@inbook{29936, author = {{Ramaswami, Arjun and Kenter, Tobias and Kühne, Thomas and Plessl, Christian}}, booktitle = {{Applied Reconfigurable Computing. Architectures, Tools, and Applications}}, isbn = {{9783030790240}}, issn = {{0302-9743}}, publisher = {{Springer International Publishing}}, title = {{{Evaluating the Design Space for Offloading 3D FFT Calculations to an FPGA for High-Performance Computing}}}, doi = {{10.1007/978-3-030-79025-7_21}}, year = {{2021}}, } @article{24788, author = {{Alhaddad, Samer and Förstner, Jens and Groth, Stefan and Grünewald, Daniel and Grynko, Yevgen and Hannig, Frank and Kenter, Tobias and Pfreundt, Franz‐Josef and Plessl, Christian and Schotte, Merlind and Steinke, Thomas and Teich, Jürgen and Weiser, Martin and Wende, Florian}}, issn = {{1532-0626}}, journal = {{Concurrency and Computation: Practice and Experience}}, keywords = {{tet_topic_hpc}}, pages = {{e6616}}, title = {{{The HighPerMeshes framework for numerical algorithms on unstructured grids}}}, doi = {{10.1002/cpe.6616}}, year = {{2021}}, } @inproceedings{29937, author = {{Karp, Martin and Podobas, Artur and Jansson, Niclas and Kenter, Tobias and Plessl, Christian and Schlatter, Philipp and Markidis, Stefano}}, booktitle = {{2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS)}}, publisher = {{IEEE}}, title = {{{High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection}}}, doi = {{10.1109/ipdps49936.2021.00116}}, year = {{2021}}, } @article{16277, abstract = {{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.}}, 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 Golze, Dorothea and Wilhelm, Jan and Chulkov, Sergey and Mohammad Hossein Bani-Hashemian, Mohammad Hossein Bani-Hashemian and Weber, Valéry and Borstnik, Urban and Taillefumier, Mathieu and Jakobovits, Alice Shoshana and Lazzaro, Alfio and Pabst, Hans and Müller, Tiziano and Schade, Robert and Guidon, Manuel and Andermatt, Samuel and Holmberg, Nico and Schenter, Gregory K. and Hehn, Anna and Bussy, Augustin and Belleflamme, Fabian and Tabacchi, Gloria and Glöß, Andreas and Lass, Michael and Bethune, Iain and Mundy, Christopher J. and Plessl, Christian and Watkins, Matt and VandeVondele, Joost and Krack, Matthias and Hutter, Jürg}}, journal = {{The Journal of Chemical Physics}}, number = {{19}}, title = {{{CP2K: An electronic structure and molecular dynamics software package - Quickstep: Efficient and accurate electronic structure calculations}}}, doi = {{10.1063/5.0007045}}, volume = {{152}}, year = {{2020}}, } @inproceedings{16898, abstract = {{Electronic structure calculations based on density-functional theory (DFT) represent a significant part of today's HPC workloads and pose high demands on high-performance computing resources. To perform these quantum-mechanical DFT calculations on complex large-scale systems, so-called linear scaling methods instead of conventional cubic scaling methods are required. In this work, we take up the idea of the submatrix method and apply it to the DFT computations in the software package CP2K. For that purpose, we transform the underlying numeric operations on distributed, large, sparse matrices into computations on local, much smaller and nearly dense matrices. This allows us to exploit the full floating-point performance of modern CPUs and to make use of dedicated accelerator hardware, where performance has been limited by memory bandwidth before. We demonstrate both functionality and performance of our implementation and show how it can be accelerated with GPUs and FPGAs.}}, author = {{Lass, Michael and Schade, Robert and Kühne, Thomas and Plessl, Christian}}, booktitle = {{Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC)}}, location = {{Atlanta, GA, US}}, pages = {{1127--1140}}, publisher = {{IEEE Computer Society}}, title = {{{A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K}}}, doi = {{10.1109/SC41405.2020.00084}}, year = {{2020}}, } @inproceedings{21632, abstract = {{FPGAs have found increasing adoption in data center applications since a new generation of high-level tools have become available which noticeably reduce development time for FPGA accelerators and still provide high-quality results. There is, however, no high-level benchmark suite available, which specifically enables a comparison of FPGA architectures, programming tools, and libraries for HPC applications. To fill this gap, we have developed an OpenCL-based open-source implementation of the HPCC benchmark suite for Xilinx and Intel FPGAs. This benchmark can serve to analyze the current capabilities of FPGA devices, cards, and development tool flows, track progress over time, and point out specific difficulties for FPGA acceleration in the HPC domain. Additionally, the benchmark documents proven performance optimization patterns. We will continue optimizing and porting the benchmark for new generations of FPGAs and design tools and encourage active participation to create a valuable tool for the community. To fill this gap, we have developed an OpenCL-based open-source implementation of the HPCC benchmark suite for Xilinx and Intel FPGAs. This benchmark can serve to analyze the current capabilities of FPGA devices, cards, and development tool flows, track progress over time, and point out specific difficulties for FPGA acceleration in the HPC domain. Additionally, the benchmark documents proven performance optimization patterns. We will continue optimizing and porting the benchmark for new generations of FPGAs and design tools and encourage active participation to create a valuable tool for the community.}}, author = {{Meyer, Marius and Kenter, Tobias and Plessl, Christian}}, booktitle = {{2020 IEEE/ACM International Workshop on Heterogeneous High-performance Reconfigurable Computing (H2RC)}}, isbn = {{9781665415927}}, keywords = {{FPGA, OpenCL, High Level Synthesis, HPC benchmarking}}, title = {{{Evaluating FPGA Accelerator Performance with a Parameterized OpenCL Adaptation of Selected Benchmarks of the HPCChallenge Benchmark Suite}}}, doi = {{10.1109/h2rc51942.2020.00007}}, year = {{2020}}, } @article{12878, abstract = {{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.}}, author = {{Rengaraj, Varadarajan and Lass, Michael and Plessl, Christian and Kühne, Thomas}}, journal = {{Computation}}, number = {{2}}, publisher = {{MDPI}}, title = {{{Accurate Sampling with Noisy Forces from Approximate Computing}}}, doi = {{10.3390/computation8020039}}, volume = {{8}}, year = {{2020}}, } @article{7689, author = {{Riebler, Heinrich and Vaz, Gavin Francis and Kenter, Tobias and Plessl, Christian}}, journal = {{ACM Trans. Archit. Code Optim. (TACO)}}, keywords = {{htrop}}, number = {{2}}, pages = {{14:1–14:26}}, publisher = {{ACM}}, title = {{{Transparent Acceleration for Heterogeneous Platforms with Compilation to OpenCL}}}, doi = {{10.1145/3319423}}, volume = {{16}}, year = {{2019}}, } @inproceedings{15478, abstract = {{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 = {{Gorlani, Paolo and Kenter, Tobias and Plessl, Christian}}, booktitle = {{Proceedings of the International Conference on Field-Programmable Technology (FPT)}}, publisher = {{IEEE}}, title = {{{OpenCL Implementation of Cannon's Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs}}}, doi = {{10.1109/ICFPT47387.2019.00020}}, year = {{2019}}, } @phdthesis{14849, author = {{Vaz, Gavin Francis}}, publisher = {{Universität Paderborn}}, title = {{{Using Just-in-Time Code Generation to Transparently Accelerate Applications in Heterogeneous Systems}}}, year = {{2019}}, } @article{21, abstract = {{We address the general mathematical problem of computing the inverse p-th root of a given matrix in an efficient way. A new method to construct iteration functions that allow calculating arbitrary p-th roots and their inverses of symmetric positive definite matrices is presented. We show that the order of convergence is at least quadratic and that adaptively adjusting a parameter q always leads to an even faster convergence. In this way, a better performance than with previously known iteration schemes is achieved. The efficiency of the iterative functions is demonstrated for various matrices with different densities, condition numbers and spectral radii.}}, author = {{Richters, Dorothee and Lass, Michael and Walther, Andrea and Plessl, Christian and Kühne, Thomas}}, journal = {{Communications in Computational Physics}}, number = {{2}}, pages = {{564--585}}, publisher = {{Global Science Press}}, title = {{{A General Algorithm to Calculate the Inverse Principal p-th Root of Symmetric Positive Definite Matrices}}}, doi = {{10.4208/cicp.OA-2018-0053}}, volume = {{25}}, year = {{2019}}, } @article{12871, author = {{Platzner, Marco and Plessl, Christian}}, issn = {{0170-6012}}, journal = {{Informatik Spektrum}}, title = {{{FPGAs im Rechenzentrum}}}, doi = {{10.1007/s00287-019-01187-w}}, year = {{2019}}, } @article{20, abstract = {{Approximate computing has shown to provide new ways to improve performance and power consumption of error-resilient applications. While many of these applications can be found in image processing, data classification or machine learning, we demonstrate its suitability to a problem from scientific computing. Utilizing the self-correcting behavior of iterative algorithms, we show that approximate computing can be applied to the calculation of inverse matrix p-th roots which are required in many applications in scientific computing. Results show great opportunities to reduce the computational effort and bandwidth required for the execution of the discussed algorithm, especially when targeting special accelerator hardware.}}, author = {{Lass, Michael and Kühne, Thomas and Plessl, Christian}}, issn = {{1943-0671}}, journal = {{Embedded Systems Letters}}, number = {{2}}, pages = {{ 33--36}}, publisher = {{IEEE}}, title = {{{Using Approximate Computing for the Calculation of Inverse Matrix p-th Roots}}}, doi = {{10.1109/LES.2017.2760923}}, volume = {{10}}, year = {{2018}}, } @misc{5414, author = {{Filmwala, Tasneem}}, publisher = {{Universität Paderborn}}, title = {{{Study Effects of Approximation on Conjugate Gradient Algorithm and Accelerate it on FPGA Platform}}}, year = {{2018}}, } @misc{5421, author = {{Gadewar, Onkar}}, publisher = {{Universität Paderborn}}, title = {{{Programmable Programs? - Designing FPGA Overlay Architectures with OpenCL}}}, year = {{2018}}, } @article{6516, author = {{Mertens, Jan Cedric and Boschmann, Alexander and Schmidt, M. and Plessl, Christian}}, issn = {{1369-7072}}, journal = {{Sports Engineering}}, number = {{4}}, pages = {{441--451}}, publisher = {{Springer Nature}}, title = {{{Sprint diagnostic with GPS and inertial sensor fusion}}}, doi = {{10.1007/s12283-018-0291-0}}, volume = {{21}}, year = {{2018}}, } @misc{5417, abstract = {{Molecular Dynamic (MD) simulations are computationally intensive and accelerating them using specialized hardware is a topic of investigation in many studies. One of the routines in the critical path of MD simulations is the three-dimensional Fast Fourier Transformation (FFT3d). The potential in accelerating FFT3d using hardware is usually bound by bandwidth and memory. Therefore, designing a high throughput solution for an FPGA that overcomes this problem is challenging. In this thesis, the feasibility of offloading FFT3d computations to FPGA implemented using OpenCL is investigated. In order to mask the latency in memory access, an FFT3d that overlaps computation with communication is designed. The implementa- tion of this design is synthesized for the Arria 10 GX 1150 FPGA and evaluated with the FFTW benchmark. Analysis shows a better performance using FPGA over CPU for larger FFT sizes, with the 643 FFT showing a 70% improvement in runtime using FPGAs. This FFT3d design is integrated with CP2K to explore the potential in accelerating molecular dynamic simulations. Evaluation of CP2K simulations using FPGA shows a 41% improvement in runtime in FFT3d computations over CPU for larger FFT3d designs.}}, author = {{Ramaswami, Arjun}}, keywords = {{FFT: FPGA, CP2K, OpenCL}}, publisher = {{Universität Paderborn}}, title = {{{Accelerating Molecular Dynamic Simulations by Offloading Fast Fourier Transformations to FPGA}}}, year = {{2018}}, } @inproceedings{1588, abstract = {{The exploration of FPGAs as accelerators for scientific simulations has so far mostly been focused on small kernels of methods working on regular data structures, for example in the form of stencil computations for finite difference methods. In computational sciences, often more advanced methods are employed that promise better stability, convergence, locality and scaling. Unstructured meshes are shown to be more effective and more accurate, compared to regular grids, in representing computation domains of various shapes. Using unstructured meshes, the discontinuous Galerkin method preserves the ability to perform explicit local update operations for simulations in the time domain. In this work, we investigate FPGAs as target platform for an implementation of the nodal discontinuous Galerkin method to find time-domain solutions of Maxwell's equations in an unstructured mesh. When maximizing data reuse and fitting constant coefficients into suitably partitioned on-chip memory, high computational intensity allows us to implement and feed wide data paths with hundreds of floating point operators. By decoupling off-chip memory accesses from the computations, high memory bandwidth can be sustained, even for the irregular access pattern required by parts of the application. Using the Intel/Altera OpenCL SDK for FPGAs, we present different implementation variants for different polynomial orders of the method. In different phases of the algorithm, either computational or bandwidth limits of the Arria 10 platform are almost reached, thus outperforming a highly multithreaded CPU implementation by around 2x.}}, author = {{Kenter, Tobias and Mahale, Gopinath and Alhaddad, Samer and Grynko, Yevgen and Schmitt, Christian and Afzal, Ayesha and Hannig, Frank and Förstner, Jens and Plessl, Christian}}, booktitle = {{Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM)}}, keywords = {{tet_topic_hpc}}, publisher = {{IEEE}}, title = {{{OpenCL-based FPGA Design to Accelerate the Nodal Discontinuous Galerkin Method for Unstructured Meshes}}}, doi = {{10.1109/FCCM.2018.00037}}, year = {{2018}}, } @inproceedings{1590, abstract = {{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. We 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 = {{Lass, Michael and Mohr, Stephan and Wiebeler, Hendrik and Kühne, Thomas and Plessl, Christian}}, booktitle = {{Proc. Platform for Advanced Scientific Computing (PASC) Conference}}, isbn = {{978-1-4503-5891-0/18/07}}, keywords = {{approximate computing, linear algebra, matrix inversion, matrix p-th roots, numeric algorithm, parallel computing}}, location = {{Basel, Switzerland}}, publisher = {{ACM}}, title = {{{A Massively Parallel Algorithm for the Approximate Calculation of Inverse p-th Roots of Large Sparse Matrices}}}, doi = {{10.1145/3218176.3218231}}, year = {{2018}}, } @inproceedings{1204, author = {{Riebler, Heinrich and Vaz, Gavin Francis and Kenter, Tobias and Plessl, Christian}}, booktitle = {{Proc. ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP)}}, isbn = {{9781450349826}}, keywords = {{htrop}}, publisher = {{ACM}}, title = {{{Automated Code Acceleration Targeting Heterogeneous OpenCL Devices}}}, doi = {{10.1145/3178487.3178534}}, year = {{2018}}, }