzerland, 2018, doi: 10.1145/3218176.3218231.'
mla: Lass, Michael, et al. “A Massively Parallel Algorithm for the Approximate Calculation
of Inverse P-Th Roots of Large Sparse Matrices.” Proc. Platform for Advanced
Scientific Computing (PASC) Conference, ACM, 2018, doi:10.1145/3218176.3218231.
short: 'M. Lass, S. Mohr, H. Wiebeler, T. Kühne, C. Plessl, in: Proc. Platform for
Advanced Scientific Computing (PASC) Conference, ACM, New York, NY, USA, 2018.'
conference:
end_date: 2018-07-04
location: Basel, Switzerland
name: Platform for Advanced Scientific Computing Conference (PASC)
start_date: 2018-07-02
date_created: 2018-03-22T10:53:01Z
date_updated: 2023-09-26T11:48:12Z
department:
- _id: '27'
- _id: '518'
- _id: '304'
doi: 10.1145/3218176.3218231
external_id:
arxiv:
- '1710.10899'
keyword:
- approximate computing
- linear algebra
- matrix inversion
- matrix p-th roots
- numeric algorithm
- parallel computing
language:
- iso: eng
place: New York, NY, USA
project:
- _id: '32'
grant_number: PL 595/2-1 / 320898746
name: Performance and Efficiency in HPC with Custom Computing
- _id: '52'
name: Computing Resources Provided by the Paderborn Center for Parallel Computing
publication: Proc. Platform for Advanced Scientific Computing (PASC) Conference
publication_identifier:
isbn:
- 978-1-4503-5891-0/18/07
publisher: ACM
quality_controlled: '1'
status: public
title: A Massively Parallel Algorithm for the Approximate Calculation of Inverse p-th
Roots of Large Sparse Matrices
type: conference
user_id: '15278'
year: '2018'
...
---
_id: '1592'
abstract:
- lang: eng
text: Compared to classical HDL designs, generating FPGA with high-level synthesis
from an OpenCL specification promises easier exploration of different design alternatives
and, through ready-to-use infrastructure and common abstractions for host and
memory interfaces, easier portability between different FPGA families. In this
work, we evaluate the extent of this promise. To this end, we present a parameterized
FDTD implementation for photonic microcavity simulations. Our design can trade-off
different forms of parallelism and works for two independent OpenCL-based FPGA
design flows. Hence, we can target FPGAs from different vendors and different
FPGA families. We describe how we used pre-processor macros to achieve this flexibility
and to work around different shortcomings of the current tools. Choosing the right
design configurations, we are able to present two extremely competitive solutions
for very different FPGA targets, reaching up to 172 GFLOPS sustained performance.
With the portability and flexibility demonstrated, code developers not only avoid
vendor lock-in, but can even make best use of real trade-offs between different
architectures.
author:
- first_name: Tobias
full_name: Kenter, Tobias
id: '3145'
last_name: Kenter
- first_name: Jens
full_name: Förstner, Jens
id: '158'
last_name: Förstner
orcid: 0000-0001-7059-9862
- first_name: Christian
full_name: Plessl, Christian
id: '16153'
last_name: Plessl
orcid: 0000-0001-5728-9982
citation:
ama: 'Kenter T, Förstner J, Plessl C. Flexible FPGA design for FDTD using OpenCL.
In: Proc. Int. Conf. on Field Programmable Logic and Applications (FPL).
IEEE; 2017. doi:10.23919/FPL.2017.8056844'
apa: Kenter, T., Förstner, J., & Plessl, C. (2017). Flexible FPGA design for
FDTD using OpenCL. Proc. Int. Conf. on Field Programmable Logic and Applications
(FPL). https://doi.org/10.23919/FPL.2017.8056844
bibtex: '@inproceedings{Kenter_Förstner_Plessl_2017, title={Flexible FPGA design
for FDTD using OpenCL}, DOI={10.23919/FPL.2017.8056844},
booktitle={Proc. Int. Conf. on Field Programmable Logic and Applications (FPL)},
publisher={IEEE}, author={Kenter, Tobias and Förstner, Jens and Plessl, Christian},
year={2017} }'
chicago: Kenter, Tobias, Jens Förstner, and Christian Plessl. “Flexible FPGA Design
for FDTD Using OpenCL.” In Proc. Int. Conf. on Field Programmable Logic and
Applications (FPL). IEEE, 2017. https://doi.org/10.23919/FPL.2017.8056844.
ieee: 'T. Kenter, J. Förstner, and C. Plessl, “Flexible FPGA design for FDTD using
OpenCL,” 2017, doi: 10.23919/FPL.2017.8056844.'
mla: Kenter, Tobias, et al. “Flexible FPGA Design for FDTD Using OpenCL.” Proc.
Int. Conf. on Field Programmable Logic and Applications (FPL), IEEE, 2017,
doi:10.23919/FPL.2017.8056844.
short: 'T. Kenter, J. Förstner, C. Plessl, in: Proc. Int. Conf. on Field Programmable
Logic and Applications (FPL), IEEE, 2017.'
date_created: 2018-03-22T11:10:23Z
date_updated: 2023-09-26T13:24:38Z
ddc:
- '000'
department:
- _id: '27'
- _id: '518'
- _id: '61'
doi: 10.23919/FPL.2017.8056844
file:
- access_level: closed
content_type: application/pdf
creator: ups
date_created: 2018-11-02T15:02:28Z
date_updated: 2018-11-02T15:02:28Z
file_id: '5291'
file_name: 08056844.pdf
file_size: 230235
relation: main_file
success: 1
file_date_updated: 2018-11-02T15:02:28Z
has_accepted_license: '1'
keyword:
- tet_topic_hpc
language:
- iso: eng
project:
- _id: '1'
grant_number: '160364472'
name: SFB 901
- _id: '4'
name: SFB 901 - Project Area C
- _id: '14'
grant_number: '160364472'
name: SFB 901 - Subproject C2
- _id: '33'
grant_number: 01|H16005A
name: HighPerMeshes
- _id: '32'
grant_number: PL 595/2-1 / 320898746
name: Performance and Efficiency in HPC with Custom Computing
- _id: '52'
name: Computing Resources Provided by the Paderborn Center for Parallel Computing
publication: Proc. Int. Conf. on Field Programmable Logic and Applications (FPL)
publisher: IEEE
quality_controlled: '1'
status: public
title: Flexible FPGA design for FDTD using OpenCL
type: conference
user_id: '15278'
year: '2017'
...
---
_id: '24'
author:
- first_name: Tobias
full_name: Kenter, Tobias
id: '3145'
last_name: Kenter
- first_name: Christian
full_name: Plessl, Christian
id: '16153'
last_name: Plessl
orcid: 0000-0001-5728-9982
citation:
ama: 'Kenter T, Plessl C. Microdisk Cavity FDTD Simulation on FPGA using OpenCL.
In: Proc. Workshop on Heterogeneous High-Performance Reconfigurable Computing
(H2RC). ; 2016.'
apa: Kenter, T., & Plessl, C. (2016). Microdisk Cavity FDTD Simulation on FPGA
using OpenCL. Proc. Workshop on Heterogeneous High-Performance Reconfigurable
Computing (H2RC).
bibtex: '@inproceedings{Kenter_Plessl_2016, title={Microdisk Cavity FDTD Simulation
on FPGA using OpenCL}, booktitle={Proc. Workshop on Heterogeneous High-performance
Reconfigurable Computing (H2RC)}, author={Kenter, Tobias and Plessl, Christian},
year={2016} }'
chicago: Kenter, Tobias, and Christian Plessl. “Microdisk Cavity FDTD Simulation
on FPGA Using OpenCL.” In Proc. Workshop on Heterogeneous High-Performance
Reconfigurable Computing (H2RC), 2016.
ieee: T. Kenter and C. Plessl, “Microdisk Cavity FDTD Simulation on FPGA using OpenCL,”
2016.
mla: Kenter, Tobias, and Christian Plessl. “Microdisk Cavity FDTD Simulation on
FPGA Using OpenCL.” Proc. Workshop on Heterogeneous High-Performance Reconfigurable
Computing (H2RC), 2016.
short: 'T. Kenter, C. Plessl, in: Proc. Workshop on Heterogeneous High-Performance
Reconfigurable Computing (H2RC), 2016.'
date_created: 2017-07-26T15:00:43Z
date_updated: 2023-09-26T13:26:17Z
ddc:
- '004'
department:
- _id: '27'
- _id: '518'
file:
- access_level: closed
content_type: application/pdf
creator: kenter
date_created: 2018-11-14T12:38:45Z
date_updated: 2018-11-14T12:38:45Z
file_id: '5602'
file_name: paper_26.pdf
file_size: 129552
relation: main_file
success: 1
file_date_updated: 2018-11-14T12:38:45Z
has_accepted_license: '1'
language:
- iso: eng
project:
- _id: '32'
grant_number: PL 595/2-1 / 320898746
name: Performance and Efficiency in HPC with Custom Computing
- _id: '1'
grant_number: '160364472'
name: SFB 901
- _id: '4'
name: SFB 901 - Project Area C
- _id: '14'
grant_number: '160364472'
name: SFB 901 - Subproject C2
publication: Proc. Workshop on Heterogeneous High-performance Reconfigurable Computing
(H2RC)
quality_controlled: '1'
status: public
title: Microdisk Cavity FDTD Simulation on FPGA using OpenCL
type: conference
user_id: '15278'
year: '2016'
...